CN116975639A - Abnormality prevention and control system and method for equipment - Google Patents
Abnormality prevention and control system and method for equipment Download PDFInfo
- Publication number
- CN116975639A CN116975639A CN202310940914.5A CN202310940914A CN116975639A CN 116975639 A CN116975639 A CN 116975639A CN 202310940914 A CN202310940914 A CN 202310940914A CN 116975639 A CN116975639 A CN 116975639A
- Authority
- CN
- China
- Prior art keywords
- production
- equipment
- information
- data
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000005856 abnormality Effects 0.000 title claims abstract description 36
- 230000002265 prevention Effects 0.000 title claims abstract description 23
- 238000004519 manufacturing process Methods 0.000 claims abstract description 322
- 238000012545 processing Methods 0.000 claims abstract description 140
- 238000004458 analytical method Methods 0.000 claims abstract description 92
- 238000012549 training Methods 0.000 claims abstract description 53
- 230000002159 abnormal effect Effects 0.000 claims abstract description 33
- 238000013499 data model Methods 0.000 claims abstract description 17
- 238000011156 evaluation Methods 0.000 claims description 32
- 230000005540 biological transmission Effects 0.000 claims description 17
- 238000012360 testing method Methods 0.000 claims description 16
- 238000012795 verification Methods 0.000 claims description 16
- 238000005516 engineering process Methods 0.000 claims description 15
- 230000007246 mechanism Effects 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 7
- 230000003203 everyday effect Effects 0.000 claims description 3
- 238000010924 continuous production Methods 0.000 abstract description 5
- 238000003860 storage Methods 0.000 description 8
- 238000004088 simulation Methods 0.000 description 7
- 238000011282 treatment Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000001960 triggered effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000013178 mathematical model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 238000010223 real-time analysis Methods 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011418 maintenance treatment Methods 0.000 description 1
- 239000011265 semifinished product Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- General Factory Administration (AREA)
Abstract
The embodiment of the invention discloses an abnormality prevention and control method and system of equipment, comprising the following steps: acquiring historical data of equipment; constructing a production anomaly analysis model, and training the production anomaly analysis model based on equipment history data to obtain a trained production anomaly analysis model; acquiring actual production data of equipment, and inputting the actual production data and the historical data of the equipment into a production anomaly analysis model to generate fault prediction information of the current equipment; inputting the fault prediction information and the actual production demand information into a production manufacturing data model to obtain a scheduling scheme; inputting the fault prediction information into a fault processing model to obtain fault processing information; and judging the abnormal point of the equipment based on the fault processing model, generating a corresponding processing instruction, and executing corresponding operation after the current equipment acquires the processing instruction. The method solves the problem that the digital twin model in the prior art can not prevent controllable production abnormality while maintaining continuous production.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to an abnormality prevention and control system and method for a device, an electronic device, and a storage medium.
Background
In the production process of enterprises, equipment failure or production abnormality can be caused by reasons of signal transmission, sensing devices, vibration, joint looseness, greasy dirt, quality errors of original station products and the like. Some complex production processes relate to a plurality of devices and production processes, and the produced production abnormality may be one or more of the abnormality produced by the association of the devices, so that the fault problem produced by the association production of the devices cannot be systematically judged, the system analyzes according to the historical production state data, a real-time analysis model is built by using time length analysis, monitoring index analysis and the like of the devices, potential hazards possibly existing are predicted, and the internet of things device processing or early warning processing is timely scheduled.
At present, a digital twin model is built by a plurality of enterprises, but the problems of equipment fault tracing and production guidance are only solved, and the occurrence of controllable production abnormality can not be prevented while continuous production is maintained.
Disclosure of Invention
The embodiment of the invention aims to provide an abnormality prevention and control system and method for equipment, electronic equipment and a storage medium, which are used for solving the problem that a digital twin model in the prior art cannot prevent controllable production abnormality while maintaining continuous production.
In order to achieve the above objective, an embodiment of the present invention provides an anomaly prevention and control method for a device, where the method specifically includes:
acquiring equipment history data, wherein the equipment history data comprises equipment use data, fault processing data and equipment types or production lines corresponding to production processes;
constructing a production anomaly analysis model, and training the production anomaly analysis model based on the equipment history data to obtain a trained production anomaly analysis model;
acquiring actual production data of equipment, and inputting the actual production data and equipment historical data into the production anomaly analysis model to generate fault prediction information of the current equipment, wherein the fault prediction information comprises probability information, time information and anomaly occurrence problem points of the current equipment;
inputting the fault prediction information and the actual production demand information into a production manufacturing data model to obtain a scheduling scheme;
constructing a fault processing model, and training the fault processing model based on the fault processing data to obtain a trained fault processing model;
inputting the fault prediction information into the fault processing model to obtain fault processing information;
and judging the abnormal point of the equipment based on the fault processing model, generating a corresponding processing instruction, and executing corresponding operation after the current equipment acquires the processing instruction.
