CN104133991A - Penicillin fermentation process fault diagnosis method based on kernel partial least squares reconstitution - Google Patents

Penicillin fermentation process fault diagnosis method based on kernel partial least squares reconstitution Download PDF

Info

Publication number
CN104133991A
CN104133991A CN201410337732.XA CN201410337732A CN104133991A CN 104133991 A CN104133991 A CN 104133991A CN 201410337732 A CN201410337732 A CN 201410337732A CN 104133991 A CN104133991 A CN 104133991A
Authority
CN
China
Prior art keywords
fermentation process
space
data set
penicillin fermentation
fault
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201410337732.XA
Other languages
Chinese (zh)
Other versions
CN104133991B (en
Inventor
张颖伟
孙荣荣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Northeastern University China
Original Assignee
Northeastern University China
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Northeastern University China filed Critical Northeastern University China
Priority to CN201410337732.XA priority Critical patent/CN104133991B/en
Priority claimed from CN201410337732.XA external-priority patent/CN104133991B/en
Publication of CN104133991A publication Critical patent/CN104133991A/en
Application granted granted Critical
Publication of CN104133991B publication Critical patent/CN104133991B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Micro-Organisms Or Cultivation Processes Thereof (AREA)

Abstract

本发明提供一种基于核偏最小二乘重构的青霉素发酵过程故障诊断方法,包括:采集青霉素发酵过程的离线历史正常数据;分别对青霉素发酵过程操作变量离线历史正常数据集和青霉素发酵过程状态变量离线历史正常数据集进行规范及标准化;利用改进的核偏最小二乘方法建立青霉素发酵过程的故障监测模型;在线监测青霉素发酵过程的故障;建立基于改进的核偏最小二乘重构的青霉素发酵过程故障相关方向模型;进行青霉素发酵过程故障诊断。本发明将输入空间划分为:与输出直接相关的主元空间,与输出无关的主元空间以及与输出无关的残差空间。与传统方法相比,既监测到了和输出相关的输入变量,又精确的监测到和输入相关的变量。

The invention provides a penicillin fermentation process fault diagnosis method based on kernel partial least squares reconstruction, comprising: collecting offline historical normal data of penicillin fermentation process; Standardize and standardize variable offline historical normal data sets; use the improved nuclear partial least squares method to establish a fault monitoring model for the fermentation process of penicillin; monitor the faults of the penicillin fermentation process online; Correlation direction model for fermentation process faults; fault diagnosis for penicillin fermentation process. The invention divides the input space into: the pivot space directly related to the output, the pivot space irrelevant to the output and the residual space irrelevant to the output. Compared with the traditional method, it not only monitors the input variables related to the output, but also accurately monitors the variables related to the input.

Description

Based on the penicillin fermentation process method for diagnosing faults of core offset minimum binary reconstruct
Technical field
The invention belongs to Fault monitoring and diagnosis technical field, be specifically related to a kind of penicillin fermentation process method for diagnosing faults based on the reconstruct of core offset minimum binary.
Background technology
Penicillin belongs to antibiotic one, it is a kind of secondary metabolic product, as shown in Figure 1, the whole production cycle comprises 4 physiology phases to its fermentation schematic flow sheet: response lag phase, thalline ramp phase, penicillin synthesis phase and thalline death (self-dissolving) phase; 2 physics sub-periods: cell cultivation stage (is called again the batch operation stage, corresponding the first two physiology phase, approximately continue 45h) and the penicillin fed-batch fermentation stage (be called again the fed-batch operational phase, corresponding latter two physiology phase, approximately continue 355h).In the sweat of penicillin, pH value and temperature adopt closed-loop control, and feed supplement adopts the control of open loop definite value, by the pH value in control course of reaction and the temperature in fermentation reactor, can make reaction carry out under top condition.As secondary microbial metabolism, the common way of this sweat is: carry out first under certain conditions the cultivation of microorganism, this is the initial incubation stage; Then by constantly supplementing glucose, promote the synthetic of penicillin, this is the penicillin fermentation stage, and this stage, required cell all produced in the initial incubation stage.At fermentation stage, penicillin starts to generate as metabolic product, through exponential phase, is continued until repose period.
Because the most penicillin fermentation process automaticities of China are also lower at present, often there will be in process of production the frequent situation about occurring of fault and abnormal conditions.Wherein, controlling when foam, if natural oil used the respiratory metabolism that can affect at most thalline, if the amount of natural oil the speed of impact fermentation at least.In controlling foam, also need to add acid, alkali to regulate the pH value of fermentation, too much or very few acid, alkali all can affect the pH value of fermentation, thereby cause penicillin fermentation failure.In addition, at cell cultivation stage, the concentration of thalline is low, and nutrient culture media is nutritious, easily forms microbiological contamination.Penicillin fermentation in earlier stage, after microbiological contamination, easily breed by miscellaneous bacteria, divides with production bacterium contention nutritional labeling and oxygen, and severe jamming is produced the growth and breeding of bacterium and the generation of product, disturbs the production order, the destruction production schedule; Ferment middle microbiological contamination meeting severe jamming is produced the metabolism of bacterium, affects the generation of product, now, generally can adopt the way of " pouring in down a chimney ", can cause like this increase of a large amount of raw-material wastes and operation cost.Therefore need to diagnose in time the abnormal and fault occurring in penicillin fermentation process.
Summary of the invention
The problem existing for prior art, the invention provides a kind of penicillin fermentation process method for diagnosing faults based on the reconstruct of core offset minimum binary.
Technical scheme of the present invention is achieved in that
Based on the penicillin fermentation process method for diagnosing faults of core offset minimum binary reconstruct, comprise the following steps:
Step 1: gather the historical normal data of off-line of penicillin fermentation process, comprise the historical normal data set of penicillin fermentation process performance variable off-line and the historical normal data set of penicillin fermentation process state variable off-line;
Penicillin fermentation process performance variable comprises the temperature of temperature, pH value and the fermentation reactor of flow velocity, the substrate feeding of ventilation rate, agitator power, substrate feeding;
Penicillin fermentation process state variable comprises the concentration of penicillin, the heat that penicillin reaction produces, concentration, the volume of nutrient culture media and the concentration of thalline of carbon dioxide;
Step 2: respectively the historical normal data set of penicillin fermentation process performance variable off-line and the historical normal data set of penicillin fermentation process state variable off-line are carried out to specification and standardization;
Step 3: utilize improved core offset minimum binary method to set up the malfunction monitoring model of penicillin fermentation process, this model be input as the historical normal data set of penicillin fermentation process performance variable off-line, this model is output as the historical normal data set of penicillin fermentation process state variable off-line;
Step 3.1: data core mapping: historical penicillin fermentation process performance variable off-line normal data set is mapped to high-dimensional feature space by kernel function from original data space;
Step 3.2: utilize kernel partial least squares that historical penicillin fermentation process performance variable off-line normal data set and the historical normal data set of penicillin fermentation process state variable off-line are divided into respectively to principal component space and residual error space;
Step 3.3: utilize principal component space that kernel principal component analysis is residual error space by the residual error spatial division of historical penicillin fermentation process performance variable off-line normal data set and the residual error space in residual error space, and then obtain the malfunction monitoring model of penicillin fermentation process:
Historical penicillin fermentation process performance variable off-line normal data set is expressed as to data set, the data set of principal component space in residual error space and the data set sum in the residual error space in residual error space of its principal component space, historical penicillin fermentation process state variable off-line normal data set is expressed as to the data set of its principal component space and the data set sum in residual error space;
Step 4: utilize the malfunction monitoring model of penicillin fermentation process, the fault of on-line monitoring penicillin fermentation process;
Step 4.1: obtain online penicillin fermentation process performance variable data and penicillin fermentation process state variable data;
Step 4.2: the penicillin fermentation process performance variable data of obtaining online and penicillin fermentation process state variable data are carried out to specification and standardization;
Step 4.3: data core mapping: the penicillin fermentation process performance variable data of obtaining are online mapped to high-dimensional feature space by kernel function from original data space;
Step 4.4: calculate Hotelling statistic in the principal component space of the historical normal data set of penicillin fermentation process performance variable off-line of the penicillin fermentation process performance variable data obtained online, online Hotelling statistic in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line of the penicillin fermentation process performance variable data obtained and the penicillin fermentation process performance variable data obtained the online SPE statistic in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line;
Step 4.5: the Hotelling statistic of the penicillin fermentation process performance variable data of obtaining online that judgement calculates in the principal component space of the historical normal data set of penicillin fermentation process performance variable off-line, in the Hotelling statistic of the penicillin fermentation process performance variable data of obtaining online in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line and the penicillin fermentation process performance variable data obtained the online SPE statistic in the residual error space of penicillin fermentation process performance variable off-line history normal data set, whether there is at least one statistic higher than its corresponding confidence limit: be, current penicillin fermentation process breaks down, execution step 5, otherwise return to step 4.1,
Step 5: set up the relevant direction model of penicillin fermentation process fault based on the reconstruct of improved core offset minimum binary;
Step 5.1: gather the off-line historical failure data of penicillin fermentation process, comprise penicillin fermentation process performance variable off-line historical failure data set and penicillin fermentation process state variable off-line historical failure data set;
Step 5.2: penicillin fermentation process performance variable off-line historical failure data set and penicillin fermentation process state variable off-line historical failure data set are carried out to specification and standardization;
Step 5.3: penicillin fermentation process performance variable off-line historical failure data set is mapped to high-dimensional feature space by kernel function from original data space;
Step 5.4: according to the historical normal data set of penicillin fermentation process performance variable off-line and penicillin fermentation process performance variable off-line historical failure data set, the fault related direction of the principal component space of reconstruct penicillin fermentation process performance variable off-line historical failure data set;
Step 5.4.1: utilize core offset minimum binary method that penicillin fermentation process performance variable off-line historical failure data set and the historical normal data set of penicillin fermentation process performance variable off-line are divided respectively to principal component space and residual error space, obtain respectively the core partial least square model of penicillin fermentation process performance variable off-line historical failure data set and the core partial least square model of the historical normal data set of penicillin fermentation process performance variable off-line;
Step 5.4.2: the data set of the principal component space of historical penicillin fermentation process performance variable off-line normal data set respectively orthogonal mapping to the load matrix in the load matrix of the principal component space of penicillin operational process performance variable off-line historical failure data set and the residual error space of penicillin operational process performance variable off-line historical failure data set, obtain the data set in the residual error space of the principal component space of the penicillin fermentation process performance variable off-line history normal data set after data set and the orthogonal mapping of principal component space of the principal component space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping;
Step 5.4.3: utilize kernel principal component analysis to determine the pivot of the data set in the residual error space of the principal component space of the historical normal data set of penicillin fermentation process performance variable off-line after pivot and the orthogonal mapping of data set of the principal component space of the principal component space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping;
Step 5.4.4: the pivot in the load matrix direction in the residual error space of the principal component space of the historical normal data set of penicillin fermentation process performance variable off-line of the data set in the pivot in the load matrix direction of the principal component space of the principal component space of the historical normal data set of penicillin fermentation process performance variable off-line of the data set of principal component space of asking respectively penicillin fermentation process performance variable off-line historical failure data set after orthogonal mapping and the residual error space of penicillin fermentation process performance variable off-line historical failure data set after orthogonal mapping, obtains respectively the fault pivot of principal component space of penicillin fermentation process performance variable off-line historical failure data set and the fault pivot in the residual error space of penicillin fermentation process performance variable off-line historical failure data set;
Step 5.4.5: proportion in the pivot of the principal component space of the principal component space of the historical normal data set of penicillin fermentation process performance variable off-line of the fault pivot of the principal component space of calculating penicillin fermentation process performance variable off-line historical failure data set after orthogonal mapping, proportion in the pivot in the residual error space of the principal component space of the historical normal data set of penicillin fermentation process performance variable off-line of the fault pivot in the residual error space of calculating penicillin fermentation process performance variable off-line historical failure data set after orthogonal mapping;
Step 5.4.6: the fault pivot that is greater than the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after fault pivot and the orthogonal mapping of principal component space of the corresponding penicillin fermentation process performance variable of the each ratio value off-line historical failure data set of the ratio lower limit of setting in two class ratio values forms respectively the pivot direction of principal component space of new penicillin fermentation process performance variable off-line historical failure data set and the pivot direction in the residual error space of new penicillin fermentation process performance variable off-line historical failure data set;
Step 5.4.7: load matrix corresponding to pivot direction of utilizing the residual error space of load matrix corresponding to the pivot direction of principal component space of new penicillin fermentation process performance variable off-line historical failure data set and new penicillin fermentation process performance variable off-line historical failure data set, the load matrix in the residual error space of the principal component space of the load matrix of the principal component space of the principal component space of the historical normal data set of reconstruct penicillin fermentation process performance variable off-line and the historical normal data set of penicillin fermentation process performance variable off-line, it is the fault related direction of the principal component space of penicillin fermentation process performance variable off-line historical failure data set,
Step 5.5: according to the fault related direction of the principal component space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line and penicillin fermentation process performance variable off-line historical failure Data set reconstruction penicillin fermentation process performance variable off-line historical failure data set;
Step 5.5.1: utilize core pivot element analysis method, be the principal component space in residual error space and the residual error space in residual error space by the residual error spatial division of the residual error space of penicillin fermentation process performance variable off-line historical failure data set and the historical normal data set of penicillin fermentation process performance variable off-line respectively, obtain respectively the kernel pivot model in residual error space of penicillin fermentation process performance variable off-line historical failure data set and the kernel pivot model in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line;
Step 5.5.2: the data set of the principal component space in the residual error space of historical penicillin fermentation process performance variable off-line normal data set respectively orthogonal mapping to the load matrix in the residual error space in the load matrix of the principal component space in the residual error space of penicillin fermentation process performance variable off-line historical failure data set and the residual error space of penicillin fermentation process performance variable off-line historical failure data set, obtain the data set in the residual error space in the residual error space of the penicillin fermentation process performance variable off-line history normal data set after data set and the orthogonal mapping of principal component space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping;
Step 5.5.3: utilize kernel principal component analysis to determine the pivot of the data set in the residual error space in the residual error space of the penicillin fermentation process performance variable off-line historical failure data set after pivot and the orthogonal mapping of data set of the principal component space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping;
Step 5.5.4: the pivot in the load matrix direction of the principal component space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line of the data set of principal component space of asking the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping, pivot in the load matrix direction in the residual error space in the residual error space of the penicillin fermentation process performance variable off-line historical failure data set of the data set in residual error space of asking the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping, it is the fault pivot in the fault pivot of principal component space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line and the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line,
Step 5.5.5: proportion in the pivot of the principal component space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line of the fault pivot of the principal component space in the residual error space of the historical normal data set of calculating penicillin fermentation process performance variable off-line after orthogonal mapping, proportion in the pivot of fault pivot principal component space in the residual error space of penicillin fermentation process performance variable off-line historical failure data set after orthogonal mapping in the residual error space in the residual error space of the historical normal data set of calculating penicillin fermentation process performance variable off-line;
Step 5.5.6: the fault pivot that is greater than the residual error space in the fault pivot of principal component space in the residual error space of the corresponding penicillin fermentation process performance variable of the each ratio value off-line historical failure data set of the ratio lower limit of setting and the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line in two class ratio values forms respectively the pivot direction in the pivot direction of principal component space in the residual error space of new penicillin fermentation process performance variable off-line historical failure data set and the residual error space in the residual error space of new penicillin fermentation process performance variable off-line historical failure data set;
Step 5.5.7: load matrix corresponding to pivot direction of utilizing the residual error space in the residual error space of load matrix corresponding to the pivot direction of principal component space in the residual error space of new penicillin fermentation process performance variable off-line historical failure data set and new penicillin fermentation process performance variable off-line historical failure data set, the load matrix in the residual error space in the load matrix of the principal component space in the residual error space of reconstruct penicillin fermentation process performance variable off-line historical failure data set and the residual error space of penicillin fermentation process performance variable off-line historical failure data set, it is the fault related direction of the principal component space in the residual error space of penicillin fermentation process performance variable off-line historical failure data set,
Step 5.6: according to the fault related direction in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line and penicillin fermentation process performance variable off-line historical failure Data set reconstruction penicillin fermentation process performance variable off-line historical failure data set;
Step 5.6.1: by the data set in the residual error space in the residual error space of historical penicillin fermentation process performance variable off-line normal data set respectively orthogonal mapping to the load matrix in the residual error space in the load matrix of the principal component space in the residual error space of penicillin fermentation process performance variable off-line historical failure data set and the residual error space of penicillin fermentation process performance variable off-line historical failure data set, obtain the residual error space in the residual error space in the residual error space of the penicillin fermentation process performance variable off-line history normal data set after principal component space and the orthogonal mapping in residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping;
Step 5.6.2: utilize kernel principal component analysis to determine the pivot of the data set in the residual error space in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after pivot and the orthogonal mapping of data set of the principal component space in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping;
Step 5.6.3: the load matrix that the data set of the principal component space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line is mapped to the principal component space in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping, the data set in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line is mapped to the load matrix in the residual error space in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping, obtain the data set of the mapping space in the residual error space in the data set of mapping space of the principal component space in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line and the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line,
Step 5.6.4: the data set of the principal component space in the residual error space of calculating penicillin fermentation process performance variable off-line historical failure data set is to the distance of the load matrix of the data set of the mapping space of the principal component space in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line, the data set in the residual error space in the residual error space of the historical normal data set of calculating penicillin fermentation process performance variable off-line is to the distance of the load matrix of the data set of the mapping space in the residual error space in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line, and calculate the ratio of two distances,
Step 5.6.5: the data set in the residual error space in the residual error space of calculating penicillin fermentation process performance variable off-line historical failure data set is to the distance of the load matrix of the data set of the mapping space of the principal component space in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line, the data set in the residual error space in the residual error space of the historical normal data set of calculating penicillin fermentation process performance variable off-line is to the distance of the load matrix of the data set of the mapping space in the residual error space in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line, and calculate the ratio of two distances,
Step 5.6.6: the ratio of this two classes distance is greater than the pivot direction that the principal component space in residual error space of penicillin fermentation process performance variable off-line historical failure data set that the ratio of its all distances of setting ratio lower limit is corresponding and the residual error space in the residual error space of penicillin fermentation process performance variable off-line historical failure data set form respectively the residual error space in the pivot direction of principal component space in the residual error space in the residual error space of new penicillin fermentation process performance variable off-line historical failure data set and the residual error space in the residual error space of new penicillin fermentation process performance variable off-line historical failure data set;
Step 5.6.7: utilize the pivot direction in the residual error space in the pivot direction of principal component space in the residual error space in the residual error space of new penicillin fermentation process performance variable off-line historical failure data set and the residual error space in the residual error space of new penicillin fermentation process performance variable off-line historical failure data set, the fault related direction in the residual error space in the residual error space of the historical normal data set of reconstruct penicillin fermentation process performance variable off-line;
Step 5.7: for all faults of penicillin fermentation process, applying step 5.1-5.6 reconstructs respectively the fault related direction of the principal component space of penicillin fermentation process performance variable off-line historical failure data set, the fault related direction of the principal component space in the residual error space of penicillin fermentation process performance variable off-line historical failure data set, the fault related direction in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line forms the penicillin fermentation process fault related direction based on the reconstruct of improved core offset minimum binary, thereby set up the model bank of the penicillin fermentation process fault related direction of improved core offset minimum binary reconstruct,
Step 6: utilize the relevant direction model of penicillin fermentation process fault to carry out penicillin fermentation process fault diagnosis;
Step 6.1: according to the fault related direction of the principal component space of penicillin fermentation process performance variable off-line historical failure data set, calculate score matrix and the corresponding Hotelling statistic thereof of the principal component space of the penicillin fermentation process performance variable data of obtaining online;
Step 6.2: according to the fault related direction of the principal component space in the residual error space of penicillin fermentation process performance variable off-line historical failure data set, calculate score matrix and the corresponding Hotelling statistic thereof in the residual error space of the penicillin fermentation process performance variable data of obtaining online;
Step 6.3: according to the fault related direction in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line, calculate the SPE statistic in the residual error space of the penicillin fermentation process performance variable data of obtaining online;
Step 6.4: the Hotelling statistic of the principal component space of the penicillin fermentation process performance variable data obtained online of judgement, online the residual error space of the penicillin fermentation process performance variable data obtained Hotelling statistic, whether the SPE statistic in the residual error space of the penicillin fermentation process performance variable data obtained all lower than the confidence limit separately of setting online, be,, when prior fault is fault real in penicillin fermentation process, be out of order combination or new fault otherwise work as prior fault.
Beneficial effect:
1. in the monitoring of traditional kernel partial least squares: have some variablees and output orthogonal in (1) principal component space, these variablees are irrelevant with output; (2) kernel partial least squares is not as kernel principal component analysis, the method of successively decreasing according to eigenwert is extracted pivot, therefore the variable in residual error space is not applied the problem of SPE statistic monitoring for classic method, the present invention is divided into the input space: with the directly related principal component space of output, with the irrelevant principal component space (principal component space in residual error space) of output and with the irrelevant residual error space (the residual error space in residual error space) of output.Compared with classic method, both monitored the input variable relevant with output, monitor accurately again and input relevant variable.
2,, thus the method for improved Kernel partial least squares regression is reconstructed to the different faults type monitoring in penicillin fermentation process.By the method for improved Kernel partial least squares regression, the performance variable that production run is obtained has carried out correlativity processing, use data after treatment to be reconstructed and to set up improved core offset minimum binary reconstruct monitoring model, by the simulation experiment result, validity of the present invention and feasibility have been described.
Brief description of the drawings
Fig. 1 is penicillin fermentation schematic flow sheet;
Fig. 2 is the malfunction monitoring statistical graph of fault 1 data of the specific embodiment of the invention;
(a) be the Hotelling statistics spirogram that obtains online the principal component space of penicillin fermentation process performance variable data;
(b) be the Hotelling statistics spirogram that obtains online the residual error space of penicillin fermentation process performance variable data;
(c) for obtaining online the SPE in the residual error space of penicillin fermentation process performance variable data xstatistics spirogram;
Wherein, curve 1: the Hotelling statistic of obtaining online the principal component space of penicillin fermentation process performance variable data; Curve 2: the confidence limit of obtaining online the Hotelling statistic of the principal component space of penicillin fermentation process performance variable data; Curve 3: the Hotelling statistic of obtaining online the residual error space of penicillin fermentation process performance variable data; Curve 4: the confidence limit of obtaining online the Hotelling statistic in the residual error space of penicillin fermentation process performance variable data; Curve 5: the SPE statistic SPE that obtains online the residual error space of penicillin fermentation process performance variable data x; Curve 6: the SPE statistic SPE that obtains online the residual error space of penicillin fermentation process performance variable data xconfidence limit;
Fig. 3 is the malfunction monitoring statistical graph of fault 2 data of the specific embodiment of the present invention;
(a) be the Hotelling statistics spirogram that obtains online the principal component space of penicillin fermentation process performance variable data;
(b) be the Hotelling statistics spirogram that obtains online the residual error space of penicillin fermentation process performance variable data;
(c) for obtaining online the SPE in the residual error space of penicillin fermentation process performance variable data xstatistics spirogram;
Wherein, curve 7: the Hotelling statistic of obtaining online the principal component space of penicillin fermentation process performance variable data; Curve 8: the confidence limit of obtaining online the Hotelling statistic of the principal component space of penicillin fermentation process performance variable data; Curve 9: the Hotelling statistic of obtaining online the residual error space of penicillin fermentation process performance variable data; Curve 10: the confidence limit of obtaining online the Hotelling statistic in the residual error space of penicillin fermentation process performance variable data; Curve 11: the SPE statistic SPE that obtains online the residual error space of penicillin fermentation process performance variable data x; Curve 12: the SPE statistic SPE that obtains online the residual error space of penicillin fermentation process performance variable data xconfidence limit;
Fig. 4 is the fault diagnosis statistics spirogram of fault 1 data of the specific embodiment of the present invention;
(a) be the Hotelling statistics spirogram of the principal component space of the performance variable data of fault related direction tracing trouble 1 data of fault 1 data foundation;
(b) be the Hotelling statistics spirogram in the residual error space of the performance variable data of fault related direction tracing trouble 1 data of fault 1 data foundation;
(c) be the SPE statistic SPE in the residual error space of the performance variable data of fault related direction tracing trouble 1 data of fault 1 data foundation xfigure;
Wherein, curve 13: the Hotelling statistic of the principal component space of the performance variable data of fault related direction tracing trouble 1 data that fault 1 data are set up; Curve 14: the confidence limit of the Hotelling statistic of the principal component space of the performance variable data of fault related direction tracing trouble 1 data that fault 1 data are set up; Curve 15: the Hotelling statistic in the residual error space of the performance variable data of fault related direction tracing trouble 1 data that fault 1 data are set up; Curve 16: the confidence limit of the Hotelling statistic in the residual error space of the performance variable data of fault related direction tracing trouble 1 data that fault 1 data are set up; Curve 17: the SPE statistic SPE in the residual error space of the performance variable data of fault related direction tracing trouble 1 data that fault 1 data are set up x; Curve 18: the SPE statistic SPE in the residual error space of the performance variable data of fault related direction tracing trouble 1 data that fault 1 data are set up xconfidence limit;
Fig. 5 is the fault diagnosis statistics spirogram of fault 1 data of the specific embodiment of the present invention;
(a) be the Hotelling statistics spirogram of the principal component space of the performance variable data of fault related direction tracing trouble 1 data of fault 2 data foundation;
(b) be the Hotelling statistics spirogram in the residual error space of the performance variable data of fault related direction tracing trouble 1 data of fault 2 data foundation;
(c) be the SPE statistic SPE in the residual error space of the performance variable data of fault related direction tracing trouble 1 data of fault 2 data foundation xfigure;
Wherein, curve 19: the Hotelling statistic of principal component space of the performance variable data of fault related direction tracing trouble 1 data of setting up for fault 2 data; Curve 20: the confidence limit of Hotelling statistic of the principal component space of the performance variable data of fault related direction tracing trouble 1 data of setting up for fault 2 data; Curve 21: the Hotelling statistic in residual error space of the performance variable data of fault related direction tracing trouble 1 data of setting up for fault 2 data; Curve 22: the confidence limit of Hotelling statistic in the residual error space of the performance variable data of fault related direction tracing trouble 1 data of setting up for fault 2 data; Curve 23: the SPE statistic SPE in residual error space of the performance variable data of fault related direction tracing trouble 1 data of setting up for fault 2 data x; Curve 24: the SPE statistic SPE in residual error space of the performance variable data of fault related direction tracing trouble 1 data of setting up for fault 2 data xconfidence limit;
Fig. 6 is the fault diagnosis statistics spirogram of fault 2 data of the specific embodiment of the present invention;
(a) be the Hotelling statistics spirogram of the principal component space of the performance variable data of fault related direction tracing trouble 2 data of fault 2 data foundation;
(b) be the Hotelling statistics spirogram in the residual error space of the performance variable data of fault related direction tracing trouble 2 data of fault 2 data foundation;
(c) be the SPE statistic SPE in the residual error space of the performance variable data of fault related direction tracing trouble 2 data of fault 2 data foundation xfigure;
Wherein, curve 25: the Hotelling statistic of principal component space of the performance variable data of fault related direction tracing trouble 2 data of setting up for fault 2 data; Curve 26: the confidence limit of Hotelling statistic of the principal component space of the performance variable data of fault related direction tracing trouble 2 data of setting up for fault 2 data; Curve 27: the Hotelling statistic in residual error space of the performance variable data of fault related direction tracing trouble 2 data of setting up for fault 2 data; Curve 28: the confidence limit of Hotelling statistic in the residual error space of the performance variable data of fault related direction tracing trouble 2 data of setting up for fault 2 data; Curve 29: the SPE statistic SPE in residual error space of the performance variable data of fault related direction tracing trouble 2 data of setting up for fault 2 data x; Curve 30: the SPE statistic SPE in residual error space of the performance variable data of fault related direction tracing trouble 2 data of setting up for fault 2 data xconfidence limit;
Fig. 7 is the fault diagnosis statistics spirogram of fault 2 data of the specific embodiment of the present invention;
(a) be the Hotelling statistics spirogram of the principal component space of the performance variable data of fault related direction tracing trouble 2 data of fault 1 data foundation;
(b) be the Hotelling statistics spirogram in the residual error space of the performance variable data of fault related direction tracing trouble 2 data of fault 1 data foundation;
(c) be the SPE statistic SPE in the residual error space of the performance variable data of fault related direction tracing trouble 2 data of fault 1 data foundation xfigure;
Wherein, curve 31: the Hotelling statistic of principal component space of the performance variable data of fault related direction tracing trouble 2 data of setting up for fault 1 data; Curve 32: the confidence limit of Hotelling statistic of the principal component space of the performance variable data of fault related direction tracing trouble 2 data of setting up for fault 1 data; Curve 33: the Hotelling statistic in residual error space of the performance variable data of fault related direction tracing trouble 2 data of setting up for fault 1 data; Curve 34: the confidence limit of Hotelling statistic in the residual error space of the performance variable data of fault related direction tracing trouble 2 data of setting up for fault 1 data; Curve 35: the SPE statistic SPE in residual error space of the performance variable data of fault related direction tracing trouble 2 data of setting up for fault 1 data x; Curve 36: the SPE statistic SPE in residual error space of the performance variable data of fault related direction tracing trouble 2 data of setting up for fault 1 data xconfidence limit;
Fig. 8 is the penicillin fermentation process method for diagnosing faults process flow diagram based on the reconstruct of core offset minimum binary of the specific embodiment of the present invention.
Embodiment
Below in conjunction with accompanying drawing, the specific embodiment of the present invention is elaborated.
Because the fault in penicillin fermentation process is Protean, even if the input of the different faults of same performance variable is also different on the impact of state variable, but finally all can affect output and the quality of penicillin.
In present embodiment there is two kinds of dissimilar faults---Class1 and type 2 in the ventilation rate of penicillin fermentation process, represent respectively step fault and slope fault, the penicillin fermentation process method for diagnosing faults of application based on the reconstruct of core offset minimum binary diagnosed for the fault type 1 of ventilation rate and the penicillin fermentation process of 2 two kinds of different fault types of type.
Based on the penicillin fermentation process method for diagnosing faults of core offset minimum binary reconstruct, as shown in Figure 8, comprise the following steps:
Step 1: gather the historical normal data of off-line of penicillin fermentation process, comprise the historical normal data set Χ '=[x of penicillin fermentation process performance variable off-line 1..., x b] ∈ (J × B) and the historical normal data set Y '=[y of penicillin fermentation process state variable off-line 1..., y b] ∈ (J ' × B), wherein, the number that subscript B is data sampling, J ', J are variable number;
Penicillin fermentation process performance variable comprises the temperature of temperature, pH value and the fermentation reactor of flow velocity, the substrate feeding of ventilation rate, agitator power, substrate feeding;
Penicillin fermentation process state variable comprises the concentration of penicillin, the heat that penicillin reaction produces, concentration, the volume of nutrient culture media and the concentration of thalline of carbon dioxide;
The historical normal data set of each penicillin fermentation process performance variable off-line and the historical normal data set of penicillin fermentation process state variable off-line respectively comprise 300 samples;
Step 2: respectively to the historical normal data set Χ '=[x of penicillin fermentation process performance variable off-line 1..., x b] and the historical normal data set Y '=[y of penicillin fermentation process state variable off-line 1..., y b] carry out specification and standardization: make respectively the historical normal data set Χ '=[x of penicillin fermentation process performance variable off-line 1..., x b] and the historical normal data set Y '=[y of penicillin fermentation process state variable off-line 1..., y b] average be 0 and variance be 1, obtain the historical normal data set Χ=[x of specification and standardized penicillin fermentation process state variable off-line 1..., x b] and specification and the historical normal data set Y=[y of standardized penicillin fermentation process state variable off-line 1..., y b];
Step 3: utilize improved core offset minimum binary method to set up the malfunction monitoring model of penicillin fermentation process, this model be input as the historical normal data set Χ=[x of penicillin fermentation process performance variable off-line 1..., x b], this model is output as the historical normal data set Y=[y of penicillin fermentation process state variable off-line 1..., y b];
Step 3.1: data core mapping: historical penicillin fermentation process performance variable off-line normal data set is mapped to high-dimensional feature space by kernel function Φ from original data space, i.e. X → Φ (X);
Step 3.2: utilize kernel partial least squares that historical penicillin fermentation process performance variable off-line normal data set Χ and the historical normal data set Y of penicillin fermentation process state variable off-line are divided into respectively to principal component space and residual error space;
Step 3.3: utilize principal component space that kernel principal component analysis is residual error space by the residual error spatial division of historical penicillin fermentation process performance variable off-line normal data set Χ and the residual error space in residual error space, and then obtain the malfunction monitoring model of penicillin fermentation process: the data set that historical penicillin fermentation process performance variable off-line normal data set is expressed as to its principal component space, the data set sum in the residual error space in the data set of the principal component space in residual error space and residual error space, historical penicillin fermentation process state variable off-line normal data set is expressed as to the data set of its principal component space and the data set sum in residual error space,
Φ ( X ) T = TP T + T x P x T + Φ ( X ‾ ) T Y T = T Q T + Y ‾ T - - - ( 1 )
Wherein, subscript T represents transposition, TP tfor the data set of the principal component space of the historical normal data set Χ of penicillin fermentation process performance variable off-line, for the data set in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line, T xp x tfor the data set of the principal component space in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line, for the data set in the residual error space in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line, TQ tfor the data set of the principal component space of the historical normal data set Y of penicillin fermentation process state variable off-line, for the data set in the residual error space of the historical normal data set Y of penicillin fermentation process state variable off-line; T is the score matrix of the principal component space of the historical normal data set Χ of penicillin fermentation process performance variable off-line, and P is the load matrix of the principal component space of the historical normal data set Χ of penicillin fermentation process performance variable off-line, T xfor the score matrix of the principal component space in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line, P xfor the load matrix of the principal component space in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line;
Step 4: utilize the malfunction monitoring model of penicillin fermentation process, the fault of on-line monitoring penicillin fermentation process;
Step 4.1: obtain online penicillin fermentation process performance variable data x ' new∈ (J × 1) and penicillin fermentation process state variable data y ' new∈ (J ' × 1);
Step 4.2: the penicillin fermentation process performance variable data of obtaining online and penicillin fermentation process state variable data are carried out to specification and standardization, obtain the penicillin fermentation process performance variable data x after specification and standardization newpenicillin fermentation process state variable data y after ∈ (J × 1) and specification and standardization new∈ (J ' × 1);
Step 4.3: data core mapping: the penicillin fermentation process performance variable data of obtaining are online mapped to high-dimensional feature space by kernel function Φ from original data space, i.e. x new→ Φ (x new);
Step 4.4: calculate the penicillin fermentation process performance variable data x obtaining online newhotelling statistic (Hotelling-T in the principal component space of the historical normal data set Χ of penicillin fermentation process performance variable off-line 2), the penicillin fermentation process performance variable data x that obtains online newhotelling statistic (Hotelling-T in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line 2) and the penicillin fermentation process performance variable data x that obtains online newat the historical normal data set x of penicillin fermentation process performance variable off-line newresidual error space in SPE statistic;
The penicillin fermentation process performance variable data x obtaining online newhotelling statistic in the principal component space of the historical normal data set Χ of penicillin fermentation process performance variable off-line is as follows:
t new = Φ ( x new ) Φ ( X ) T u k = K t u k T 2 = t new Λ - 1 t new T - - - ( 2 )
In formula, t newfor the penicillin fermentation process performance variable data x obtaining online newnonlinear principal component in high-dimensional feature space; K tfor the penicillin fermentation process performance variable data x obtaining online newwith the inner product vector of the historical normal data set Χ of penicillin fermentation process performance variable off-line, u kfor the latent variable of the historical normal data set Χ of penicillin fermentation process performance variable off-line; Λ is the covariance matrix of the historical normal data set Χ of penicillin fermentation process performance variable off-line; T 2represent the penicillin fermentation process performance variable data x obtaining online newhotelling statistic (Hotelling-T in the principal component space of the historical normal data set Χ of penicillin fermentation process performance variable off-line 2);
The penicillin fermentation process performance variable data x obtaining online newscore vector and Hotelling statistic in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line are as follows:
t x , new = P x T Φ ( x ^ new ) T x 2 = t x , new Λ x - 1 t x , new T - - - ( 3 )
In formula, t x, newfor the penicillin fermentation process performance variable data x obtaining online newresidual error nonlinear principal component in high-dimensional feature space; for x from original data space is mapped to high-dimensional feature space newresidual error, Λ xit is the covariance matrix in the residual error space of the historical normal data set Χ of penicillin operational process off-line; represent x newhotelling statistic in the residual error space of the historical normal data set Χ of penicillin operational process off-line;
The penicillin fermentation process performance variable data x obtaining online newsPE statistic in the residual error space of the historical normal data set Χ of penicillin operational process off-line is as follows:
e x , new = ( I - P x P x T ) Φ ( x ^ new ) SPE x = | | e x , new | | 2 - - - ( 4 )
In formula, e x, newfor the penicillin fermentation process performance variable data x obtaining online newresidual error residual error in high-dimensional feature space, SPE xfor the penicillin fermentation process performance variable data x obtaining online newsPE statistic in the residual error space of the historical normal data set Χ of penicillin operational process off-line;
Step 4.5: the penicillin fermentation process performance variable data x obtaining online that judgement calculates newhotelling statistic T in the principal component space of the historical normal data set Χ of penicillin fermentation process performance variable off-line 2, the penicillin fermentation process performance variable data x that obtains online newhotelling statistic in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line the penicillin fermentation process performance variable data x obtaining online newsPE statistic SPE in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line xin whether have at least one statistic higher than its corresponding confidence limit: be, current penicillin fermentation process breaks down, execution step 5, otherwise return to step 4.1;
Step 5: set up the relevant direction model of penicillin fermentation process fault based on the reconstruct of improved core offset minimum binary;
Step 5.1: gather the off-line historical failure data of penicillin fermentation process, comprise penicillin fermentation process performance variable off-line historical failure data set Χ ' f=[x 1f..., x bf] ∈ (J × B) and penicillin fermentation process state variable off-line historical failure data set Y f'=[y 1f..., y bf] ∈ (J ' × B);
Step 5.2: to penicillin fermentation process performance variable off-line historical failure data set Χ ' f=[x 1f..., x bf] and penicillin fermentation process state variable off-line historical failure data set Y f'=[y 1f..., y bf] carry out specification and standardization:
Make respectively penicillin fermentation process performance variable off-line historical failure data set Χ ' f=[x 1f..., x bf] and penicillin fermentation process state variable off-line historical failure data set Y f'=[y 1f..., y bf] average be 0 and variance be 1, obtain specification and standardized penicillin fermentation process performance variable off-line historical failure data set Χ f=[x 1f..., x bf] and specification and standardized penicillin fermentation process state variable off-line historical failure data set Y f=[y 1f..., y bf];
Step 5.3: penicillin fermentation process performance variable off-line historical failure data set is mapped to high-dimensional feature space by kernel function Φ from original data space, i.e. X f→ Φ (X f);
Step 5.4: according to the historical normal data set Χ of penicillin fermentation process performance variable off-line and penicillin fermentation process performance variable off-line historical failure data set Χ f, reconstruct penicillin fermentation process performance variable off-line historical failure data set Χ fthe fault related direction of principal component space;
Step 5.4.1: utilize core offset minimum binary method by penicillin fermentation process performance variable off-line historical failure data set Χ fhistorical normal data set Χ divides respectively principal component space and residual error space with penicillin fermentation process performance variable off-line, obtains respectively penicillin fermentation process performance variable off-line historical failure data set Χ fcore partial least square model Φ (X f) tcore partial least square model Φ (X) with the historical normal data set Χ of penicillin fermentation process performance variable off-line t;
Φ ( X ) T = Φ ( X ~ ) T + Φ ( X ^ ) T = T P T + Φ ( X ^ ) T = Φ ( X ) T PP T + Φ ( X ^ ) T = Φ ( X ) T Φ ( X ) αα T Φ ( X ) T + Φ ( X ^ ) T = K αα T Φ ( X ) T + Φ ( X ^ ) T - - - ( 5 )
Φ ( X f ) T = Φ ( X ~ f ) T + Φ ( X ^ f ) T = T f P f T + Φ ( X f ) T P f * P f * T = Φ ( X f ) T P f P f T + Φ ( X f ) T P f * P f * T = Φ ( X f ) T Φ ( X f ) α f α f T Φ ( X f ) T + Φ ( X f ) T P f * P f * T = K f α f α f T Φ ( X f ) T + Φ ( X f ) T P f * P f * T - - - ( 6 )
In formula, for the data set of the principal component space of the historical normal data set Χ of penicillin fermentation process performance variable off-line, for the data set in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line, for penicillin fermentation process performance variable off-line historical failure data set Χ fthe data set of principal component space, for penicillin fermentation process performance variable off-line historical failure data set Χ fthe data set in residual error space, α is the proper vector of the principal component space of Φ (X), α ffor Φ (X f) the proper vector of principal component space, P ffor penicillin fermentation process performance variable off-line historical failure data set Χ fthe load matrix of principal component space, for penicillin fermentation process performance variable off-line historical failure data set Χ fthe load matrix in residual error space, K is the historical normal data set Χ of penicillin fermentation process performance variable off-line and the interior product matrix of penicillin fermentation process performance variable off-line history normal data set Χ, K ffor penicillin fermentation process performance variable off-line historical failure data set Χ fwith penicillin fermentation process performance variable off-line historical failure data set Χ finterior product matrix, and P=Φ (X) α, K=Φ (X) tΦ (X), P f=Φ (X f) α f, K f=Φ (X f) tΦ (X f);
Step 5.4.2: the data set of the principal component space of the historical normal data set Χ of penicillin fermentation process performance variable off-line orthogonal mapping is to penicillin operational process performance variable off-line historical failure data set Χ respectively fthe load matrix P of principal component space fwith penicillin operational process performance variable off-line historical failure data set Χ fthe load matrix P in residual error space f *, obtain the books of the principal component space of the principal component space of the historical normal data set Χ of penicillin fermentation process performance variable off-line after orthogonal mapping data set with the residual error space of the principal component space of the historical normal data set Χ of penicillin fermentation process performance variable off-line after orthogonal mapping
Φ ( X ~ nf ) T = Φ ( X ~ ) T P f P f T = Φ ( X ) T P P T P f P f T = Φ ( X ) T Φ ( X ) αα T Φ ( X ) T Φ f ( X ) α f α f T Φ ( X f ) T = K αα T K N α f α f T Φ ( X f ) T - - - ( 7 )
Φ ( X ~ nf ) * T = Φ ( X ~ ) T P f * P f * T = Φ ( X ) T P P T P f * P f * T = Φ ( X ) T Φ ( X ) αα T Φ ( X ) T Φ f ( X ) α f * α f * T Φ ( X f ) T = K αα T K N α f * α f * T Φ ( X f ) T - - - ( 8 )
In formula, for Φ (X f) the proper vector in residual error space, Κ nfor the historical normal data set Χ of penicillin fermentation process performance variable off-line and penicillin operational process performance variable off-line historical failure data set Χ finterior product matrix, k n=Φ (X) tΦ (X f);
Step 5.4.3: utilize kernel principal component analysis to determine the principal component space data set of the principal component space of the historical normal data set Χ of penicillin fermentation process performance variable off-line after orthogonal mapping pivot T cresidual error space data sets with the principal component space of the historical normal data set Χ of penicillin fermentation process performance variable off-line after orthogonal mapping pivot
T c = Φ ( X ~ nf ) T = K αα T K N α f α f T Φ ( X f ) T Φ ( X f ) α f α f T K N T αα T K T α c = K αα T K N α f α f T K f α f α f T K N T αα T K T α c - - - ( 9 )
T c * = Φ ( X ~ nf ) * T p c * = K αα T K N α f * α f * T K f α f * α f * T K N T αα T K T α c * - - - ( 10 )
In above formula, α cfor the proper vector of principal component space, for the proper vector of principal component space, P cfor load matrix, for load matrix, P c = Φ ( X ~ nf ) α c , P c * = Φ ( X ~ nf ) * α c * ;
Step 5.4.4: ask respectively penicillin fermentation process performance variable off-line historical failure data set Χ fthe data set of principal component space the load matrix P of the principal component space of the principal component space of the historical normal data set Χ of penicillin fermentation process performance variable off-line after orthogonal mapping cpivot in direction and penicillin fermentation process performance variable off-line historical failure data set Χ fthe data set in residual error space the load matrix in the residual error space of the principal component space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping pivot in direction, obtains respectively the fault pivot T of the principal component space of penicillin fermentation process performance variable off-line historical failure data set fcfault pivot T with the residual error space of penicillin fermentation process performance variable off-line historical failure data set fc *;
T fc =Φ ( X ~ f ) T P c = Φ ( X ~ f ) T Φ ( X ~ nf ) α c = Φ ( X f ) T P f P f T Φ ( X ~ nf ) α c = K f α f α f T K N α f α f T K N T αα T K T α c - - - ( 11 )
T fc * =Φ ( X ^ f ) T P c * = Φ ( X ^ f ) T Φ ( X ~ nf ) * α c * = Φ ( X f ) T P f * P f * T Φ ( X ~ nf ) * α c * = K f α f * α f * T K N α f * α f * T K N T αα T K T α c * - - - ( 12 )
Step 5.4.5: the fault pivot T that calculates the principal component space of penicillin fermentation process performance variable off-line historical failure data set fcthe pivot T of the principal component space of the principal component space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping cmiddle proportion RT fc, i, calculate the fault pivot T in the residual error space of penicillin fermentation process performance variable off-line historical failure data set fc *the pivot T in the residual error space of the principal component space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping c *middle proportion
RT fc , i = var ( T fc ( : , i ) ) var ( T c ( : , i ) ) ( i = 1,2 , · · · , R c ) - - - ( 13 )
RT fc , i * = var ( T fc * ( : , i ) ) var ( T c * ( : , i ) ) ( i = 1,2 , · · · , R c * ) - - - ( 14 )
In formula, var () represents variance, (:, i) represent that the i of a matrix is listed as, the fault pivot T in above formula fcat pivot T cmiddle proportion RT fc, iwith fault pivot T fc *at pivot T c *middle proportion larger, represent fault data principal component space larger to the contribution of Hotelling statistic along each load direction (being the direction of the load vector representative in load matrix);
Step 5.4.6: the fault pivot that is greater than the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after fault pivot and the orthogonal mapping of principal component space of the corresponding penicillin fermentation process performance variable of the each ratio value off-line historical failure data set of the ratio lower limit of setting in two class ratio values forms respectively the pivot direction R of the principal component space of new penicillin fermentation process performance variable off-line historical failure data set fcpivot direction with the residual error space of new penicillin fermentation process performance variable off-line historical failure data set
Step 5.4.7: the pivot direction R that utilizes the principal component space of new penicillin fermentation process performance variable off-line historical failure data set fccorresponding load matrix P fcpivot direction with the residual error space of new penicillin fermentation process performance variable off-line historical failure data set corresponding load matrix P fc *, the load matrix P of the principal component space of the principal component space of the historical normal data set Χ of reconstruct penicillin fermentation process performance variable off-line cload matrix P with the residual error space of the principal component space of the historical normal data set of penicillin fermentation process performance variable off-line c *, i.e. the fault related direction P of the principal component space of penicillin fermentation process performance variable off-line historical failure data set rec, c;
P rec , c = [ P fc , P fc * ] = [ Φ ( X ~ nf ) α fc , Φ ( X ~ nf ) * α fc * ] - - - ( 15 )
Wherein, α fcfor with pivot direction R fccharacteristic of correspondence vector, α fc *for with pivot direction characteristic of correspondence vector;
Step 5.5: according to the historical normal data set Χ of penicillin fermentation process performance variable off-line and penicillin fermentation process performance variable off-line historical failure data set Χ freconstruct penicillin fermentation process performance variable off-line historical failure data set Χ fthe fault related direction of principal component space in residual error space;
Step 5.5.1: utilize core pivot element analysis method, respectively by penicillin fermentation process performance variable off-line historical failure data set Χ fresidual error space and the residual error spatial division of the historical normal data set Χ of penicillin fermentation process performance variable off-line be the principal component space in residual error space and the residual error space in residual error space, obtain respectively the kernel pivot model in the residual error space of penicillin fermentation process performance variable off-line historical failure data set kernel pivot model with the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line
In formula, for the data set of the principal component space in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line, for the data set in the residual error space in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line, for penicillin fermentation process performance variable off-line historical failure data set Χ fthe data set of principal component space in residual error space, E f tfor penicillin fermentation process performance variable off-line historical failure data set Χ fthe data set in residual error space in residual error space, P xfor the load matrix in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line, P x *for penicillin fermentation process performance variable off-line historical failure data set Χ fthe load matrix in residual error space, α ifor the proper vector of principal component space, α i *for the proper vector in residual error space, α iffor the proper vector of principal component space, α if *for the proper vector in residual error space, P x,ffor penicillin fermentation process performance variable off-line historical failure data set Χ fthe load matrix of principal component space in residual error space, P x,f *for penicillin fermentation process performance variable off-line historical failure data set Χ fthe load matrix in residual error space in residual error space, K ifor the data set in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line data set with the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line interior product matrix, K iffor penicillin fermentation process performance variable off-line historical failure data set Χ fthe data set in residual error space with penicillin fermentation process performance variable off-line historical failure data set Χ fthe data set in residual error space interior product matrix, and P x = Φ ( X ^ ) α i , P x * = Φ ( X ^ ) α i * , K i = Φ ( X ^ ) T Φ ( X ^ ) , P x , f = Φ ( X ^ f ) α if , P x , f * = Φ ( X ^ f ) α if * , K if = Φ ( X ^ f ) T Φ ( X ^ f ) ;
Step 5.5.2: the data set of the principal component space in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line orthogonal mapping is to penicillin fermentation process performance variable off-line historical failure data set Χ respectively fthe load matrix P of principal component space in residual error space x,fwith penicillin fermentation process performance variable off-line historical failure data set Χ fthe load matrix P in residual error space in residual error space x,f *, obtain the data set of the principal component space in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line after orthogonal mapping data set with the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping
In formula, Κ mfor the data set in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line with penicillin fermentation process performance variable off-line historical failure data set Χ fresidual error space data sets interior product matrix, and K M = Φ ( X ^ ) T Φ ( X ^ f ) ;
Step 5.5.3: utilize kernel principal component analysis to determine the data set of the principal component space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping pivot T pdata set with the residual error space in the residual error space of the penicillin fermentation process performance variable off-line historical failure data set after orthogonal mapping pivot T p *;
In formula, α pfor the proper vector of principal component space, for the proper vector of principal component space, P pfor load matrix, for load matrix,
Step 5.5.4: the data set of asking the principal component space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line the load matrix P of the principal component space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping ppivot in direction, asks the data set in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line the load matrix in the residual error space in the residual error space of the penicillin fermentation process performance variable off-line historical failure data set after orthogonal mapping pivot in direction, i.e. the fault pivot T of the principal component space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line fpfault pivot T with the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line fp *;
Step 5.5.5: the fault pivot T that calculates the principal component space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line fpthe pivot T of the principal component space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping pmiddle proportion, calculates the fault pivot in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line the pivot of the principal component space in the residual error space of penicillin fermentation process performance variable off-line historical failure data set after orthogonal mapping middle proportion;
RT fp , i = var ( T fp ( : , i ) ) var ( T p ( : , i ) ) ( i = 1,2 , · · · , R p ) - - - ( 24 )
RT fp , i * = var ( T fp * ( : , i ) ) var ( T p * ( : , i ) ) ( i = 1,2 , · · · , R p * ) - - - ( 25 )
In above formula, fault pivot T fpat pivot T pmiddle proportion RT fp, iwith fault pivot in pivot middle proportion larger, the residual error space of expression penicillin fermentation process performance variable off-line historical failure data set along each load direction to Hotelling statistic contribute larger;
Step 5.5.6: the fault pivot that is greater than the fault pivot of principal component space in the residual error space of the corresponding penicillin fermentation process performance variable of the each ratio value off-line historical failure data set of the ratio lower limit of setting and the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line in two class ratio values forms respectively the pivot direction R of the principal component space in the residual error space of new penicillin fermentation process performance variable off-line historical failure data set fppivot direction with the residual error space in the residual error space of new penicillin fermentation process performance variable off-line historical failure data set
Step 5.5.7: the pivot direction R that utilizes the principal component space in the residual error space of new penicillin fermentation process performance variable off-line historical failure data set fpcorresponding load matrix P fppivot direction with the residual error space in the residual error space of new penicillin fermentation process performance variable off-line historical failure data set corresponding load matrix the load matrix P of the principal component space in the residual error space of reconstruct penicillin fermentation process performance variable off-line historical failure data set pload matrix with the residual error space in the residual error space of penicillin fermentation process performance variable off-line historical failure data set be the fault related direction P of the principal component space in the residual error space of penicillin fermentation process performance variable off-line historical failure data set rec, p;
Wherein, α fpfor with R fpcharacteristic of correspondence vector, α fp *for with characteristic of correspondence vector;
Step 5.6: according to the historical normal data set Χ of penicillin fermentation process performance variable off-line and penicillin fermentation process performance variable off-line historical failure data set Χ freconstruct penicillin fermentation process performance variable off-line historical failure data set Χ fthe fault related direction in residual error space in residual error space;
Step 5.6.1: by the data set E in the residual error space in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line torthogonal mapping is to penicillin fermentation process performance variable off-line historical failure data set Χ respectively fthe load matrix P of principal component space in residual error space x,fload matrix P with the residual error space in the residual error space of penicillin fermentation process performance variable off-line historical failure data set x,f *, obtain the principal component space in the residual error space in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line after orthogonal mapping residual error space with the residual error space in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line after orthogonal mapping
E nf T = E T P x , f P x , f T = Φ ( X ^ ) T P x * P x * T P x , f P x , f T = K i α i * α i * T Φ ( X ^ ) T Φ ( X ^ f ) α if α if T Φ ( X ^ f ) T = K i α i * α i * T K M α if α if T Φ ( X ^ f ) T - - - ( 27 )
E nf * T = E T P x , f * P x , f * T = Φ ( X ^ ) T P x * P x * T P x , f * P x , f * T = K i α i * α i * T Φ ( X ^ ) T Φ ( X ^ f ) α if * α if * T Φ ( X ^ f ) T = K i α i * α i * T K M α if * α if * T Φ ( X ^ f ) T - - - ( 28 )
Step 5.6.2: utilize kernel principal component analysis to determine the data set of the principal component space in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping pivot T edata set with the residual error space in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping pivot
T e = E nf T P e = K i α i * T K M α if α if T Φ ( X ^ f ) T Φ ( X ^ f ) α if α if T K M T α i * α i * T K i T α nf = K i α i * α i * T K M α if α if T K if α if α if T K M T α i * α i * T K i T α nf - - - ( 29 )
T e * = E nf * T P e * = K i α i * α i * T K M α if * α if * T K if α if * α if * T K M T α i * α i * T K i T α nf * - - - ( 30 )
In formula, α nffor Ε nfthe proper vector of principal component space, for Ε nf *the proper vector of principal component space, P efor E nfthe load matrix of principal component space, for Ε nf *the load matrix of principal component space, P e=E nfα nf,
Step 5.6.3: the data set of the principal component space in the residual error space of penicillin fermentation process performance variable off-line historical failure data set be mapped to the load matrix P of the principal component space in the residual error space in the residual error space of the penicillin fermentation process performance variable off-line historical failure data set after orthogonal mapping e, the data set E in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line f tbe mapped to the load matrix in the residual error space in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line after orthogonal mapping obtain the data set of the mapping space of the principal component space in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line data set E with the mapping space in the residual error space in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line f,e;
E f , e = E f T P e * P e * T = K if α if * α if * T K M α if * α if * T K M T α i * α i * T K i T α nf * α nf * T K i α i * α i * T K M α if * α if * T Φ ( X ^ f ) T - - - ( 32 )
Step 5.6.4: calculate penicillin fermentation process performance variable off-line historical failure data set Χ fthe data set of principal component space in residual error space arrive the data set of the mapping space of the principal component space in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line the distance of load matrix, calculate the data set E in residual error space in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line to the data set of the mapping space in the residual error space in the residual error space in the residual error space of penicillin fermentation process performance variable off-line history normal data set the distance of load matrix, and calculate the ratio R T of two distances f, e;
Step 5.6.5: calculate penicillin fermentation process performance variable off-line historical failure data set Χ fthe data set E in residual error space in residual error space farrive the data set of the mapping space of the principal component space in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line the distance of load matrix, calculate the data set E in residual error space in the residual error space of the historical normal data set Χ of penicillin fermentation process performance variable off-line to the data set of the mapping space in the residual error space in the residual error space in the residual error space of penicillin fermentation process performance variable off-line history normal data set the distance of load matrix, and calculate the ratio of two distances
RT f , e * = | | E f P f , e * P f , e * T | | 2 | | EP f , e * P f , e * T | | 2 , ( e = 1,2 , · · · , Be * ) - - - ( 34 )
In formula, || || represent Euclid's length, P f,efor mapping space load matrix, for mapping space E f,eload matrix, this ratio of distances constant is larger, represents the residual error space of penicillin fermentation process performance variable off-line historical failure data set larger to the contribution of SPE statistic along each load direction;
Step 5.6.6: the ratio of this two classes distance is greater than the pivot direction V that the principal component space in residual error space of penicillin fermentation process performance variable off-line historical failure data set that the ratio of its all distances of setting ratio lower limit is corresponding and the residual error space in the residual error space of penicillin fermentation process performance variable off-line historical failure data set form respectively the principal component space in the residual error space in the residual error space of new penicillin fermentation process performance variable off-line historical failure data set fepivot direction with the residual error space in the residual error space in the residual error space of new penicillin fermentation process performance variable off-line historical failure data set
Step 5.6.7: the pivot direction V that utilizes the principal component space in the residual error space in the residual error space of new penicillin fermentation process performance variable off-line historical failure data set fepivot direction with the residual error space in the residual error space in the residual error space of new penicillin fermentation process performance variable off-line historical failure data set the fault related direction P in the residual error space in the residual error space of the historical normal data set of reconstruct penicillin fermentation process performance variable off-line rec, e;
P rec , e = [ V fe , V fe * ] = [ E nf α fe , E nf * , α fe * ] - - - ( 35 )
Wherein, α fefor pivot direction V fecharacteristic of correspondence vector, for pivot direction characteristic of correspondence vector;
Step 5.7: for all faults of penicillin fermentation process, applying step 5.1-5.6 reconstructs respectively the fault related direction P of the principal component space of penicillin fermentation process performance variable off-line historical failure data set rec, c, penicillin fermentation process performance variable off-line historical failure data set the fault related direction P of principal component space in residual error space rec, p, the historical normal data set of penicillin fermentation process performance variable off-line the fault related direction P in residual error space in residual error space rec, eform the penicillin fermentation process fault related direction based on the reconstruct of improved core offset minimum binary, thereby set up the model bank of the penicillin fermentation process fault related direction of improved core offset minimum binary reconstruct;
Step 6: utilize the relevant direction model of penicillin fermentation process fault to carry out penicillin fermentation process fault diagnosis;
Step 6.1: according to the fault related direction P of the principal component space of penicillin fermentation process performance variable off-line historical failure data set rec, c, the score matrix Τ of the principal component space of the penicillin fermentation process performance variable data that calculating is obtained online foand corresponding Hotelling statistic
Φ ( X ~ f , rec , new ) T = Φ ( X ~ f , new ) T P rec , c P rec , c T Φ ( X ~ fo ) T = Φ ( X ~ f , new ) T - Φ ( X ~ f , rec , new ) T - - - ( 36 )
T fo = Φ ( X ~ fo ) T P = Φ ( X ~ f , new ) T P - Φ ( X ~ f , rec , new ) T P = K f , new α f , new α f , new T Φ ( X f , new ) T Φ ( X ) α - Φ ( X ~ f , new ) T P rec , c P rec , c T Φ ( X ) α = K f , new α f , new α f , new T K N , new T α - Φ ( X ~ f , new ) T Φ ( X f ) α f α f T K N T αα T K T α fc α fc T K αα T K N α f α f T Φ ( X f ) T Φ ( X ) α - Φ ( X ~ f , new ) T Φ f ( X ) α f * α f * T K N T αα T K T α fc * α fc * T K αα T K N α f * α f * T Φ ( X f ) T Φ ( X ) α = K f , new α f , new α f , new T K N , new T α - K f , c , new α f α f T K N T αα T K T α fc α fc T K αα T K N α f α f T K f α - K f , c , new α f * α f * T K N T αα T K T α fc * α fc * T K αα T K N α f * α f * T K f α - - - ( 37 )
T fo , i 2 = t fo , i T Λ fo - 1 t fo , i , ( i = 1,2 , · · · , J new ) - - - ( 38 )
In formula, for x newthe set of principal component space, t fofor score matrix Τ forow vector, Λ fofor the covariance matrix of the principal component space of penicillin fermentation process performance variable off-line historical failure data set, J newfor the number of samples of the penicillin fermentation process performance variable data obtained online, K f, newfor the penicillin fermentation process performance variable data x obtaining online newset X newwith the penicillin fermentation process performance variable data x obtaining online newset X newinterior product matrix, K n, newfor the historical normal data set Χ of penicillin fermentation process performance variable off-line and the penicillin fermentation process performance variable data x obtaining online newset X newinterior product matrix, K f, c, newfor the penicillin fermentation process performance variable data x obtaining online newset X newprincipal component space data set and penicillin fermentation process performance variable off-line historical failure data set Χ finterior product matrix, α f, newfor Φ (X f, new) the proper vector of principal component space;
Step 6.2: according to the fault related direction of the principal component space in the residual error space of penicillin fermentation process performance variable off-line historical failure data set, calculate the score matrix Τ in the residual error space of the penicillin fermentation process performance variable data of obtaining online x, foand corresponding Hotelling statistic
T x , fo , i 2 = t x , fo , i T Λ x , fo - 1 t x , fo , i , ( i = 1,2 , · · · , J new ) - - - ( 41 )
In formula, t x, fofor score matrix Τ x, forow vector, Λ x, fofor the covariance matrix in the residual error space of penicillin fermentation process performance variable off-line historical failure data set, K if, newfor the penicillin fermentation process performance variable data x obtaining online newset X newresidual error space data sets with the penicillin fermentation process performance variable data x obtaining online newset X newresidual error space data sets interior product matrix, K i, newfor the residual error space data sets of the historical normal data set Χ of penicillin operational process off-line with the penicillin fermentation process performance variable data x obtaining online newset X newresidual error space data sets interior product matrix, K f, p, newfor the penicillin fermentation process performance variable data x obtaining online newset X newthe principal component space data set in residual error space with penicillin fermentation process performance variable off-line historical failure data set Χ fthe data in residual error space interior product matrix, α if, newfor the proper vector of principal component space;
Step 6.3: according to the barrier related direction in the residual error space in the residual error space of the historical normal data set of penicillin fermentation process performance variable off-line, calculate the SPE statistic in the residual error space of the penicillin fermentation process performance variable data of obtaining online;
SPE x , fo , i = e x , fo . i T e x , fo , i , ( i = 1,2 , · · · , J new ) - - - ( 44 )
In formula, e x, fofor score matrix Ε x, forow vector;
Step 6.4: the Hotelling statistic of the principal component space of the penicillin fermentation process performance variable data that judgement is obtained online the Hotelling statistic in the residual error space of the penicillin fermentation process performance variable data of obtaining online whether the SPE statistic in the residual error space of the penicillin fermentation process performance variable data of obtaining is online all lower than the confidence limit separately of setting, be,, when prior fault is fault real in penicillin fermentation process, be out of order combination or new fault otherwise work as prior fault.
In present embodiment, first choose 300 sampled points of the historical normal data of off-line of penicillin fermentation process, utilize improved core offset minimum binary method to set up the malfunction monitoring model of penicillin fermentation process, then on-line monitoring fault type 1 and fault type 2, the data of table 1~table 5 are partial data:
Table 1 is set up four groups of data in penicillin fermentation process malfunction monitoring model
Table 2 is set up four groups of data in the fault data 1 in the relevant direction model of penicillin fermentation process fault of improved core offset minimum binary reconstruct
Table 3 is set up four groups of data in the fault data 2 in the relevant direction model of penicillin fermentation process fault of improved core offset minimum binary reconstruct
Table 4 is monitored one group of data in the fault data 1 of penicillin fermentation process
Table 5 is monitored one group of data in the fault data 2 of penicillin fermentation process
Can find out the Hotelling statistic of the performance variable principal component space in penicillin fermentation process and the Hotelling statistic in process variable residual error space by Fig. 2 and Fig. 3 in 200 points, all do not exceed confidence limit with SPE statistic, since the 300th sampled point, there is significantly transfiniting phenomenon in above-mentioned three statistics, and this is true to life.Illustrate that the penicillin fermentation process method for diagnosing faults based on the reconstruct of core offset minimum binary can be good at diagnosing out the fault in Penicillium sweat.
Then, the reconstruct fault related direction that 300 history samples points of fault type 1 carry out, inline diagnosis fault type 1, as seen from Figure 4, the Hotelling statistic in the Hotelling statistic of the principal component space of the performance variable in penicillin fermentation process and the residual error space of performance variable all lower than confidence limit, illustrate that fault type 1 is for current fault with SPE statistic, and the relevant direction model of this fault can be good at diagnosis and is out of order.
With the fault related direction on-line monitoring fault type 2 of 300 sampled point reconstruct of fault type 1, as seen from Figure 7, the Hotelling statistic (Hotelling-T of the principal component space of the performance variable in penicillin fermentation process 2) and the Hotelling statistic in the residual error space of performance variable all higher than confidence limit, the relevant direction model of the fault of application fault type 1 can not be diagnosed fault type 2 with SPE statistic.
Utilize equally 300 sampled points of fault type 2 to be reconstructed fault related direction, inline diagnosis fault type 2, as seen from Figure 6, the Hotelling statistic in the Hotelling statistic of the principal component space of the performance variable in penicillin fermentation process and the residual error space of performance variable all lower than confidence limit, explanation fault type 1 is current fault with SPE statistic, and the relevant direction model of this fault can be good at diagnosis and is out of order.
Next, use the fault related direction on-line monitoring fault type 1 of 300 sampled point reconstruct of fault type 2, as seen from Figure 5, the Hotelling statistic (Hotelling-T of the principal component space of the performance variable in penicillin fermentation process 2) and the Hotelling statistic in the residual error space of performance variable all higher than confidence limit, the relevant direction model of the fault of application fault type 2 can not be diagnosed fault type 1 with SPE statistic.
Comparison diagram 4 and Fig. 5 or (Fig. 6 and Fig. 7) can find out that the present invention is to diagnosing the different faults of same performance variable.
Can be obtained by the above results, by penicillin fermentation process method for diagnosing faults of the present invention, can effectively monitor the different faults type of same process variable.
Although more than described the specific embodiment of the present invention, the those skilled in the art in this area should be appreciated that these only illustrate, and can make various changes or modifications to these embodiments, and not deviate from principle of the present invention and essence.Scope of the present invention is only limited by appended claims.

Claims (4)

1.基于核偏最小二乘重构的青霉素发酵过程故障诊断方法,其特征在于:包括以下步骤:1. The penicillin fermentation process fault diagnosis method based on nuclear partial least squares reconstruction, it is characterized in that: comprise the following steps: 步骤1:采集青霉素发酵过程的离线历史正常数据,包括青霉素发酵过程操作变量离线历史正常数据集和青霉素发酵过程状态变量离线历史正常数据集;Step 1: Collect the offline historical normal data of the penicillin fermentation process, including the offline historical normal data set of the operation variable of the penicillin fermentation process and the offline historical normal data set of the state variable of the penicillin fermentation process; 青霉素发酵过程操作变量包括通风率、搅拌器功率、底物喂料的流速、底物喂料的温度、PH值及发酵反应器的温度;The operating variables of the penicillin fermentation process include ventilation rate, agitator power, flow rate of substrate feed, temperature of substrate feed, pH value and temperature of fermentation reactor; 青霉素发酵过程状态变量包括青霉素的浓度、青霉素反应产生的热量、二氧化碳的浓度、培养基的体积和菌体的浓度;The state variables of the penicillin fermentation process include the concentration of penicillin, the heat generated by the penicillin reaction, the concentration of carbon dioxide, the volume of the medium and the concentration of the bacteria; 步骤2:分别对青霉素发酵过程操作变量离线历史正常数据集和青霉素发酵过程状态变量离线历史正常数据集进行规范及标准化;Step 2: Standardize and standardize the offline historical normal data set of the operation variable of the penicillin fermentation process and the offline historical normal data set of the state variable of the penicillin fermentation process; 步骤3:利用改进的核偏最小二乘方法建立青霉素发酵过程的故障监测模型,该模型的输入为青霉素发酵过程操作变量离线历史正常数据集,该模型的输出为青霉素发酵过程状态变量离线历史正常数据集;Step 3: Use the improved kernel partial least squares method to establish a fault monitoring model for the penicillin fermentation process. The input of the model is the off-line history normal data set of the operation variable of the penicillin fermentation process, and the output of the model is the offline history normal of the state variable of the penicillin fermentation process data set; 步骤3.1:数据核映射:将青霉素发酵过程操作变量离线历史正常数据集通过核函数从原始数据空间映射到高维特征空间;Step 3.1: Data Kernel Mapping: Map the offline historical normal data set of operating variables in the penicillin fermentation process from the original data space to the high-dimensional feature space through the kernel function; 步骤3.2:利用核偏最小二乘法将青霉素发酵过程操作变量离线历史正常数据集和青霉素发酵过程状态变量离线历史正常数据集分别划分为主元空间和残差空间;Step 3.2: Use the kernel partial least squares method to divide the offline historical normal data set of the operation variable of the penicillin fermentation process and the offline historical normal data set of the state variable of the penicillin fermentation process into the principal component space and the residual space respectively; 步骤3.3:利用核主元分析法将青霉素发酵过程操作变量离线历史正常数据集的残差空间划分为残差空间的主元空间和残差空间的残差空间,进而得到青霉素发酵过程的故障监测模型:Step 3.3: Using kernel principal component analysis method to divide the residual space of the offline historical normal data set of operating variables in the penicillin fermentation process into the principal component space of the residual space and the residual space of the residual space, and then obtain the fault monitoring of the penicillin fermentation process Model: 将青霉素发酵过程操作变量离线历史正常数据集表示为其主元空间的数据集、残差空间的主元空间的数据集和残差空间的残差空间的数据集之和,将青霉素发酵过程状态变量离线历史正常数据集表示为其主元空间的数据集和残差空间的数据集之和;The offline historical normal data set of the operation variable of the penicillin fermentation process is expressed as the sum of the data set of the pivot space, the data set of the pivot space of the residual space and the data set of the residual space of the residual space, and the state of the penicillin fermentation process is The variable offline historical normal data set is expressed as the sum of the data set in the pivot space and the data set in the residual space; 步骤4:利用青霉素发酵过程的故障监测模型,在线监测青霉素发酵过程的故障;Step 4: Utilize the failure monitoring model of the penicillin fermentation process to monitor the failure of the penicillin fermentation process online; 步骤4.1:在线获取青霉素发酵过程操作变量数据和青霉素发酵过程状态变量数据;Step 4.1: Obtain the operating variable data and the penicillin fermentation state variable data of the penicillin fermentation process online; 步骤4.2:对在线获取的青霉素发酵过程操作变量数据和青霉素发酵过程状态变量数据进行规范及标准化;Step 4.2: standardize and standardize the operational variable data of the penicillin fermentation process and the state variable data of the penicillin fermentation process obtained online; 步骤4.3:数据核映射:将在线获取的青霉素发酵过程操作变量数据通过核函数从原始数据空间映射到高维特征空间;Step 4.3: Data kernel mapping: Map the operating variable data obtained online from the original data space to the high-dimensional feature space through the kernel function; 步骤4.4:计算在线获取的青霉素发酵过程操作变量数据在青霉素发酵过程操作变量离线历史正常数据集的主元空间中的霍特林统计量、在线获取的青霉素发酵过程操作变量数据在青霉素发酵过程操作变量离线历史正常数据集的残差空间中的霍特林统计量和在线获取的青霉素发酵过程操作变量数据在青霉素发酵过程操作变量离线历史正常数据集的残差空间中的SPE统计量;Step 4.4: Calculate the Hotelling statistics in the pivot space of the operating variable data of the penicillin fermentation process obtained online in the off-line historical normal data set of the penicillin fermentation process, and the operating variable data of the penicillin fermentation process obtained online are operated in the penicillin fermentation process The Hotelling statistic in the residual space of the variable offline historical normal data set and the SPE statistic in the residual space of the penicillin fermentation process operating variable data obtained online in the penicillin fermentation process operating variable offline historical normal data set; 步骤4.5:判断计算得到的在线获取的青霉素发酵过程操作变量数据在青霉素发酵过程操作变量离线历史正常数据集的主元空间中的霍特林统计量、在线获取的青霉素发酵过程操作变量数据在青霉素发酵过程操作变量离线历史正常数据集的残差空间中的霍特林统计量和在线获取的青霉素发酵过程操作变量数据在青霉素发酵过程操作变量离线历史正常数据集的残差空间中的SPE统计量中是否有至少一个统计量高于其相应的置信限:是,则当前青霉素发酵过程出现故障,执行步骤5,否则返回步骤4.1;Step 4.5: Judging the calculated Hotelling statistics in the pivot space of the operating variable data of the penicillin fermentation process obtained online in the offline historical normal data set of the penicillin fermentation process, and the operating variable data of the penicillin fermentation process acquired online in the penicillin The Hotelling statistics in the residual space of the offline historical normal data set of the manipulated variable of the fermentation process and the SPE statistics of the manipulated variable data of the penicillin fermentation process acquired online in the residual space of the offline historical normal data set of the manipulated variable of the penicillin fermentation process Whether at least one statistic in is higher than its corresponding confidence limit: yes, then the current penicillin fermentation process is faulty, go to step 5, otherwise return to step 4.1; 步骤5:建立基于改进的核偏最小二乘重构的青霉素发酵过程故障相关方向模型;Step 5: Establish a fault-related direction model in the penicillin fermentation process based on the improved kernel partial least squares reconstruction; 步骤5.1:采集青霉素发酵过程的离线历史故障数据,包括青霉素发酵过程操作变量离线历史故障数据集和青霉素发酵过程状态变量离线历史故障数据集;Step 5.1: Collect the offline historical fault data of the penicillin fermentation process, including the offline historical fault data set of the operation variable of the penicillin fermentation process and the offline historical fault data set of the state variable of the penicillin fermentation process; 步骤5.2:对青霉素发酵过程操作变量离线历史故障数据集和青霉素发酵过程状态变量离线历史故障数据集进行规范及标准化;Step 5.2: Standardize and standardize the off-line historical fault data set of operating variables in the penicillin fermentation process and the offline historical fault data set of the state variables in the penicillin fermentation process; 步骤5.3:将青霉素发酵过程操作变量离线历史故障数据集通过核函数从原始数据空间映射到高维特征空间;Step 5.3: Map the offline historical fault data set of operating variables in the penicillin fermentation process from the original data space to the high-dimensional feature space through the kernel function; 步骤5.4:根据青霉素发酵过程操作变量离线历史正常数据集和青霉素发酵过程操作变量离线历史故障数据集,重构青霉素发酵过程操作变量离线历史故障数据集的主元空间的故障相关方向;Step 5.4: According to the off-line historical normal data set of the operating variable in the penicillin fermentation process and the offline historical fault data set of the operating variable in the penicillin fermentation process, reconstruct the fault-related direction of the pivot space of the offline historical fault data set of the operating variable in the penicillin fermentation process; 步骤5.5:根据青霉素发酵过程操作变量离线历史正常数据集和青霉素发酵过程操作变量离线历史故障数据集重构青霉素发酵过程操作变量离线历史故障数据集的残差空间的主元空间的故障相关方向;Step 5.5: Reconstruct the fault correlation direction of the pivot space of the residual space of the offline historical fault data set of the operational variable of the penicillin fermentation process according to the offline historical normal data set of the operational variable of the penicillin fermentation process and the offline historical fault data set of the operational variable of the penicillin fermentation process; 步骤5.6:根据青霉素发酵过程操作变量离线历史正常数据集和青霉素发酵过程操作变量离线历史故障数据集重构青霉素发酵过程操作变量离线历史故障数据集的残差空间的残差空间的故障相关方向;Step 5.6: Reconstruct the fault-related direction of the residual space of the residual space of the penicillin fermentation process operating variable offline historical fault data set according to the offline historical normal data set of the operating variable in the penicillin fermentation process and the offline historical fault data set of the operating variable in the penicillin fermentation process; 步骤5.7:针对青霉素发酵过程的所有故障,应用步骤5.1-5.6分别重构出青霉素发酵过程操作变量离线历史故障数据集的主元空间的故障相关方向、青霉素发酵过程操作变量离线历史故障数据集的残差空间的主元空间的故障相关方向、青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的故障相关方向构成基于改进的核偏最小二乘重构的青霉素发酵过程故障相关方向,从而建立了改进的核偏最小二乘重构的青霉素发酵过程故障相关方向的模型库;Step 5.7: For all faults in the penicillin fermentation process, apply steps 5.1-5.6 to reconstruct the fault-related direction of the pivot space of the operational variable offline historical fault data set of the penicillin fermentation process, and the The fault correlation direction of the pivot space of the residual space, the fault correlation direction of the residual space of the residual space of the operating variable offline historical normal data set of the penicillin fermentation process constitute the fault of the penicillin fermentation process based on the improved kernel partial least squares reconstruction Correlation directions, thus establishing a model library of improved kernel partial least squares reconstruction of penicillin fermentation process fault-correlation directions; 步骤6:利用青霉素发酵过程故障相关方向模型进行青霉素发酵过程故障诊断;Step 6: use the penicillin fermentation process fault related direction model to carry out the fault diagnosis of the penicillin fermentation process; 步骤6.1:根据青霉素发酵过程操作变量离线历史故障数据集的主元空间的故障相关方向,计算在线获取的青霉素发酵过程操作变量数据的主元空间的得分矩阵及其对应的霍特林统计量;Step 6.1: Calculate the score matrix and corresponding Hotelling statistics of the pivot space of the operating variable data of the penicillin fermentation process obtained online according to the fault correlation direction of the pivot space of the operating variable offline historical fault data set of the penicillin fermentation process; 步骤6.2:根据青霉素发酵过程操作变量离线历史故障数据集的残差空间的主元空间的故障相关方向,计算在线获取的青霉素发酵过程操作变量数据的残差空间的得分矩阵及其对应的霍特林统计量;Step 6.2: According to the fault correlation direction of the principal component space of the residual space of the operational variable data set of the penicillin fermentation process offline historical fault, calculate the score matrix of the residual space of the operational variable data of the penicillin fermentation process obtained online and its corresponding Huot forest statistics; 步骤6.3:根据青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的故障相关方向,计算在线获取的青霉素发酵过程操作变量数据的残差空间的SPE统计量;Step 6.3: Calculate the SPE statistics of the residual space of the operational variable data of the penicillin fermentation process obtained online according to the fault-related direction of the residual space of the offline historical normal data set of the operational variable of the penicillin fermentation process; 步骤6.4:判断在线获取的青霉素发酵过程操作变量数据的主元空间的霍特林统计量、在线获取的青霉素发酵过程操作变量数据的残差空间的霍特林统计量、在线获取的青霉素发酵过程操作变量数据的残差空间的SPE统计量是否均低于设定的各自的置信限,是,则当前故障即为青霉素发酵过程中真正的故障,否则当前故障为已有故障的组合或是新的故障。Step 6.4: Determine the Hotelling statistics of the pivot space of the operating variable data of the penicillin fermentation process obtained online, the Hotelling statistics of the residual space of the operating variable data of the penicillin fermentation process obtained online, and the penicillin fermentation process obtained online Whether the SPE statistics of the residual space of the manipulated variable data are all lower than the respective set confidence limits, if yes, the current fault is the real fault in the penicillin fermentation process, otherwise the current fault is a combination of existing faults or a new fault failure. 2.根据权利要求1所述的基于核偏最小二乘重构的青霉素发酵过程故障诊断方法,其特征在于:所述步骤5.4具体按以下步骤执行:2. the penicillin fermentation process fault diagnosis method based on nuclear partial least squares reconstruction according to claim 1, is characterized in that: described step 5.4 is specifically carried out in the following steps: 步骤5.4.1:利用核偏最小二乘方法将青霉素发酵过程操作变量离线历史故障数据集和青霉素发酵过程操作变量离线历史正常数据集分别划分主元空间和残差空间,分别得到青霉素发酵过程操作变量离线历史故障数据集的核偏最小二乘模型和青霉素发酵过程操作变量离线历史正常数据集的核偏最小二乘模型;Step 5.4.1: Use the kernel partial least squares method to divide the off-line historical fault data set of the operating variable of the penicillin fermentation process and the offline historical normal data set of the operating variable of the penicillin fermentation process into the principal component space and the residual space, respectively, and obtain the operation of the penicillin fermentation process Kernel partial least squares model of variable offline historical failure data set and kernel partial least squares model of operating variable offline historical normal data set of penicillin fermentation process; 步骤5.4.2:把青霉素发酵过程操作变量离线历史正常数据集的主元空间的数据集分别正交映射到青霉素运行过程操作变量离线历史故障数据集的主元空间的负载矩阵和青霉素运行过程操作变量离线历史故障数据集的残差空间的负载矩阵,得到正交映射后的青霉素发酵过程操作变量离线历史正常数据集的主元空间的主元空间的数据集和正交映射后的青霉素发酵过程操作变量离线历史正常数据集的主元空间的残差空间的数据集;Step 5.4.2: Orthogonally map the data set of the pivot space of the offline historical normal data set of the operating variable of the penicillin fermentation process to the load matrix of the pivot space of the offline historical fault data set of the operating variable of the penicillin operation process and the penicillin operating process operation The load matrix of the residual space of the variable offline historical fault data set, and the data set of the pivot space of the principal component space of the operating variable offline historical normal data set and the penicillin fermentation process after the orthogonal mapping are obtained Operate the data set of the residual space of the pivot space of the offline historical normal data set of the variable; 步骤5.4.3:利用核主元分析法确定正交映射后的青霉素发酵过程操作变量离线历史正常数据集的主元空间的主元空间的数据集的主元和正交映射后的青霉素发酵过程操作变量离线历史正常数据集的主元空间的残差空间的数据集的主元;Step 5.4.3: Determine the penicillin fermentation process after orthogonal mapping by using Kernel PCA Operate the pivot of the data set of the residual space of the pivot space of the offline historical normal data set of the variable; 步骤5.4.4:分别求青霉素发酵过程操作变量离线历史故障数据集的主元空间的数据集在正交映射后的青霉素发酵过程操作变量离线历史正常数据集的主元空间的主元空间的负载矩阵方向上的主元和青霉素发酵过程操作变量离线历史故障数据集的残差空间的数据集在正交映射后的青霉素发酵过程操作变量离线历史正常数据集的主元空间的残差空间的负载矩阵方向上的主元,分别得到青霉素发酵过程操作变量离线历史故障数据集的主元空间的故障主元和青霉素发酵过程操作变量离线历史故障数据集的残差空间的故障主元;Step 5.4.4: Calculate the load of the pivot space of the offline historical fault data set of the operation variable of the penicillin fermentation process in the pivot space of the offline historical normal data set of the operation variable of the penicillin fermentation process after orthogonal mapping Pivot in the matrix direction and loading of the residual space in the residual space of the off-line historical failure data set of the operating variable of the penicillin fermentation process in the penicillin fermentation process operating variable offline historical normal data set after orthogonal mapping The pivots in the matrix direction are respectively obtained the fault pivot of the pivot space of the offline historical fault data set of the operating variable of the penicillin fermentation process and the fault pivot of the residual space of the offline historical fault data set of the operational variable of the penicillin fermentation process; 步骤5.4.5:计算青霉素发酵过程操作变量离线历史故障数据集的主元空间的故障主元在正交映射后的青霉素发酵过程操作变量离线历史正常数据集的主元空间的主元空间的主元中所占比例,计算青霉素发酵过程操作变量离线历史故障数据集的残差空间的故障主元在正交映射后的青霉素发酵过程操作变量离线历史正常数据集的主元空间的残差空间的主元中所占比例;Step 5.4.5: Calculate the principal of the fault pivot in the pivot space of the offline historical fault data set of the operating variable of the penicillin fermentation process. The proportion of the element, calculate the fault principal element of the residual space of the offline historical fault data set of the operating variable of the penicillin fermentation process in the residual space of the principal element space of the offline historical normal data set of the operating variable of the penicillin fermentation process after orthogonal mapping The proportion in the pivot; 步骤5.4.6:两类比例值中大于设定的比例下限的各比例值所对应的青霉素发酵过程操作变量离线历史故障数据集的主元空间的故障主元和正交映射后的青霉素发酵过程操作变量离线历史正常数据集的残差空间的故障主元分别组成新的青霉素发酵过程操作变量离线历史故障数据集的主元空间的主元方向和新的青霉素发酵过程操作变量离线历史故障数据集的残差空间的主元方向;Step 5.4.6: The fault pivot of the pivot space of the offline historical fault data set of the penicillin fermentation process operation variable corresponding to each proportion value greater than the set lower limit of the proportion value of the two types and the penicillin fermentation process after orthogonal mapping The fault pivots of the residual space of the operating variable offline historical normal data set form the pivot direction of the pivot space of the new penicillin fermentation process operating variable offline historical fault data set and the new penicillin fermentation process operating variable offline historical fault data set The pivot direction of the residual space of ; 步骤5.4.7:利用新的青霉素发酵过程操作变量离线历史故障数据集的主元空间的主元方向对应的负载矩阵和新的青霉素发酵过程操作变量离线历史故障数据集的残差空间的主元方向对应的负载矩阵,重构青霉素发酵过程操作变量离线历史正常数据集的主元空间的主元空间的负载矩阵和青霉素发酵过程操作变量离线历史正常数据集的主元空间的残差空间的负载矩阵,即青霉素发酵过程操作变量离线历史故障数据集的主元空间的故障相关方向。Step 5.4.7: Use the load matrix corresponding to the pivot direction of the pivot space of the new penicillin fermentation process operating variable offline historical fault data set and the new pivot element of the residual space of the penicillin fermentation process operating variable offline historical fault data set The loading matrix corresponding to the direction, reconstructing the loading matrix of the pivot space of the pivot space of the offline historical normal data set of the operating variable of the penicillin fermentation process and the loading of the residual space of the pivot space of the offline historical normal data set of the operating variable of the penicillin fermentation process Matrix, the fault-related direction of the pivot space of the offline historical fault data set of operational variables for the penicillin fermentation process. 3.根据权利要求1所述的基于核偏最小二乘重构的青霉素发酵过程故障诊断方法,其特征在于:所述步骤5.5具体按以下步骤执行:3. the penicillin fermentation process fault diagnosis method based on nuclear partial least squares reconstruction according to claim 1, is characterized in that: described step 5.5 is specifically carried out in the following steps: 步骤5.5.1:利用核主元分析方法,分别将青霉素发酵过程操作变量离线历史故障数据集的残差空间和青霉素发酵过程操作变量离线历史正常数据集的残差空间划分为残差空间的主元空间和残差空间的残差空间,分别得到青霉素发酵过程操作变量离线历史故障数据集的残差空间的核主元模型和青霉素发酵过程操作变量离线历史正常数据集的残差空间的核主元模型;Step 5.5.1: Using the kernel principal component analysis method, the residual space of the offline historical fault data set of the operating variable in the penicillin fermentation process and the residual space of the offline historical normal data set of the operating variable in the penicillin fermentation process are divided into the main residual space. The residual space of the meta space and the residual space, the kernel principal element model of the residual space of the offline historical fault data set of the operating variable of the penicillin fermentation process and the kernel principal element model of the residual space of the offline historical normal data set of the operating variable of the penicillin fermentation process are respectively obtained. meta model; 步骤5.5.2:把青霉素发酵过程操作变量离线历史正常数据集的残差空间的主元空间的数据集分别正交映射到青霉素发酵过程操作变量离线历史故障数据集的残差空间的主元空间的负载矩阵和青霉素发酵过程操作变量离线历史故障数据集的残差空间的残差空间的负载矩阵,得到正交映射后的青霉素发酵过程操作变量离线历史正常数据集的残差空间的主元空间的数据集和正交映射后的青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的数据集;Step 5.5.2: Orthogonally map the data sets of the pivot space of the residual space of the offline historical normal data set of the operational variable of the penicillin fermentation process to the pivot space of the residual space of the offline historical fault data set of the operational variable of the penicillin fermentation process The load matrix of the operating variable of the penicillin fermentation process and the load matrix of the residual space of the residual space of the offline historical fault data set of the operating variable of the penicillin fermentation process are obtained, and the principal component space of the residual space of the operating variable of the penicillin fermentation process of the offline historical normal data set is obtained after orthogonal mapping The data set of the data set and the residual space of the residual space of the offline historical normal data set of the operating variable of the penicillin fermentation process after orthogonal mapping; 步骤5.5.3:利用核主元分析法确定正交映射后的青霉素发酵过程操作变量离线历史正常数据集的残差空间的主元空间的数据集的主元和正交映射后的青霉素发酵过程操作变量离线历史故障数据集的残差空间的残差空间的数据集的主元;Step 5.5.3: Use Kernel Principal Component Analysis to determine the principal component of the dataset of the residual space of the operational variable offline historical normal dataset of the residual space of the penicillin fermentation process after the orthogonal mapping and the penicillin fermentation process after the orthogonal mapping The pivot of the data set of the residual space of the residual space of the operating variable offline historical fault data set; 步骤5.5.4:求青霉素发酵过程操作变量离线历史正常数据集的残差空间的主元空间的数据集在正交映射后的青霉素发酵过程操作变量离线历史正常数据集的残差空间的主元空间的负载矩阵方向上的主元,求青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的数据集在正交映射后的青霉素发酵过程操作变量离线历史故障数据集的残差空间的残差空间的负载矩阵方向上的主元,即青霉素发酵过程操作变量离线历史正常数据集的残差空间的主元空间的故障主元和青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的故障主元;Step 5.5.4: Calculate the principal component of the residual space of the offline historical normal data set of the operating variable of the penicillin fermentation process. The principal component in the direction of the load matrix of the space is to find the residual space of the offline historical normal data set of the operating variable of the penicillin fermentation process. Pivot in the load matrix direction of the residual space of the difference space, that is, the fault pivot of the residual space of the residual space of the penicillin fermentation process operating variable offline historical normal data set and the fault pivot of the penicillin fermentation process operating variable offline historical normal data set the fault pivot of the residual space of the residual space; 步骤5.5.5:计算青霉素发酵过程操作变量离线历史正常数据集的残差空间的主元空间的故障主元在正交映射后的青霉素发酵过程操作变量离线历史正常数据集的残差空间的主元空间的主元中所占比例,计算青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的故障主元在正交映射后青霉素发酵过程操作变量离线历史故障数据集的残差空间的主元空间的主元中所占比例;Step 5.5.5: Calculate the principal component of the fault pivot space of the residual space of the offline historical normal data set of the operating variable of the penicillin fermentation process. Calculate the proportion of the principal element in the metaspace, and calculate the residual space of the residual space of the operating variable of the penicillin fermentation process in the residual space of the normal data set. The proportion of the pivot space in the difference space; 步骤5.5.6:两类比例值中大于设定的比例下限的各比例值所对应的青霉素发酵过程操作变量离线历史故障数据集的残差空间的主元空间的故障主元和青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的故障主元分别组成新的青霉素发酵过程操作变量离线历史故障数据集的残差空间的主元空间的主元方向和新的青霉素发酵过程操作变量离线历史故障数据集的残差空间的残差空间的主元方向;Step 5.5.6: The fault pivot and penicillin fermentation process operation of the penicillin fermentation process operation variable in the residual space of the residual space of the offline historical fault data set corresponding to each proportion value of the two types of proportion values greater than the set proportion lower limit Variables Offline History Normal Dataset Residual Space, Fault Pivot, Residual Space Pivot Direction and New Penicillin Fermentation Process Manipulation Variable Offline History Fault Space Pivot Space, Pivot Direction, and New Penicillin Fermentation Process, respectively The pivot direction of the residual space of the residual space of the operating variable offline historical fault data set; 步骤5.5.7:利用新的青霉素发酵过程操作变量离线历史故障数据集的残差空间的主元空间的主元方向对应的负载矩阵和新的青霉素发酵过程操作变量离线历史故障数据集的残差空间的残差空间的主元方向对应的负载矩阵,重构青霉素发酵过程操作变量离线历史故障数据集的残差空间的主元空间的负载矩阵和青霉素发酵过程操作变量离线历史故障数据集的残差空间的残差空间的负载矩阵,即青霉素发酵过程操作变量离线历史故障数据集的残差空间的主元空间的故障相关方向。Step 5.5.7: Use the load matrix corresponding to the pivot direction of the pivot space of the residual space of the residual space of the new penicillin fermentation process operating variable offline historical fault data set and the residual of the new penicillin fermentation process operating variable offline historical fault data set The load matrix corresponding to the pivot direction of the residual space of the space, the load matrix of the pivot space of the residual space of the residual space of the operating variable offline historical fault data set of the penicillin fermentation process and the residual of the offline historical fault data set of the operating variable of the penicillin fermentation process The loading matrix of the residual space of the difference space, that is, the fault correlation direction of the pivot space of the residual space of the operational variable offline historical fault data set of the penicillin fermentation process. 4.根据权利要求1所述的基于核偏最小二乘重构的青霉素发酵过程故障诊断方法,其特征在于:所述步骤5.6具体按以下步骤执行:4. the penicillin fermentation process fault diagnosis method based on nuclear partial least squares reconstruction according to claim 1, is characterized in that: described step 5.6 is specifically carried out in the following steps: 步骤5.6.1:将青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的数据集分别正交映射到青霉素发酵过程操作变量离线历史故障数据集的残差空间的主元空间的负载矩阵和青霉素发酵过程操作变量离线历史故障数据集的残差空间的残差空间的负载矩阵,得到正交映射后的青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的主元空间和正交映射后的青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的残差空间;Step 5.6.1: Orthogonally map the data sets of the residual space of the residual space of the offline historical normal data set of the operating variable of the penicillin fermentation process to the pivot space of the residual space of the offline historical fault data set of the operating variable of the penicillin fermentation process The load matrix of the operating variable of the penicillin fermentation process and the load matrix of the residual space of the residual space of the offline historical fault data set of the operating variable of the penicillin fermentation process are obtained, and the residual space of the residual space of the offline historical normal data set of the operating variable of the penicillin fermentation process is obtained after orthogonal mapping The principal component space and the residual space of the residual space of the offline historical normal data set of the operating variable of the penicillin fermentation process after orthogonal mapping; 步骤5.6.2:利用核主元分析法确定正交映射后的青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的主元空间的数据集的主元和正交映射后的青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的残差空间的数据集的主元;Step 5.6.2: Determine the principal component of the residual space of the residual space of the offline historical normal data set of the operational variables of the penicillin fermentation process after orthogonal mapping and after orthogonal mapping using Kernel Principal Component Analysis The principal element of the residual space of the residual space of the offline historical normal data set of the operating variable of the penicillin fermentation process; 步骤5.6.3:把青霉素发酵过程操作变量离线历史正常数据集的残差空间的主元空间的数据集映射到正交映射后的青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的主元空间的负载矩阵,把青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的数据集映射到正交映射后的青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的残差空间的负载矩阵,得到青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的主元空间的映射空间的数据集和青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的残差空间的映射空间的数据集;Step 5.6.3: Map the data set of the principal component space of the residual space of the offline historical normal data set of the operating variable of the penicillin fermentation process to the residual space of the residual space of the offline historical normal data set of the operating variable of the penicillin fermentation process after orthogonal mapping. The loading matrix of the principal component space of the difference space maps the data set of the residual space of the residual space of the offline historical normal data set of the operating variable of the penicillin fermentation process to the offline historical normal data set of the operating variable of the penicillin fermentation process after orthogonal mapping The load matrix of the residual space of the residual space of the residual space, and the data set of the mapping space of the residual space of the residual space of the offline historical normal data set of the operating variable of the penicillin fermentation process and the operating variable of the penicillin fermentation process A data set of the mapping space of the residual space of the residual space of the offline historical normal data set; 步骤5.6.4:计算青霉素发酵过程操作变量离线历史故障数据集的残差空间的主元空间的数据集到青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的主元空间的映射空间的数据集的负载矩阵的距离,计算青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的数据集到青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的残差空间的映射空间的数据集的负载矩阵的距离,并计算两个距离的比值;Step 5.6.4: Calculate the pivot space of the residual space of the penicillin fermentation process operating variable offline historical fault data set from the pivot space to the residual space of the penicillin fermentation process operating variable offline historical normal data set of the pivot space The distance of the loading matrix of the mapping space dataset to calculate the residual space of the residual space of the offline historical normal dataset of the operating variable of the penicillin fermentation process to the residual space of the offline historical normal dataset of the operating variable of the penicillin fermentation process The distance of the loading matrix of the data set of the mapping space of the residual space of the residual space, and calculate the ratio of the two distances; 步骤5.6.5:计算青霉素发酵过程操作变量离线历史故障数据集的残差空间的残差空间的数据集到青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的主元空间的映射空间的数据集的负载矩阵的距离,计算青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的数据集到青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的残差空间的映射空间的数据集的负载矩阵的距离,并计算两个距离的比值;Step 5.6.5: Calculate the pivot space of the residual space of the residual space of the operating variable offline historical fault data set of the penicillin fermentation process operation variable to the residual space of the residual space of the offline historical normal data set of the operating variable of the penicillin fermentation process The distance of the loading matrix of the mapping space dataset to calculate the residual space of the residual space of the offline historical normal dataset of the operating variable of the penicillin fermentation process to the residual space of the offline historical normal dataset of the operating variable of the penicillin fermentation process The distance of the loading matrix of the data set of the mapping space of the residual space of the residual space, and calculate the ratio of the two distances; 步骤5.6.6:该两类距离的比值大于其设定比值下限的所有距离的比值对应的青霉素发酵过程操作变量离线历史故障数据集的残差空间的主元空间和青霉素发酵过程操作变量离线历史故障数据集的残差空间的残差空间分别组成新的青霉素发酵过程操作变量离线历史故障数据集的残差空间的残差空间的主元空间的主元方向和新的青霉素发酵过程操作变量离线历史故障数据集的残差空间的残差空间的残差空间的主元方向;Step 5.6.6: The ratio of the two types of distances is greater than the lower limit of the ratio of all distances corresponding to the ratio of the penicillin fermentation process operation variable offline history failure data set, the pivot space of the residual space and the penicillin fermentation process operation variable offline history The residual space of the fault data set consists of the new penicillin fermentation process operating variable offline, the residual space of the historical fault data set, the pivot space of the residual space, the pivot direction of the pivot space and the new penicillin fermentation process operating variable offline The pivot direction of the residual space of the residual space of the historical fault data set; 步骤5.6.7:利用新的青霉素发酵过程操作变量离线历史故障数据集的残差空间的残差空间的主元空间的主元方向和新的青霉素发酵过程操作变量离线历史故障数据集的残差空间的残差空间的残差空间的主元方向,重构青霉素发酵过程操作变量离线历史正常数据集的残差空间的残差空间的故障相关方向。Step 5.6.7: Use the new Penicillin Fermentation Process Manipulation Variable Offline History Fault Dataset Residual Space Pivot Space Pivot Space Pivot Direction and New Penicillin Fermentation Process Manipulation Variable Offline History Fault Dataset Residual The pivot direction of the residual space of the residual space of the space, and the fault-related direction of the residual space of the residual space of the residual space of the operating variable offline historical normal data set of the reconstructed penicillin fermentation process.
CN201410337732.XA 2014-07-15 Penicillin fermentation process method for diagnosing faults based on the reconstruct of core offset minimum binary Active CN104133991B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410337732.XA CN104133991B (en) 2014-07-15 Penicillin fermentation process method for diagnosing faults based on the reconstruct of core offset minimum binary

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410337732.XA CN104133991B (en) 2014-07-15 Penicillin fermentation process method for diagnosing faults based on the reconstruct of core offset minimum binary

Publications (2)

Publication Number Publication Date
CN104133991A true CN104133991A (en) 2014-11-05
CN104133991B CN104133991B (en) 2017-01-04

Family

ID=

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104503441A (en) * 2014-12-22 2015-04-08 北京化工大学 Process fault monitoring method based on improved dynamic visible graph
CN106529079A (en) * 2016-11-29 2017-03-22 上海电机学院 Chemical process failure detection method based on failure-dependent principal component space
CN106843172A (en) * 2016-12-29 2017-06-13 中国矿业大学 Complex industrial process On-line quality prediction method based on JY KPLS
CN106845095A (en) * 2017-01-10 2017-06-13 上海第二工业大学 A kind of recognition methods of 2-KLG industrial fermentation processes metabolic activity critical stage
CN107817784A (en) * 2017-10-26 2018-03-20 东北大学 A kind of procedure failure testing method based on concurrent offset minimum binary
CN108369666A (en) * 2015-11-26 2018-08-03 福满代谢组技术有限公司 Data analysis set-up, method and program
CN109308063A (en) * 2018-12-03 2019-02-05 北京工业大学 Stage division method of fermentation process based on score matrix
CN110794814A (en) * 2019-11-27 2020-02-14 中国人民解放军火箭军工程大学 A fault determination method and system based on generalized principal components

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
OUNI KHALED ETC: ""A New Fault Diagnosis Method Using Fault Directions in Partial Least Square"", 《IJCSET》 *
张颖伟 等: ""基于DKPLS的非线性过程故障检测"", 《华中科技大学学报(自然科学版)》 *
贾之阳 等: ""基于改进MICA的青霉素发酵过程监控与故障诊断"", 《中国科技论文在线》 *

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104503441A (en) * 2014-12-22 2015-04-08 北京化工大学 Process fault monitoring method based on improved dynamic visible graph
CN104503441B (en) * 2014-12-22 2017-02-22 北京化工大学 Process fault monitoring method based on improved dynamic visible graph
CN108369666A (en) * 2015-11-26 2018-08-03 福满代谢组技术有限公司 Data analysis set-up, method and program
CN106529079A (en) * 2016-11-29 2017-03-22 上海电机学院 Chemical process failure detection method based on failure-dependent principal component space
CN106843172A (en) * 2016-12-29 2017-06-13 中国矿业大学 Complex industrial process On-line quality prediction method based on JY KPLS
CN106843172B (en) * 2016-12-29 2019-04-09 中国矿业大学 On-line quality prediction method of complex industrial process based on JY-KPLS
CN106845095A (en) * 2017-01-10 2017-06-13 上海第二工业大学 A kind of recognition methods of 2-KLG industrial fermentation processes metabolic activity critical stage
CN107817784A (en) * 2017-10-26 2018-03-20 东北大学 A kind of procedure failure testing method based on concurrent offset minimum binary
WO2019080489A1 (en) * 2017-10-26 2019-05-02 东北大学 Process fault detection method based on concurrent partial least squares
CN109308063A (en) * 2018-12-03 2019-02-05 北京工业大学 Stage division method of fermentation process based on score matrix
CN110794814A (en) * 2019-11-27 2020-02-14 中国人民解放军火箭军工程大学 A fault determination method and system based on generalized principal components
CN110794814B (en) * 2019-11-27 2022-06-28 中国人民解放军火箭军工程大学 Fault determination method and system based on generalized principal component

Similar Documents

Publication Publication Date Title
Han et al. An optimized long short-term memory network based fault diagnosis model for chemical processes
CN101158693B (en) Bulk production process malfunction detection method based on multiple nucleus independent elements analysis
CN101308385B (en) Non-linear procedure failure testing method based on two-dimensional dynamic kernel principal component analysis
CN103853152B (en) A kind of batch process fault monitoring method based on AR-PCA
CN101964021B (en) Penicillin fermentation process failure monitoring method based on recursive kernel principal component analysis
CN104914723B (en) Soft sensor modeling method for industrial process based on collaborative training partial least squares model
CN106843172A (en) Complex industrial process On-line quality prediction method based on JY KPLS
Shah et al. Multi‐rate observer design and optimal control to maximize productivity of an industry‐scale fermentation process
CN103729562A (en) Penicillin fermentation process fault monitoring method based on reconstruction discriminatory analysis
Hong et al. Progressive multi-block modelling for enhanced fault isolation in batch processes
Zhang et al. Dynamical process monitoring using dynamical hierarchical kernel partial least squares
Gunther et al. Fault detection and diagnosis in an industrial fed‐batch cell culture process
CN116153388A (en) Quantitative relationship model and its application, cell state monitoring method, device, system
CN109144039A (en) A kind of batch process fault detection method keeping extreme learning machine based on timing extension and neighborhood
CN117229905A (en) Biological feed fermentation control method and system
CN113838530B (en) Method for monitoring biological manufacturing process by using cell metabolism network
CN103903065A (en) Penicillin production process product quality prediction method based on kernel learning technology
CN104133991A (en) Penicillin fermentation process fault diagnosis method based on kernel partial least squares reconstitution
Qin et al. Simultaneous fault detection and isolation based on multi-task long short-term memory neural networks
CN116030904A (en) Method and system for forecasting concentration of biological enzyme in microbial fermentation process
CN111931349B (en) Multiplicative Fault Diagnosis Method of CSTH Based on Dynamic Principal Component Analysis
CN113554061B (en) The Selection Method of the Number of Pivot Components in Reconstruction PCA Algorithm
Facco et al. Transfer of process monitoring models between plants: Batch systems
CN108037668A (en) A kind of new Chemical Batch Process modeling and monitoring method
CN111027645B (en) Microbial fermentation process fault monitoring method based on high-order statistic construction in sub-stage

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant