CN117171670B - Textile production process fault monitoring method, device and system - Google Patents
Textile production process fault monitoring method, device and system Download PDFInfo
- Publication number
- CN117171670B CN117171670B CN202311451578.4A CN202311451578A CN117171670B CN 117171670 B CN117171670 B CN 117171670B CN 202311451578 A CN202311451578 A CN 202311451578A CN 117171670 B CN117171670 B CN 117171670B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- parameter
- parameters
- value
- degree
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 313
- 238000000034 method Methods 0.000 title claims abstract description 120
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 97
- 239000004753 textile Substances 0.000 title claims abstract description 79
- 230000002159 abnormal effect Effects 0.000 claims abstract description 35
- 238000010219 correlation analysis Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000005856 abnormality Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012806 monitoring device Methods 0.000 claims description 2
- 230000000875 corresponding effect Effects 0.000 description 27
- 238000004458 analytical method Methods 0.000 description 17
- 238000001514 detection method Methods 0.000 description 4
- 229920000742 Cotton Polymers 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004445 quantitative analysis Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000004801 process automation Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000009987 spinning Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- General Factory Administration (AREA)
Abstract
The invention discloses a method, a device and a system for monitoring faults in a textile production process, and relates to the technical field of data processing. Mainly comprises the following steps: comparing each value in the time sequence of the monitoring parameter with a normal value to obtain the fluctuation degree of the monitoring parameter; obtaining the priority of the monitoring parameters by using an analytic hierarchy process so as to obtain the fault degree of the monitoring parameters by combining the fluctuation degree; obtaining a first association coefficient between any two monitoring parameters through correlation analysis, and obtaining a second association coefficient between the two monitoring parameters according to the probability that any two monitoring parameters are abnormal at the same time; obtaining a fault value of the monitoring parameter; and when the fault value of the monitoring parameter is larger than a preset first threshold value, overhauling the production equipment corresponding to the monitoring parameter. The method and the device can identify the abnormal equipment in time according to the real-time textile data.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a method, a device and a system for monitoring faults in a textile production process.
Background
The sales of the textile and clothing industry is inferior to the travel industry and the information industry at present, and the market is dominant in the world economy. The textile not only can meet the basic demands of people's life, but also is an economic and decaying sunny rain watch, and is valued by governments of various countries. An important part of the textile industry is the textile production line, so how to control the efficient and safe operation of the textile production line becomes an important link in the textile process.
In the prior art, for monitoring and fault analysis of textile production process, data exception rules are formulated in advance mainly by human; or collecting a large amount of data formed in the production process, manually marking whether the data are abnormal data, and training through a neural network to discover and report the abnormal data in the daily production process to related personnel.
Whether the data anomaly rule is formulated manually in advance, or whether a large amount of data is marked manually and whether the data is anomaly data or not, a large amount of workload exists, the problems of low efficiency, low accuracy and the like exist in the manual rule formulation or marking, and the real whole process automation can not be realized to obtain the position where the anomaly data occurs so as to process the position where the anomaly data occurs subsequently.
Disclosure of Invention
Aiming at the technical problems, the embodiment of the invention provides a method, a device and a system for monitoring faults in a textile production process, which are used for acquiring monitoring data of a textile production line and comparing the monitoring data with values under normal conditions to obtain the fluctuation degree of the monitoring data so as to obtain a fault value of a monitoring parameter by combining a first correlation coefficient and a second correlation coefficient among the monitoring data, and overhauling equipment corresponding to the monitoring parameter when the fault value of the monitoring parameter is larger than a preset first threshold. The method has the advantages that the abnormal rules of the data are not required to be set manually or a large amount of historical data are required to be marked manually, the recognition efficiency of the abnormal data in the textile production process is improved, abnormal equipment in the production process can be obtained, related personnel are informed to process in time, full automation of the analysis of the production process is realized, the processing efficiency is improved, and meanwhile, the efficiency of the textile production process can be promoted.
In a first aspect, the present invention provides a method for monitoring faults in a textile production process, comprising:
and acquiring a time sequence of each monitoring parameter of each device on the textile production line within a preset time length, and respectively preprocessing the time sequence of each monitoring parameter to remove abnormal values.
And comparing each value in the time sequence of the monitoring parameter with the value of the monitoring parameter in a normal state to obtain the fluctuation degree of the monitoring parameter.
And respectively obtaining the priority corresponding to each monitoring parameter by using an analytic hierarchy process so as to obtain the fault degree of the monitoring parameter by combining the fluctuation degree of the monitoring parameter.
And obtaining a first association coefficient between any two monitoring parameters through correlation analysis, and obtaining a second association coefficient between any two monitoring parameters according to the probability that any two monitoring parameters are abnormal at the same time.