Based on the technical scheme, the invention can also be improved as follows:
further, the acquiring the equipment history data, where the equipment history data includes equipment usage data, fault processing data, and equipment types or production lines corresponding to the production process, includes:
acquiring fault information of equipment in the manufacturing process, and recording element information of the equipment with faults;
acquiring operation element information of equipment, wherein the operation element information comprises startup time and shutdown time;
acquiring service production technology element information of equipment, wherein the service production technology element information comprises service production order information, order commodity information, scheduling information and production process information;
and acquiring historical abnormal occurrence problem points, fault processing information corresponding to the abnormal occurrence problem points and a scheduling mechanism.
Further, training the production anomaly analysis model based on the equipment history data to obtain a trained production anomaly analysis model, comprising:
dividing the equipment history data into a training set, a testing set and a verification set;
training the production anomaly analysis model based on the training set;
performing performance evaluation on the trained production anomaly analysis model based on the verification set to obtain a production anomaly analysis model meeting performance conditions;
and evaluating the analysis result of the production anomaly analysis model meeting the performance condition based on the test set to obtain an evaluation index corresponding to the production anomaly analysis model.
Further, the inputting the fault prediction information and the actual production requirement information into a production manufacturing data model to obtain a production arrangement scheme includes:
and screening the production process suitable for the current order according to the production technology element information of the current order, screening the production line with the least order, and if a plurality of production lines exist and are all arranged at the least, selecting the production line with the optimal quality of all equipment elements in the current production line.
Further, the inputting the fault prediction information and the actual production requirement information into a production manufacturing data model to obtain a production scheduling scheme further includes:
and scoring the equipment based on the operation element information of each equipment on the production line, and solving a weighted average value of equipment scores of the production line every day based on the failure frequency = total failure times/startup times in the preset time as a scoring dimension, wherein the weighted average value is the production line score.
Further, the constructing the fault handling model includes:
establishing a scheduling mechanism corresponding to each process node device and information transmission, and corresponding each device or transmission channel for processing abnormal schedulable internet of things devices or transmission interfaces, so as to form an abnormal processing knowledge graph based on real-time production of all devices and transmission interfaces of the existing system;
dividing the fault processing data into a training set, a testing set and a verification set;
training the fault handling model based on the training set;
performing performance evaluation on the trained production anomaly analysis model based on the verification set to obtain a fault processing model meeting performance conditions;
and evaluating the processing result of the fault processing model meeting the performance condition based on the test set to obtain an evaluation index corresponding to the fault processing model.
Further, the judging the abnormal point of the device based on the fault processing model and generating a corresponding processing instruction, and executing corresponding operation after the current device acquires the processing instruction, including:
and analyzing the current use condition data of the equipment of each node based on the equipment historical data and the actual production data to predict probability information, time information and abnormal occurrence problem points of the current equipment abnormality, and triggering a scheduling mechanism before the time of predicting the occurrence of the abnormality according to the real-time production information in the current single production to prevent the equipment abnormality.
An anomaly prevention and control system for a device, comprising:
the first acquisition module is used for acquiring equipment historical data, wherein the equipment historical data comprises equipment use data, fault processing data and equipment types or production lines corresponding to production processes;
the first construction module is used for constructing a production anomaly analysis model;
the first training module is used for training the production anomaly analysis model based on the equipment historical data to obtain a trained production anomaly analysis model;
the second acquisition module is used for acquiring actual production data of the equipment;
inputting the actual production data and the equipment history data into the production anomaly analysis model to generate the fault prediction information of the current equipment, wherein the fault prediction information comprises probability information, time information and anomaly occurrence problem points of the current equipment;
a production manufacturing data model for obtaining a scheduling scheme based on the failure prediction information and actual production demand information;
the second construction module is used for constructing a fault processing model;
the second training module is used for training the fault processing model based on the fault processing data to obtain a trained fault processing model;
inputting the fault prediction information into the fault processing model to obtain fault processing information;
and the instruction module is used for judging the abnormal point of the equipment based on the fault processing model and generating a corresponding processing instruction, and the current equipment executes corresponding operation after acquiring the processing instruction.
An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method when the computer program is executed.
A non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method.
The embodiment of the invention has the following advantages:
the abnormal control method of the equipment acquires equipment history data, wherein the equipment history data comprises equipment use data, fault processing data and equipment types or production lines corresponding to production processes; constructing a production anomaly analysis model, and training the production anomaly analysis model based on the equipment history data to obtain a trained production anomaly analysis model; acquiring actual production data of equipment, and inputting the actual production data and equipment historical data into the production anomaly analysis model to generate fault prediction information of the current equipment, wherein the fault prediction information comprises probability information, time information and anomaly occurrence problem points of the current equipment; inputting the fault prediction information and the actual production demand information into a production manufacturing data model to obtain a scheduling scheme; constructing a fault processing model, and training the fault processing model based on the fault processing data to obtain a trained fault processing model; inputting the fault prediction information into the fault processing model to obtain fault processing information; judging the abnormal point of the equipment based on the fault processing model, generating a corresponding processing instruction, and executing corresponding operation after the current equipment acquires the processing instruction; the problem that the digital twin model in the prior art cannot prevent controllable production abnormality while maintaining continuous production is solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It will be apparent to those skilled in the art from this disclosure that the drawings described below are merely exemplary and that other embodiments may be derived from the drawings provided without undue effort.
The structures, proportions, sizes, etc. shown in the present specification are shown only for the purposes of illustration and description, and are not intended to limit the scope of the invention, which is defined by the claims, so that any structural modifications, changes in proportions, or adjustments of sizes, which do not affect the efficacy or the achievement of the present invention, should fall within the scope of the invention.
FIG. 1 is a flow chart of an anomaly prevention and control method of the apparatus of the present invention;
FIG. 2 is a block diagram of an anomaly prevention and control system of the apparatus of the present invention;
fig. 3 is a schematic diagram of an entity structure of an electronic device according to the present invention.
Wherein the reference numerals are as follows:
a first acquisition module 10, a first build module 20, a first training module 30, a second acquisition module 40, a production manufacturing data model 50, a second build module 60, a second training module 70, an instruction module 80, an electronic device 90, a processor 901, a memory 902, a bus 903.
Detailed Description
Other advantages and advantages of the present invention will become apparent to those skilled in the art from the following detailed description, which, by way of illustration, is to be read in connection with certain specific embodiments, but not all embodiments. 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 production process of enterprises, equipment failure or production abnormality can be caused by reasons such as signal transmission, sensing devices, vibration, joint loosening, greasy dirt, original station product quality errors and the like. Some complex production processes relate to a plurality of devices and production processes, and the produced production abnormality may be one or more of the abnormality produced by the association of the devices, so that the fault problem produced by the association production of the devices cannot be systematically judged, the system analyzes according to the historical production state data, a real-time analysis model is built by using time length analysis, monitoring index analysis and the like of the devices, potential hazards possibly existing are predicted, and the internet of things device processing or early warning processing is timely scheduled. And (3) establishing an equipment production abnormal knowledge graph, and establishing historical production data comparison and the like based on the single production activity time and the production process links of the equipment.
Examples
Fig. 1 is a flowchart of an embodiment of an anomaly prevention and control method of an apparatus according to the present invention, as shown in fig. 1, where the anomaly prevention and control method of an apparatus according to the embodiment of the present invention includes the following steps:
s101, acquiring equipment history data, wherein the equipment history data comprises equipment use data, fault processing data and equipment types or production lines corresponding to production processes;
specific: registering equipment purchasing time, longest single-use time, production line to which equipment belongs and corresponding process links of production, and generating equipment element information in a simulation system.
And recording the startup time, shutdown time, fault information and the like of all the equipment, and generating equipment operation element information in the simulation system.
Acquiring fault information of equipment in the manufacturing process, and recording element information of the equipment with faults;
acquiring operation element information of equipment, wherein the operation element information comprises startup time and shutdown time;
and acquiring service production technology element information of the equipment, wherein the service production technology element information comprises service production order information, order commodity information, scheduling information and production process information.
And acquiring equipment information, wherein the equipment information comprises equipment purchasing time, the longest single-use time, a production line to which equipment belongs and a process link corresponding to production, and equipment element information in a simulation system is generated.
And acquiring the parts of the history, which are judged by human or platform automatic prediction and are generated by the equipment faults, the corresponding fault processing schemes, the scheduling mechanism and the like, and generating knowledge element information in a simulation system.
And constructing a simulation system based on the failed equipment element information, the business production technology element information, the operation element information and the knowledge element information.
S102, constructing a production anomaly analysis model, and training the production anomaly analysis model based on equipment history data to obtain a trained production anomaly analysis model;
specifically, the device history data is divided into a training set, a testing set and a verification set;
training the production anomaly analysis model based on the training set;
performing performance evaluation on the trained production anomaly analysis model based on the verification set to obtain a production anomaly analysis model meeting performance conditions;
and evaluating the analysis result of the production anomaly analysis model meeting the performance condition based on the test set to obtain an evaluation index corresponding to the production anomaly analysis model.
Performing performance evaluation on the trained production anomaly analysis model based on the verification set to obtain a production anomaly analysis model meeting performance conditions; and evaluating the analysis result of the production anomaly analysis model meeting the performance condition based on the test set to obtain an evaluation index corresponding to the production anomaly analysis model. Performing performance evaluation on the production anomaly analysis model to obtain a percent score (namely, the highest score is 100 points and the lowest score is 0 points), and determining the production anomaly analysis model with the score larger than a set value based on the percent score, for example, the production anomaly analysis model 40 with the score larger than 90 points is the production anomaly analysis model meeting the performance condition;
and carrying out evaluation index calculation on the production anomaly analysis model meeting the performance condition to obtain evaluation indexes of the production anomaly analysis model, and calculating to obtain an evaluation value corresponding to each evaluation index, wherein the evaluation value is used for representing the capability value of the production anomaly analysis model on the evaluation indexes.
S103, acquiring actual production data of the equipment, and inputting the actual production data and the equipment historical data into a production anomaly analysis model to generate fault prediction information of the current equipment, wherein the fault prediction information comprises probability information, time information and anomaly occurrence problem points of the current equipment;
s104, inputting the fault prediction information and the actual production demand information into a production manufacturing data model to obtain a scheduling scheme;
specifically, the dispatching center of the simulation platform completes the production line distribution of the current order information to be produced according to the data of the current equipment element information, the equipment operation element information, the production element information, the knowledge element information, the production technology element information and the like, and the main process is as follows:
and screening the production process suitable for the current order according to the production technology element information of the current order, screening the production line with the least order, and if a plurality of production lines exist and are all arranged at the least, selecting the production line with the optimal quality of all equipment elements in the current production line.
As a production line for producing the current order. How to judge the optimum: the operation element information of each device on the production line is used for scoring the device, the device sum is used as a scoring dimension, and the device start-up times are used as a scoring dimension; the equipment is scored based on the operation element information of each equipment on the production line, and the failure frequency = total failure times/startup times in the preset time is used as a scoring dimension, preferably, the preset time is about one month; a weighted average of the daily line equipment scores is determined, the weighted average being the line score. And selecting the production line with the highest score, and if a plurality of production lines belong to the production line with the highest score, randomly selecting one production line as the production line of the current order.
And generating a production and manufacturing digital twin model according to the actual production information of the current order and the information of the order production based on the scheduling production rule model.
S105, constructing a fault processing model, and training the fault processing model based on the fault processing data to obtain a trained fault processing model;
specifically, a scheduling mechanism corresponding to each process node device and information transmission is established, and each device or transmission channel is used for processing an abnormally schedulable internet of things device or transmission interface, so that an abnormal processing knowledge graph based on real-time production of all devices and transmission interfaces of the existing system is formed.
Dividing the fault processing data into a training set, a testing set and a verification set;
training the fault handling model based on the training set;
performing performance evaluation on the trained fault processing model based on the verification set to obtain a fault processing model meeting performance conditions;
and evaluating an analysis result of the fault processing model meeting the performance condition based on the test set to obtain an evaluation index corresponding to the fault processing model.
Performing performance evaluation on the trained fault processing model based on the verification set to obtain a fault processing model meeting performance conditions; and evaluating the processing result of the fault processing model meeting the performance condition based on the test set to obtain an evaluation index corresponding to the fault processing model. Performing performance evaluation on the fault treatment model to obtain a percentage score (namely, the maximum score is 100 points and the minimum score is 0 points), and determining the fault treatment model with the score larger than a set value based on the percentage score, wherein for example, the fault treatment model 40 with the score larger than 90 points is a fault treatment model meeting the performance condition;
and calculating an evaluation index of the fault processing model meeting the performance condition to obtain the evaluation index of the fault processing model, and calculating to obtain an evaluation value corresponding to each evaluation index, wherein the evaluation value is used for representing the capacity value of the fault processing model on the evaluation index.
S106, inputting the fault prediction information into a fault processing model to obtain fault processing information;
s107, judging the abnormal point of the equipment based on the fault processing model, generating a corresponding processing instruction, and executing corresponding operation after the current equipment acquires the processing instruction;
specifically, the current use condition data of the equipment of each node is analyzed based on the historical data and the actual production data of the equipment to predict probability information, time information and abnormal occurrence problem points of the current equipment, and a scheduling mechanism before the time of predicting the occurrence of faults is triggered according to the real-time production information in the current single production to prevent the equipment from being abnormal.
The abnormality prevention and control method of the device further comprises the following steps:
the method comprises the steps of obtaining production process information of a business system, obtaining the type of production equipment or production line corresponding to the production process, for example, for the process of carrying semi-finished products in the production process, selecting equipment (such as an intelligent carrier), for example, after the intelligent carrier is obtained from commodities, selecting a designated production line according to the production process. In the commodity production process, the process required to be experienced establishes a corresponding production and manufacturing model on a simulation platform, and binds equipment information of an equipment information registration system on each flow node (for example, the flow node of an intelligent carrier needs to be selected and the flow node of a production line needs to be selected) to form a real-time production schedulable knowledge graph of a production and manufacturing mathematical model.
And identifying the states of normal production, abnormal production, closed production and the like of each production node, and generating a time sequence record model of production equipment, production data and transmission data states of each production line in the process of generating each state record.
According to the historical equipment faults and the production records (total production duration, single production duration, startup frequency and the like) of the equipment, the situation that the faults finally occur and cannot be predicted is recorded, and therefore data sources for abnormal prediction analysis learning are continuously enriched.
According to the historical equipment fault record information and the actual physical production data acquired in the current production and manufacture mathematical model, the current use condition data of equipment of each node is analyzed by combining the production real-time record data, for example, the characteristics of the current equipment such as total production time length, single production time length, starting frequency and the like are compared with the equipment information recorded by the historical faults, the probability information, time information and abnormal occurrence problem points of the current equipment are predicted, the real-time production information acquired according to the rotating speed, temperature, friction and the like in the current single production is used, a scheduling mechanism before the time of predicting the occurrence of the faults is triggered, for example, the oiling treatment of the Internet of things equipment of the current equipment is automatically triggered, or an alarm mechanism is triggered to remind people to perform maintenance treatment. In the real-time abnormity monitoring, if the communication interface is monitored to not receive related data interface information, triggering the communication interface module to send an interface request, and timely acquiring the interface information;
and establishing a continuous abnormality prediction and processing mechanism through a digital twin model, and preventing production abnormality caused by equipment or communication service abnormality.
