CN118396252B - MES client data analysis optimization method based on cloud computing - Google Patents
MES client data analysis optimization method based on cloud computing Download PDFInfo
- Publication number
- CN118396252B CN118396252B CN202410869723.9A CN202410869723A CN118396252B CN 118396252 B CN118396252 B CN 118396252B CN 202410869723 A CN202410869723 A CN 202410869723A CN 118396252 B CN118396252 B CN 118396252B
- Authority
- CN
- China
- Prior art keywords
- data
- production
- risk
- early warning
- risk early
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004519 manufacturing process Methods 0.000 description 124
- 230000007613 environmental effect Effects 0.000 description 32
- 238000011156 evaluation Methods 0.000 description 30
- 238000000034 method Methods 0.000 description 19
- 238000012502 risk assessment Methods 0.000 description 15
- 238000012544 monitoring process Methods 0.000 description 13
- 238000007405 data analysis Methods 0.000 description 12
- 238000005457 optimization Methods 0.000 description 12
- 238000004458 analytical method Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 8
- 238000004140 cleaning Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 230000010354 integration Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000006872 improvement Effects 0.000 description 5
- 241000669618 Nothes Species 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- 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
-
- 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
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/26—Discovering frequent patterns
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Educational Administration (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- General Factory Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a MES client data analysis optimization method based on cloud computing, which relates to the technical field of data analysis optimization and comprises the following steps: identifying data sources required to be integrated by the MES system, evaluating importance and data quality of each data source, determining an integration priority, accessing each data source into the MES system, and cleaning and integrating data of each data source, wherein each data source comprises production field equipment, a sensor, an ERP system and a CRM system. According to the invention, through the cloud computing platform, various data in the production process can be collected, stored and analyzed in real time by the MES client, the running condition of the production line can be rapidly mastered by real-time data monitoring, the system can rapidly respond when abnormal conditions occur, and when equipment fails or the product quality does not reach the standard, the system can immediately give out early warning and start a corresponding emergency plan, so that production delay and loss caused by untimely finding of problems are avoided.
Description
Technical Field
The invention relates to the technical field of data analysis optimization, in particular to a MES client data analysis optimization method based on cloud computing.
Background
With development and maturity of cloud computing technology, more and more enterprises begin to migrate services to the cloud to utilize elasticity, expandability and cost effectiveness of the cloud computing technology, and with the advent of the 4.0 era of industry, manufacturing industry is undergoing unprecedented transformation, digital transformation becomes a key trend, cloud MES software is used as an important tool for digital transformation, digitization, intellectualization and networking of a production site can be achieved, production efficiency and product quality are improved, and cloud MES clients can provide accurate production state insight and decision support for the enterprises through real-time collection, storage, processing and analysis of data of the production site.
In the prior art, a cloud MES system is generally required to integrate a plurality of different data sources, and under a cloud computing environment, the integration of the plurality of data sources can cause the increase of overall complexity, so that the scenes requiring quick response and real-time risk early warning are interfered, and the timeliness and the accuracy of production management decisions are influenced, so that how to ensure the early warning accuracy of production management and the effectiveness of evaluation prediction under the multi-source environment is a problem to be solved, and a MES client data analysis optimization method based on cloud computing is provided.
Disclosure of Invention
The invention aims to provide a MES client data analysis and optimization method based on cloud computing, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention adopts the following technical scheme:
the MES client data analysis optimization method based on cloud computing comprises the following steps:
Step 1, identifying data sources required to be integrated by an MES system, evaluating importance and data quality of each data source, determining an integration priority, accessing each data source into the MES system, and cleaning and integrating data of each data source, wherein each data source comprises production field equipment, a sensor, an ERP system and a CRM system;
step 2, acquiring data of a production site based on an automation device and a sensor technology, preprocessing the acquired raw data and analyzing the data, and determining service requirements and targets to be optimized in production management, wherein the acquired raw data comprises historical data and real-time data;
step 3, according to the business requirement and the target to be optimized, performing model training by using the preprocessed historical data, constructing a risk assessment model, applying the constructed risk assessment model to actual production, and performing production trend prediction and anomaly detection;
step 4, combining the production trend prediction result and the preprocessed historical data to obtain a risk early warning coefficient of the MES system, setting a risk early warning level, and matching a corresponding risk early warning threshold;
and 5, identifying potential risks in the production process, evaluating and quantifying the risks, automatically triggering early warning notification according to the risk evaluation result, and outputting data analysis result and risk early warning information.
The technical scheme of the invention is further improved as follows: in the step 1, the cleaning and integrating process of the data source data is as follows:
Step 101, determining data sources required to be integrated by an MES system, wherein the data sources comprise production field equipment, sensors, an ERP system and a CRM system, the production field equipment data are equipment running state, production rate and fault information data, the sensor data are environmental parameter data of temperature, humidity and pressure in the production process, the ERP system data are production orders, material demand plans and inventory information data, and the CRM system data are used for feeding back customer demands and market dynamic data;
102, carrying out importance analysis on each data source, evaluating the contribution degree of each data source data to an MES system, carrying out data quality evaluation on each data source data, checking the accuracy, the integrity, the consistency, the reliability and the timeliness of the data, knowing the data acquisition, the processing and the storage processes of each data source, and evaluating possible data quality problems;
Step 103, determining an integration priority according to the importance of the data sources and the evaluation result, determining the integration sequence of the data sources according to the service demand and the influence degree, and preferentially processing the data sources with the greatest influence on the production and management decision;
Step 104, configuring a data access interface, accessing an MES system, such as an MQTT or an OPC UA, to production field devices and sensors by adopting an industrial Internet of things technology and a protocol, accessing the MES system by adopting an ETL tool to an ERP system and a CRM system, and ensuring that data can be transmitted from each data source to the MES system;
And 105, cleaning and integrating the data transmitted by each accessed data source, and storing the processed data in a temporary database, wherein errors, repetition or invalidation data are removed by cleaning the accessed data, the data in different formats are converted into a uniform format, the data from different data sources are combined to form a data view, and data association is established.
The technical scheme of the invention is further improved as follows: in the step 2, the process of defining the service requirement and the target to be optimized in the production management is as follows:
Step 201, collecting data of a production site by utilizing industrial automation equipment such as a PLC (programmable logic controller) and a DCS (distributed control system) and various sensors such as a temperature sensor, a humidity sensor and a pressure sensor, wherein the collected data type comprises historical data and real-time data, the historical data is used for analyzing past production conditions, the real-time data is used for monitoring the current production state, and the collected data is transmitted to an MES system to be stored by utilizing a temporary database so as to ensure the stability and safety of data transmission;
Step 202, after data cleaning and standardization processing are carried out on the collected data, integrating the data from different data sources to form a data set;
Step 203, determining key performance indexes and points to be optimized in production management by combining actual conditions and business targets of a production site, wherein the points to be optimized comprise frequent equipment faults, low production efficiency and unstable product quality, and setting specific optimization targets according to identification results of the points to be optimized, wherein the specific optimization targets comprise improvement of production efficiency, reduction of equipment fault rate and improvement of product quality.
The technical scheme of the invention is further improved as follows: in the step 3, the construction and application process of the risk assessment model is as follows:
Step 301, extracting preprocessed historical data from a temporary database, and extracting associated characteristic variables from the preprocessed historical data, wherein the characteristic variables comprise production equipment states, production rates and environment parameters, and risk indexes of equipment failure rates and production delay probabilities are defined to obtain a characteristic data set;
Step 302, determining sub-factors of each characteristic variable based on the extracted associated characteristic variables, wherein the sub-factors of the production equipment state comprise running time, downtime and maintenance times, the sub-factors of the production rate comprise output per hour and production cycle time, and the sub-factors of the environmental parameters comprise temperature, humidity and pressure;
Step 303, performing comprehensive analysis according to the sub-factors of each characteristic variable to respectively obtain an equipment state evaluation index, a production rate evaluation index and an environmental state evaluation index;
Step 304, dividing the characteristic data set into a training set and a testing set, constructing a risk assessment model by combining data in the training set with a neural network, and assessing the performance of the model by using the data in the testing set;
And 305, deploying the trained model into an MES system, configuring an input data interface and an output data interface required by the model, immediately predicting the current production data by using a risk assessment model, and analyzing and predicting long-term trends of production efficiency and product quality by combining an equipment state assessment index, a production rate assessment index and an environmental state assessment index.
The technical scheme of the invention is further improved as follows: the calculation formula of the equipment state evaluation index is as follows:
；
Wherein, Representing the device state evaluation index(s),The number of times the device is operated is indicated,Representing device NoThe total time of the secondary operation is set,Representing device NoThe time of the secondary shutdown is that,The value range of (2) is 0 to 1;
The calculation formula of the production rate evaluation index is as follows:
；
Wherein, The production rate evaluation index is represented by the formula,The production time is indicated as a function of the production time,Represent the firstThe yield of one hour was set to be,The average value of the production per hour is shown,Standard deviation representing the hourly production;
the calculation formula of the environmental state evaluation index is as follows:
；
Wherein, Represents an environmental state-assessment index that,Which is indicative of the kind of the environmental parameter,Representing any environmental parameterIs used for the measurement of (a),Representing the optimal value of the environmental parameter,Representing the maximum value of the environmental parameter,Representing a minimum value of the environmental parameter,The value of (2) is in the range of 0 to 1.
The technical scheme of the invention is further improved as follows: in the step 4, the risk early warning coefficient acquisition process of the MES system is as follows:
Step 401, collecting and sorting historical data related to production trend prediction, and acquiring risk early warning coefficients of an MES system by combining an equipment state evaluation index, a production rate evaluation index and an environmental state evaluation index;
step 402, evaluating the risk type and level affecting the production according to the relevant historical data, and setting different risk early-warning levels, namely a low risk early-warning level, a medium risk early-warning level and a high risk early-warning level;
Step 403, setting corresponding risk early-warning thresholds according to different risk early-warning levels and combining risk early-warning coefficients of the MES system, making early-warning rules, and clearly triggering risk early-warning and the corresponding time of the risk early-warning level.
The technical scheme of the invention is further improved as follows: the calculation formula of the risk early warning coefficient is as follows:
；
；
Wherein, Representing risk early warning coefficients for comprehensively evaluating risk levels in the MES system,Representing an index representing an equipment state evaluation index, a production rate evaluation index, an environmental state evaluation index,Representing an exponential functionIs added to the negative weighted sum of (c),Representing the index of the summation, corresponding to three different indices,Representing weight coefficients for adjusting different indicesThe importance in the risk assessment is that,Representing a normalization function for normalizationIs used as a reference to the value of (a),Representation ofIs used for the average value of (a),Representation ofIs set in the standard deviation of (2),The range of the values is as follows。
The technical scheme of the invention is further improved as follows: the risk early warning levels correspond to the risk early warning thresholds, wherein the risk early warning thresholds comprise an upper limit threshold and a lower limit threshold;
the risk early warning levels and the risk early warning thresholds satisfy the following relationship:
Low risk early warning level ; All key indexes approach or reach the optimal state, the production process is stable, the risk is low, the current operation is maintained, the monitoring data is continued, the trend is ensured to be stable, and possible small fluctuation is prepared to be dealt with;
Medium risk early warning grade ; Some key indexes may deviate from the optimal state, have medium risk, need attention, increase monitoring frequency, analyze the cause of data deviation, prepare to adjust production plans or take measures to optimize equipment state and environmental conditions;
High risk early warning level ; The plurality of key indexes deviate from the optimal state remarkably, the production process may face high risk of interruption or quality reduction, the production process and related indexes are inspected immediately, emergency measures are taken to correct the deviation, such as equipment setting adjustment, environmental condition improvement or temporary production stoppage for maintenance;
Wherein, As the risk pre-warning coefficient,A lower threshold corresponding to the low risk early warning level and an upper threshold corresponding to the medium risk early warning level,For the lower threshold value corresponding to the risk early warning level and the upper threshold value corresponding to the high risk early warning level,，。
The technical scheme of the invention is further improved as follows: in the step 5, the process of triggering the early warning notification is as follows:
step 501, determining the type of risk, such as equipment failure, raw material supply interruption, production quality problem and the like, based on the risk assessment and identification result, formulating logic and conditions for automatic triggering and early warning by using preset risk early warning threshold values and rules, and comprehensively judging the production trend prediction result, the abnormality detection result and the set risk early warning threshold values;
Step 502, carrying out real-time monitoring in combination with the collected data related to production, analyzing the change trend and abnormal situation of the data, and sending an early warning notice to related personnel in a mail, short message or mobile application mode in combination with the risk assessment and identification result, wherein the risk early warning information comprises abnormal data, trend analysis, risk type, risk early warning level and influence range;
And step 503, according to the risk early warning information, adopting corresponding risk countermeasures, adjusting the production plan, reducing or avoiding the occurrence of risks, and continuously monitoring the identified risks to ensure that the risks are controlled.
By adopting the technical scheme, compared with the prior art, the invention has the following technical progress:
1. according to the MES client data analysis optimization method based on cloud computing, various data in the production process can be collected, stored and analyzed in real time by the cloud computing platform, the running condition of a production line can be rapidly mastered by real-time data monitoring, the system can rapidly respond when abnormal conditions occur, and when equipment fails or the product quality does not reach the standard, the system can immediately send out early warning and start corresponding emergency plans, so that production delay and loss caused by untimely finding of problems are avoided.
2. The invention provides a cloud computing-based MES client data analysis optimization method, which utilizes a big data technology and a machine learning algorithm to deeply mine and analyze mass data, can find rules and trends in the production process through analysis of historical data, can identify bottlenecks and waste links in the production process through analysis of production data, and provides improvement suggestions so as to optimize the production flow and adjust equipment parameters, thereby achieving the purposes of reducing the production cost and improving the production efficiency.