And obtaining a fault value of the monitoring parameter according to the fault degree of the monitoring parameter and the first association parameter and the second association parameter between the monitoring parameter and other monitoring parameters.
And when the fault value of the monitoring parameter is larger than a preset first threshold value, overhauling the production equipment corresponding to the monitoring parameter.
In a possible embodiment, comparing each value in the time sequence of the monitored parameter with the value of the monitored parameter in the normal state to obtain the fluctuation degree of the monitored parameter includes:
wherein,to monitor the degree of fluctuation of the parameter +.>In time series for monitoring parameters +.>Personal value (s)/(s)>For monitoring the values of the parameter in the normal state, z is the number of values contained in the time series of the monitored parameter, +.>Is a natural constant.
In a possible embodiment, obtaining the second association coefficient between any two monitoring parameters according to the probability that the two monitoring parameters are abnormal at the same time includes:
wherein,is->The monitoring parameters and->Said second associated parameter between said monitored parameters,is->The process number corresponding to the monitoring parameter is the same as the +.>Difference of process numbers corresponding to the monitoring parameters, < ->Is->The monitoring parameters and->Probability of abnormality of each of said monitoring parameters at the same time, < >>For monitoring the number of parameters +.>A preset first value greater than zero.
In a possible embodiment, the process numbers are obtained by arranging the process numbers from front to back on the textile production line, and each of the monitoring parameters corresponds to one process number.
In a possible embodiment, the process of obtaining the fault value of the monitoring parameter includes:
wherein the method comprises the steps ofIs->Fault value of each of said monitored parameters, +.>Is->The degree of failure of each of the monitored parameters,is->Said degree of failure of each of said monitored parameters, < >>Is->The monitoring parameters and->Said first correlation parameter between said monitoring parameters,/or->Is->The monitoring parameters and->Said second associated parameter between said monitoring parameters,/or->To monitor the number of parameters.
In one possible embodiment, preprocessing the time series of each monitored parameter to remove outliers includes:
and respectively carrying out histogram statistics on the time sequences of the monitoring parameters, and respectively removing the data with the occurrence frequency smaller than a preset second threshold value from the time sequences of the monitoring parameters.
In one possible embodiment, the process of obtaining the value of the monitoring parameter in the normal state includes:
performing DBSCAN clustering on historical data of the monitoring parameters to obtain a plurality of categories, finding out the category with the largest data quantity contained in each category, and taking the average value of the data contained in the category as the numerical value of the monitoring parameters in a normal state.
In a possible embodiment, the degree of failure of the monitoring parameter is obtained from the product of the degree of fluctuation of the monitoring parameter and the priority.
In a second aspect, the present invention provides a device for monitoring faults in a textile production process, comprising:
the data acquisition module is used for acquiring the time sequence of each monitoring parameter of each device on the textile production line within a preset duration, and respectively preprocessing the time sequence of each monitoring parameter to remove abnormal values.
And the first calculation module is used for comparing each value in the time sequence of the monitoring parameter with the value of the monitoring parameter in the normal state to obtain the fluctuation degree of the monitoring parameter.
And the second calculation module is used for respectively obtaining the priority corresponding to each monitoring parameter by using an analytic hierarchy process so as to obtain the fault degree of the monitoring parameter by combining the fluctuation degree of the monitoring parameter.
And the third calculation module is used for obtaining a first association coefficient between any two monitoring parameters through correlation analysis and obtaining a second association coefficient between the two monitoring parameters according to the probability that any two monitoring parameters are abnormal at the same time.
And the fourth calculation module is used for obtaining the fault value of the monitoring parameter according to the fault degree of the monitoring parameter and the first association parameter and the second association parameter between the monitoring parameter and other monitoring parameters.
And the judging and processing module is used for overhauling the production equipment corresponding to the monitoring parameter when the fault value of the monitoring parameter is larger than a preset first threshold value.
In a third aspect, the present invention provides a system for monitoring faults in a textile production process, comprising: the system comprises a memory and a processor, wherein the processor executes a computer program stored in the memory to realize the fault monitoring method of the textile production process in the embodiment of the invention.
The embodiment of the invention provides a method, a device and a system for monitoring faults in a textile production process, which are used for acquiring monitoring data of a textile production line and comparing the monitoring data with values under normal conditions to obtain the fluctuation degree of the monitoring data so as to obtain a fault value of a monitoring parameter by combining a first correlation coefficient and a second correlation coefficient among all the monitoring data, and overhauling equipment corresponding to the monitoring parameter when the fault value of the monitoring parameter is larger than a preset first threshold value.
Compared with the prior art, the embodiment of the invention has the beneficial effects that: the method has the advantages that the abnormal rules of the data are not required to be set manually or a large amount of historical data are required to be marked manually, the recognition efficiency of the abnormal data in the textile production process is improved, abnormal equipment in the production process can be obtained, related personnel are informed to process in time, full automation of the analysis of the production process is realized, the processing efficiency is improved, and meanwhile, the efficiency of the textile production process can be promoted.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for monitoring faults in a textile production process according to an embodiment of the present invention.
Fig. 2 is a schematic flow chart of a fault monitoring device for textile production process according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
The terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first", "a second" may include one or more such features, either explicitly or implicitly; in the description of the present embodiment, unless otherwise specified, the meaning of "plurality" is two or more.
The method mainly regulates and controls textile production, acquires each monitoring parameter through data acquisition equipment of each process, analyzes abnormal conditions of each monitoring parameter, analyzes correlation among the monitoring parameters through a correlation analysis model of the monitoring parameters, and acquires influence degree among the monitoring parameters; further, based on the running condition and the correlation analysis result of each monitoring parameter, the system is used for comprehensively detecting and analyzing the production process of the textile, and early warning the working procedure or equipment corresponding to the monitoring parameter with the fault condition, timely informing relevant staff to perform fault detection and elimination, ensuring the smooth operation of the production process of the textile, and improving the production efficiency of the textile.
The embodiment of the invention provides a method for monitoring faults in a textile production process, which is shown in fig. 1 and comprises the following steps:
step S101, acquiring time sequences of all monitoring parameters of all equipment on a textile production line within a preset duration, and respectively preprocessing the time sequences of all the monitoring parameters to remove abnormal values.
Step S102, comparing each value in the time sequence of the monitoring parameter with the value of the monitoring parameter in a normal state to obtain the fluctuation degree of the monitoring parameter.
Step S103, respectively obtaining the corresponding priority of each monitoring parameter by using an analytic hierarchy process so as to obtain the fault degree of the monitoring parameter by combining the fluctuation degree of the monitoring parameter.
Step S104, obtaining a first association coefficient between any two monitoring parameters through correlation analysis, and obtaining a second association coefficient between any two monitoring parameters according to the probability that any two monitoring parameters are abnormal at the same time.
Step 105, obtaining a fault value of the monitoring parameter according to the fault degree of the monitoring parameter, and the first correlation parameter and the second correlation parameter between the monitoring parameter and other monitoring parameters.
And S106, when the fault value of the monitoring parameter is larger than a preset first threshold value, overhauling the production equipment corresponding to the monitoring parameter.
Further, step S101 is to obtain a time sequence of each monitoring parameter of each device on the textile production line within a preset duration, and pre-process the time sequence of each monitoring parameter to remove abnormal values. The method specifically comprises the following steps:
firstly, arranging data acquisition equipment in each process, and acquiring state information of each process to acquire each monitoring parameter in the production process in real time.
The textile production process comprises a plurality of working procedures, mainly including processes of cotton cleaning, cotton carding, combing, drawing, roving, spinning and the like, wherein each working procedure corresponds to a subsystem device and is used for completing the work of each working procedure. In order to realize the comprehensive monitoring of the textile production process, the invention is provided with every otherThe time period is used for carrying out fault monitoring on the production process once, a specific numerical value implementer of the preset time period can be set according to the actual situation, and as an example, the preset time period is 5 minutes in the embodiment of the invention, and all monitoring parameters in the production process are collected to obtain multidimensional data in the textile production process.
In order to realize state detection of textile production process, the embodiment of the invention is provided with a plurality of types of sensor groups for collecting various monitoring parameters in the running process of each procedure in textile production, such as monitoring parameters of equipment working temperature, cotton machine drum speed, mechanical equipment vibration frequency, wind pressure and the like, and the purpose of the step is to collect multidimensional monitoring parameters in the textile production process for subsequent analysis of the production process.
Optionally, the sensor is used as a source for acquiring monitoring parameters in each process of textile production, and the measurement result directly influences the accuracy of detection and analysis in the production process. When each collected operation data is enough to cover all operation conditions, abnormal points such as noise may be generated, so that the abnormal data is necessary to be removed. The process for eliminating the abnormal data specifically comprises the following steps: for the time sequence corresponding to the monitoring parameters, counting the occurrence times of each numerical value in the time sequence of the monitoring parameters, establishing corresponding histograms, respectively analyzing the time sequence of each monitoring parameter to remove small probability data in a data set, taking the data with occurrence frequency smaller than a preset second threshold value as abnormal data, and deleting the abnormal data from the time sequence, so that the accuracy of the extraction of the monitoring parameters can be improved, and the analysis precision of each monitoring parameter in the textile production process is ensured.
Further, step S102 is to compare each value in the time sequence of the monitored parameter with the value of the monitored parameter in the normal state, so as to obtain the fluctuation degree of the monitored parameter. The method specifically comprises the following steps:
for each monitoring parameter data set, the invention establishes the process fluctuation degree analysis to detect each process running state based on each monitoring parameter. The process fluctuation degree analysis model specifically comprises the following steps:
firstly, for each monitoring parameter, a large amount of corresponding historical data is obtained in the embodiment of the invention and is used for obtaining the optimal data of the monitoring parameter in a normal working state, the embodiment of the invention adopts a clustering algorithm to analyze the historical data of the monitoring parameter and divide the historical data into a plurality of clusters, in order to improve the clustering precision and further avoid the influence of noise points and the like, the invention adopts a DBSCAN algorithm to carry out clustering analysis on the historical data of the monitoring parameter, as an example, the clustering radius is set to be 1, the clustering density threshold is set to be 10, then the average value of all data contained in the class with the most data is calculated for each class after clustering, and the average value is used as the optimal data of the monitoring parameter in the normal working state.
It should be noted that DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a comparatively representative Density-based clustering algorithm. Unlike the partitioning and hierarchical clustering method, which defines clusters as the largest set of densely connected points, it is possible to partition a region having a sufficiently high density into clusters and find clusters of arbitrary shape in a noisy spatial database.
Further, the embodiment of the invention analyzes the fluctuation degree of each monitoring parameter, namely detects the running state of each process monitoring parameter. The analysis model of the fluctuation degree is as follows:
wherein,to monitor the degree of fluctuation of the parameter +.>In time series for monitoring parameters +.>Personal value (s)/(s)>For monitoring the values of the parameter in the normal state, z is the number of values contained in the time series of the monitored parameter, +.>Is a natural constant.
Therefore, the fluctuation degree corresponding to each monitoring parameter can be obtained respectively, so that the faults of the textile production process can be detected and analyzed in the subsequent step.
Further, step S103 is to obtain priorities corresponding to the monitoring parameters by using an analytic hierarchy process, so as to obtain the failure degree of the monitoring parameters in combination with the fluctuation degree of the monitoring parameters. The method specifically comprises the following steps:
the embodiment of the invention takes the fluctuation degree of each monitoring parameter corresponding to each working procedure as the running state index of each monitoring parameter, and is used for monitoring the fault degree in the textile production process. Based on each running state index, obtaining the fault degree of each monitoring parameter, wherein the calculation process of the fault degree comprises the following steps:
in the method, in the process of the invention,to monitor the degree of failure of a parameter +.>The priority corresponding to the monitoring parameters is the influence degree of the monitoring parameters on the textile production process, and the priority can be obtained according to a analytic hierarchy process.
It should be noted that, the analytic hierarchy process (The Analytic Hierarchy Process) is abbreviated as AHP, which is a simple decision method for complex decision problems with multiple objectives, multiple criteria or no structural characteristics by using less quantitative information to make the decision thinking process mathematical on the basis of deep analysis of the nature, influence factors, internal relations, and the like of the complex decision problems. The method is a qualitative and quantitative combined decision analysis method for solving the complex problem of multiple targets. The method combines quantitative analysis and qualitative analysis, judges the relative importance degree between the standards which can be realized by each measuring target by using the experience of a decision maker, reasonably gives the weight of each standard of each decision scheme, and utilizes the weight to calculate the order of the quality of each scheme, thereby being more effectively applied to the problems which are difficult to solve by a quantitative method.
So far, the fault degree of each monitoring parameter in the textile production process can be obtained, so that the faults of the textile production process can be comprehensively monitored in the subsequent steps.
Further, step S104 is to obtain a first correlation coefficient between any two monitoring parameters through correlation analysis, and obtain a second correlation coefficient between any two monitoring parameters according to the probability that any two monitoring parameters are abnormal at the same time. The method specifically comprises the following steps:
furthermore, in order to realize accurate monitoring and identification of faults in the textile production process, the invention carries out relevance analysis on each production process so as to acquire the influence degree among different processes and improve the detection precision of the system.
In the embodiment of the invention, each process and each corresponding monitoring parameter are connected according to the fault type, the characteristic parameter and other attributes of the process corresponding to each monitoring parameter, so that the first correlation parameter among the monitoring parameters is obtained by utilizing correlation analysis, wherein the correlation analysis refers to analysis of two or more variable elements with correlation, so that the correlation degree of the two factors is measured, and certain connection or probability exists between the correlated elements to perform the correlation analysis.
Specifically, each monitoring parameter is taken as a target parameter, the relation between other monitoring parameters and the target parameter is analyzed, and a first association coefficient between the monitoring parameters is constructed，/>For characterizing the correlation between two monitored parameters, wherein +.>The larger the association between the two is considered to be the larger.
It should be noted that, in this embodiment, the first correlation coefficientThe values of the monitoring parameters can be evaluated by textile industry experts or experienced related operators, and the embodiment of the invention takes each monitoring parameter as a node respectively and analyzes objective association among the monitoring parameters. In the embodiment of the invention, the statistics of target nodes is carried out based on a large amount of historical data>And nodeProbability of simultaneous failure and obtaining target node and nodeThe edge weight of the connecting line is specifically as follows: and numbering each procedure in the textile production process in sequence according to the production sequence, and taking the difference value of the procedure numbers of the two nodes as the edge weight. Based on the probability value and the edge weight value, the invention sets a correlation coefficient analysis model to analyze objective relation between the target node and any other node j, and the calculation process of the second correlation coefficient comprises the following steps:
wherein,is->Monitoring parameters and->A second correlation parameter between the individual monitoring parameters, < >>Is->Process number and +.>Difference of process numbers corresponding to the monitoring parameters, < ->Is->Monitoring parameters and->Probability of abnormality of each monitoring parameter at the same time, +.>For monitoring the number of parameters +.>Is a preset first value.
As an example, in the embodiment of the present invention. Therefore, according to the method, each monitoring parameter can be respectively used as a target node to be analyzed so as to obtain a second association coefficient between each monitoring parameter and any other monitoring parameter, and the subsequent analysis of faults in the textile production process is facilitated.
Further, in step S105, a fault value of the monitoring parameter is obtained according to the fault degree of the monitoring parameter, and the first correlation parameter and the second correlation parameter between the monitoring parameter and other monitoring parameters. The method specifically comprises the following steps:
the embodiment of the invention realizes the monitoring of the fault degree in the textile production process mainly through the running state indexes of all the monitoring parameters and the relevance among all the working procedures. Therefore, the embodiment of the invention respectively obtains the fault influence of the faults of each monitoring parameter on the textile production process on the basis of the fault degree and the first association coefficient and the second association coefficient among the monitoring parameters, and simultaneously, the embodiment characterizes the influence degree through the fault value, and the acquisition process of the fault value of the monitoring parameter comprises the following steps:
wherein the method comprises the steps ofIs->Fault value of individual monitoring parameters +.>Is->The degree of failure of the individual monitoring parameters,/->Is->The degree of failure of the individual monitoring parameters,/->Is->Monitoring parameters and->A first correlation parameter between the individual monitoring parameters, < >>Is->Monitoring parameters and->A second correlation parameter between the individual monitoring parameters, < >>In order to monitor the number of parameters, fault values of the monitored parameters in the textile production process can be obtained.
Further, in step S106, when the fault value of the monitoring parameter is greater than a preset first threshold, the production equipment corresponding to the monitoring parameter is overhauled. The method specifically comprises the following steps:
because each monitoring parameter has corresponding equipment or working procedure, when the fault value of the monitoring parameter is larger than a preset first threshold value, the corresponding equipment or working procedure has abnormal conditions, and the equipment or working procedure needs to be checked to eliminate faults in the production process, so that the production efficiency of textiles is improved.
The embodiment of the invention provides a device for monitoring faults in a textile production process, which is shown in fig. 2 and comprises the following components:
the data acquisition module 201 is configured to acquire a time sequence of each monitoring parameter of each device on the textile production line within a preset duration, and perform preprocessing on the time sequence of each monitoring parameter to reject abnormal values.
The first calculation module 202 is configured to compare each value in the time sequence of the monitored parameter with the value of the monitored parameter in the normal state, so as to obtain the fluctuation degree of the monitored parameter.
The second calculation module 203 is configured to obtain priorities corresponding to the monitoring parameters by using an analytic hierarchy process, so as to obtain a failure degree of the monitoring parameters in combination with a fluctuation degree of the monitoring parameters.
The third calculation module 204 is configured to obtain a first correlation coefficient between any two monitoring parameters through correlation analysis, and obtain a second correlation coefficient between any two monitoring parameters according to a probability that any two monitoring parameters are abnormal at the same time.
The fourth calculation module 205 is configured to obtain a fault value of the monitoring parameter according to the fault degree of the monitoring parameter, and the first correlation parameter and the second correlation parameter between the monitoring parameter and other monitoring parameters.
And the judging and processing module 206 is configured to overhaul the production equipment corresponding to the monitoring parameter when the fault value of the monitoring parameter is greater than a preset first threshold value.
Based on the same inventive concept as the above method, the present embodiment also provides a system for monitoring faults in textile production process, where the system for monitoring faults in textile production process includes a memory and a processor, and the processor executes a computer program stored in the memory to implement monitoring faults in textile production process as described in the method embodiment for monitoring faults in textile production process.
Since the embodiments of the method for monitoring faults in the textile production process have already been described, the description thereof is omitted here.
In summary, the embodiments of the present invention provide a method, an apparatus, and a system for monitoring a failure in a textile production process, which acquire monitoring data of a textile production line and compare the monitoring data with values under normal conditions to obtain a fluctuation degree of the monitoring data, so as to combine a first correlation coefficient and a second correlation coefficient between the monitoring data to obtain a failure value of a monitoring parameter, and when the failure value of the monitoring parameter is greater than a preset first threshold, overhaul equipment corresponding to the monitoring parameter. The method has the advantages that the abnormal rules of the data are not required to be set manually or a large amount of historical data are required to be marked manually, the recognition efficiency of the abnormal data in the textile production process is improved, abnormal equipment in the production process can be obtained, related personnel are informed to process in time, full automation of the analysis of the production process is realized, the processing efficiency is improved, and meanwhile, the efficiency of the textile production process can be promoted.
In this disclosure, terms such as "comprising," "including," "having," and the like are open-ended terms that mean "including, but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It should also be noted that in the methods and systems of the present invention, components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered equivalent to the present disclosure.
The above examples are given for clarity of illustration only and are not to be construed as limiting the scope of the invention. Other variations or modifications of the various aspects will be apparent to persons skilled in the art from the foregoing description, and it is not necessary nor intended to be exhaustive of all embodiments. All designs that are the same or similar to the present invention are within the scope of the present invention.
Claims (8)
1. A method for monitoring faults in a textile manufacturing process, comprising:
acquiring a time sequence of each monitoring parameter of each device on a textile production line within a preset time length, and respectively preprocessing the time sequence of each monitoring parameter to remove abnormal values;
comparing each value in the time sequence of the monitoring parameter with the value of the monitoring parameter in a normal state to obtain the fluctuation degree of the monitoring parameter;
respectively obtaining the priority corresponding to each monitoring parameter by using an analytic hierarchy process so as to obtain the fault degree of the monitoring parameter by combining the fluctuation degree of the monitoring parameter;
obtaining a first association coefficient between any two monitoring parameters through correlation analysis, and obtaining a second association coefficient between any two monitoring parameters according to the probability that any two monitoring parameters are abnormal at the same time;
obtaining a fault value of the monitoring parameter according to the fault degree of the monitoring parameter and the first association parameter and the second association parameter between the monitoring parameter and other monitoring parameters;
when the fault value of the monitoring parameter is larger than a preset first threshold value, overhauling production equipment corresponding to the monitoring parameter;
obtaining a second association coefficient between any two monitoring parameters according to the probability of the simultaneous occurrence of abnormality of the two monitoring parameters, wherein the second association coefficient comprises the following steps:
wherein,；/>is->The monitoring parameters and->Said second associated parameter between said monitoring parameters,/or->Is->The process number corresponding to the monitoring parameter is the same as the +.>Difference of process numbers corresponding to the monitoring parameters, < ->Is->The monitoring parameters and->Probability of abnormality of each of said monitoring parameters at the same time, < >>For monitoring the number of parameters +.>A preset first value greater than zero;
the method for acquiring the first association coefficient comprises the following steps: respectively taking each monitoring parameter as a target parameter, analyzing the relation between other monitoring parameters and the target parameter, and constructing a first association coefficient between the monitoring parameters;
the process for acquiring the fault value of the monitoring parameter comprises the following steps:
wherein the method comprises the steps ofIs->Fault value of each of said monitored parameters, +.>Is->Said degree of failure of each of said monitored parameters, < >>Is->Said degree of failure of each of said monitored parameters, < >>Is->The monitoring parameters and->Said first correlation parameter between said monitoring parameters,/or->Is->The monitoring parameters and->Said second associated parameter between said monitoring parameters,/or->To monitor the number of parameters;
based on each running state index, obtaining the fault degree of each monitoring parameter, wherein the calculation process of the fault degree comprises the following steps:
in the method, in the process of the invention,to monitor the degree of failure of a parameter +.>For monitoring the priority corresponding to the parameter, the priority is obtained according to the analytic hierarchy process>To monitor the extent of fluctuation of the parameter.
2. The method for monitoring the faults in the textile production process according to claim 1, wherein comparing each value in the time series of the monitored parameter with the value of the monitored parameter in the normal state to obtain the fluctuation degree of the monitored parameter comprises:
wherein,to monitor the degree of fluctuation of the parameter +.>In time series for monitoring parameters +.>Personal value (s)/(s)>For monitoring the values of the parameter in the normal state, z is the number of values contained in the time series of the monitored parameter, +.>Is a natural constant.
3. The method according to claim 1, wherein the process numbers are obtained by arranging the textile production line from front to back, and each of the monitoring parameters corresponds to one process number.
4. A method of monitoring faults in a textile production process according to claim 1, in which the time series of each monitored parameter is pre-treated separately to reject outliers, comprising:
and respectively carrying out histogram statistics on the time sequences of the monitoring parameters, and respectively removing the data with the occurrence frequency smaller than a preset second threshold value from the time sequences of the monitoring parameters.
5. A method for monitoring faults in textile production processes according to claim 1 in which the acquisition of values of the monitored parameters in normal conditions comprises:
performing DBSCAN clustering on historical data of the monitoring parameters to obtain a plurality of categories, finding out the category with the largest data quantity contained in each category, and taking the average value of the data contained in the category as the numerical value of the monitoring parameters in a normal state.
6. A method of monitoring a textile production process failure according to claim 1, characterized in that the failure level of the monitoring parameter is obtained from the product of the fluctuation level and priority of the monitoring parameter.
7. A textile production process fault monitoring device, comprising:
the data acquisition module is used for acquiring time sequences of all monitoring parameters of all equipment on the textile production line within a preset duration, and respectively preprocessing the time sequences of all the monitoring parameters to remove abnormal values;
the first calculation module is used for comparing each value in the time sequence of the monitoring parameter with the value of the monitoring parameter in a normal state to obtain the fluctuation degree of the monitoring parameter;
the second calculation module is used for respectively obtaining the priority corresponding to each monitoring parameter by using an analytic hierarchy process so as to obtain the fault degree of the monitoring parameter by combining the fluctuation degree of the monitoring parameter;
the third calculation module is used for obtaining a first association coefficient between any two monitoring parameters through correlation analysis and obtaining a second association coefficient between the two monitoring parameters according to the probability that any two monitoring parameters are abnormal at the same time;
a fourth calculation module, configured to obtain a fault value of the monitoring parameter according to the fault degree of the monitoring parameter, and the first correlation parameter and the second correlation parameter between the monitoring parameter and other monitoring parameters;
the judging and processing module is used for overhauling the production equipment corresponding to the monitoring parameter when the fault value of the monitoring parameter is larger than a preset first threshold value;
obtaining a second association coefficient between any two monitoring parameters according to the probability of the simultaneous occurrence of abnormality of the two monitoring parameters, wherein the second association coefficient comprises the following steps:
wherein,；/>is->The monitoring parameters and->Said second associated parameter between said monitoring parameters,/or->Is->The process number corresponding to the monitoring parameter is the same as the +.>Difference of process numbers corresponding to the monitoring parameters, < ->Is->The monitoring parameters and->Probability of abnormality of each of said monitoring parameters at the same time, < >>For monitoring the number of parameters +.>A preset first value greater than zero;
the method for acquiring the first association coefficient comprises the following steps: respectively taking each monitoring parameter as a target parameter, analyzing the relation between other monitoring parameters and the target parameter, and constructing a first association coefficient between the monitoring parameters;
the process for acquiring the fault value of the monitoring parameter comprises the following steps:
wherein the method comprises the steps ofIs->Fault value of each of said monitored parameters, +.>Is->Said degree of failure of each of said monitored parameters, < >>Is->Said degree of failure of each of said monitored parameters, < >>Is->The monitoring parameters and->Said first correlation parameter between said monitoring parameters,/or->Is->The monitoring parameters and->Said second associated parameter between said monitoring parameters,/or->To monitor the number of parameters;
based on each running state index, obtaining the fault degree of each monitoring parameter, wherein the calculation process of the fault degree comprises the following steps:
in the method, in the process of the invention,to monitor the degree of failure of a parameter +.>For monitoring the priority corresponding to the parameter, the priority is obtained according to the analytic hierarchy process>To monitor the extent of fluctuation of the parameter.
8. A system for monitoring a textile manufacturing process for faults, comprising: a memory and a processor, characterized in that the processor executes a computer program stored in the memory to implement the method for monitoring faults in a textile production process according to any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311451578.4A CN117171670B (en) | 2023-11-03 | 2023-11-03 | Textile production process fault monitoring method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311451578.4A CN117171670B (en) | 2023-11-03 | 2023-11-03 | Textile production process fault monitoring method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117171670A CN117171670A (en) | 2023-12-05 |
| CN117171670B true CN117171670B (en) | 2024-02-13 |
Family
ID=88945402
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311451578.4A Active CN117171670B (en) | 2023-11-03 | 2023-11-03 | Textile production process fault monitoring method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117171670B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN115496644A (en) * | 2022-11-18 | 2022-12-20 | 山东超华环保智能装备有限公司 | Solid waste treatment equipment monitoring method based on data identification |
| CN116660669A (en) * | 2023-07-26 | 2023-08-29 | 威海双城电气有限公司 | Power equipment fault on-line monitoring system and method |
| CN116775408A (en) * | 2023-06-19 | 2023-09-19 | 上海启斯云计算有限公司 | Intelligent monitoring method for operation state of energy storage equipment |
| CN116805068A (en) * | 2023-05-24 | 2023-09-26 | 江苏卓特电气科技有限公司 | Fault monitoring and early warning system and method based on big data |
| CN116859843A (en) * | 2023-07-05 | 2023-10-10 | 安徽如柒信息科技有限公司 | Production equipment fault monitoring method and system based on industrial big data |
-
2023
- 2023-11-03 CN CN202311451578.4A patent/CN117171670B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN115496644A (en) * | 2022-11-18 | 2022-12-20 | 山东超华环保智能装备有限公司 | Solid waste treatment equipment monitoring method based on data identification |
| CN116805068A (en) * | 2023-05-24 | 2023-09-26 | 江苏卓特电气科技有限公司 | Fault monitoring and early warning system and method based on big data |
| CN116775408A (en) * | 2023-06-19 | 2023-09-19 | 上海启斯云计算有限公司 | Intelligent monitoring method for operation state of energy storage equipment |
| CN116859843A (en) * | 2023-07-05 | 2023-10-10 | 安徽如柒信息科技有限公司 | Production equipment fault monitoring method and system based on industrial big data |
| CN116660669A (en) * | 2023-07-26 | 2023-08-29 | 威海双城电气有限公司 | Power equipment fault on-line monitoring system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117171670A (en) | 2023-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113657221B (en) | Power plant equipment state monitoring method based on intelligent sensing technology | |
| CN115409131B (en) | Production line abnormity detection method based on SPC process control system | |
| CN112505549A (en) | New energy automobile battery abnormity detection method based on isolated forest algorithm | |
| CN114004306A (en) | Equipment fault evaluation system and method based on multi-dimensional data of Internet of things | |
| CN111046582A (en) | Nuclear power station diesel generating set coil temperature early warning method and system | |
| CN112288597A (en) | Energy consumption online anomaly detection method based on hierarchical clustering and histogram algorithm | |
| CN112417763B (en) | Defect diagnosis method, device and equipment for power transmission line and storage medium | |
| CN105930629A (en) | On-line fault diagnosis method based on massive amounts of operating data | |
| CN115576284A (en) | Clothing workshop intelligent management method and system | |
| CN117289778B (en) | Real-time monitoring method for health state of industrial control host power supply | |
| CN113810792B (en) | Edge data acquisition and analysis system based on cloud computing | |
| CN109214522B (en) | Equipment performance degradation evaluation method based on multiple attributes | |
| CN118376936B (en) | Intelligent diagnosis method and system for lithium battery state | |
| CN117309042A (en) | Intelligent manufacturing data real-time monitoring method and system based on Internet of things technology | |
| CN116339253A (en) | Intelligent mechanical production monitoring management and control system based on Internet of things | |
| CN117807155B (en) | Method, equipment and storage medium for generating multi-dimensional early warning prompt information | |
| CN112202630A (en) | Network quality abnormity detection method and device based on unsupervised model | |
| CN117113135A (en) | Carbon emission anomaly monitoring and analyzing system capable of sorting and classifying anomaly data | |
| CN114878172A (en) | Method and system for extracting temperature signal characteristics of marine main engine cylinder | |
| CN117171670B (en) | Textile production process fault monitoring method, device and system | |
| CN117786445A (en) | Intelligent processing method for operation data of automatic yarn reeling machine | |
| CN114789468A (en) | Automatic fault detection and repair system, method, equipment and terminal | |
| CN113868948A (en) | User-oriented dynamic threshold model training system and method | |
| CN111636123B (en) | Intelligent spinning production line fault detection system | |
| CN116841790A (en) | Off-line business monitoring method and system based on risk control |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 226100, Group 8, Dieshi Village, Sanxing Town, Haimen City, Nantong City, Jiangsu Province Patentee after: Nantong Haimen Dixiu Household Textile Co.,Ltd. Country or region after: China Address before: 226100, Group 8, Dieshi Village, Sanxing Town, Haimen City, Nantong City, Jiangsu Province Patentee before: Haimen Dixiu Home Textiles Co.,Ltd. Country or region before: China |