FIG. 2 is a flow chart of an embodiment of an anomaly prevention and control system of the apparatus of the present invention; as shown in fig. 2, the abnormality prevention and control system for a device provided by the embodiment of the invention includes the following steps:
a first obtaining module 10, configured to obtain equipment history data, where the equipment history data includes equipment usage data, fault processing data, and an equipment type or a production line corresponding to a production process;
a first construction module 20 for constructing a production anomaly analysis model;
a first training module 30, configured to train the production anomaly analysis model based on the equipment history data to obtain a trained production anomaly analysis model;
a second acquisition module 40 for acquiring actual production data of the apparatus;
inputting the actual production data and the equipment history data into the production anomaly analysis model to generate the fault prediction information of the current equipment, wherein the fault prediction information comprises probability information, time information and anomaly occurrence problem points of the current equipment;
a manufacturing data model 50 for deriving a scheduling scheme based on the failure prediction information and actual production demand information;
a second construction module 60 for constructing a fault handling model;
a second training module 70, configured to train the fault handling model based on the fault handling data to obtain a trained fault handling model;
inputting the fault prediction information into the fault processing model to obtain fault processing information;
the instruction module 80 is configured to determine an abnormal point of the device based on the fault processing model and generate a corresponding processing instruction, and execute a corresponding operation after the current device acquires the processing instruction.
The first acquisition module 10 is further configured to:
acquiring fault information of equipment in the manufacturing process, and recording element information of the equipment with faults;
acquiring operation element information of equipment, wherein the operation element information comprises startup time and shutdown time;
and acquiring service production technology element information of the equipment, wherein the service production technology element information comprises service production order information, order commodity information, scheduling information and production process information.
The first training module 30 is further configured to:
dividing the equipment history data into a training set, a testing set and a verification set;
training the production anomaly analysis model based on the training set;
performing performance evaluation on the trained production anomaly analysis model based on the verification set to obtain a production anomaly analysis model meeting performance conditions;
and evaluating the analysis result of the production anomaly analysis model meeting the performance condition based on the test set to obtain an evaluation index corresponding to the production anomaly analysis model.
The manufacturing data model 50 is also used to:
and screening the production process suitable for the current order according to the production technology element information of the current order, screening the production line with the least order, and if a plurality of production lines exist and are all arranged at the least, selecting the production line with the optimal quality of all equipment elements in the current production line.
And scoring the equipment based on the operation element information of each equipment on the production line, and solving a weighted average value of equipment scores of the production line every day based on the failure frequency = total failure times/startup times in the preset time as a scoring dimension, wherein the weighted average value is the production line score.
The second building block 60 is further configured to: and establishing a scheduling mechanism corresponding to each process node device and information transmission, and corresponding to each device or transmission channel for processing abnormal schedulable internet-of-things devices or transmission interfaces, so as to form an abnormal processing knowledge graph based on real-time production of all devices and transmission interfaces of the existing system.
The instruction module 80 is further configured to: and analyzing the current use condition data of the equipment of each node based on the equipment historical data and the actual production data to predict probability information, time information and abnormal occurrence problem points of the current equipment abnormality, and triggering a scheduling mechanism before the time of predicting the occurrence of the abnormality according to the real-time production information in the current single production to prevent the equipment abnormality.
According to the abnormality prevention and control system of the equipment, equipment history data is acquired through the first acquisition module 10, wherein the equipment history data comprises equipment use data, fault processing data and equipment types or production lines corresponding to production processes; building a production anomaly analysis model by a first build module 20; training the production anomaly analysis model based on the equipment history data by a first training module 30 to obtain a trained production anomaly analysis model; acquiring actual production data of the equipment through a second acquisition module 40; inputting the actual production data and the equipment history data into the production anomaly analysis model to generate the fault prediction information of the current equipment, wherein the fault prediction information comprises probability information, time information and anomaly occurrence problem points of the current equipment; deriving a scheduling scheme based on the failure prediction information and actual production demand information by the production manufacturing data model 50; constructing a fault handling model by a second construction module 60; training the fault handling model based on the fault handling data by a second training module 70 to obtain a trained fault handling model; inputting the fault prediction information into the fault processing model to obtain fault processing information; the instruction module 80 judges the abnormal point of the equipment based on the fault processing model and generates a corresponding processing instruction, and the current equipment executes corresponding operation after acquiring the processing instruction. The abnormality prevention and control method of the equipment solves the problem that the digital twin model in the prior art can not prevent controllable production abnormality while maintaining continuous production.
Fig. 3 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present invention, as shown in fig. 3, an electronic device 90 includes: a processor 901 (processor), a memory 902 (memory), and a bus 903;
the processor 901 and the memory 902 complete communication with each other through the bus 903;
the processor 901 is configured to call program instructions in the memory 902 to perform the methods provided in the above method embodiments, for example, including: acquiring equipment history data, wherein the equipment history data comprises equipment use data, fault processing data and equipment types or production lines corresponding to production processes; constructing a production anomaly analysis model, and training the production anomaly analysis model based on the equipment history data to obtain a trained production anomaly analysis model; acquiring actual production data of equipment, and inputting the actual production data and equipment historical data into the production anomaly analysis model to generate fault prediction information of the current equipment, wherein the fault prediction information comprises probability information, time information and anomaly occurrence problem points of the current equipment; inputting the fault prediction information and the actual production demand information into a production manufacturing data model to obtain a scheduling scheme; constructing a fault processing model, and training the fault processing model based on the fault processing data to obtain a trained fault processing model; inputting the fault prediction information into the fault processing model to obtain fault processing information; and judging the abnormal point of the equipment based on the fault processing model, generating a corresponding processing instruction, and executing corresponding operation after the current equipment acquires the processing instruction.
The present embodiment provides a non-transitory computer readable storage medium storing computer instructions that cause a computer to perform the methods provided by the above-described method embodiments, for example, including: acquiring equipment history data, wherein the equipment history data comprises equipment use data, fault processing data and equipment types or production lines corresponding to production processes; constructing a production anomaly analysis model, and training the production anomaly analysis model based on the equipment history data to obtain a trained production anomaly analysis model; acquiring actual production data of equipment, and inputting the actual production data and equipment historical data into the production anomaly analysis model to generate fault prediction information of the current equipment, wherein the fault prediction information comprises probability information, time information and anomaly occurrence problem points of the current equipment; inputting the fault prediction information and the actual production demand information into a production manufacturing data model to obtain a scheduling scheme; constructing a fault processing model, and training the fault processing model based on the fault processing data to obtain a trained fault processing model; inputting the fault prediction information into the fault processing model to obtain fault processing information; and judging the abnormal point of the equipment based on the fault processing model, generating a corresponding processing instruction, and executing corresponding operation after the current equipment acquires the processing instruction.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware associated with program instructions, where the foregoing program may be stored in a computer readable storage medium, and when executed, the program performs steps including the above method embodiments; and the aforementioned storage medium includes: various storage media such as ROM, RAM, magnetic or optical disks may store program code.
The apparatus embodiments described above are merely illustrative, wherein elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on such understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the embodiments or the methods of some parts of the embodiments.
While the invention has been described in detail in the foregoing general description and specific examples, it will be apparent to those skilled in the art that modifications and improvements can be made thereto. Accordingly, such modifications or improvements may be made without departing from the spirit of the invention and are intended to be within the scope of the invention as claimed.
Claims (10)
1. The abnormality prevention and control method for the equipment is characterized by specifically comprising the following steps of:
acquiring equipment history data, wherein the equipment history data comprises equipment use data, fault processing data and equipment types or production lines corresponding to production processes;
constructing a production anomaly analysis model, and training the production anomaly analysis model based on the equipment history data to obtain a trained production anomaly analysis model;
acquiring actual production data of equipment, and inputting the actual production data and equipment historical data into the production anomaly analysis model to generate fault prediction information of the current equipment, wherein the fault prediction information comprises probability information, time information and anomaly occurrence problem points of the current equipment;
inputting the fault prediction information and the actual production demand information into a production manufacturing data model to obtain a scheduling scheme;
constructing a fault processing model, and training the fault processing model based on the fault processing data to obtain a trained fault processing model;
inputting the fault prediction information into the fault processing model to obtain fault processing information;
and judging the abnormal point of the equipment based on the fault processing model, generating a corresponding processing instruction, and executing corresponding operation after the current equipment acquires the processing instruction.
2. The anomaly prevention and control method of a device of claim 1, wherein the obtaining device history data, wherein the device history data includes device usage data, fault handling data, and a device type or line corresponding to a production process, comprises:
acquiring fault information of equipment in the manufacturing process, and recording element information of the equipment with faults;
acquiring operation element information of equipment, wherein the operation element information comprises startup time and shutdown time;
acquiring service production technology element information of equipment, wherein the service production technology element information comprises service production order information, order commodity information, scheduling information and production process information;
and acquiring historical abnormal occurrence problem points, fault processing information corresponding to the abnormal occurrence problem points and a scheduling mechanism.
3. The anomaly prevention and control method of a device of claim 1, wherein the training the production anomaly analysis model based on the device history data to obtain a trained production anomaly analysis model comprises:
dividing the equipment history data into a training set, a testing set and a verification set;
training the production anomaly analysis model based on the training set;
performing performance evaluation on the trained production anomaly analysis model based on the verification set to obtain a production anomaly analysis model meeting performance conditions;
and evaluating the analysis result of the production anomaly analysis model meeting the performance condition based on the test set to obtain an evaluation index corresponding to the production anomaly analysis model.
4. The anomaly prevention and control method of a device according to claim 1, wherein inputting the failure prediction information and actual production demand information into a production manufacturing data model to obtain a scheduling scheme comprises:
and screening the production process suitable for the current order according to the production technology element information of the current order, screening the production line with the least order, and if a plurality of production lines exist and are all arranged at the least, selecting the production line with the optimal quality of all equipment elements in the current production line.
5. The anomaly prevention and control method for a device of claim 4 wherein said inputting said failure prediction information and actual production demand information into a production manufacturing data model results in a scheduling scheme, further comprising:
and scoring the equipment based on the operation element information of each equipment on the production line, and solving a weighted average value of equipment scores of the production line every day based on the failure frequency = total failure times/startup times in the preset time as a scoring dimension, wherein the weighted average value is the production line score.
6. The anomaly prevention and control method of a device of claim 1, wherein the constructing a fault handling model comprises:
establishing a scheduling mechanism corresponding to each process node device and information transmission, and corresponding each device or transmission channel for processing abnormal schedulable internet of things devices or transmission interfaces, so as to form an abnormal processing knowledge graph based on real-time production of all devices and transmission interfaces of the existing system;
dividing the fault processing data into a training set, a testing set and a verification set;
training the fault handling model based on the training set;
performing performance evaluation on the trained production anomaly analysis model based on the verification set to obtain a fault processing model meeting performance conditions;
and evaluating the processing result of the fault processing model meeting the performance condition based on the test set to obtain an evaluation index corresponding to the fault processing model.
7. The method for preventing and controlling abnormality of a device according to claim 1, wherein the determining a point of abnormality of the device based on the fault handling model and generating a corresponding handling instruction, and executing a corresponding operation after the current device obtains the handling instruction, includes:
and analyzing the current use condition data of the equipment of each node based on the equipment historical data and the actual production data to predict probability information, time information and abnormal occurrence problem points of the current equipment abnormality, and triggering a scheduling mechanism before the time of predicting the occurrence of the abnormality according to the real-time production information in the current single production to prevent the equipment abnormality.
8. An abnormality prevention and control system of an apparatus, comprising:
the first acquisition module is used for acquiring equipment historical data, wherein the equipment historical data comprises equipment use data, fault processing data and equipment types or production lines corresponding to production processes;
the first construction module is used for constructing a production anomaly analysis model;
the first training module is used for training the production anomaly analysis model based on the equipment historical data to obtain a trained production anomaly analysis model;
the second acquisition module is used for acquiring actual production data of the equipment;
inputting the actual production data and the equipment history data into the production anomaly analysis model to generate the fault prediction information of the current equipment, wherein the fault prediction information comprises probability information, time information and anomaly occurrence problem points of the current equipment;
a production manufacturing data model for obtaining a scheduling scheme based on the failure prediction information and actual production demand information;
the second construction module is used for constructing a fault processing model;
the second training module is used for training the fault processing model based on the fault processing data to obtain a trained fault processing model;
inputting the fault prediction information into the fault processing model to obtain fault processing information;
and the instruction module is used for judging the abnormal point of the equipment based on the fault processing model and generating a corresponding processing instruction, and the current equipment executes corresponding operation after acquiring the processing instruction.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 7 when the computer program is executed.
10. A non-transitory computer readable medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310940914.5A CN116975639B (en) | 2023-07-28 | Abnormality prevention and control system and method for equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310940914.5A CN116975639B (en) | 2023-07-28 | Abnormality prevention and control system and method for equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116975639A true CN116975639A (en) | 2023-10-31 |
| CN116975639B CN116975639B (en) | 2024-07-12 |
Family
ID=
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117893101A (en) * | 2024-03-15 | 2024-04-16 | 丰睿成科技(深圳)股份有限公司 | Production quality evaluation method, system and storage medium for bond alloy wires |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105427021A (en) * | 2015-10-30 | 2016-03-23 | 江苏云道信息技术有限公司 | Intelligent clothes production scheduling method |
| CN106875120A (en) * | 2017-02-16 | 2017-06-20 | 吉林大学 | A kind of discrete type production line production capacity wave process and its disturbance degree evaluation method |
| CN107239064A (en) * | 2016-03-27 | 2017-10-10 | 中国食品发酵工业研究院 | A kind of method for assessing filling production lines efficiency and board state |
| CN110380880A (en) * | 2018-04-13 | 2019-10-25 | 中国科学院沈阳自动化研究所 | A kind of architecture of the vehicle manufacture intelligent plant based on edge calculations frame |
| CN111860882A (en) * | 2020-06-17 | 2020-10-30 | 国网江苏省电力有限公司 | Method and device for constructing power grid dispatching fault processing knowledge graph |
| CN114003728A (en) * | 2021-09-28 | 2022-02-01 | 广东电网有限责任公司 | Fault processing method and device for power grid line |
| WO2022048168A1 (en) * | 2020-09-03 | 2022-03-10 | 上海上讯信息技术股份有限公司 | Training method and device for failure prediction neural network model |
| CN115238925A (en) * | 2022-07-25 | 2022-10-25 | 北京卓尔忠诚科技有限公司 | Motor equipment supervision method and system |
| CN116127695A (en) * | 2022-11-17 | 2023-05-16 | 华中科技大学 | Production line construction method and system based on comprehensive performance evaluation |
| CN116415002A (en) * | 2023-04-17 | 2023-07-11 | 合肥工业大学 | Power grid fault recovery error-proof checking method based on graph matching |
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105427021A (en) * | 2015-10-30 | 2016-03-23 | 江苏云道信息技术有限公司 | Intelligent clothes production scheduling method |
| CN107239064A (en) * | 2016-03-27 | 2017-10-10 | 中国食品发酵工业研究院 | A kind of method for assessing filling production lines efficiency and board state |
| CN106875120A (en) * | 2017-02-16 | 2017-06-20 | 吉林大学 | A kind of discrete type production line production capacity wave process and its disturbance degree evaluation method |
| CN110380880A (en) * | 2018-04-13 | 2019-10-25 | 中国科学院沈阳自动化研究所 | A kind of architecture of the vehicle manufacture intelligent plant based on edge calculations frame |
| CN111860882A (en) * | 2020-06-17 | 2020-10-30 | 国网江苏省电力有限公司 | Method and device for constructing power grid dispatching fault processing knowledge graph |
| WO2022048168A1 (en) * | 2020-09-03 | 2022-03-10 | 上海上讯信息技术股份有限公司 | Training method and device for failure prediction neural network model |
| CN114003728A (en) * | 2021-09-28 | 2022-02-01 | 广东电网有限责任公司 | Fault processing method and device for power grid line |
| CN115238925A (en) * | 2022-07-25 | 2022-10-25 | 北京卓尔忠诚科技有限公司 | Motor equipment supervision method and system |
| CN116127695A (en) * | 2022-11-17 | 2023-05-16 | 华中科技大学 | Production line construction method and system based on comprehensive performance evaluation |
| CN116415002A (en) * | 2023-04-17 | 2023-07-11 | 合肥工业大学 | Power grid fault recovery error-proof checking method based on graph matching |
Non-Patent Citations (3)
| Title |
|---|
| FEI TAO ET AL.: "Digital Twin Shop-Floor: A New Shop-Floor Paradigm Towards Smart Manufacturing", 《IEEE ACCESS》, pages 20418 - 20427 * |
| YAN BAI ET AL.: "Design and Optimization of Smart Factory Control System Based on Digital Twin System Model", 《MATHEMATICAL PROBLEMS IN ENGINEERING》, pages 1 - 16 * |
| 梁兴明: "基于虚实融合的车间实时生产监控***的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》, pages 140 - 384 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117893101A (en) * | 2024-03-15 | 2024-04-16 | 丰睿成科技(深圳)股份有限公司 | Production quality evaluation method, system and storage medium for bond alloy wires |
| CN117893101B (en) * | 2024-03-15 | 2024-06-07 | 丰睿成科技(深圳)股份有限公司 | Production quality evaluation method, system and storage medium for bond alloy wires |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111679952B (en) | Alarm threshold generation method and device | |
| US8694196B1 (en) | Methods and systems for centrally managed maintenance program for aircraft fleets | |
| KR20180108446A (en) | System and method for management of ict infra | |
| US20110307301A1 (en) | Decision aid tool for competency analysis | |
| KR20190021560A (en) | Failure prediction system using big data and failure prediction method | |
| US20170169342A1 (en) | System and method for diagnosing at least one component requiring maintenance in an appliance and/or installation | |
| JP7333473B2 (en) | Method and system for monitoring and predicting air preheating equipment contamination in real time | |
| CN115280337A (en) | Machine learning based data monitoring | |
| US10733514B1 (en) | Methods and apparatus for multi-site time series data analysis | |
| JP7475978B2 (en) | Maintenance improvement support device and maintenance improvement support method | |
| CN111984442A (en) | Method and device for detecting abnormality of computer cluster system, and storage medium | |
| CN110244686A (en) | The fault handling method and device of smart machine | |
| JP2009086896A (en) | Failure prediction system and failure prediction method for computer | |
| Becherer et al. | Intelligent choice of machine learning methods for predictive maintenance of intelligent machines | |
| Letot et al. | An adaptive degradation‐based maintenance model taking into account both imperfect adjustments and AGAN replacements | |
| Wu et al. | Adaptive sequential predictive maintenance policy with nonperiodic inspection for hard failures | |
| JP2006276924A (en) | Equipment diagnostic device and equipment diagnostic program | |
| CN116997867A (en) | Method and system for predicting the operation of a technical installation | |
| Moat et al. | Survival analysis and predictive maintenance models for non-sensored assets in facilities management | |
| CN109669796A (en) | A kind of prediction technique and device of disk failure | |
| CN116975639B (en) | Abnormality prevention and control system and method for equipment | |
| CN116258482B (en) | Method for automatically selecting maintenance scheme, server and electronic equipment | |
| CN116975639A (en) | Abnormality prevention and control system and method for equipment | |
| CN116702597A (en) | Mechanical equipment operation life prediction and health management method, system and medium | |
| JP7062505B2 (en) | Equipment management support system |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240614 Address after: 523000 room 1301, unit 2, building 4, Tian'an Digital City, No. 1, Huangjin Road, Nancheng street, Dongguan City, Guangdong Province Applicant after: Dongguan Mengda Group Co.,Ltd. Country or region after: China Applicant after: Shenzhen Yipinhui Information Technology Co.,Ltd. Address before: 523000 room 1301, unit 2, building 4, Tian'an Digital City, No. 1, Huangjin Road, Nancheng street, Dongguan City, Guangdong Province Applicant before: Dongguan Mengda Group Co.,Ltd. Country or region before: China |
|
| GR01 | Patent grant |