3. The invention provides a MES client data analysis optimization method based on cloud computing, which can timely discover potential quality problems by monitoring and analyzing key parameters in a production process, correct the potential quality problems by taking corresponding measures, greatly improve the qualification rate and stability of products, establish perfect risk early warning and coping mechanisms, timely discover potential risk factors and provide early warning information by monitoring and analyzing production data in real time, automatically trigger corresponding emergency plans according to the risk types and grades, help rapidly cope with risks, greatly reduce risk loss and improve anti-risk capacity.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings for a person having ordinary skill in the art.
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a flow chart of the construction and application of the risk assessment model of the present invention;
FIG. 3 is a flow chart of risk early warning coefficient acquisition for the MES system of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment 1, as shown in fig. 1 and 2, the present invention provides a MES client data analysis optimization method based on cloud computing, which includes the following steps:
Step 1, identifying data sources needing to be integrated of an MES system, evaluating importance and data quality of each data source, determining integration priority, accessing each data source into the MES system, cleaning and integrating data of each data source, wherein each data source comprises production field equipment, a sensor, an ERP system and a CRM system, determining the data sources needing to be integrated of the MES system, comprising the production field equipment, the sensor, the ERP system and the CRM system, wherein the production field equipment data are equipment running state, production rate and fault information data, the sensor data are environmental parameter data of temperature, humidity and pressure in the production process, the ERP system data are production order, material demand plan and inventory information data, the CRM system data are used for feeding back customer demand and market dynamic data, carrying out importance analysis on each data source, evaluating contribution degree of each data source data to the MES system, and evaluating the data quality of each data source, checking the accuracy, integrity, consistency, reliability and timeliness of the data, knowing the data acquisition, processing and storage processes of each data source, evaluating the possible data quality problems, determining the integration priority according to the importance and evaluation result of the data source, determining the integration sequence of the data source according to the service requirement and the influence degree, preferentially processing the data source with the largest influence on the production and management decision, configuring a data access interface, accessing the industrial Internet of things technology and protocol to the production field device and the sensor to an MES system, such as MQTT or OPC UA, accessing an ETL tool to the MES system to ensure that the data can be transmitted from each data source to the MES system, cleaning the data transmitted by each accessed data source and integrating the data, storing the processed data in a temporary database, wherein the data is cleaned, error, repetition or invalid data are removed, the data in different formats are converted into a uniform format, the data from different data sources are combined to form a data view, and data association is established;
Step 2, acquiring data of a production site based on an automation device and a sensor technology, preprocessing the acquired raw data and analyzing the data, determining service requirements and targets to be optimized in production management, wherein the acquired raw data comprises historical data and real-time data, acquiring data of the production site by utilizing industrial automation devices such as a PLC (programmable logic controller) and a DCS (distributed control system) as well as a temperature sensor, a humidity sensor and a pressure sensor, wherein the acquired data comprises historical data and real-time data, the historical data is used for analyzing the past production condition, the real-time data is used for monitoring the current production state, the acquired data is transmitted to an MES system and is stored by utilizing a temporary database, the stability and the safety of data transmission are ensured, the acquired data is integrated with data from different data sources after being subjected to data cleaning and standardization processing to form a data set, the actual condition and the service targets of the production site are combined, the aim of determining key performance indexes and the data to be optimized in the production management, the data to comprise equipment failure occurrence, low production efficiency, unstable quality of products, the quality of the products to be optimized is improved, the quality of the products is improved, and the quality of the products to be optimized is improved, and the quality of the products is set to be optimized;
Step 3, performing model training by using preprocessed historical data according to business requirements and targets to be optimized, constructing a risk assessment model, applying the constructed risk assessment model to actual production, performing production trend prediction and anomaly detection, extracting preprocessed historical data from a temporary database, extracting associated characteristic variables from the historical data, including a production equipment state, a production rate and environmental parameters, defining risk indexes of equipment failure rate and production delay probability, obtaining a characteristic data set, determining sub factors of each characteristic variable based on the extracted associated characteristic variables, wherein the sub factors of the production equipment state comprise running time, downtime and maintenance times, the sub factors of the production rate comprise hourly yield and production cycle time, the sub factors of the environmental parameters comprise temperature, humidity and pressure, performing comprehensive analysis according to the sub factors of each characteristic variable, respectively obtaining equipment state assessment index, production rate assessment index and environmental state assessment index, dividing the characteristic data set into a training set and a test set, constructing the risk assessment model by utilizing data in the training set and combining neural network, deploying the training set data into the training set, and performing instant analysis on the production state index and the production state of the MES by using the test set data, and the required by the configuration data interface and the production rate and the production state index, and the current state assessment system is predicted by the output and the production state index and the production rate is subjected to the prediction and the quality assessment model;
further, the calculation formula of the device state evaluation index is:
；
Wherein, Representing the device state evaluation index(s),The number of times the device is operated is indicated,Representing device NoThe total time of the secondary operation is set,Representing device NoThe time of the secondary shutdown is that,The greater the ratio of run time to total time (run time plus downtime) is, the more the value of (1) ranges from 0 to 1,The higher the value, the better the device state;
The calculation formula of the production rate evaluation index is as follows:
；
Wherein, The production rate evaluation index is represented by the formula,The production time is indicated as a function of the production time,Represent the firstThe yield of one hour was set to be,The average value of the production per hour is shown,The standard deviation of the production per hour is expressed, and it is noted that the larger the deviation of the production from the average production,The more the value deviates from 0, a positive value indicates that the production rate is above average;
the calculation formula of the environmental state evaluation index is as follows:
；
Wherein, Represents an environmental state-assessment index that,Which is indicative of the kind of the environmental parameter,Representing any environmental parameterIs used for the measurement of (a),Representing the optimal value of the environmental parameter,Representing the maximum value of the environmental parameter,Representing a minimum value of the environmental parameter,The value range of (2) is 0 to 1, it should be noted that, the smaller the square ratio of the square of the difference between the measured value of the environmental parameter and the optimal value to the square ratio of the difference range of the maximum and minimum values of the environmental parameter,The higher the value, the more ideal the environmental state;
step 4, combining the production trend prediction result and the preprocessed historical data to obtain a risk early warning coefficient of the MES system, setting a risk early warning level, and matching a corresponding risk early warning threshold;
and 5, identifying potential risks in the production process, evaluating and quantifying the risks, automatically triggering early warning notification according to the risk evaluation result, and outputting data analysis result and risk early warning information.
In embodiment 2, as shown in fig. 3, on the basis of embodiment 1, the present invention provides a technical scheme: preferably, in step 4, the risk early warning coefficient acquiring process of the MES system is as follows:
Collecting and sorting historical data related to production trend prediction, combining an equipment state evaluation index, a production rate evaluation index and an environment state evaluation index to obtain risk early warning coefficients of an MES system, evaluating risk types and levels affecting production according to the related historical data, setting different risk early warning levels, namely a low risk early warning level, a medium risk early warning level and a high risk early warning level, respectively, setting corresponding risk early warning thresholds according to the different risk early warning levels, respectively, setting early warning rules, and clearly triggering the risk early warning and the timing of the corresponding risk early warning level according to the risk early warning coefficients of the MES system;
further, the calculation formula of the risk early warning coefficient is:
；
；
Wherein, Representing risk early warning coefficients for comprehensively evaluating risk levels in the MES system,Representing an index representing an equipment state evaluation index, a production rate evaluation index, an environmental state evaluation index,Representing an exponential functionIs added to the negative weighted sum of (c),Representing the index of the summation, corresponding to three different indices,Representing weight coefficients for adjusting different indicesThe importance in the risk assessment is that,Representing a normalization function for normalizationIs used as a reference to the value of (a),Representation ofIs used for the average value of (a),Representation ofIs set in the standard deviation of (2),The range of the values is as followsIt should be noted that, when all the indicators are good, i.e. the risk is low,Proximity to; When the index is poor, i.e. the risk is high,Proximity to; When (when)When the value of (a) increases, i.e. indexDeviation from ideal, exponential functionWill decrease in value, resulting inA decrease, indicating an increase in risk;
Further, the plurality of risk early warning levels correspond to a plurality of risk early warning thresholds, wherein the risk early warning thresholds comprise an upper threshold and a lower threshold;
The plurality of risk early warning levels and the plurality of risk early warning thresholds satisfy the following relationship:
Low risk early warning level ; All key indexes approach or reach the optimal state, the production process is stable, the risk is low, the current operation is maintained, the monitoring data is continued, the trend is ensured to be stable, and possible small fluctuation is prepared to be dealt with;
Medium risk early warning grade ; Some key indexes may deviate from the optimal state, have medium risk, need attention, increase monitoring frequency, analyze the cause of data deviation, prepare to adjust production plans or take measures to optimize equipment state and environmental conditions;
High risk early warning level ; The plurality of key indexes deviate from the optimal state remarkably, the production process may face high risk of interruption or quality reduction, the production process and related indexes are inspected immediately, emergency measures are taken to correct the deviation, such as equipment setting adjustment, environmental condition improvement or temporary production stoppage for maintenance;
Wherein, As the risk pre-warning coefficient,A lower threshold corresponding to the low risk early warning level and an upper threshold corresponding to the medium risk early warning level,For the lower threshold value corresponding to the risk early warning level and the upper threshold value corresponding to the high risk early warning level,，；
In step 5, the process of triggering the early warning notification is as follows:
based on the risk assessment recognition result, determining the type of risk, such as equipment failure, raw material supply interruption, production quality problem and the like, using preset risk early warning threshold values and rules to formulate automatic triggering early warning logic and conditions, comprehensively judging the production trend prediction result, the abnormality detection result and the set risk early warning threshold values, carrying out real-time monitoring in combination with the collected data related to production, analyzing the change trend and the abnormality of the data, combining with the risk assessment recognition result, sending early warning notification to related personnel in a mail, short message or mobile application mode, presenting risk early warning information, wherein the risk early warning information comprises abnormal data, trend analysis, risk type, risk early warning level and influence range, adopting corresponding risk countermeasure according to the risk early warning information, adjusting the production plan, reducing or avoiding risk, and continuously monitoring the recognized risk to ensure that the risk is controlled.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (7)
1. The MES client data analysis and optimization method based on cloud computing is characterized by comprising the following steps of: the method comprises the following steps:
Step 1, identifying data sources required to be integrated by an MES system, evaluating importance and data quality of each data source, determining an integration priority, accessing each data source into the MES system, and cleaning and integrating data of each data source, wherein each data source comprises production field equipment, a sensor, an ERP system and a CRM system;
step 2, acquiring data of a production site based on an automation device and a sensor technology, preprocessing the acquired raw data and analyzing the data, and determining service requirements and targets to be optimized in production management, wherein the acquired raw data comprises historical data and real-time data;
step 3, according to the business requirement and the target to be optimized, performing model training by using the preprocessed historical data, constructing a risk assessment model, applying the constructed risk assessment model to actual production, and performing production trend prediction and anomaly detection;
Step 4, combining the production trend prediction result and the preprocessed historical data to obtain a risk early-warning coefficient of the MES system, setting a risk early-warning level, and matching a corresponding risk early-warning threshold, wherein in the step 4, the risk early-warning coefficient obtaining process of the MES system is as follows:
Step 401, collecting and sorting historical data related to production trend prediction, and acquiring risk early warning coefficients of an MES system by combining an equipment state evaluation index, a production rate evaluation index and an environmental state evaluation index;
step 402, evaluating the risk type and level affecting the production according to the relevant historical data, and setting different risk early-warning levels, namely a low risk early-warning level, a medium risk early-warning level and a high risk early-warning level;
Step 403, aiming at different risk early-warning levels, respectively setting corresponding risk early-warning thresholds by combining risk early-warning coefficients of an MES system, making an early-warning rule, and definitely triggering the risk early-warning and the opportunity of the corresponding risk early-warning level, wherein the calculation formula of the risk early-warning coefficients is as follows:
Wherein, M p represents a risk early warning coefficient, I p represents an index, represents an equipment state evaluation index, a production rate evaluation index and an environmental state evaluation index, p represents a summation index, corresponds to three different indexes, w p represents a weight coefficient, f (I p) represents a standardized function for standardizing the value of I p, avg (I p) represents the average value of I p, std (I p) represents the standard deviation of I p, and the value range of M p is (0, 1);
and 5, identifying potential risks in the production process, evaluating and quantifying the risks, automatically triggering early warning notification according to the risk evaluation result, and outputting data analysis result and risk early warning information.
2. The method for optimizing data analysis of a MES client based on cloud computing according to claim 1, wherein: in the step 1, the cleaning and integrating process of the data source data is as follows:
Step 101, determining data sources required to be integrated by an MES system, wherein the data sources comprise production field equipment, sensors, an ERP system and a CRM system, the production field equipment data are equipment running state, production rate and fault information data, the sensor data are environmental parameter data of temperature, humidity and pressure in the production process, the ERP system data are production orders, material demand plans and inventory information data, and the CRM system data are used for feeding back customer demands and market dynamic data;
102, carrying out importance analysis on each data source, evaluating the contribution degree of each data source data to an MES system, carrying out data quality evaluation on each data source data, knowing the data acquisition, processing and storage processes of each data source, and evaluating possible data quality problems;
Step 103, determining an integration priority according to the importance of the data sources and the evaluation result, determining the integration sequence of the data sources according to the service demand and the influence degree, and preferentially processing the data sources with the greatest influence on the production and management decision;
Step 104, configuring a data access interface, accessing an MES system by adopting an industrial Internet of things technology and a protocol for production field devices and sensors, and accessing the MES system by adopting an ETL tool for an ERP system and a CRM system;
And 105, carrying out data cleaning and data integration on the data transmitted by each accessed data source, storing the processed data in a temporary database, combining the data from different data sources to form a data view, and establishing data association.
3. The method for optimizing data analysis of a MES client based on cloud computing according to claim 2, wherein: in the step 2, the process of defining the service requirement and the target to be optimized in the production management is as follows:
step 201, acquiring data of a production site by using industrial automation equipment and various sensors, wherein the acquired data type comprises historical data and real-time data, and transmitting the acquired data to an MES system for storage by using a temporary database;
Step 202, after data cleaning and standardization processing are carried out on the collected data, integrating the data from different data sources to form a data set;
Step 203, determining key performance indexes and points to be optimized in production management by combining actual conditions and business targets of a production site, wherein the points to be optimized comprise frequent equipment faults, low production efficiency and unstable product quality, and setting specific optimization targets according to identification results of the points to be optimized.
4. A MES client data analysis optimization method based on cloud computing as claimed in claim 3, wherein: in the step 3, the construction and application process of the risk assessment model is as follows:
Step 301, extracting preprocessed historical data from a temporary database, and extracting associated characteristic variables from the preprocessed historical data, wherein the characteristic variables comprise production equipment states, production rates and environment parameters, and risk indexes of equipment failure rates and production delay probabilities are defined to obtain a characteristic data set;
Step 302, determining sub-factors of each characteristic variable based on the extracted associated characteristic variables, wherein the sub-factors of the production equipment state comprise running time, downtime and maintenance times, the sub-factors of the production rate comprise output per hour and production cycle time, and the sub-factors of the environmental parameters comprise temperature, humidity and pressure;
Step 303, performing comprehensive analysis according to the sub-factors of each characteristic variable to respectively obtain an equipment state evaluation index, a production rate evaluation index and an environmental state evaluation index;
Step 304, dividing the characteristic data set into a training set and a testing set, constructing a risk assessment model by combining data in the training set with a neural network, and assessing the performance of the model by using the data in the testing set;
And 305, deploying the trained model into an MES system, configuring an input data interface and an output data interface required by the model, immediately predicting the current production data by using a risk assessment model, and analyzing and predicting long-term trends of production efficiency and product quality by combining an equipment state assessment index, a production rate assessment index and an environmental state assessment index.
5. The method for optimizing data analysis of a MES client based on cloud computing as recited in claim 4, wherein: the calculation formula of the equipment state evaluation index is as follows:
Wherein, EI represents equipment state evaluation index, N represents equipment operation times, RT i represents total time of ith operation of equipment, ST i represents ith downtime of equipment, and the value range of EI is 0to 1;
The calculation formula of the production rate evaluation index is as follows:
wherein PI represents a production rate evaluation index, M represents a production time, PH j represents a production amount at the j-th hour, μph represents an average value of production amounts per hour, σph represents a standard deviation of production amounts per hour;
the calculation formula of the environmental state evaluation index is as follows:
Wherein, NI represents an environmental state evaluation index, P represents a type of an environmental parameter, E k represents a measured value of any environmental parameter k, E opt represents an optimal value of the environmental parameter, E max represents a maximum value of the environmental parameter, E min represents a minimum value of the environmental parameter, and the range of the value of NI is 0 to 1.
6. The method for optimizing data analysis of a MES client based on cloud computing according to claim 1, wherein: the risk early warning levels correspond to the risk early warning thresholds, wherein the risk early warning thresholds comprise an upper limit threshold and a lower limit threshold;
the risk early warning levels and the risk early warning thresholds satisfy the following relationship:
Low risk early warning level M zy≤Mp <1;
Medium risk early warning level M gy≤Mp<Mzy;
high risk early warning level 0< m p<Mgy;
Wherein, M p is a risk early warning coefficient, M zy is a lower threshold corresponding to a low risk early warning level and an upper threshold corresponding to a medium risk early warning level, M gy is a lower threshold corresponding to a medium risk early warning level and an upper threshold corresponding to a high risk early warning level, and M zy＝0.8,Mzy =0.5.
