CN116449786A - Abnormality diagnosis method, device and equipment for production equipment and storage medium - Google Patents
Abnormality diagnosis method, device and equipment for production equipment and storage medium Download PDFInfo
- Publication number
- CN116449786A CN116449786A CN202310506477.6A CN202310506477A CN116449786A CN 116449786 A CN116449786 A CN 116449786A CN 202310506477 A CN202310506477 A CN 202310506477A CN 116449786 A CN116449786 A CN 116449786A
- Authority
- CN
- China
- Prior art keywords
- abnormal
- production
- data
- abnormality
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 374
- 230000005856 abnormality Effects 0.000 title claims abstract description 220
- 238000000034 method Methods 0.000 title claims abstract description 106
- 238000003745 diagnosis Methods 0.000 title claims abstract description 102
- 238000003860 storage Methods 0.000 title claims abstract description 11
- 230000002159 abnormal effect Effects 0.000 claims abstract description 265
- 238000004458 analytical method Methods 0.000 claims abstract description 91
- 230000008569 process Effects 0.000 claims abstract description 71
- 238000005259 measurement Methods 0.000 claims abstract description 37
- 238000012544 monitoring process Methods 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims description 30
- 238000012545 processing Methods 0.000 claims description 20
- 238000012790 confirmation Methods 0.000 claims description 19
- 238000005303 weighing Methods 0.000 claims description 19
- 230000001939 inductive effect Effects 0.000 claims description 17
- 238000005516 engineering process Methods 0.000 claims description 13
- 238000012163 sequencing technique Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract description 9
- 230000004580 weight loss Effects 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000005299 abrasion Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000010485 coping Effects 0.000 description 2
- 230000006698 induction Effects 0.000 description 2
- 230000003014 reinforcing effect Effects 0.000 description 2
- 238000012824 chemical production Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000763 evoking effect Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/4184—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by fault tolerance, reliability of production system
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/31—From computer integrated manufacturing till monitoring
- G05B2219/31088—Network communication between supervisor and cell, machine group
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses an abnormality diagnosis method, device, equipment and storage medium of production equipment, wherein the method comprises the following steps: and monitoring the running state data and the process data of each production device and the sensor data of each vibration sensor, determining the overall correlation of each production device with respect to the production line when the accuracy of the weightlessness measurement is abnormal, analyzing the running state data and the process data of each production device abnormally according to the analysis sequence of the overall correlation from high to low, determining the abnormal factor event of the production device, and generating a report. Therefore, when the weight loss metering accuracy is abnormal in the production line, the overall correlation degree of each production device can be evaluated, the overall correlation degree is a correlation measurement index of the abnormal evaluation of the production device on the whole production line, and on the basis, abnormal factor events which cause the abnormality of the production line are rapidly determined according to the analysis sequence of the correlation degree from high to low, so that the efficiency of the abnormality diagnosis of the production device is improved.
Description
Technical Field
The present application relates to the field of chemical production material metering technology, and more particularly, to an abnormality diagnosis method, apparatus, device and storage medium for production equipment.
Background
With the development of industrial technology, the operation state of the production line is strictly concerned in the industrial production field, and the ordered and normal production of the production line is ensured. When the production equipment state is abnormal in the production line, such as serious shaking, the abnormal state can be detected by the vibration sensor, abnormal factors can be analyzed by the diagnosis analysis model, and specific diagnosis results include bearing abrasion, gear abrasion, equipment assembly abnormality and the like, so that the abnormality can be timely detected and corresponding coping strategies can be adopted. When the production line is abnormal, such as abnormal precision of the weightlessness meter, a plurality of production devices are abnormal in one period, and engineers are needed to intervene in analyzing a data curve and an operation state in the working process of the production line so as to find out key factors causing the abnormality of the production line.
As can be seen from the above, regarding the situation that the production line is abnormal, no study is currently performed to analyze the correlation between a single production device and the whole production line, but the efficiency of the human intervention analysis is not high, which results in low efficiency of diagnosing the abnormality of the production device and delays the normal production operation of the production line.
How to analyze the correlation between a single production device and the whole production line, so that the abnormality diagnosis of the production device can be timely carried out when the production line is abnormal, and the method is a problem needing attention.
Disclosure of Invention
In view of the foregoing, the present application has been made in order to provide an abnormality diagnosis method, apparatus, device, and storage medium for a production facility, to improve the efficiency of abnormality diagnosis of the production facility.
In order to achieve the above object, the following specific solutions are proposed:
a method of abnormality diagnosis of a production facility, comprising:
monitoring respective equipment running state data of each production equipment, respective process data of each production equipment and sensor data of each vibration sensor in a production line, wherein each production equipment comprises a plurality of weightless meters, the process data of each weightless meter comprises flow data of the weightless meter, and each vibration sensor is connected with a plurality of production equipment in a deployment range;
determining the precision state of each weightlessness metering scale according to the flow data of the weightlessness metering scale;
when the accuracy of one or more weightless weighing scales is detected to be abnormal, determining that the vibration sensor with abnormal current sensor data is an abnormal vibration sensor;
Determining the integral relativity of the production line of each production device according to the relation between each production device and each abnormal vibration sensor connected with and deployed on the production device;
according to the analysis sequence of the whole relativity of the production line from high to low, carrying out abnormal analysis on the equipment running state data and the process technology data of each production equipment with the whole relativity of the production line, and determining an abnormal factor event of the production equipment;
an anomaly diagnostic analysis report is generated based on the anomaly event for each production facility.
Optionally, the determining the accuracy state of each weightless metering scale according to the flow data of the weightless metering scale includes:
when the flow data of each weightlessness measurement scale is larger than a preset abnormal value, determining the accuracy state of the weightlessness measurement scale as an accuracy abnormality;
and when the flow data of each weightlessness measurement scale is not greater than the preset abnormal value, determining the accuracy state of the weightlessness measurement scale as normal accuracy.
Optionally, determining the overall relevance of the production line of each production device according to the relation between the production device and each abnormal vibration sensor connected with and deploying the production device comprises:
determining a weight score between each production device and each abnormal vibration sensor according to the deployment distance of each abnormal vibration sensor which is connected and deployed to each production device;
And accumulating the weight scores between each production device and each abnormal vibration sensor to obtain the integral relevance of the production line of the production device.
Optionally, after the monitoring the respective equipment operation status data of each production equipment, the respective process technology data of each production equipment and the sensor data of each vibration sensor in the production line, the method further comprises:
sequencing and merging the running state data of each device, the process data of each process and the sensor data according to the time sequence to obtain a time sequence data sequence, so as to analyze the abnormal event of the production line within the range defined by the preset time period in the data sequence.
Optionally, the generating an abnormality diagnosis analysis report based on the abnormality factor event of each production device includes:
determining abnormality occurrence probability of abnormality factor events of each production device for inducing the abnormality of the precision data;
and sequencing the abnormal factor events according to the sequence of the abnormal probability of the abnormal factor events from high to low or from low to high, and generating an abnormal diagnosis analysis report based on the sequenced abnormal factor events.
Optionally, the determining the anomaly probability that the anomaly factor event of each production device induces the anomaly of the precision data includes:
inputting the abnormal factor event of each production device into a pre-established diagnosis analysis model, and outputting the abnormality probability of the abnormal factor event for inducing the abnormality of the precision data.
Optionally, the determining the anomaly probability that the anomaly factor event of each production device induces the anomaly of the precision data includes:
inputting an abnormal factor event of each production device into a pre-established diagnosis analysis model, and outputting an abnormal diagnosis probability that the abnormal factor event induces the abnormality of the precision data;
analyzing abnormal factor events of each production device through a pre-established artificial experience model, and determining an abnormal reason priority level of the abnormal factor event for inducing the abnormality of the precision data;
based on the abnormality diagnosis probability of the abnormality factor event of each production facility and the abnormality cause priority of the abnormality factor event, an abnormality occurrence probability of the abnormality factor event inducing abnormality of the accuracy data is calculated.
Optionally, after the ordering of the abnormality causing probabilities of the abnormality causing events according to the order from high to low or from low to high, the generating of the abnormality diagnosis analysis report based on the ordered abnormality causing events further includes:
And inputting the abnormality diagnosis analysis report into the artificial experience model, and outputting an abnormality processing strategy.
Optionally, after inputting the anomaly diagnosis analysis into the artificial experience model and outputting an anomaly processing strategy, the method further comprises:
and performing secondary confirmation on the output exception handling strategy, taking the output exception handling strategy after secondary confirmation as a training sample, and performing training adjustment on the artificial experience model to obtain a trained and adjusted artificial experience model.
Optionally, after analyzing the anomaly factor event of each production device through the pre-established artificial experience model and determining the anomaly cause priority level of the anomaly factor event for inducing the anomaly of the precision data, the method further comprises:
and carrying out secondary confirmation on the abnormality cause priority level of each abnormality factor event, taking the abnormality cause priority level of each abnormality factor event after secondary confirmation as a training sample, and carrying out training adjustment on the artificial experience model to obtain a trained and adjusted artificial experience model.
An abnormality diagnosis device of a production facility, comprising:
the system comprises a data acquisition unit, a control unit and a control unit, wherein the data acquisition unit is used for monitoring respective equipment running state data of each production equipment, respective process data of each production equipment and sensor data of each vibration sensor in a production line, each production equipment comprises a plurality of weightlessness weighing scales, the process data of each weightlessness weighing scale comprises flow data of the weightlessness weighing scale, and each vibration sensor is connected with a plurality of production equipment in a deployment range;
The precision state determining unit is used for determining the precision state of each weightlessness metering scale according to the flow data of the weightlessness metering scale;
the abnormal sensor determining unit is used for determining that the vibration sensor with abnormal current sensor data is an abnormal vibration sensor when the accuracy of one or more weightless weighing scales is monitored to be abnormal;
an overall correlation determination unit for determining the overall correlation of the production line of each production device according to the relationship between each production device and each abnormal vibration sensor connected with and deployed with the production device;
the abnormal factor determining unit is used for carrying out abnormal analysis on the equipment running state data and the process technology data of each production equipment with the whole relevance of the production line according to the analysis sequence from high to low of the whole relevance of the production line, and determining an abnormal factor event of the production equipment;
and a diagnosis output unit for generating an abnormality diagnosis analysis report based on the abnormality factor event of each production facility.
Optionally, the precision state determining unit includes:
the precision abnormality judging unit is used for determining the precision state of each weightlessness measurement scale as the precision abnormality when the flow data of the weightlessness measurement scale is larger than a preset abnormal value;
And the accuracy normal judgment unit is used for determining that the accuracy state of each weightlessness measurement scale is accuracy normal when the flow data of the weightlessness measurement scale is not greater than the preset abnormal value.
Optionally, the overall correlation determining unit includes:
a weight score determining unit for determining a weight score between each production equipment and each abnormal vibration sensor according to a deployment distance of each abnormal vibration sensor which is deployed for each production equipment connection;
and the production line overall correlation determining unit is used for accumulating the weight scores between each production device and each abnormal vibration sensor to obtain the production line overall correlation of the production device.
Optionally, the apparatus further comprises:
the data time sequence merging unit is used for sequencing and merging the running state data of each device, the process data of each process and the sensor data of each vibration sensor according to time sequence after monitoring the running state data of each production device, the process data of each production device and the sensor data of each vibration sensor in the production line to obtain a time sequence arranged data sequence so as to analyze within a range limited by a preset time period in the data sequence when an abnormal event occurs in the production line.
Optionally, the diagnostic output unit includes:
an abnormality occurrence probability determination unit configured to determine an abnormality occurrence probability at which an abnormality factor event of each production facility induces an abnormality of the precision data;
and the analysis report generation unit is used for sequencing the abnormal factor events according to the sequence of the abnormal probability of the abnormal factor events from high to low or from low to high, and generating an abnormal diagnosis analysis report based on the sequenced abnormal factor events.
Optionally, the anomaly probability determining unit includes:
the model diagnosis unit is used for inputting the abnormal factor event of each production device into a pre-established diagnosis analysis model and outputting the abnormality probability of the abnormal factor event for inducing the abnormality of the precision data.
Optionally, the anomaly probability determining unit includes:
an abnormality diagnosis probability determination unit for inputting an abnormality factor event of each production apparatus into a diagnosis analysis model established in advance, and outputting an abnormality diagnosis probability that the abnormality factor event induces abnormality of the precision data;
the priority determining unit is used for analyzing the abnormal factor event of each production device through a pre-established artificial experience model and determining the priority of the abnormal reason of the abnormal factor event for inducing the abnormal precision data;
An abnormality causing probability calculation unit configured to calculate an abnormality causing probability that the abnormality factor event induces abnormality of the precision data based on the abnormality diagnosis probability of the abnormality factor event for each production facility and the abnormality cause priority of the abnormality factor event.
Optionally, the apparatus further comprises:
and the processing strategy output unit is used for sequencing the abnormal factor events according to the sequence from high to low or from low to high of the abnormality causing probability of the abnormal factor events, generating an abnormal diagnosis analysis report based on the sequenced abnormal factor events, inputting the abnormal diagnosis analysis report into the artificial experience model and outputting an abnormal processing strategy.
Optionally, the apparatus further comprises:
and the first artificial experience model adjusting unit is used for carrying out secondary confirmation on the output abnormality processing strategy after inputting the abnormality diagnosis analysis into the artificial experience model and outputting the abnormality processing strategy, taking the output abnormality processing strategy after the secondary confirmation as a training sample, and carrying out training adjustment on the artificial experience model to obtain the trained and adjusted artificial experience model.
Optionally, the apparatus further comprises:
and the second artificial experience model adjusting unit is used for analyzing the abnormal factor event of each production device through the pre-established artificial experience model, determining the abnormal cause priority level of the abnormal factor event for inducing the abnormality of the precision data, secondarily confirming the abnormal cause priority level of each abnormal factor event, taking the abnormal cause priority level of each abnormal factor event after secondary confirmation as a training sample, and training and adjusting the artificial experience model to obtain the trained and adjusted artificial experience model.
An abnormality diagnosis apparatus of a production apparatus includes a memory and a processor;
the memory is used for storing programs;
the processor is configured to execute the program to implement the respective steps of the abnormality diagnosis method of the production apparatus as described above.
A storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the abnormality diagnosis method of a production facility as described above.
By means of the technical scheme, the method and the device for monitoring the abnormal state of the production equipment in the production line through monitoring the equipment operation state data of the production equipment, the process data of the production equipment and the sensor data of the vibration sensors, wherein the production equipment comprises a plurality of weightless measurement scales, the process data of each weightless measurement scale comprises flow data of the weightless measurement scales, the production equipment is arranged in the deployment range of each vibration sensor in a connecting mode, further, the precision state of the weightless measurement scale is determined according to the flow data of each weightless measurement scale, when the precision abnormality of one or more weightless measurement scales is monitored, the vibration sensor with abnormal current sensor data is determined to be the abnormal vibration sensor, the overall relevance of the production line of the production equipment is determined according to the relation between each production equipment and the abnormal vibration sensor connected with the production equipment, the equipment operation state data and the process data of each production equipment with the overall relevance of the production line are analyzed according to the analysis sequence from high to low, the abnormal production line overall relevance is analyzed, and the abnormal production event is generated based on the abnormal event analysis factors. Therefore, when the weight loss metering accuracy is abnormal in the production line, the overall relevance of the production line of each production device can be estimated, the overall relevance of the production line is a relevance measurement index of the abnormal evaluation of each production device on the whole production line, analysis is carried out according to the sequence from high to low of the relevance on the basis, and abnormal factor events causing the abnormality of the production line can be rapidly determined, so that the efficiency of abnormality diagnosis of the production device is improved.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 is a schematic flow chart of abnormality diagnosis of a production facility according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of an apparatus for abnormality diagnosis of a production facility according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an apparatus for abnormality diagnosis of a production apparatus according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The method and the system can be realized based on the terminal with data processing capability, the terminal can be a computer, a server, a cloud end and the like, and the terminal can be applied to an abnormality diagnosis system, so that the abnormality diagnosis system performs abnormality diagnosis on production equipment.
Next, as described in connection with fig. 1, the abnormality diagnosis method of the production apparatus of the present application may include the steps of:
step S110 monitors respective equipment operation status data of respective production equipment, respective process data of respective production equipment, and sensor data of respective vibration sensors in the production line.
Wherein, each production facility can include a plurality of weightlessness measure, a plurality of batch feeder, a plurality of storage tank, a plurality of blender. The equipment operational status data for each production equipment may include a switch status of the production equipment. The process data of each batch feeder can comprise the weight of the batch feeder, the process data of each storage tank can comprise the weight and the pressure of the storage tank, the process data of each mixer can comprise the rotating speed and the current of the mixer, and the process data of each weightless metering scale can comprise the weight, the flow data and the set flow of the weightless metering scale. Each vibration sensor is connected and deployed with a plurality of production devices in the deployment range, and the deployment distance of each production device connected and deployed by each vibration sensor in the deployment range can be different.
And step S120, determining the precision state of each weightlessness measurement scale according to the flow data of the weightlessness measurement scale.
Specifically, the precision state of the weightless metering scale can include normal precision and abnormal precision, the weightless metering scale with normal precision can work normally on a production line, and the abnormal precision of the weightless metering scale can indicate that the production line is abnormal, and the reasons of the abnormality need to be checked.
And step S130, when the accuracy of one or more weightless meters is detected to be abnormal, determining that the vibration sensor with abnormal current sensor data is an abnormal vibration sensor.
It can be understood that the vibration sensor can be aligned to each production device in the deployment range to implement abnormality monitoring, when a certain production device is abnormal, the production device can shake, so that a plurality of vibration sensors for deploying the production device acquire signals of abnormal shake of the device, sensor data of the vibration sensor are abnormal, based on the fact that when one or more weightless weighing scales are detected to be abnormal, the vibration sensor with abnormal sensor data in the production line can be indicated, and accordingly the vibration sensor with abnormal current sensor data can be determined to be the abnormal vibration sensor.
And step 140, determining the integral relevance of the production line of each production device according to the relation between each production device and each abnormal vibration sensor connected with and deployed with the production device.
Specifically, the overall relevance of the production line of each production device may represent the weight ratio of the production device to the main factor causing the abnormality when the abnormality occurs in the production line.
And S150, carrying out anomaly analysis on equipment operation state data and process technology data of each production equipment with the whole relevance of the production line according to the analysis sequence from high to low of the whole relevance of the production line, and determining an anomaly factor event of the production equipment.
It can be understood that according to the analysis sequence of the whole relativity of the production line from high to low, the production equipment with the highest weight proportion causing the abnormality of the production line can be preferentially analyzed, so that the abnormality factor event of the production equipment can be obtained more quickly.
Specifically, a correlation threshold can be set, production equipment with the overall correlation of the production line higher than the correlation threshold is screened, then the abnormal analysis is performed on the equipment running state data and the process technology data of each production equipment obtained by screening according to the analysis sequence of the overall correlation of the production line from high to low, and the abnormal factor event of the production equipment is determined, so that the abnormal analysis efficiency is improved.
Step S160, generating an abnormality diagnosis analysis report based on the abnormality factor event of each production device.
Specifically, the abnormality diagnostic analysis reports may be ordered and listed according to the time of acquisition of the abnormality event.
According to the abnormality diagnosis method for the production equipment, through monitoring the respective equipment operation state data of the production equipment, the respective process data of the production equipment and the sensor data of the vibration sensors in the production line, the production equipment comprises a plurality of weightless measurement scales, the process data of each weightless measurement scale comprises flow data, the production equipment is arranged in a deployment range of each vibration sensor in a connected mode, further, the accuracy state of each weightless measurement scale is determined according to the flow data of each weightless measurement scale, when the accuracy abnormality of one or more weightless measurement scales is monitored, the vibration sensor with the abnormal current sensor data is determined to be the abnormal vibration sensor, the overall relevance of the production line of the production equipment is determined according to the relation between each production equipment and the abnormal vibration sensor connected with the production equipment, the equipment operation state data and the process data of each production equipment with the overall relevance of the production line are analyzed according to the analysis sequence from high to low, the abnormal event is determined, and the abnormal event is generated based on the abnormal event analysis factors. Therefore, when the weight loss metering accuracy is abnormal in the production line, the overall relevance of the production line of each production device can be estimated, the overall relevance of the production line is a relevance measurement index of the abnormal evaluation of each production device on the whole production line, analysis is carried out according to the sequence from high to low of the relevance on the basis, and abnormal factor events causing the abnormality of the production line can be rapidly determined, so that the efficiency of abnormality diagnosis of the production device is improved.
In some embodiments of the present application, the process of determining the accuracy state of each weightless scale according to the flow data of each weightless scale in step S120 is described, where the process may include the following two cases:
firstly, when the flow data of each weightlessness measurement scale is larger than a preset abnormal value, determining the accuracy state of the weightlessness measurement scale as abnormal accuracy.
Specifically, the preset outlier may represent a critical value for the accuracy anomaly determination. The preset abnormal value can be customized, can be set flow, can be a percentage of the set flow, and can be a percentage deviation value of the set flow.
And secondly, when the flow data of each weightlessness measurement scale is not larger than a preset abnormal value, determining the accuracy state of the weightlessness measurement scale as normal accuracy.
According to the abnormality diagnosis method for the production equipment, through comparing the flow data of the weightlessness weighing scale with the preset abnormal value, the accuracy abnormality of the weightlessness weighing scale is determined when the flow data exceeds the preset abnormal value, and the accuracy of the weightlessness weighing scale is determined to be normal when the flow data does not exceed the preset abnormal value, so that whether the production line is abnormal or not is accurately monitored.
In some embodiments of the present application, the process of determining the overall relevance of the production line of each production device according to the relationship between each production device and each abnormal vibration sensor connected to and deployed to the production device in step S140 is described, where the process may include:
s1, determining a weight fraction between each production device and each abnormal vibration sensor according to the deployment distance of each abnormal vibration sensor which is connected and deployed to each production device.
Specifically, the weight score between each production device and each abnormal vibration sensor may be determined according to a pre-established correspondence table of deployment distances and weight scores.
Wherein, when the deployment distance of each abnormal vibration sensor that each production equipment is connected and deployed is shorter, the weight score between the production equipment and the abnormal vibration sensor can be larger, and vice versa.
For example, if the deployment distance of the production apparatus a connected to the deployment of the abnormal vibration sensor a is 1m and the deployment distance of the production apparatus b connected to the deployment is 2m, the weight score between the production apparatus a and the abnormal vibration sensor a can be determined to be 1, and the weight score between the production apparatus b and the abnormal vibration sensor a can be determined to be 0.5.
S2, accumulating the weight scores between each production device and each abnormal vibration sensor to obtain the integral relevance of the production line of the production device.
It is understood that there may be a single production facility in the production line that is connected and deployed by multiple vibration sensors, and therefore, when one or more vibration sensors are abnormal vibration sensors in the multiple vibration sensors connected and deployed to a certain production facility, the weight score between each production facility and each abnormal vibration sensor may be accumulated to obtain the overall relevance of the production line of the production facility.
For example, the production equipment a is connected and deployed by the abnormal vibration sensor a and the abnormal vibration sensor B, the weight score between the production equipment a and the abnormal vibration sensor a is 1, and the weight score between the production equipment a and the abnormal vibration sensor B is 0.3, so that the overall relevance of the production line of the production equipment a is 1+0.3=1.3.
According to the abnormality diagnosis method for the production equipment, the weight score between each production equipment and each abnormal vibration sensor is determined according to the deployment distance of each abnormal vibration sensor which is connected and deployed to each production equipment, and the weight scores between each production equipment and each abnormal vibration sensor are accumulated to obtain the integral relevance of the production line of the production equipment, so that the production equipment which needs to be subjected to main analysis can be more accurately distinguished.
In view of more orderly arrangement of acquired data information to facilitate line anomaly analysis, in some embodiments of the present application, after monitoring respective equipment operational status data of respective production equipment, respective process data of respective production equipment, and sensor data of respective vibration sensors in a production line as mentioned in the above embodiments, a process of arranging the data information may be included, which may include:
sequencing and merging the running state data of each device, the process data of each process and the sensor data according to the time sequence to obtain a time sequence data sequence, so as to analyze the abnormal event of the production line within the range defined by the preset time period in the data sequence.
It will be appreciated that the acquired data includes the respective equipment operating status data of each production equipment, the respective process data of each production equipment and the sensor data of each vibration sensor, which are all provided with time information, and the occurrence of the abnormal event of the production line is concentrated within a time period, so that the data are time-series arranged and combined, so that when the abnormal event of the production line occurs, the analysis can be performed within a range defined by a preset time period in the data sequence.
In some embodiments of the present application, a process of generating an abnormality diagnosis analysis report based on the abnormality factor event of each production apparatus in step S160 is described, and the process may include:
s1, determining abnormality occurrence probability of abnormality of the abnormality factor event induced precision data of each production device.
Specifically, the process of determining the anomaly occurrence probability of anomalies in the anomaly factor event induced precision data for each production facility may include the following two cases:
1) And inputting the abnormal factor event of each production device into a pre-established diagnosis analysis model, and outputting the abnormality occurrence probability of the abnormal precision data induced by the abnormal factor event.
Specifically, the diagnostic analysis model can evaluate the possibility that various abnormal factor events induce the abnormality of the weightless weighing precision data, so that the abnormal factor events of each production device can be input into the pre-established diagnostic analysis model, and the diagnostic analysis model outputs the abnormality occurrence probability of the abnormal weight weighing precision data.
2) S11, inputting the abnormal factor event of each production device into a pre-established diagnosis analysis model, and outputting the abnormal diagnosis probability of the abnormal factor event inducing the abnormality of the precision data.
It can be understood that the diagnosis analysis model can evaluate the possibility that various abnormal factor events induce the abnormality of the weight loss meter accuracy data, and the result output by the diagnosis analysis model can be used as a reference part for evaluating the abnormality occurrence probability of the abnormality of the accuracy data, so that the abnormal factor event of each production device can be input into the pre-established diagnosis analysis model, and the abnormality diagnosis probability of the abnormality of the accuracy data caused by the abnormal factor event can be output.
S12, analyzing the abnormal factor event of each production device through a pre-established artificial experience model, and determining the priority level of the abnormal reason of the abnormal factor event inducing the abnormality of the precision data.
Specifically, the artificial experience model is an experience obtained by counting the induction factors of the production equipment aiming at various abnormal events of the production line by an expert, and the experience is used as training data to train, so that the result output by the artificial experience model can be used as a reference part for evaluating the abnormal probability of the abnormal induction precision data.
S13, calculating abnormality occurrence probability of abnormality of the abnormality factor event induced precision data based on the abnormality diagnosis probability of the abnormality factor event of each production device and the abnormality cause priority of the abnormality factor event.
Specifically, considering that the evaluation weights of the reference parts for evaluating the abnormality occurrence probability of the abnormality of the induced precision data may be different, a first weight ratio may be assigned to the abnormality diagnosis probability, a second weight ratio may be assigned to the abnormality cause priority, then the abnormality diagnosis probability of the abnormality factor event of each production facility may be multiplied by the first weight ratio to obtain a first evaluation score, the abnormality cause priority of each abnormality factor event may be multiplied by the second weight ratio to obtain a second evaluation score, and finally the first evaluation score may be added to the second evaluation score to obtain a value as the abnormality occurrence probability of the abnormality of the induced precision data of the abnormality factor event.
S2, sequencing the abnormal factor events according to the sequence of the abnormal probability of the abnormal factor events from high to low or from low to high, and generating an abnormal diagnosis analysis report based on the sequenced abnormal factor events.
Specifically, the abnormality diagnosis analysis report may include abnormality factor events, which may be ordered in the order of high to low abnormality probability or low to high abnormality probability, so that a worker may quickly learn the abnormality factor event with the highest abnormality probability from the abnormality diagnosis analysis report.
Considering that the artificial experience model mentioned in the above embodiment is an experience that an expert statistically judges the evoked factors of the production equipment for various abnormal events of the production line, and uses this experience as training data to train, the artificial experience model can also use an abnormality processing strategy that is obtained by analyzing an abnormality diagnosis analysis report as training data experience for the expert during training, so that the artificial experience model has a function of analyzing the abnormality diagnosis analysis report and outputting a corresponding abnormality processing strategy, and in some embodiments of the present application, after sorting the abnormal event according to the order of the abnormality occurrence probability of each abnormal event from high to low or from low to high, and generating the abnormality diagnosis analysis report based on each ordered abnormal event, the process may include a process of generating the abnormality coping strategy, which may include:
and inputting the abnormality diagnosis analysis report into the artificial experience model, and outputting an abnormality processing strategy.
Specifically, the exception handling policy may represent handling manners required to cope with and take for each exception factor event reported by the exception diagnosis analysis and corresponding exception probability.
Given that the artificial experience model mentioned in the above embodiments has limited training data during the building, the capability of the process policy analysis of the artificial experience model needs to be improved, based on which, in some embodiments of the present application, after the anomaly diagnosis analysis mentioned in the above embodiments includes inputting the anomaly diagnosis analysis into the artificial experience model and outputting the anomaly processing policy, a process of reinforcing the model may be included, which may include:
and performing secondary confirmation on the output exception handling strategy, taking the output exception handling strategy after the secondary confirmation as a training sample, and performing training adjustment on the artificial experience model to obtain a trained and adjusted artificial experience model.
Specifically, the process of performing secondary confirmation on the output exception handling policy may be to manually verify the output exception handling policy, for example, apply the output exception handling policy to a production line, determine whether an exception of the production line is eliminated/resolved, if the exception of the production line can be eliminated/resolved based on the output exception handling policy, indicate that the output exception handling policy is secondarily confirmed, or manually formulate an exception handling policy, and use the manually formulated exception handling policy as a training sample of a manual experience model to implement reinforcement training on the manual experience model.
In view of the limited training data during the building of the artificial experience model mentioned in the above embodiments, the evaluation capability of the analysis of the abnormality cause priority of the artificial experience model is to be improved, based on this, in some embodiments of the present application, after analyzing the abnormality factor event of each production facility by the artificial experience model established in advance, to determine the abnormality cause priority of the abnormality factor event induced accuracy data mentioned in the above embodiments, a process of reinforcing the model may include:
and carrying out secondary confirmation on the abnormal cause priority level of each abnormal factor event, taking the abnormal cause priority level of each abnormal factor event after secondary confirmation as a training sample, and carrying out training adjustment on the artificial experience model to obtain the trained and adjusted artificial experience model.
Specifically, the process of secondarily confirming the priority of the abnormal cause of each abnormal factor event may be that the priority of the abnormal cause of the abnormal factor event is manually evaluated, for example, the priority of the abnormal cause is manually classified for the abnormal factor event, whether the priority of the abnormal cause of each abnormal factor event is consistent with the manually classified priority of the abnormal cause is judged, if so, the output abnormal processing strategy is secondarily confirmed, otherwise, the manually classified priority of the abnormal cause is used as a training sample of the artificial experience model, and the reinforced training is implemented on the artificial experience model.
The device for implementing the abnormality diagnosis of the production equipment provided in the embodiment of the present application is described below, and the device for implementing the abnormality diagnosis of the production equipment described below and the method for implementing the abnormality diagnosis of the production equipment described above may be referred to correspondingly to each other.
Referring to fig. 2, fig. 2 is a schematic structural diagram of an apparatus for implementing abnormality diagnosis of a production facility according to an embodiment of the present application.
As shown in fig. 2, the apparatus may include:
the data acquisition unit 11 is configured to monitor respective equipment operation state data of each production equipment in the production line, respective process technology data of each production equipment, and sensor data of each vibration sensor, where each production equipment includes a plurality of weightless meters, the process technology data of each weightless meter includes flow data of the weightless meter, and each vibration sensor is connected with and deployed with a plurality of production equipment in a deployment range thereof;
a precision state determining unit 12, configured to determine a precision state of each weightless scale according to flow data of the weightless scale;
an abnormal sensor determining unit 13 for determining that the vibration sensor whose current sensor data is abnormal is an abnormal vibration sensor when an abnormality in accuracy of one or more weightless weighing scales is detected;
An overall correlation determination unit 14 for determining the overall correlation of the production line of each production apparatus based on the relationship between each production apparatus and the respective abnormal vibration sensor connected to the production apparatus in which the production apparatus is disposed;
an anomaly factor determining unit 15, configured to perform anomaly analysis on equipment operation state data and process data of each production equipment with the overall relevance of the production line according to an analysis order from high to low of the overall relevance of the production line, and determine an anomaly factor event of the production equipment;
and a diagnosis output unit 16 for generating an abnormality diagnosis analysis report based on the abnormality factor event of each production facility.
Optionally, the precision state determining unit includes:
the precision abnormality judging unit is used for determining the precision state of each weightlessness measurement scale as the precision abnormality when the flow data of the weightlessness measurement scale is larger than a preset abnormal value;
and the accuracy normal judgment unit is used for determining that the accuracy state of each weightlessness measurement scale is accuracy normal when the flow data of the weightlessness measurement scale is not greater than the preset abnormal value.
Optionally, the overall correlation determining unit includes:
a weight score determining unit for determining a weight score between each production equipment and each abnormal vibration sensor according to a deployment distance of each abnormal vibration sensor which is deployed for each production equipment connection;
And the production line overall correlation determining unit is used for accumulating the weight scores between each production device and each abnormal vibration sensor to obtain the production line overall correlation of the production device.
Optionally, the apparatus further comprises:
the data time sequence merging unit is used for sequencing and merging the running state data of each device, the process data of each process and the sensor data of each vibration sensor according to time sequence after monitoring the running state data of each production device, the process data of each production device and the sensor data of each vibration sensor in the production line to obtain a time sequence arranged data sequence so as to analyze within a range limited by a preset time period in the data sequence when an abnormal event occurs in the production line.
Optionally, the diagnostic output unit includes:
an abnormality occurrence probability determination unit configured to determine an abnormality occurrence probability at which an abnormality factor event of each production facility induces an abnormality of the precision data;
and the analysis report generation unit is used for sequencing the abnormal factor events according to the sequence of the abnormal probability of the abnormal factor events from high to low or from low to high, and generating an abnormal diagnosis analysis report based on the sequenced abnormal factor events.
Optionally, the anomaly probability determining unit includes:
the model diagnosis unit is used for inputting the abnormal factor event of each production device into a pre-established diagnosis analysis model and outputting the abnormality probability of the abnormal factor event for inducing the abnormality of the precision data.
Optionally, the anomaly probability determining unit includes:
an abnormality diagnosis probability determination unit for inputting an abnormality factor event of each production apparatus into a diagnosis analysis model established in advance, and outputting an abnormality diagnosis probability that the abnormality factor event induces abnormality of the precision data;
the priority determining unit is used for analyzing the abnormal factor event of each production device through a pre-established artificial experience model and determining the priority of the abnormal reason of the abnormal factor event for inducing the abnormal precision data;
an abnormality causing probability calculation unit configured to calculate an abnormality causing probability that the abnormality factor event induces abnormality of the precision data based on the abnormality diagnosis probability of the abnormality factor event for each production facility and the abnormality cause priority of the abnormality factor event.
Optionally, the apparatus further comprises:
and the processing strategy output unit is used for sequencing the abnormal factor events according to the sequence from high to low or from low to high of the abnormality causing probability of the abnormal factor events, generating an abnormal diagnosis analysis report based on the sequenced abnormal factor events, inputting the abnormal diagnosis analysis report into the artificial experience model and outputting an abnormal processing strategy.
Optionally, the apparatus further comprises:
and the first artificial experience model adjusting unit is used for carrying out secondary confirmation on the output abnormality processing strategy after inputting the abnormality diagnosis analysis into the artificial experience model and outputting the abnormality processing strategy, taking the output abnormality processing strategy after the secondary confirmation as a training sample, and carrying out training adjustment on the artificial experience model to obtain the trained and adjusted artificial experience model.
Optionally, the apparatus further comprises:
and the second artificial experience model adjusting unit is used for analyzing the abnormal factor event of each production device through the pre-established artificial experience model, determining the abnormal cause priority level of the abnormal factor event for inducing the abnormality of the precision data, secondarily confirming the abnormal cause priority level of each abnormal factor event, taking the abnormal cause priority level of each abnormal factor event after secondary confirmation as a training sample, and training and adjusting the artificial experience model to obtain the trained and adjusted artificial experience model.
The device for abnormality diagnosis of the production equipment provided by the embodiment of the application can be applied to equipment for abnormality diagnosis of the production equipment, such as a terminal: cell phones, computers, etc. Alternatively, fig. 3 shows a hardware configuration block diagram of an apparatus for abnormality diagnosis of a production apparatus, and referring to fig. 3, the hardware configuration of the apparatus for abnormality diagnosis of a production apparatus may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;
In the embodiment of the application, the number of the processor 1, the communication interface 2, the memory 3 and the communication bus 4 is at least one, and the processor 1, the communication interface 2 and the memory 3 complete communication with each other through the communication bus 4;
processor 1 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention, etc.;
the memory 3 may comprise a high-speed RAM memory, and may further comprise a non-volatile memory (non-volatile memory) or the like, such as at least one magnetic disk memory;
wherein the memory stores a program, the processor is operable to invoke the program stored in the memory, the program operable to:
monitoring respective equipment running state data of each production equipment, respective process data of each production equipment and sensor data of each vibration sensor in a production line, wherein each production equipment comprises a plurality of weightless meters, the process data of each weightless meter comprises flow data of the weightless meter, and each vibration sensor is connected with a plurality of production equipment in a deployment range;
Determining the precision state of each weightlessness metering scale according to the flow data of the weightlessness metering scale;
when the accuracy of one or more weightless weighing scales is detected to be abnormal, determining that the vibration sensor with abnormal current sensor data is an abnormal vibration sensor;
determining the integral relativity of the production line of each production device according to the relation between each production device and each abnormal vibration sensor connected with and deployed on the production device;
according to the analysis sequence of the whole relativity of the production line from high to low, carrying out abnormal analysis on the equipment running state data and the process technology data of each production equipment with the whole relativity of the production line, and determining an abnormal factor event of the production equipment;
an anomaly diagnostic analysis report is generated based on the anomaly event for each production facility.
Alternatively, the refinement function and the extension function of the program may be described with reference to the above.
The embodiment of the application also provides a storage medium, which may store a program adapted to be executed by a processor, the program being configured to:
monitoring respective equipment running state data of each production equipment, respective process data of each production equipment and sensor data of each vibration sensor in a production line, wherein each production equipment comprises a plurality of weightless meters, the process data of each weightless meter comprises flow data of the weightless meter, and each vibration sensor is connected with a plurality of production equipment in a deployment range;
Determining the precision state of each weightlessness metering scale according to the flow data of the weightlessness metering scale;
when the accuracy of one or more weightless weighing scales is detected to be abnormal, determining that the vibration sensor with abnormal current sensor data is an abnormal vibration sensor;
determining the integral relativity of the production line of each production device according to the relation between each production device and each abnormal vibration sensor connected with and deployed on the production device;
according to the analysis sequence of the whole relativity of the production line from high to low, carrying out abnormal analysis on the equipment running state data and the process technology data of each production equipment with the whole relativity of the production line, and determining an abnormal factor event of the production equipment;
an anomaly diagnostic analysis report is generated based on the anomaly event for each production facility.
Alternatively, the refinement function and the extension function of the program may be described with reference to the above.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the present specification, each embodiment is described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and may be combined according to needs, and the same similar parts may be referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (13)
1. A method for diagnosing abnormality of production facility, comprising:
monitoring respective equipment running state data of each production equipment, respective process data of each production equipment and sensor data of each vibration sensor in a production line, wherein each production equipment comprises a plurality of weightless meters, the process data of each weightless meter comprises flow data of the weightless meter, and each vibration sensor is connected with a plurality of production equipment in a deployment range;
Determining the precision state of each weightlessness metering scale according to the flow data of the weightlessness metering scale;
when the accuracy of one or more weightless weighing scales is detected to be abnormal, determining that the vibration sensor with abnormal current sensor data is an abnormal vibration sensor;
determining the integral relativity of the production line of each production device according to the relation between each production device and each abnormal vibration sensor connected with and deployed on the production device;
according to the analysis sequence of the whole relativity of the production line from high to low, carrying out abnormal analysis on the equipment running state data and the process technology data of each production equipment with the whole relativity of the production line, and determining an abnormal factor event of the production equipment;
an anomaly diagnostic analysis report is generated based on the anomaly event for each production facility.
2. The method of claim 1, wherein determining the accuracy status of each weightless scale based on the flow data of the weightless scale comprises:
when the flow data of each weightlessness measurement scale is larger than a preset abnormal value, determining the accuracy state of the weightlessness measurement scale as an accuracy abnormality;
and when the flow data of each weightlessness measurement scale is not greater than the preset abnormal value, determining the accuracy state of the weightlessness measurement scale as normal accuracy.
3. The method of claim 1, wherein determining the overall line relevance of each production facility based on the relationship of each production facility to the respective abnormal vibration sensor connected to deploy the production facility comprises:
determining a weight score between each production device and each abnormal vibration sensor according to the deployment distance of each abnormal vibration sensor which is connected and deployed to each production device;
and accumulating the weight scores between each production device and each abnormal vibration sensor to obtain the integral relevance of the production line of the production device.
4. The method of claim 1, further comprising, after monitoring the respective equipment operational status data of each production equipment, the respective process data of each production equipment, and the sensor data of each vibration sensor in the production line:
sequencing and merging the running state data of each device, the process data of each process and the sensor data according to the time sequence to obtain a time sequence data sequence, so as to analyze the abnormal event of the production line within the range defined by the preset time period in the data sequence.
5. The method of any one of claims 1-4, wherein generating an anomaly diagnostic analysis report based on anomaly event for each production device comprises:
determining abnormality occurrence probability of abnormality factor events of each production device for inducing the abnormality of the precision data;
and sequencing the abnormal factor events according to the sequence of the abnormal probability of the abnormal factor events from high to low or from low to high, and generating an abnormal diagnosis analysis report based on the sequenced abnormal factor events.
6. The method of claim 5, wherein said determining anomaly probability that an anomaly factor event for each production facility induces an anomaly in the accuracy data comprises:
inputting the abnormal factor event of each production device into a pre-established diagnosis analysis model, and outputting the abnormality probability of the abnormal factor event for inducing the abnormality of the precision data.
7. The method of claim 5, wherein said determining anomaly probability that an anomaly factor event for each production facility induces an anomaly in the accuracy data comprises:
inputting an abnormal factor event of each production device into a pre-established diagnosis analysis model, and outputting an abnormal diagnosis probability that the abnormal factor event induces the abnormality of the precision data;
Analyzing abnormal factor events of each production device through a pre-established artificial experience model, and determining an abnormal reason priority level of the abnormal factor event for inducing the abnormality of the precision data;
based on the abnormality diagnosis probability of the abnormality factor event of each production facility and the abnormality cause priority of the abnormality factor event, an abnormality occurrence probability of the abnormality factor event inducing abnormality of the accuracy data is calculated.
8. The method of claim 7, further comprising, after said ordering of each anomaly event in order of high to low or low to high anomaly probability for each anomaly event and generating an anomaly diagnostic analysis report based on each anomaly event ordered:
and inputting the abnormality diagnosis analysis report into the artificial experience model, and outputting an abnormality processing strategy.
9. The method of claim 8, further comprising, after inputting the anomaly diagnostic analysis to the artificial experience model and outputting an anomaly handling policy:
and performing secondary confirmation on the output exception handling strategy, taking the output exception handling strategy after secondary confirmation as a training sample, and performing training adjustment on the artificial experience model to obtain a trained and adjusted artificial experience model.
10. The method of claim 7, further comprising, after analyzing the anomaly factor event of each production facility by the pre-established human experience model and determining an anomaly cause priority for the anomaly factor event to induce the anomaly in the accuracy data:
and carrying out secondary confirmation on the abnormality cause priority level of each abnormality factor event, taking the abnormality cause priority level of each abnormality factor event after secondary confirmation as a training sample, and carrying out training adjustment on the artificial experience model to obtain a trained and adjusted artificial experience model.
11. An abnormality diagnosis device for a production facility, comprising:
the system comprises a data acquisition unit, a control unit and a control unit, wherein the data acquisition unit is used for monitoring respective equipment running state data of each production equipment, respective process data of each production equipment and sensor data of each vibration sensor in a production line, each production equipment comprises a plurality of weightlessness weighing scales, the process data of each weightlessness weighing scale comprises flow data of the weightlessness weighing scale, and each vibration sensor is connected with a plurality of production equipment in a deployment range;
The precision state determining unit is used for determining the precision state of each weightlessness metering scale according to the flow data of the weightlessness metering scale;
the abnormal sensor determining unit is used for determining that the vibration sensor with abnormal current sensor data is an abnormal vibration sensor when the accuracy of one or more weightless weighing scales is monitored to be abnormal;
an overall correlation determination unit for determining the overall correlation of the production line of each production device according to the relationship between each production device and each abnormal vibration sensor connected with and deployed with the production device;
the abnormal factor determining unit is used for carrying out abnormal analysis on the equipment running state data and the process technology data of each production equipment with the whole relevance of the production line according to the analysis sequence from high to low of the whole relevance of the production line, and determining an abnormal factor event of the production equipment;
and a diagnosis output unit for generating an abnormality diagnosis analysis report based on the abnormality factor event of each production facility.
12. An abnormality diagnosis apparatus of a production apparatus, characterized by comprising a memory and a processor;
the memory is used for storing programs;
the processor for executing the program to realize the respective steps of the abnormality diagnosis method of the production apparatus according to any one of claims 1 to 10.
13. A storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, realizes the respective steps of the abnormality diagnosis method of the production apparatus according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310506477.6A CN116449786A (en) | 2023-05-06 | 2023-05-06 | Abnormality diagnosis method, device and equipment for production equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310506477.6A CN116449786A (en) | 2023-05-06 | 2023-05-06 | Abnormality diagnosis method, device and equipment for production equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116449786A true CN116449786A (en) | 2023-07-18 |
Family
ID=87132128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310506477.6A Pending CN116449786A (en) | 2023-05-06 | 2023-05-06 | Abnormality diagnosis method, device and equipment for production equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116449786A (en) |
-
2023
- 2023-05-06 CN CN202310506477.6A patent/CN116449786A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9465387B2 (en) | Anomaly diagnosis system and anomaly diagnosis method | |
| US9122273B2 (en) | Failure cause diagnosis system and method | |
| JP6879873B2 (en) | Failure probability evaluation system | |
| US20020152056A1 (en) | Monitoring and fault detection system and method using improved empirical model for range extrema | |
| KR102355777B1 (en) | Process anomalous state diagnostic device and process anomalous state diagnosis method | |
| EP3940352A1 (en) | Weighing scale diagnostics method | |
| CN109839915A (en) | Diagnostic device, diagnostic method and storage medium | |
| CN103154693A (en) | System for monitoring an engine test bed | |
| JP6711323B2 (en) | Abnormal state diagnosis method and abnormal state diagnosis device | |
| JP5621967B2 (en) | Abnormal data analysis system | |
| EP2743667B1 (en) | Load cell residual fatigue life estimation system and method | |
| CN101832872A (en) | Progressive method for identifying damaged cables and support displacement based on spatial coordinate monitoring | |
| JPH08234832A (en) | Device and method for monitoring and diagnostic plant | |
| KR20180040452A (en) | Method for detecting anomaly using equipment age index and apparatus thereof | |
| TWI756628B (en) | Operation evaluation device, operation evaluation method, and program | |
| Catelani et al. | Toward a new definition of FMECA approach | |
| CN114239734A (en) | Distributed vehicle-mounted health management system | |
| CN110414086B (en) | Sensitivity-based comprehensive stress acceleration factor calculation method | |
| CN101819098B (en) | Mixed monitoring based progressive method for identifying damaged cables and support displacement | |
| JP6702297B2 (en) | Abnormal state diagnosis method and abnormal state diagnosis device | |
| US20060069521A1 (en) | Methods and systems for analyzing structural test data | |
| Tsai et al. | A study of function-based diagnosis strategy and testability analysis for a system | |
| CN116449786A (en) | Abnormality diagnosis method, device and equipment for production equipment and storage medium | |
| JP5048822B2 (en) | Abnormality detection method for weighing device and weighing device | |
| JP2005147920A (en) | Metering apparatus and method for detecting abnormality of the same |
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 |