CN102736546A - State monitoring device of complex electromechanical system for flow industry and method - Google Patents
State monitoring device of complex electromechanical system for flow industry and method Download PDFInfo
- Publication number
- CN102736546A CN102736546A CN2012102190783A CN201210219078A CN102736546A CN 102736546 A CN102736546 A CN 102736546A CN 2012102190783 A CN2012102190783 A CN 2012102190783A CN 201210219078 A CN201210219078 A CN 201210219078A CN 102736546 A CN102736546 A CN 102736546A
- Authority
- CN
- China
- Prior art keywords
- data
- monitoring
- fault
- module
- mrow
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 86
- 238000012806 monitoring device Methods 0.000 title claims abstract description 10
- 238000012544 monitoring process Methods 0.000 claims abstract description 76
- 238000005457 optimization Methods 0.000 claims abstract description 22
- 230000002159 abnormal effect Effects 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 17
- 230000003993 interaction Effects 0.000 claims abstract description 14
- 230000008569 process Effects 0.000 claims description 38
- 238000001514 detection method Methods 0.000 claims description 30
- 238000004458 analytical method Methods 0.000 claims description 19
- 238000007405 data analysis Methods 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 230000001186 cumulative effect Effects 0.000 claims description 8
- 230000009467 reduction Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 238000012847 principal component analysis method Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 9
- 238000000513 principal component analysis Methods 0.000 abstract description 4
- 230000007812 deficiency Effects 0.000 abstract 1
- 238000010792 warming Methods 0.000 abstract 1
- 239000011159 matrix material Substances 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000000354 decomposition reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000009776 industrial production Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000012824 chemical production Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000013341 scale-up Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to a state monitoring device of a complex electromechanical system for a flow industry and a method. The device comprises a man-machine interaction module, a data collecting module, a data preprocessing module, a data analyzing module and a failure case library. According to the device and the method provided by the invention, whether the system fails or is in abnormal states or not can be monitored and early warming for tripping accidents or other accidents of the flow industry system can be made. Meanwhile, a KPCA (Kernel Principal Component Analysis) method with double parameter optimization is used to overcome the deficiency that parameters are selected by empirical formula in conventional KPCA methods, thereby improving the state monitoring ability. Furthermore, the failure case database is adequately used in the historical production process so that failures of the system can be monitored more immediately and accurately.
Description
Technical Field
The invention belongs to the technical field of electromechanical system monitoring, relates to a state monitoring device and method, and particularly relates to a state monitoring device and method for a complicated electromechanical system in the process industry.
Background
In the process industry, as industrial processes continue to scale up and become increasingly complex, the safety and reliability requirements of production systems are increasing. The long-term safe, stable and efficient operation of a production system and the avoidance of malignant safety accidents become an important task of modern industry. Therefore, in the system operation process, the occurrence of a fault or an abnormal state needs to be detected in time, the fault type needs to be judged, the fault source needs to be positioned, and adverse influence factors need to be eliminated. Conventional condition monitoring methods can be divided into three categories: analytic-based methods, knowledge-based methods, and data-driven-based methods. The method based on analysis is based on strict mathematical model, such as Kalman filter, parameter estimation, equivalent space and other methods; the knowledge-based method is mainly to establish a model according to the knowledge of the process, such as a Fault Tree (FTA), a Decision Tree (DT) and the like; the data-based method mainly uses collected process data as a basis, and digs system state information implied in the data through various data processing and analyzing methods so as to guide the production process, such as a multivariate statistical method, cluster analysis, spectrum analysis and the like. Because production systems in the process industry are becoming complex and it is difficult to obtain strict mathematical models and detailed system knowledge, analytical and knowledge-based methods are limited; in addition, the industrial system usually collects and records the equipment running state data, and the state monitoring data just contains essential information such as system running conditions, system abnormal state evolution rules and the like, so that the analysis method based on data driving is widely applied to the aspects of state monitoring, fault diagnosis and the like in the process industry.
From the viewpoint of scientific research, a process industrial production system represented by chemical production is a distributed complex electromechanical system formed by coupling a plurality of large-scale power mechanical equipment, chemical reaction devices and an automatic control system through an energy network, a fluid network, an information network and a control network. In the actual condition monitoring process, such a complex electromechanical system faces 3 problems: (1) the monitoring variables are huge in quantity, correlation and strong coupling exist among the variables, and all the variables are difficult to monitor simultaneously in a manual mode. (2) The monitoring data has the characteristic of coexistence of multiple characteristics such as slowly varying, massive, nonlinear and atypical characteristics, and the equipment state characteristic information contained in the data is not mined by an effective means. (3) Modern process industrial production systems are in a multi-media coupled network environment, and currently, there is no device system and method for effectively monitoring the state at the system level.
The following brief introduction and definition are made to the KPCA theory, wavelet noise reduction and other concepts related to the present invention:
kernel Principal Component Analysis (KPCA), short, is a common method for fault detection based on data driving. The basic idea of kernel principal component analysis is to map the data matrix X of the input space to a high-dimensional feature space F by a non-linear mapping function phi, then to do principal component analysis to the mapped data in the high-dimensional space, to extract the linear feature of the data in the high-dimensional space, that is, the dataNon-linear characteristics in a low dimensional space. This non-linear mapping is achieved by introducing a kernel function to compute the inner product of the data in the input space. KPCA constructs process statistics T based on process principal component feature signal subspace information2And the statistic SPE of the residual error information subspace information, determining the control limit of the SPE, and further realizing state monitoring.
The traditional KPCA method has the following defects in practical application: (1) the selection of the KPCA kernel parameters and the number of the principal elements is very subjective, and currently, the selection of the kernel parameters has no uniform criterion, and most of the kernel parameters adopt an empirical formula method. The selection of the number of the principal elements in the KPCA generally adopts a simple and common principal element Cumulative contribution rate method (CPV), but the contribution rate is most suitable and has no uniform standard, and when the number of the principal elements is solved by adopting the principal element Cumulative contribution rate in the KPCA, the selection of the kernel parameters is firstly influenced; (2) the entire monitoring process does not utilize known fault case data, but rather builds a KPCA model based on the given parameters to detect all kinds of faults. However, a fixed system model cannot have a good detection effect on all faults, and can only be very sensitive to one fault or a certain type of faults. The invention provides a set of device and method to overcome the above problems based on the improved KPCA model with double-parameter optimization.
Wavelet noise reduction, data collected in an actual industrial process is often polluted and interfered by noise, such as white noise, electromagnetic interference and the like, wherein useful signals are generally represented as low-frequency signals or relatively stable signals, and noise signals are generally represented as high-frequency signals. When the wavelet decomposition is carried out on the actually acquired data, the noise part is mainly contained in the high-frequency wavelet coefficient, so that the wavelet coefficient can be processed by applying forms such as threshold value and the like, and then the purposes of noise reduction and interference resistance can be achieved by reconstructing the signal, thereby improving the data quality and the fault detection capability and accuracy.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a state monitoring device and a state monitoring method for a complex electromechanical system in the process industry, aiming at the characteristics of multivariable, mass, nonlinearity and the like of monitoring data of the complex electromechanical system in the process industry, the state monitoring in the production process is realized from the system level, the state monitoring capability can be improved, and faults and abnormal states can be found in time.
The purpose of the invention is solved by the following technical scheme:
the state monitoring device of the complicated electromechanical system in the process industry comprises:
a human-computer interaction module: the system is used for realizing interaction between a user and a state monitoring system, comprises input and output of system state monitoring information, and calls a data acquisition module, a data preprocessing module and a data analysis module;
a data acquisition module: the DCS control system is used for extracting the detection data of the historical state of the system and the real-time data generated in the operation process of the DCS control system;
a data preprocessing module: the system comprises a data acquisition unit, a data processing unit and a data processing unit, wherein the data acquisition unit is used for acquiring data of a monitored variable;
a data analysis module: the system is used for modeling the monitoring system, comparing real-time monitoring data with the established model and detecting the abnormal state of the system;
a fault case library: the system comprises a data storage module, a fault analysis module and a fault analysis module, wherein the data storage module is used for storing and managing historical fault information of a monitored system, and comprises fault time, fault reason and fault mode;
the human-computer interaction module is respectively connected with the data acquisition module, the data preprocessing module and the data analysis module and is used as a carrier for information transmission; meanwhile, the data acquisition module, the data preprocessing module and the data analysis module are respectively connected with the fault case library, and information is extracted from the fault case library to complete modeling and analysis functions.
The functions in the data analysis module include: a KPCA model analysis method of two-parameter optimization; establishing a KPCA model set of the monitoring system by combining data information of a system case base; comparing the real-time monitoring data with the established KPCA model set, and detecting the abnormal state of the system; and judging the operation condition of the whole process industrial system, and providing targeted safety early warning information.
The invention also provides a state monitoring method of the complicated electromechanical system of the process industry based on the device, which comprises the following steps:
1) data acquisition: extracting the normal working condition historical data of the monitored object from the fault case library and collecting the real-time monitoring data of the monitored object; the historical data is used for establishing a system model, and the real-time data is used for monitoring the system state;
2) data preprocessing: firstly, denoising extracted normal working condition historical data and collected real-time monitoring data of a monitoring object by adopting a wavelet denoising method; then, carrying out standardization processing on the data subjected to noise reduction, and eliminating the influence of inconsistent dimension of each monitoring variable;
3) establishing a system model: establishing a KPCA model according to normal working condition historical data by adopting a kernel principal component analysis method of double-parameter optimization, and optimizing the kernel parameters and the number of principal components in the KPCA model by combining with known fault case data to obtain a KPCA model set for detecting whether a system is in an abnormal state;
4) monitoring an abnormal state: calculating monitoring statistics of the acquired real-time monitoring data under the established model, comparing the monitoring statistics with the upper limit value of the monitoring statistics of the model, and judging that the system is in an abnormal state in the statistical sense if the monitoring statistics exceeds the upper limit value of the statistics;
5) and displaying the analysis result and the effective early warning information through a man-machine interaction module.
Further, the step 3) specifically comprises the following steps:
a) establishing a two-parameter target optimization problem, and solving a statistic T2The kernel parameter sigma and the number p of the principal elements when the statistic relevance ratio and the SPE statistic relevance ratio are maximum are expressed by the following formula:
wherein:
σ -nuclear parameter;
p is the number of principal elements;
n is the number of principal elements at 85% cumulative contribution rate;
m is the dimension of the input space, namely the number of variables;
Ft(σ, p) -T at given nuclear parameters and pivot numbers2A statistic detection rate;
Fs(σ, p) -SPE statistic relevance ratio under given nuclear parameters and principal component number conditions;
b) acquiring data under a normal working condition as a training sample, standardizing, and establishing a KPCA model by using initial kernel parameters and the number of principal elements; the initial kernel parameter σ =10m, where m is an input space dimension, that is, the number of variables; selecting the initial principal component number according to a method that the cumulative contribution rate reaches 85%;
c) obtaining T under the condition that the inspection level alpha is 99% according to the number of the initial principal elements2Statistics and SPE statistics upper limit values;
d) acquiring fault case data, and standardizing each variable by using the standard deviation and the mean value of the vector corresponding to the training data;
e) solving the principal component vector of the fault case data under the initial parameters to obtain T2Statistics and SPE statistics;
f) comparing the statistic value with the statistic upper limit value, and respectively calculating T2The average detection rate is obtained according to the percentage of the samples with the statistic and the SPE statistic exceeding the upper limit value;
g) changing initial parameters, calculating the average relevance ratio of statistics under the new parameters according to the steps, comparing the average relevance ratio with the previous average relevance ratio, and keeping the kernel parameters and the number of principal elements with higher average relevance ratio;
h) repeating the steps until the average detection rate meets a certain detection rate required by fault detection or a convergence solution is obtained; the kernel parameters and the number of principal elements at this time are the optimal KPCA model parameters for the fault.
The invention has the following beneficial effects:
the device and the method for monitoring the state of the complex electromechanical system in the process industry can monitor whether the system has faults or abnormal states, and can give early warning to the vehicle jumping accident or other safety accidents of the process industry system. Meanwhile, the KPCA method optimized by double parameters is utilized, so that the fault detection capability of the traditional KPCA monitoring method is improved. Moreover, the fault case database established in the process industrial process system is fully utilized, so that the system fault is monitored more timely and accurately.
Drawings
FIG. 1 is a schematic diagram of the apparatus of the present invention;
FIG. 2 is a flow chart of the operation of the present invention;
FIG. 3 is a KPCA method solution flow for two-parameter optimization;
FIG. 4 is a system block diagram of an embodiment of the present invention;
fig. 5 is a diagram of the monitoring of the status of the system according to the invention.
Detailed Description
Referring to fig. 1, the state monitoring device of the complicated electromechanical system in process industry of the invention comprises:
a human-computer interaction module: the system is used for realizing interaction between a user and a state monitoring system, and comprises input and output of system state monitoring information, and a data acquisition module, a data preprocessing module and a data analysis module are called. The system fault case library can be modified and updated, historical/real-time monitoring data can be managed, and a data analysis module can be called to carry out state monitoring.
A data acquisition module: the method is used for extracting the historical state monitoring data of the system and the real-time monitoring data generated by the DCS control system in the system operation process.
A data preprocessing module: the method is used for removing the white Gaussian noise of the monitoring variable data, standardizing the collected data, and removing the influence of dimensions so as to facilitate subsequent analysis.
A data analysis module: this module is the core part of the device of the invention. And by combining the data information of the system case base, on the basis of KPCA modeling of the monitoring system, comparing the real-time monitoring data with the established KPCA model set, quickly and effectively detecting the abnormal state of the system, judging the running condition of the whole process industrial system, and providing effective safety early warning information.
A fault case library: the system is used for storing and managing historical fault information of a monitored system, and comprises relevant information such as fault time, fault reason, fault mode and the like.
The human-computer interaction module is respectively connected with the data acquisition module, the data preprocessing module and the data analysis module and is used as a carrier for information transmission; meanwhile, the data acquisition module, the data preprocessing module and the data analysis module are respectively connected with the fault case library, and information is extracted from the fault case library to complete modeling and analysis functions.
The functions in the data analysis module include: a KPCA model analysis method of two-parameter optimization; establishing a KPCA model set of the monitoring system by combining data information of a system case base; comparing the real-time monitoring data with the established KPCA model set, and detecting the abnormal state of the system; and judging the operation condition of the whole process industrial system, and providing targeted safety early warning information.
The invention can adopt a computer memory to store the data information of the system fault case, the monitoring historical data, the real-time data and the data analysis process, and adopts an input and output interface to connect a keyboard, an external memory and a display, and KPCA model set information, analysis results and the like generated in the analysis process can be expressed in the display in a man-machine interaction mode.
Based on the above device, the working flow of the method for monitoring and analyzing the state of the complicated electromechanical system in the process industry is shown in fig. 2, and the method comprises the following specific steps:
step 1: and (3) extracting data of the monitored object, wherein the data of normal working conditions stored in a historical database is effectively extracted according to the specific monitored object and in combination with the monitoring target, and real-time data of monitoring variables corresponding to the historical data can be extracted.
Step 2: preprocessing the extracted real-time/historical data; preprocessing of the data includes wavelet de-noising and normalization (making the mean zero and variance 1). The method specifically comprises the following steps:
(a) wavelet denoising is performed on the extracted real-time/historical data. According to the principle of wavelet transform threshold denoising, wavelet transform threshold denoising generally comprises the following 3 steps: (1) selecting a proper wavelet base and determining the decomposition level to perform wavelet decomposition on the signal; (2) determining the threshold value of each layer of detail coefficient, and processing the wavelet coefficient by using a soft threshold value or hard threshold value method; (3) the inverse wavelet transform reconstructs the signal.
(b) And carrying out standardization processing on the data subjected to wavelet transform threshold denoising. Different variables often have different dimensions and magnitudes. In order to compare the degree of variation of different variables on the same order of magnitude, it is necessary to eliminate the influence of the dimension, so the data is normalized. The mean and variance of the normalized data were 0 and 1, respectively.
And step 3: and establishing a KPCA model based on historical normal working condition data. Original input data matrix X belongs to Rn×m(m observation variables, n sampling times) are n samples in the normal operation state, and the data matrix after the pretreatment of the step 2 isUsing a Gaussian radial basis kernel function
A kernel matrix K is calculated.
Centralizing the kernel matrix K and solving the eigenvalue and eigenvector a of KkNormalizing the feature vector so that<ak,ak>=1/λk. Wherein λkIs the corresponding characteristic value.
Computing a non-linear pivot tk：
Wherein,
is the feature vector after the normalization and is,
is the kernel matrix K after centering.
And 4, step 4: and (4) constructing a KPCA model set optimized by double parameters by combining a fault case library. And optimizing the core parameters and the number of the principal elements of the KPCA for each fault in the fault case library to obtain a KPCA model corresponding to each fault. The specific optimization method refers to the specification (3).
And 5: KPCA state monitoring based on two-parameter optimization. For a new sample data x for real-time monitoringnew∈R1×mConstructing corresponding statistic T2And SPE and its corresponding control threshold value Tα 2And SPEαThe system status is monitored. Statistic T2And its corresponding control threshold value Tα 2Can be determined by the following formula:
T2=[t1,.,tp]Λ-1[t1，…,tp]T （2）
wherein Λ-1Is the inverse of the diagonal matrix formed by the eigenvalues corresponding to the principal elements, FαAnd (k, n-k) is an upper limit value of F distribution with the confidence coefficient of alpha and the degrees of freedom of p and n-p respectively, and can be obtained by looking up a table. SPE is defined as:
when the verify level is α, the SPE control limit is
SPE controls X with limited degree of freedom of h2And (4) distribution. If a and b are the mean and variance of SPE, respectively, g = b/2a and h = 2a2/b。
Step 6: and displaying the analysis result and the effective early warning information. Comparing the statistic value of the real-time monitoring data with the statistic upper limit value of the KPCA model, if Ta<T or SPEa<And SPE shows that the system is in an abnormal state. And the analysis result is displayed through the man-machine interaction module, and the system abnormal state prompt is given to an operator.
The KPCA method optimization process of the above two-parameter optimization is as follows:
referring to fig. 3, fig. 3 is a schematic diagram of a solution flow of the KPCA method for two-parameter optimization. And (4) constructing a double-parameter optimized KPCA model for each fault in the case library by combining the fault case library. Establishing a two-parameter target optimization problem, solving the equation T2The nuclear parameter sigma and the number of principal elements p when the detection rate and the SPE detection rate are maximum can be expressed by the following formula:
wherein:
σ -nuclear parameter;
p is the number of principal elements;
n is the number of principal elements at 85% cumulative contribution rate;
m is the dimension of the input space, namely the number of variables;
Ft(σ, p) -T at given nuclear parameters and pivot numbers2A statistic detection rate;
Fs(σ, p) -SPE statistic relevance ratio under given nuclear parameters and principal component number conditions;
for a two-parameter target optimization problem, the specific solution comprises the following steps:
step 1: and acquiring data under a normal working condition as a training sample, standardizing, and establishing a KPCA model by using initial kernel parameters and the number of principal elements. The initial kernel parameter σ =10m, which is the input spatial dimension, i.e. the number of variables. The initial principal component number is selected according to the method that the cumulative contribution rate reaches 85%.
Step 2, obtaining T under the condition that the inspection level alpha is 99 percent according to the number of the initial principal elements2Statistics and SPE statistics upper limit.
And step 3: and acquiring fault case data, and standardizing each variable by using the standard deviation and the mean value of the vector corresponding to the training data.
And 4, step 4: solving the principal component vector of the fault case data under the initial parameters to obtain T2Statistics and SPE statistics.
And 5: comparing the statistic value with the statistic upper limit value, and respectively calculating T2And obtaining the average detection rate by the percentage of the sample with the statistic and the SPE statistic exceeding the upper limit value.
Step 6: and changing the initial parameters, calculating the average relevance ratio of the statistic under the new parameters according to the steps, comparing the average relevance ratio with the previous average relevance ratio, and keeping the kernel parameters and the number of the principal elements with higher average relevance ratio.
And 7: and repeating the steps until the average detection rate meets a certain detection rate required by fault detection or a convergence solution is obtained. The kernel parameters and the number of principal elements at this time are the optimal KPCA model parameters for the fault.
In the process of solving the optimization problem, the kernel parameter σ needs to be considered to be too large, so as to prevent the kernel function from being too generalized and losing the advantage of extracting the nonlinear features. When the number p of pivot elements is calculated, if the larger the number of pivot elements is, the higher the failure detection rate is, a balance between the enhancement of the dimensionality reduction effect and the enhancement of the failure detection rate needs to be considered.
The two-parameter optimization KPCA method adopted by the invention combines the fault case data, and has more pertinence to the known fault. When faults similar to those in the fault case library occur in the system operation process, the KPCA method based on the double-parameter optimization can enable the fault detection effect to be optimal.
Referring to fig. 4-5, fig. 4 is a schematic diagram of a compressor assembly. The compressor set system consists of a 5EH-8BD steam turbine, a RIK100-4 radial isothermal compact air compressor, an RBZ45-7 radial barrel supercharger, a TX36/1C gearbox and a plurality of auxiliary devices and equipment. 70 monitoring variables closely related to the running state of the compressor set system are selected as observation variables.
Fig. 5 is a diagram of detection of system faults by the two-parameter optimization KPCA. The fault causes the low-load operation of the air compressor due to the pressure drop of the steam pipe network. And after optimization, selecting the kernel parameter to be 495 and the number of the principal elements to be 8, establishing a KPCA model and monitoring the running state of the compressor unit. It can be seen from the graph that both statistics show significant overrun around the 800 th sample, and both statistics are effective in detecting the fault. Wherein, T2The detection rate of the statistic is 94.2%, the detection rate of the SPE statistic is 99.4%, and the average detection rate is 96.8%.
The system in the actual process industrial production is complex and has a plurality of system faults, so that a rich fault case database needs to be established to give targeted early warning to the abnormal state of the system. On the basis, the state monitoring result is further subjected to accepting or analyzing by using experience knowledge of technicians, and further fault diagnosis is performed.
Claims (4)
1. A condition monitoring device for a complex electromechanical system in the process industry, comprising:
a human-computer interaction module: the system is used for realizing interaction between a user and a state monitoring system, comprises input and output of system state monitoring information, and calls a data acquisition module, a data preprocessing module and a data analysis module;
a data acquisition module: the DCS control system is used for extracting the detection data of the historical state of the system and the real-time data generated in the operation process of the DCS control system;
a data preprocessing module: the system comprises a data acquisition unit, a data processing unit and a data processing unit, wherein the data acquisition unit is used for acquiring data of a monitored variable;
a data analysis module: the system is used for modeling the monitoring system, comparing real-time monitoring data with the established model and detecting the abnormal state of the system;
a fault case library: the system comprises a data storage module, a fault analysis module and a fault analysis module, wherein the data storage module is used for storing and managing historical fault information of a monitored system, and comprises fault time, fault reason and fault mode;
the human-computer interaction module is respectively connected with the data acquisition module, the data preprocessing module and the data analysis module and is used as a carrier for information transmission; meanwhile, the data acquisition module, the data preprocessing module and the data analysis module are respectively connected with the fault case library, and information is extracted from the fault case library to complete modeling and analysis functions.
2. The condition monitoring device of process industry complex electromechanical system according to claim 1, wherein the functions in the data analysis module include: a KPCA model analysis method of two-parameter optimization; establishing a KPCA model set of the monitoring system by combining data information of a system case base; comparing the real-time monitoring data with the established KPCA model set, and detecting the abnormal state of the system; and judging the operation condition of the whole process industrial system and providing safety early warning information.
3. A method for monitoring the state of a complex electromechanical system in the process industry based on the device of claim 1, which comprises the following steps:
1) data acquisition: extracting the normal working condition historical data of the monitored object from the fault case library and collecting the real-time monitoring data of the monitored object; the historical data is used for establishing a system model, and the real-time data is used for monitoring the system state;
2) data preprocessing: firstly, denoising extracted normal working condition historical data and collected real-time monitoring data of a monitoring object by adopting a wavelet denoising method; then, carrying out standardization processing on the data subjected to noise reduction, and eliminating the influence of inconsistent dimension of each monitoring variable;
3) establishing a system model: establishing a KPCA model according to normal working condition historical data by adopting a kernel principal component analysis method of double-parameter optimization, and optimizing the kernel parameters and the number of principal components in the KPCA model by combining with known fault case data to obtain a KPCA model set for detecting whether a system is in an abnormal state;
4) monitoring an abnormal state: calculating monitoring statistics of the acquired real-time monitoring data under the established model, comparing the monitoring statistics with the upper limit value of the monitoring statistics of the model, and judging that the system is in an abnormal state in the statistical sense if the monitoring statistics exceeds the upper limit value of the statistics;
5) and displaying the analysis result and the effective early warning information through a man-machine interaction module.
4. The method for monitoring the state of the complex electromechanical system in the process industry according to claim 3, wherein the step 3) comprises the following steps:
a) establishing a two-parameter target optimization problem, solving the equation T2The kernel parameter sigma and the number p of the principal elements when the statistic relevance ratio and the SPE statistic relevance ratio are maximum are expressed by the following formula:
wherein:
σ -nuclear parameter;
p is the number of principal elements;
n is the number of principal elements at 85% cumulative contribution rate;
m is the dimension of the input space, namely the number of variables;
Ft(σ, p) -T at given nuclear parameters and pivot numbers2A statistic detection rate;
Fs(σ, p) -SPE statistic relevance ratio under given nuclear parameters and principal component number conditions;
b) acquiring data under a normal working condition as a training sample, standardizing, and establishing a KPCA model by using initial kernel parameters and the number of principal elements; the initial kernel parameter σ =10m, where m is an input space dimension, that is, the number of variables; selecting the initial principal component number according to a method that the cumulative contribution rate reaches 85%;
c) obtaining T under the condition that the inspection level alpha is 99% according to the number of the initial principal elements2Statistics and SPE statistics upper limit values;
d) acquiring fault case data, and standardizing each variable by using the standard deviation and the mean value of the vector corresponding to the training data;
e) solving the principal component vector of the fault case data under the initial parameters to obtain T2Statistics and SPE statistics;
f) comparing the statistic value with the statistic upper limit value, and respectively calculating T2The average detection rate is obtained according to the percentage of the samples with the statistic and the SPE statistic exceeding the upper limit value;
g) changing initial parameters, calculating the average relevance ratio of statistics under the new parameters according to the steps, comparing the average relevance ratio with the previous average relevance ratio, and keeping the kernel parameters and the number of principal elements with higher average relevance ratio;
h) repeating the steps until the average detection rate meets a certain detection rate required by fault detection or a convergence solution is obtained; the kernel parameters and the number of principal elements at this time are the optimal KPCA model parameters for the fault.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210219078.3A CN102736546B (en) | 2012-06-28 | 2012-06-28 | State monitoring device of complex electromechanical system for flow industry and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210219078.3A CN102736546B (en) | 2012-06-28 | 2012-06-28 | State monitoring device of complex electromechanical system for flow industry and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102736546A true CN102736546A (en) | 2012-10-17 |
| CN102736546B CN102736546B (en) | 2014-06-04 |
Family
ID=46992216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210219078.3A Active CN102736546B (en) | 2012-06-28 | 2012-06-28 | State monitoring device of complex electromechanical system for flow industry and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102736546B (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103439091A (en) * | 2013-06-25 | 2013-12-11 | 国电大渡河检修安装有限公司 | Method and system for early warning and diagnosing water turbine runner blade crack breakdown |
| CN103575334A (en) * | 2013-11-08 | 2014-02-12 | 苏州康开电气有限公司 | Electromechanical device intelligent analysis system |
| CN103913698A (en) * | 2014-03-27 | 2014-07-09 | 长沙学院 | Switching current circuit fault diagnosis method based on wavelet fractal and kernel principal characteristics |
| CN104182623A (en) * | 2014-08-12 | 2014-12-03 | 南京工程学院 | Thermal process data detection method based on equivalent change rate calculation |
| CN104777830A (en) * | 2015-04-01 | 2015-07-15 | 浙江大学 | Multi-work-condition process monitoring method based on KPCA (kernel principal component analysis) mixture model |
| CN104777831A (en) * | 2015-04-09 | 2015-07-15 | 武汉船用机械有限责任公司 | Fault diagnosis method of hydraulic submerged pump system |
| CN106682835A (en) * | 2016-12-29 | 2017-05-17 | 西安交通大学 | Data-driven complex electromechanical system service quality state evaluation method |
| CN107045548A (en) * | 2017-04-13 | 2017-08-15 | 南京南瑞继保电气有限公司 | A kind of system and method for calculating wind-powered electricity generation capacity usage ratio |
| CN107292061A (en) * | 2017-07-28 | 2017-10-24 | 西安交通大学 | A kind of process industry complex electromechanical systems information modelling approach of data-driven |
| CN108508860A (en) * | 2018-05-10 | 2018-09-07 | 西安交通大学 | A kind of process industry production system data monitoring method based on coupled relation |
| CN108664696A (en) * | 2018-04-02 | 2018-10-16 | 国家计算机网络与信息安全管理中心 | A kind of assessment method and device of handpiece Water Chilling Units operating status |
| CN109542070A (en) * | 2018-12-13 | 2019-03-29 | 宁波大学 | A kind of dynamic process monitoring method based on biobjective scheduling algorithm |
| CN109726505A (en) * | 2019-01-14 | 2019-05-07 | 哈尔滨工程大学 | A kind of forging machine tool main drive gear fault diagnosis system based on intelligent trouble tree |
| CN109945930A (en) * | 2019-04-16 | 2019-06-28 | 山东理工职业学院 | A kind of electromechanical equipment fault detection approach based on electromagnetic technique |
| CN110046146A (en) * | 2019-04-16 | 2019-07-23 | 中国联合网络通信集团有限公司 | The monitoring method and device of industrial equipment based on mobile edge calculations |
| CN111077876A (en) * | 2019-12-11 | 2020-04-28 | 湖南大唐先一科技有限公司 | Power station equipment state intelligent evaluation and early warning method, device and system |
| CN111797943A (en) * | 2020-07-28 | 2020-10-20 | 中车青岛四方机车车辆股份有限公司 | Urban rail vehicle and passenger room door fault diagnosis method thereof |
| CN112002114A (en) * | 2020-07-22 | 2020-11-27 | 温州大学 | Electromechanical equipment wireless data acquisition system and method based on 5G-ZigBee communication |
| CN112537559A (en) * | 2019-09-20 | 2021-03-23 | 中国石油化工股份有限公司 | Oil gas monitoring method and system for oil depot |
| CN113632015A (en) * | 2019-03-29 | 2021-11-09 | 尤尼弗莱克斯-液压有限责任公司 | Method for producing a plurality of composite structures |
| CN114723082A (en) * | 2022-04-19 | 2022-07-08 | 镇江西门子母线有限公司 | Abnormity early warning method and system for intelligent low-voltage complete equipment |
| CN115095534A (en) * | 2022-04-11 | 2022-09-23 | 中核核电运行管理有限公司 | KPCA-based CANDU6 reactor main pump fault diagnosis method |
| CN116704735A (en) * | 2023-08-08 | 2023-09-05 | 湖南江河能源科技股份有限公司 | Hydropower station intelligent alarm method, system, terminal and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101196743A (en) * | 2007-12-26 | 2008-06-11 | 西安交通大学 | Dynamoelectric system safety analyzing device and method based on cause-effect network model |
| CN101446827A (en) * | 2008-11-06 | 2009-06-03 | 西安交通大学 | Process fault analysis device of process industry system and method therefor |
| CN101634851A (en) * | 2009-08-25 | 2010-01-27 | 西安交通大学 | Method based on cause-and-effect relation of variables for diagnosing failures in process industry |
-
2012
- 2012-06-28 CN CN201210219078.3A patent/CN102736546B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101196743A (en) * | 2007-12-26 | 2008-06-11 | 西安交通大学 | Dynamoelectric system safety analyzing device and method based on cause-effect network model |
| CN101446827A (en) * | 2008-11-06 | 2009-06-03 | 西安交通大学 | Process fault analysis device of process industry system and method therefor |
| CN101634851A (en) * | 2009-08-25 | 2010-01-27 | 西安交通大学 | Method based on cause-and-effect relation of variables for diagnosing failures in process industry |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103439091B (en) * | 2013-06-25 | 2015-11-18 | 国电大渡河检修安装有限公司 | The early warning of water turbine runner blade crackle fault and diagnostic method and system |
| CN103439091A (en) * | 2013-06-25 | 2013-12-11 | 国电大渡河检修安装有限公司 | Method and system for early warning and diagnosing water turbine runner blade crack breakdown |
| CN103575334A (en) * | 2013-11-08 | 2014-02-12 | 苏州康开电气有限公司 | Electromechanical device intelligent analysis system |
| CN103913698A (en) * | 2014-03-27 | 2014-07-09 | 长沙学院 | Switching current circuit fault diagnosis method based on wavelet fractal and kernel principal characteristics |
| CN104182623A (en) * | 2014-08-12 | 2014-12-03 | 南京工程学院 | Thermal process data detection method based on equivalent change rate calculation |
| CN104777830A (en) * | 2015-04-01 | 2015-07-15 | 浙江大学 | Multi-work-condition process monitoring method based on KPCA (kernel principal component analysis) mixture model |
| CN104777831A (en) * | 2015-04-09 | 2015-07-15 | 武汉船用机械有限责任公司 | Fault diagnosis method of hydraulic submerged pump system |
| CN106682835A (en) * | 2016-12-29 | 2017-05-17 | 西安交通大学 | Data-driven complex electromechanical system service quality state evaluation method |
| CN106682835B (en) * | 2016-12-29 | 2020-05-22 | 西安交通大学 | Data-driven complex electromechanical system service quality state evaluation method |
| CN107045548A (en) * | 2017-04-13 | 2017-08-15 | 南京南瑞继保电气有限公司 | A kind of system and method for calculating wind-powered electricity generation capacity usage ratio |
| CN107045548B (en) * | 2017-04-13 | 2021-02-09 | 南京南瑞继保电气有限公司 | System and method for calculating wind power energy utilization rate |
| CN107292061A (en) * | 2017-07-28 | 2017-10-24 | 西安交通大学 | A kind of process industry complex electromechanical systems information modelling approach of data-driven |
| CN108664696A (en) * | 2018-04-02 | 2018-10-16 | 国家计算机网络与信息安全管理中心 | A kind of assessment method and device of handpiece Water Chilling Units operating status |
| CN108508860A (en) * | 2018-05-10 | 2018-09-07 | 西安交通大学 | A kind of process industry production system data monitoring method based on coupled relation |
| CN109542070A (en) * | 2018-12-13 | 2019-03-29 | 宁波大学 | A kind of dynamic process monitoring method based on biobjective scheduling algorithm |
| CN109726505A (en) * | 2019-01-14 | 2019-05-07 | 哈尔滨工程大学 | A kind of forging machine tool main drive gear fault diagnosis system based on intelligent trouble tree |
| CN109726505B (en) * | 2019-01-14 | 2023-03-17 | 哈尔滨工程大学 | Forging and pressing lathe main drive mechanism fault diagnosis system based on intelligence trouble tree |
| CN113632015B (en) * | 2019-03-29 | 2024-05-28 | 尤尼弗莱克斯-液压有限责任公司 | Method for producing a plurality of composite structures |
| CN113632015A (en) * | 2019-03-29 | 2021-11-09 | 尤尼弗莱克斯-液压有限责任公司 | Method for producing a plurality of composite structures |
| CN109945930A (en) * | 2019-04-16 | 2019-06-28 | 山东理工职业学院 | A kind of electromechanical equipment fault detection approach based on electromagnetic technique |
| CN110046146A (en) * | 2019-04-16 | 2019-07-23 | 中国联合网络通信集团有限公司 | The monitoring method and device of industrial equipment based on mobile edge calculations |
| CN112537559A (en) * | 2019-09-20 | 2021-03-23 | 中国石油化工股份有限公司 | Oil gas monitoring method and system for oil depot |
| CN111077876A (en) * | 2019-12-11 | 2020-04-28 | 湖南大唐先一科技有限公司 | Power station equipment state intelligent evaluation and early warning method, device and system |
| CN112002114A (en) * | 2020-07-22 | 2020-11-27 | 温州大学 | Electromechanical equipment wireless data acquisition system and method based on 5G-ZigBee communication |
| CN111797943B (en) * | 2020-07-28 | 2024-02-02 | 中车青岛四方机车车辆股份有限公司 | Urban rail vehicle and passenger compartment door fault diagnosis method thereof |
| CN111797943A (en) * | 2020-07-28 | 2020-10-20 | 中车青岛四方机车车辆股份有限公司 | Urban rail vehicle and passenger room door fault diagnosis method thereof |
| CN115095534A (en) * | 2022-04-11 | 2022-09-23 | 中核核电运行管理有限公司 | KPCA-based CANDU6 reactor main pump fault diagnosis method |
| CN115095534B (en) * | 2022-04-11 | 2024-07-16 | 中核核电运行管理有限公司 | CANDU6 reactor main pump fault diagnosis method based on KPCA |
| CN114723082A (en) * | 2022-04-19 | 2022-07-08 | 镇江西门子母线有限公司 | Abnormity early warning method and system for intelligent low-voltage complete equipment |
| CN114723082B (en) * | 2022-04-19 | 2023-08-18 | 镇江西门子母线有限公司 | Abnormality early warning method and system for intelligent low-voltage complete equipment |
| CN116704735A (en) * | 2023-08-08 | 2023-09-05 | 湖南江河能源科技股份有限公司 | Hydropower station intelligent alarm method, system, terminal and storage medium |
| CN116704735B (en) * | 2023-08-08 | 2023-11-03 | 湖南江河能源科技股份有限公司 | Hydropower station intelligent alarm method, system, terminal and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102736546B (en) | 2014-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102736546A (en) | State monitoring device of complex electromechanical system for flow industry and method | |
| CN110738274A (en) | nuclear power device fault diagnosis method based on data driving | |
| CN105259895B (en) | A kind of detection of industrial process small fault and separation method and its monitoring system | |
| CN104699077B (en) | A kind of failure variable partition method based on nested iterations Fei Sheer discriminant analyses | |
| CN102339389B (en) | Fault detection method for one-class support vector machine based on density parameter optimization | |
| CN104714537B (en) | A kind of failure prediction method based on the relative mutation analysis of joint and autoregression model | |
| CN104062968A (en) | Continuous chemical process fault detection method | |
| CN112598172A (en) | Wind turbine bearing temperature early warning method | |
| CN116383636A (en) | Coal mill fault early warning method based on PCA and LSTM fusion algorithm | |
| CN103729444B (en) | The abnormal deviation data examination method of potential relation between a kind of data based on monitoring of equipment | |
| CN113537328A (en) | Rotary machine fault diagnosis method and device based on deep learning | |
| CN112002114A (en) | Electromechanical equipment wireless data acquisition system and method based on 5G-ZigBee communication | |
| CN109298633A (en) | Chemical production process fault monitoring method based on adaptive piecemeal Non-negative Matrix Factorization | |
| Li et al. | Canonical variate residuals-based contribution map for slowly evolving faults | |
| CN118430092B (en) | Data general acquisition method based on MCC system | |
| CN110751217A (en) | Equipment energy consumption ratio early warning analysis method based on principal component analysis | |
| CN103309347B (en) | A kind of multiple operating modes process method for supervising based on rarefaction representation | |
| CN112598144A (en) | CNN-LSTM burst fault early warning method based on correlation analysis | |
| CN114254904B (en) | Method and device for evaluating operation health degree of engine room of wind turbine generator | |
| CN105629959A (en) | Industrial process fault detection method | |
| CN103559401A (en) | Failure monitoring method based on semi-supervised principal component analysis | |
| CN103995985B (en) | Fault detection method based on Daubechies wavelet transform and elastic network | |
| CN106295712A (en) | A kind of fault detection method and system | |
| CN114112390B (en) | Nonlinear complex system early fault diagnosis method | |
| Chang et al. | Application of fault monitoring and diagnosis in process industry based on fourth order moment and singular value decomposition |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20181130 Address after: 310018 M10-15-7 Block, 12th Street, Hangzhou Economic and Technological Development Zone, Zhejiang Province Patentee after: Hangzhou Hollysys Automation Co., Ltd. Address before: 710049 Xianning West Road, Xi'an, Xi'an, Shaanxi Patentee before: Xi'an Jiaotong University |
|
| TR01 | Transfer of patent right |