7. The cloud computing-based MES client data analysis optimization method according to claim 6, wherein: in the step 5, the process of triggering the early warning notification is as follows:
step 501, determining the type of risk based on a risk assessment and identification result, formulating logic and conditions for automatic triggering and early warning by using a preset risk early warning threshold and rules, and comprehensively judging a production trend prediction result, an abnormality detection result and a set risk early warning threshold;
Step 502, carrying out real-time monitoring in combination with the collected data related to production, analyzing the change trend and abnormal situation of the data, and sending an early warning notice to related personnel in a mail, short message or mobile application mode in combination with the risk assessment and identification result, wherein the risk early warning information comprises abnormal data, trend analysis, risk type, risk early warning level and influence range;
and step 503, according to the risk early warning information, adopting corresponding risk countermeasures, adjusting the production plan, and continuously monitoring the identified risk.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410869723.9A CN118396252B (en) | 2024-07-01 | 2024-07-01 | MES client data analysis optimization method based on cloud computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410869723.9A CN118396252B (en) | 2024-07-01 | 2024-07-01 | MES client data analysis optimization method based on cloud computing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118396252A CN118396252A (en) | 2024-07-26 |
| CN118396252B true CN118396252B (en) | 2024-08-30 |
Family
ID=91985210
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410869723.9A Active CN118396252B (en) | 2024-07-01 | 2024-07-01 | MES client data analysis optimization method based on cloud computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118396252B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119204544A (en) * | 2024-09-18 | 2024-12-27 | 英汇智能(深圳)有限公司 | Manufacturing process optimization method based on MES system |
| CN119087945B (en) * | 2024-09-18 | 2025-02-18 | 厦门多多云技术创新研究院有限公司 | Industrial data collection and management method based on Internet of Things |
| CN119026919B (en) * | 2024-10-25 | 2025-01-24 | 深度(山东)数字科技集团有限公司 | Industrial chain risk assessment and early warning system and method based on multidimensional data map |
| CN119151155A (en) * | 2024-11-14 | 2024-12-17 | 宏景科技股份有限公司 | Industrial intelligent production method, system and terminal equipment based on pre-training large model |
| CN119512021A (en) * | 2025-01-23 | 2025-02-25 | 成都精锐环科技有限公司 | Data analysis method and system of intelligent production equipment based on industrial Internet |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117350492A (en) * | 2023-10-13 | 2024-01-05 | 宿迁云瑞国科信息技术有限公司 | MES operation management system capable of intelligently controlling comparison historical data |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200067789A1 (en) * | 2016-06-24 | 2020-02-27 | QiO Technologies Ltd. | Systems and methods for distributed systemic anticipatory industrial asset intelligence |
| KR102464762B1 (en) * | 2022-02-17 | 2022-11-09 | 주식회사 디엠테크컨설팅 | Predictive maintenance method for equipment failure using artificial intelligence based on experiential shared knowledge |
-
2024
- 2024-07-01 CN CN202410869723.9A patent/CN118396252B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117350492A (en) * | 2023-10-13 | 2024-01-05 | 宿迁云瑞国科信息技术有限公司 | MES operation management system capable of intelligently controlling comparison historical data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118396252A (en) | 2024-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118396252B (en) | MES client data analysis optimization method based on cloud computing | |
| CN110320892B (en) | Fault diagnosis system and method for sewage treatment equipment based on Lasso regression | |
| CN109240244B (en) | Data-driven equipment running state health degree analysis method and system | |
| CN117176560B (en) | Monitoring equipment supervision system and method based on Internet of things | |
| CN118915566A (en) | Heating ventilation equipment abnormity on-line monitoring system based on Internet of things | |
| CN118868426B (en) | Power energy management system based on smart IoT | |
| CN118430092B (en) | Data general acquisition method based on MCC system | |
| CN118534883B (en) | Intelligent diagnosis method, system and medium for equipment failure based on industrial Internet of Things | |
| CN113128707A (en) | Situation risk assessment method for distribution automation terminal | |
| CN112580858A (en) | Equipment parameter prediction analysis method and system | |
| CN119001068A (en) | Online monitoring system and method for lubricating oil of thermal power plant equipment | |
| CN117078227A (en) | Environment monitoring operation and maintenance platform based on identification analysis | |
| CN118244709A (en) | Associated fault equipment and influence factor acquisition method, device and exception handling system | |
| CN116611953A (en) | Electric energy meter production and manufacturing real-time data management method and system based on Internet of things | |
| CN118114023A (en) | Pharmaceutical production line state monitoring and alarming method and system based on Internet of things | |
| CN118014115A (en) | Production line loss monitoring method based on long-short-term memory network | |
| CN117009741A (en) | Abnormal analysis method and system based on generated energy | |
| CN118826294B (en) | A digital management method and system for substation-based operation and maintenance | |
| CN118550958B (en) | A device abnormality determination method, system and medium based on industrial Internet of Things | |
| CN118898038A (en) | An AI-assisted big data anomaly detection and risk assessment system | |
| CN118066934A (en) | Intelligent fault positioning system for weapon equipment | |
| CN117591949A (en) | Equipment abnormality identification method, equipment and medium | |
| CN115755664A (en) | Maintenance method and system for manufacturing equipment of discrete enterprise | |
| CN119026886B (en) | A production scheduling control method based on industrial edge gateway | |
| CN119335940B (en) | A real-time monitoring method and system for sewage treatment data based on the Internet of Things |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |