CN112541017A - Industrial production process state monitoring method, device, equipment and storage medium - Google Patents

Industrial production process state monitoring method, device, equipment and storage medium Download PDF

Info

Publication number
CN112541017A
CN112541017A CN202011393319.7A CN202011393319A CN112541017A CN 112541017 A CN112541017 A CN 112541017A CN 202011393319 A CN202011393319 A CN 202011393319A CN 112541017 A CN112541017 A CN 112541017A
Authority
CN
China
Prior art keywords
dynamic
production process
static
characteristic
working condition
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.)
Pending
Application number
CN202011393319.7A
Other languages
Chinese (zh)
Inventor
沈勇
曹晓红
刁俊武
论国柱
蓝新志
陆鹏飞
汪谷银
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.)
CNOOC Information Technology Co Ltd
Original Assignee
CNOOC Information Technology Co Ltd
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 CNOOC Information Technology Co Ltd filed Critical CNOOC Information Technology Co Ltd
Priority to CN202011393319.7A priority Critical patent/CN112541017A/en
Publication of CN112541017A publication Critical patent/CN112541017A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2462—Approximate or statistical queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2477—Temporal data queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Human Resources & Organizations (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Optimization (AREA)
  • Educational Administration (AREA)
  • Strategic Management (AREA)
  • Mathematical Analysis (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Pure & Applied Mathematics (AREA)
  • Economics (AREA)
  • Computational Mathematics (AREA)
  • Development Economics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Algebra (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Game Theory and Decision Science (AREA)
  • Evolutionary Biology (AREA)
  • Marketing (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • General Factory Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application discloses a method, a device, equipment and a storage medium for monitoring the state of an industrial production process, wherein the method comprises the following steps: collecting normal working condition data and carrying out standardized processing; extracting a first slow characteristic from normal working condition data by an MWSFA method, taking the unextracted characteristic as a first fast characteristic, and calculating a transformation matrix; calculating a static index control limit and a dynamic index control limit; carrying out standardization processing on the working condition data to be detected; acquiring a second slow characteristic and a second fast characteristic corresponding to the working condition data to be detected; calculating static statistics and dynamic statistics of the working condition data to be measured; and comparing the static statistic with the static index control limit, comparing the dynamic statistic with the dynamic index control limit, and judging the production state of the industrial production process according to the comparison result. Therefore, the time dynamic characteristics contained in the production process data are extracted, the state change of the production process is effectively judged, whether real faults occur or not can be judged, invalid early warning is reduced, and the working efficiency is improved.

Description

Industrial production process state monitoring method, device, equipment and storage medium
Technical Field
The invention relates to the field of monitoring of industrial production process states, in particular to a method, a device, equipment and a storage medium for monitoring the industrial production process states.
Background
The safety and stability of the production state of the industrial production process are the prerequisite for the production priority of enterprises. With the development of advanced intelligent instrumentation technology, a large number of sensors and databases acquire and store a large amount of industrial production data for monitoring the state of the production process. By analyzing the production state information contained in the industrial production data, the abnormal production state can be early warned and corresponding adjustment measures can be taken, so that the stable and efficient operation of the industrial production process is ensured.
The traditional production process state monitoring method based on data analysis is to compare actual monitoring data with a preset control limit, and if the actual monitoring data exceeds the preset control limit, a fault is considered to occur. However, the deviation result of the actual monitoring data and the control limit may be caused by the change of the production working condition or the transient process, and is not a fault, so that a large amount of invalid early warnings are generated in the actual operation, and the judgment needs to be performed in a manual mode, thereby reducing the production working efficiency.
Therefore, how to solve the problems of high generation rate of invalid early warning and low production efficiency is a technical problem to be solved urgently by the technical personnel in the field.
Disclosure of Invention
In view of this, the present invention provides a method, an apparatus, a device and a storage medium for monitoring a state of an industrial process, which can determine whether a real failure occurs, reduce invalid warning and improve work efficiency. The specific scheme is as follows:
a method of monitoring the condition of an industrial process, comprising:
collecting normal working condition data and carrying out standardized processing;
extracting a first slow characteristic from the processed normal working condition data by an MWSFA method, taking the unextracted characteristic as a first fast characteristic, and calculating a transformation matrix;
calculating a static index control limit and a dynamic index control limit according to the first slow characteristic and the first fast characteristic;
carrying out standardization processing on the working condition data to be detected;
acquiring a second slow characteristic and a second fast characteristic corresponding to the working condition data to be detected according to the calculated transformation matrix and the processed working condition data to be detected;
calculating static statistics and dynamic statistics of the working condition data to be measured according to the second slow characteristic and the second fast characteristic;
and comparing the static statistic with the static index control limit, comparing the dynamic statistic with the dynamic index control limit, and judging the production state of the industrial production process according to the comparison result.
Preferably, in the method for monitoring the state of the industrial process provided by the embodiment of the present invention, the second slow characteristic and the second fast characteristic are obtained by using the following formulas:
sd＝WdxT
se＝WexT
wherein s isdFor the second slow feature, seAs the second fast feature, WdFor the calculated transformation matrix corresponding to said first slow feature, WeAnd x is the working condition data to be measured for the calculated transformation matrix corresponding to the first fast characteristic.
Preferably, in the method for monitoring the state of the industrial production process provided by the embodiment of the present invention, the following formula is adopted to calculate the static statistics of the to-be-measured working condition data:
Figure BDA0002813498130000021
Figure BDA0002813498130000022
wherein, TdA static statistic, T, corresponding to the second slow featureeA static statistic, s, corresponding to the second fast featuredFor the second slow feature, seIs the second fast feature.
Preferably, in the method for monitoring the state of the industrial production process provided by the embodiment of the present invention, the following formula is adopted to calculate the dynamic statistics of the working condition data to be measured:
Figure BDA0002813498130000023
Figure BDA0002813498130000024
Figure BDA0002813498130000025
Figure BDA0002813498130000026
x＝[x1 x2 … xN]T
wherein S isdDynamic statistics, S, corresponding to said second slow featureseDynamic statistics corresponding to the second fast features,
Figure BDA0002813498130000031
for the amount of change corresponding to the second slow feature,
Figure BDA0002813498130000032
the variation corresponding to the second fast characteristic.
Preferably, in the method for monitoring a state of an industrial production process provided in an embodiment of the present invention, the determining a production state of the industrial production process according to the comparison result specifically includes:
if the static statistic is within the static index control limit and the dynamic statistic is within the dynamic index control limit, judging that the industrial production process is in a normal working state and no fault occurs;
and if the static statistic exceeds the static index control limit and the dynamic statistic exceeds the dynamic index control limit, judging that the industrial production process is abnormal and the control function is disabled, and performing early warning.
Preferably, in the method for monitoring a state of an industrial production process provided in an embodiment of the present invention, the determining a production state of the industrial production process according to the comparison result specifically further includes:
and if the static statistic exceeds the static index control limit and the dynamic statistic is within the dynamic index control limit, judging that the industrial production process is switched to a new working condition, and recalculating the static statistic without early warning.
Preferably, in the method for monitoring a state of an industrial production process provided in an embodiment of the present invention, the determining a production state of the industrial production process according to the comparison result specifically further includes:
and if the static statistic is within the static index control limit and the dynamic statistic exceeds the dynamic index control limit, judging that the interference contained in the working condition data to be detected causes dynamic change in the industrial production process, and timely checking the industrial production process.
The embodiment of the invention also provides a device for monitoring the state of the industrial production process, which comprises:
the first data processing module is used for acquiring normal working condition data and carrying out standardized processing;
the first feature extraction module is used for extracting a first slow feature from the processed normal working condition data through an MWSFA method, taking the feature which is not extracted as a first fast feature, and calculating a transformation matrix;
the control limit calculation module is used for calculating a static index control limit and a dynamic index control limit according to the first slow characteristic and the first fast characteristic;
the second data processing module is used for carrying out standardized processing on the working condition data to be detected;
the second characteristic acquisition module is used for acquiring a second slow characteristic and a second fast characteristic corresponding to the working condition data to be detected according to the calculated transformation matrix and the processed working condition data to be detected;
the statistic calculation module is used for calculating the static statistic and the dynamic statistic of the working condition data to be measured according to the second slow characteristic and the second fast characteristic;
and the production state judging module is used for comparing the static statistic with the static index control limit, comparing the dynamic statistic with the dynamic index control limit, and judging the production state of the industrial production process according to the comparison result.
The embodiment of the invention also provides industrial production process state judgment equipment which comprises a processor and a memory, wherein the industrial production process state monitoring method provided by the embodiment of the invention is realized when the processor executes the computer program stored in the memory.
The embodiment of the present invention further provides a computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the above-mentioned industrial process state monitoring method provided by the embodiment of the present invention.
According to the technical scheme, the industrial production process state monitoring method provided by the invention comprises the following steps: collecting normal working condition data and carrying out standardized processing; extracting a first slow characteristic from the processed normal working condition data by an MWSFA method, taking the unextracted characteristic as a first fast characteristic, and calculating a transformation matrix; calculating a static index control limit and a dynamic index control limit according to the first slow characteristic and the first fast characteristic; carrying out standardization processing on the working condition data to be detected; acquiring a second slow characteristic and a second fast characteristic corresponding to the working condition data to be detected according to the calculated transformation matrix and the processed working condition data to be detected; calculating static statistics and dynamic statistics of the working condition data to be measured according to the second slow characteristic and the second fast characteristic; and comparing the static statistic with the static index control limit, comparing the dynamic statistic with the dynamic index control limit, and judging the production state of the industrial production process according to the comparison result.
Because the production process has a nonlinear relation and is influenced by the working condition change and the time-varying characteristic, the invention adopts the MWSFA method to divide the working condition data into a slow characteristic space and a fast characteristic space, has small calculation amount, extracts the time dynamic characteristic contained in the production process data to effectively judge the real-time running state change of the production process so as to judge whether a real fault occurs, reduces invalid early warning, provides reasonable basis for the production process monitoring and fault diagnosis of industrial enterprises, and improves the working efficiency. In addition, the invention also provides a corresponding device, equipment and a computer readable storage medium for the industrial production process state monitoring method, so that the method has higher practicability, and the device, the equipment and the computer readable storage medium have corresponding advantages.
Drawings
In order to more clearly illustrate the embodiments of the present invention or technical solutions in related arts, the drawings used in the description of the embodiments or related arts will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a method for monitoring the status of an industrial process according to an embodiment of the present invention;
FIG. 2 is a flow chart of an embodiment of the present invention for monitoring the status of an industrial process;
fig. 3 is a schematic structural diagram of a device for monitoring the state of an industrial process according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a method for monitoring the state of an industrial production process, which comprises the following steps as shown in figure 1:
s101, collecting normal working condition data and carrying out standardization processing;
in practical application, the normal working condition data is data stored in a historical database according to experience of operators and production results; the specific process of the standardization treatment is (variable-mean)/standard deviation;
s102, extracting a first Slow Feature from the processed normal working condition data by an MWSFA (Moving Window Slow Feature Analysis, based on sliding Window) method, taking the Feature which is not extracted as a first fast Feature, and calculating a transformation matrix W;
it should be noted that, because the production process has a nonlinear relation and is influenced by the working condition change and the time-varying characteristic, the model can be updated in time by adopting the sliding window method, and the calculated amount of the model is effectively reduced; the obtained transformation matrix W is the transformation matrix corresponding to the normal working condition data and is used for extracting slow features in the data, namely S is WXTPreparing for subsequently calculating a second slow characteristic corresponding to the working condition data to be measured, wherein the second slow characteristic comprises [ W ]d,We]May be called WdTransformation matrix for first slow feature, WeA transformation matrix corresponding to the first fast feature;
s103, calculating a static index control limit T according to the first slow characteristic and the first fast characteristicd,lim，Te,limAnd dynamic index control limit Sd,lim，Se,lim；
It should be noted that d represents a slow feature space, and e represents a fast feature space; when k slow features are extracted, the feature vectors corresponding to the k slow features are slow feature spaces, the rest unextracted features are used as fast features, and the feature vectors corresponding to the fast features are fast feature spaces; the production process data has dynamic characteristics, and is divided into a slow characteristic space and a fast characteristic space by an SFA method, so that the essential characteristics of the data can be effectively extracted and the dynamic characteristics of the production process data can be reflected;
s104, standardizing the working condition data x to be detected;
s105, acquiring a second slow characteristic and a second fast characteristic corresponding to the working condition data to be detected according to the calculated transformation matrix and the processed working condition data x to be detected;
s106, calculating static statistics and dynamic statistics of the working condition data to be measured according to the second slow characteristic and the second fast characteristic;
it should be noted that by distinguishing static statistics and dynamic statistics and deeply analyzing the reasons for generating the abnormality, the state of generating the real fault can be found out, so that invalid early warning is reduced, and the working efficiency is improved;
s107, comparing the static statistic with the static index control limit, comparing the dynamic statistic with the dynamic index control limit, and judging the production state of the industrial production process according to the comparison result.
In the method for monitoring the state of the industrial production process provided by the embodiment of the invention, the MWSFA method is adopted to divide the working condition data into the slow characteristic space and the fast characteristic space, the calculated amount is small, the time dynamic characteristics contained in the production process data are extracted to effectively judge the real-time running state change of the production process so as to judge whether a real fault occurs or not, invalid early warning is reduced, a reasonable basis is provided for the production process monitoring and fault diagnosis of industrial enterprises, and the working efficiency is improved.
Further, in practical implementation, in the method for monitoring the state of the industrial production process provided by the embodiment of the present invention, when step S105 is executed, the following formulas are used to obtain the second slow feature and the second fast feature:
sd＝WdxT
se＝WexT
wherein s isdFor the second slow feature, seAs a second fast feature, WdFor the transformation matrix corresponding to the first slow feature calculated, WeAnd x is the data of the working condition to be measured, wherein the x is the transformation matrix corresponding to the calculated first fast characteristic.
In specific implementation, in the method for monitoring the state of the industrial production process provided by the embodiment of the present invention, when step S106 is executed, the following formula is used to calculate the static statistics of the working condition data to be measured:
Figure BDA0002813498130000071
Figure BDA0002813498130000072
wherein, TdFor the static statistic corresponding to the second slow feature, TeFor the static statistic corresponding to the second fast feature, sdFor the second slow feature, seThe second fast feature.
In specific implementation, in the method for monitoring the state of the industrial production process provided in the embodiment of the present invention, when step S106 is executed, the following formula is used to calculate the dynamic statistics of the working condition data to be measured:
Figure BDA0002813498130000073
Figure BDA0002813498130000074
Figure BDA0002813498130000075
Figure BDA0002813498130000076
x＝[x1 x2 … xN]T
wherein S isdFor the dynamic statistic corresponding to the second slow feature, SeFor the dynamic statistics corresponding to the second fast features,
Figure BDA0002813498130000077
for the amount of change corresponding to the second slow feature,
Figure BDA0002813498130000078
the variation corresponding to the second fast feature. Can be combined with
Figure BDA0002813498130000079
Is modified into
Figure BDA00028134981300000710
I.e. the difference between the current second slow characteristic and the last second slow characteristic, and in the same way,
Figure BDA00028134981300000711
i.e. the difference between the present second fast feature and the last second fast feature.
In a specific implementation, in the method for monitoring the state of the industrial production process provided by the embodiment of the present invention, when step S107 is executed, the method for determining the production state of the industrial production process according to the comparison result may specifically include, as shown in fig. 2: if the static statistic is in the control limit T of the static indexd,lim，Te,limInternal and dynamic statistics within dynamic index control limit Sd,lim，Se,limIf so, judging that the industrial production process is in a normal working state without fault, and recalculating the statistical index when new data are acquired; if the static statistic exceeds the static index control limit Td,lim，Te,limAnd if the dynamic statistic exceeds the control limit of the dynamic index, judging that the industrial production process is abnormal and the control function is disabled, and carrying out early warning to prompt that a fault occurs.
Further, in a specific implementation, in the method for monitoring the state of the industrial production process provided by the embodiment of the present invention, when step S107 is executed, the method for monitoring the state of the industrial production process determines the production state of the industrial production process according to the comparison result, as shown in fig. 2, specifically, the method may further include: if the static statistic exceeds the static index control limit Td,lim，Te,limAnd the dynamic statistic is within the dynamic index control limit Sd,lim，Se,limAnd if so, judging that the industrial production process is switched to a new working condition, and eliminating the influence of the transition process through a control action without early warning. And due to the change of the working condition, the static statistics before updating is needed, and the MWSFA method is adopted to update the model.
Further, in a specific implementation, in the method for monitoring the state of the industrial process according to the embodiment of the present invention, when step S107 is executed, the method for monitoring the state of the industrial process determines the production state of the industrial process according to the comparison result, as shown in fig. 2, specifically, the method may further include: if the static statistic is in the control limit T of the static indexd,lim，Te,limInternal and dynamic statistics exceed dynamic index control limit Sd,lim，Se,limIf the interference contained in the working condition data to be detected causes dynamic change in the industrial production process, the dynamic change can be eliminated through the closed-loop control action of the production process, but the production process still needs to be inspected in time to prevent faults.
Through the steps, the real-time running state of the industrial production process can be effectively judged, the running state change rule can be analyzed, and the method has practical application value and guiding significance for further fault diagnosis analysis and production process state optimization.
Based on the same inventive concept, the embodiment of the invention also provides a device for monitoring the state of the industrial production process, and as the principle of solving the problems of the device is similar to that of the method for monitoring the state of the industrial production process, the implementation of the device can refer to the implementation of the method for monitoring the state of the industrial production process, and repeated parts are not repeated.
In specific implementation, the device for monitoring the state of the industrial production process, as shown in fig. 3, specifically includes:
the first data processing module 11 is used for acquiring normal working condition data and performing standardized processing;
a first feature extraction module 12, configured to extract a first slow feature from the processed normal working condition data by using the MWSFA method, where the feature that is not extracted is used as a first fast feature, and a transformation matrix is calculated;
the control limit calculation module 13 is used for calculating a static index control limit and a dynamic index control limit according to the first slow characteristic and the first fast characteristic;
the second data processing module 14 is used for carrying out standardization processing on the working condition data to be detected;
the second characteristic obtaining module 15 is configured to obtain a second slow characteristic and a second fast characteristic corresponding to the working condition data to be detected according to the calculated transformation matrix and the processed working condition data to be detected;
the statistic calculation module 16 is used for calculating the static statistic and the dynamic statistic of the working condition data to be measured according to the second slow characteristic and the second fast characteristic;
and the production state judging module 17 is used for comparing the static statistic with the static index control limit, comparing the dynamic statistic with the dynamic index control limit, and judging the production state of the industrial production process according to the comparison result.
In the industrial production process state monitoring device provided by the embodiment of the invention, the time dynamic characteristics contained in the production process data can be extracted through the interaction of the seven modules, the real-time running state change of the production process is judged to judge whether a real fault occurs or not, the invalid early warning is reduced, a reasonable basis is provided for the production process monitoring and fault diagnosis of industrial enterprises, the working efficiency is high, and the calculated amount is small.
For more specific working processes of the modules, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
Correspondingly, the embodiment of the invention also discloses equipment for judging the state of the industrial production process, which comprises a processor and a memory; the processor executes the computer program stored in the memory to realize the industrial production process state monitoring method disclosed by the embodiment.
For more specific processes of the above method, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
Further, the present invention also discloses a computer readable storage medium for storing a computer program; the computer program, when executed by a processor, implements the industrial process condition monitoring method disclosed above.
For more specific processes of the above method, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device, the equipment and the storage medium disclosed by the embodiment correspond to the method disclosed by the embodiment, so that the description is relatively simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The industrial production process state monitoring method provided by the embodiment of the invention comprises the following steps: collecting normal working condition data and carrying out standardized processing; extracting a first slow characteristic from the processed normal working condition data by an MWSFA method, taking the unextracted characteristic as a first fast characteristic, and calculating a transformation matrix; calculating a static index control limit and a dynamic index control limit according to the first slow characteristic and the first fast characteristic; carrying out standardization processing on the working condition data to be detected; acquiring a second slow characteristic and a second fast characteristic corresponding to the working condition data to be detected according to the calculated transformation matrix and the processed working condition data to be detected; calculating static statistics and dynamic statistics of the working condition data to be measured according to the second slow characteristic and the second fast characteristic; and comparing the static statistic with the static index control limit, comparing the dynamic statistic with the dynamic index control limit, and judging the production state of the industrial production process according to the comparison result. The MWSFA method is adopted to divide the working condition data into the slow characteristic space and the fast characteristic space, the calculated amount is small, the time dynamic characteristics contained in the production process data are extracted to effectively judge the real-time running state change of the production process so as to judge whether real faults occur or not, the invalid early warning is reduced, a reasonable basis is provided for the production process monitoring and fault diagnosis of industrial enterprises, and the working efficiency is improved. In addition, the invention also provides a corresponding device, equipment and a computer readable storage medium for the industrial production process state monitoring method, so that the method has higher practicability, and the device, the equipment and the computer readable storage medium have corresponding advantages.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The method, the device, the equipment and the storage medium for monitoring the industrial production process state provided by the invention are described in detail, the principle and the implementation mode of the invention are explained by applying specific examples, and the description of the examples is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.

Claims (10)

1. A method of monitoring the condition of an industrial process, comprising:
collecting normal working condition data and carrying out standardized processing;
extracting a first slow characteristic from the processed normal working condition data by an MWSFA method, taking the unextracted characteristic as a first fast characteristic, and calculating a transformation matrix;
calculating a static index control limit and a dynamic index control limit according to the first slow characteristic and the first fast characteristic;
carrying out standardization processing on the working condition data to be detected;
acquiring a second slow characteristic and a second fast characteristic corresponding to the working condition data to be detected according to the calculated transformation matrix and the processed working condition data to be detected;
calculating static statistics and dynamic statistics of the working condition data to be measured according to the second slow characteristic and the second fast characteristic;
and comparing the static statistic with the static index control limit, comparing the dynamic statistic with the dynamic index control limit, and judging the production state of the industrial production process according to the comparison result.
2. The method of claim 1, wherein the second slow characteristic and the second fast characteristic are obtained using the following equations:
sd＝WdxT
se＝WexT
wherein s isdFor the second slow feature, seAs the second fast feature, WdFor the calculated transformation matrix corresponding to said first slow feature, WeAnd x is the working condition data to be measured for the calculated transformation matrix corresponding to the first fast characteristic.
3. The method for monitoring the state of the industrial production process according to claim 2, characterized in that the static statistics of the data of the working conditions to be measured are calculated by the following formula:
Figure FDA0002813498120000011
Figure FDA0002813498120000012
wherein, TdA static statistic, T, corresponding to the second slow featureeA static statistic, s, corresponding to the second fast featuredFor the second slow feature, seIs the second fast feature.
4. The method for monitoring the state of the industrial production process according to claim 3, wherein the dynamic statistics of the data of the working conditions to be measured are calculated by adopting the following formula:
Figure FDA0002813498120000021
Figure FDA0002813498120000022
Figure FDA0002813498120000023
Figure FDA0002813498120000024
x＝[x1 x2 … xN]T
wherein S isdDynamic statistics, S, corresponding to said second slow featureseDynamic statistics corresponding to the second fast features,
Figure FDA0002813498120000025
for the amount of change corresponding to the second slow feature,
Figure FDA0002813498120000026
the variation corresponding to the second fast characteristic.
5. The method for monitoring the state of the industrial production process according to claim 4, wherein the step of determining the production state of the industrial production process according to the comparison result specifically comprises:
if the static statistic is within the static index control limit and the dynamic statistic is within the dynamic index control limit, judging that the industrial production process is in a normal working state and no fault occurs;
and if the static statistic exceeds the static index control limit and the dynamic statistic exceeds the dynamic index control limit, judging that the industrial production process is abnormal and the control function is disabled, and performing early warning.
6. The method for monitoring the state of the industrial production process according to claim 5, wherein the determining the production state of the industrial production process according to the comparison result further comprises:
and if the static statistic exceeds the static index control limit and the dynamic statistic is within the dynamic index control limit, judging that the industrial production process is switched to a new working condition, and recalculating the static statistic without early warning.
7. The method for monitoring the state of the industrial production process according to claim 6, wherein the determining the production state of the industrial production process according to the comparison result further comprises:
and if the static statistic is within the static index control limit and the dynamic statistic exceeds the dynamic index control limit, judging that the interference contained in the working condition data to be detected causes dynamic change in the industrial production process, and timely checking the industrial production process.
8. An industrial process condition monitoring device, comprising:
the first data processing module is used for acquiring normal working condition data and carrying out standardized processing;
the first feature extraction module is used for extracting a first slow feature from the processed normal working condition data through an MWSFA method, taking the feature which is not extracted as a first fast feature, and calculating a transformation matrix;
the control limit calculation module is used for calculating a static index control limit and a dynamic index control limit according to the first slow characteristic and the first fast characteristic;
the second data processing module is used for carrying out standardized processing on the working condition data to be detected;
the second characteristic acquisition module is used for acquiring a second slow characteristic and a second fast characteristic corresponding to the working condition data to be detected according to the calculated transformation matrix and the processed working condition data to be detected;
the statistic calculation module is used for calculating the static statistic and the dynamic statistic of the working condition data to be measured according to the second slow characteristic and the second fast characteristic;
and the production state judging module is used for comparing the static statistic with the static index control limit, comparing the dynamic statistic with the dynamic index control limit, and judging the production state of the industrial production process according to the comparison result.
9. An industrial process state determination device comprising a processor and a memory, wherein the processor implements the industrial process state monitoring method according to any one of claims 1 to 7 when executing a computer program stored in the memory.
10. A computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the industrial process state monitoring method of any of claims 1 to 7.
CN202011393319.7A 2020-12-02 2020-12-02 Industrial production process state monitoring method, device, equipment and storage medium Pending CN112541017A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011393319.7A CN112541017A (en) 2020-12-02 2020-12-02 Industrial production process state monitoring method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011393319.7A CN112541017A (en) 2020-12-02 2020-12-02 Industrial production process state monitoring method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN112541017A true CN112541017A (en) 2021-03-23

Family

ID=75015422

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011393319.7A Pending CN112541017A (en) 2020-12-02 2020-12-02 Industrial production process state monitoring method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112541017A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113033683A (en) * 2021-03-31 2021-06-25 中南大学 Industrial system working condition monitoring method and system based on static and dynamic joint analysis

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108803531A (en) * 2018-07-17 2018-11-13 浙江大学 Closed-loop system process monitoring method based on sound feature Cooperative Analysis and orderly Time segments division
CN109143995A (en) * 2018-07-13 2019-01-04 浙江大学 A kind of fine method for monitoring operation states of closed-loop system sufficiently decomposed based on the related slow feature of quality
CN109184821A (en) * 2018-09-11 2019-01-11 浙江大学 A kind of on-line monitoring method of the closed-loop information analysis towards intelligent power plant's Generator Set steam turbine
CN109238760A (en) * 2018-09-11 2019-01-18 浙江大学 On-line monitoring method based on canonical correlation analysis Yu the intelligent power plant soot generating set coal pulverizer of slow signature analysis
CN110879580A (en) * 2019-12-10 2020-03-13 浙江大学 Analysis and monitoring method for large-range non-steady transient continuous process

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109143995A (en) * 2018-07-13 2019-01-04 浙江大学 A kind of fine method for monitoring operation states of closed-loop system sufficiently decomposed based on the related slow feature of quality
CN108803531A (en) * 2018-07-17 2018-11-13 浙江大学 Closed-loop system process monitoring method based on sound feature Cooperative Analysis and orderly Time segments division
CN109184821A (en) * 2018-09-11 2019-01-11 浙江大学 A kind of on-line monitoring method of the closed-loop information analysis towards intelligent power plant's Generator Set steam turbine
CN109238760A (en) * 2018-09-11 2019-01-18 浙江大学 On-line monitoring method based on canonical correlation analysis Yu the intelligent power plant soot generating set coal pulverizer of slow signature analysis
CN110879580A (en) * 2019-12-10 2020-03-13 浙江大学 Analysis and monitoring method for large-range non-steady transient continuous process

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113033683A (en) * 2021-03-31 2021-06-25 中南大学 Industrial system working condition monitoring method and system based on static and dynamic joint analysis
CN113033683B (en) * 2021-03-31 2022-05-06 中南大学 Industrial system working condition monitoring method and system based on static and dynamic joint analysis

Similar Documents

Publication Publication Date Title
CN107742053B (en) Wind turbine generator set abnormity identification method and device
CN111949941B (en) Equipment fault detection method, system, device and storage medium
CN110807245B (en) Automatic modeling method and system for equipment fault early warning
CN108052974B (en) Fault diagnosis method, system, equipment and storage medium
CN111368428B (en) Sensor precision degradation fault detection method based on monitoring second-order statistics
CN111796233B (en) Method for evaluating secondary errors of multiple voltage transformers in double-bus connection mode
CN113579851B (en) Non-stationary drilling process monitoring method based on adaptive segmented PCA
CN116028887B (en) Analysis method of continuous industrial production data
CN113902241A (en) Power grid equipment maintenance strategy system and method based on comprehensive state evaluation
CN112541017A (en) Industrial production process state monitoring method, device, equipment and storage medium
CN111797533A (en) Nuclear power device operation parameter abnormity detection method and system
CN117333143A (en) Cost subject dictionary setting method and system
CN111507374A (en) Power grid mass data anomaly detection method based on random matrix theory
CN114112390B (en) Nonlinear complex system early fault diagnosis method
CN115167364A (en) Early fault detection method based on probability transformation and statistical characteristic analysis
CN115828114A (en) Energy consumption abnormity detection method for aluminum profile extruder
CN111428345B (en) Performance evaluation system and method of random load disturbance control system
CN112228042B (en) Method for judging working condition similarity of pumping well based on cloud edge cooperative computing
CN110259435B (en) Well condition change identification method based on oil pumping unit electrical parameters
CN108052087A (en) Manufacturing process multivariate quality diagnostic classification device based on comentropy
EP2052451A1 (en) Model-based method for monitoring a power supply network, and system for carrying out said method
CN107203198A (en) Improved manufacturing process multivariate quality diagnostic classification device
CN107291065A (en) The improved manufacturing process multivariate quality diagnostic classification device based on decision tree
CN113361730A (en) Risk early warning method, device, equipment and medium for maintenance plan
CN112116014A (en) Test data outlier detection method for distribution automation equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination