CN116483042A - Digital lean diagnosis method for lean production control platform - Google Patents
Digital lean diagnosis method for lean production control platform Download PDFInfo
- Publication number
- CN116483042A CN116483042A CN202310499057.XA CN202310499057A CN116483042A CN 116483042 A CN116483042 A CN 116483042A CN 202310499057 A CN202310499057 A CN 202310499057A CN 116483042 A CN116483042 A CN 116483042A
- Authority
- CN
- China
- Prior art keywords
- data
- production
- model
- lean
- production process
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 152
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000003745 diagnosis Methods 0.000 title claims abstract description 26
- 238000004458 analytical method Methods 0.000 claims abstract description 31
- 238000012544 monitoring process Methods 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 24
- 238000004140 cleaning Methods 0.000 claims abstract description 10
- 230000002159 abnormal effect Effects 0.000 claims abstract description 7
- 238000013079 data visualisation Methods 0.000 claims abstract description 7
- 230000006872 improvement Effects 0.000 claims description 35
- 238000007726 management method Methods 0.000 claims description 22
- 239000002699 waste material Substances 0.000 claims description 16
- 239000000463 material Substances 0.000 claims description 15
- 238000012423 maintenance Methods 0.000 claims description 14
- 230000002950 deficient Effects 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 11
- 230000000694 effects Effects 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000000611 regression analysis Methods 0.000 claims description 8
- 238000003066 decision tree Methods 0.000 claims description 7
- 238000003326 Quality management system Methods 0.000 claims description 5
- 230000007613 environmental effect Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 description 13
- 238000011161 development Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/41885—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by modeling, simulation of the manufacturing system
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32339—Object oriented modeling, design, analysis, implementation, simulation language
Abstract
The invention provides a digital lean diagnosis method of a lean production control platform, which comprises the following steps: and (3) data acquisition: collecting data in the production process through sensor equipment; and (3) data processing: uploading the acquired data to a data warehouse, and cleaning, processing and analyzing the data to find potential problems and rules in the data; establishing a model; and (3) real-time monitoring: the production process is monitored in real time in a data visualization, report form and early warning mode, and abnormal production conditions are found in time to perform early warning and reminding; the digital lean diagnosis platform can discover problems and bottlenecks in the production process through real-time monitoring and analysis of the production process, optimize the production flow and improve the production efficiency and the yield. Meanwhile, through monitoring and analysis of the human resource data, the work performance of staff can be estimated, and the staff efficiency and the work quality are improved.
Description
Technical Field
The invention relates to the technical field of lean production, in particular to a digital lean diagnosis method of a lean production management and control platform.
Background
The technology currently applied to the digital lean diagnosis platform comprises a plurality of technologies such as an industrial Internet of things technology, a big data technology, an artificial intelligence technology, a cloud computing technology, a visualization technology and the like, and the technologies can support the functions of real-time monitoring, data processing and analysis, model establishment and optimization, data visualization, decision support and the like of the digital lean diagnosis platform.
Monitoring and control are not in time: under the traditional production management mode, the monitoring and the control mainly depend on manual operation and experience judgment, and problems and bottlenecks in the production process cannot be found in time, so that the problems are enlarged, and the production efficiency and the quality are influenced. The data quality is low: under the traditional production management mode, data acquisition mainly relies on manual recording and statistics, has the problems of low data quality, inaccuracy, incompleteness and the like, and cannot meet the requirements of accurate monitoring and analysis. The decision effect is low: under the traditional production management mode, the decision is mainly dependent on manual experience and feel, data support and decision basis are lacked, the decision effect is low, and optimization and improvement of the production process are difficult to realize. In contrast, the digital lean diagnosis platform can solve the problems existing in the traditional production management mode through the digital, intelligent and lean modes, and improves the production efficiency, the product quality and the decision-making effect. Therefore, the digital lean diagnosis platform is an important background technology and can support enterprises to realize digital, intelligent and lean production management.
Disclosure of Invention
The invention provides a digital lean diagnosis method for a lean production control platform, which aims to solve the problems of the background technology.
The invention is realized in such a way that the digital lean diagnosis method of the lean production control platform comprises the following steps: and (3) data acquisition: collecting data in the production process through sensor equipment;
and (3) data processing: uploading the acquired data to a data warehouse, and cleaning, processing and analyzing the data to find potential problems and rules in the data;
and (3) establishing a model: selecting proper modeling methods and tools according to data characteristics and requirements, establishing a prediction model and a trend analysis model, and predicting problems in the production process;
and (3) real-time monitoring: the production process is monitored in real time in a data visualization, report form and early warning mode, and abnormal production conditions are found timely to perform early warning and reminding.
Analysis improvement: according to the model prediction and real-time monitoring results, analyzing problems and bottlenecks existing in the production process, providing improvement measures, optimizing the production flow, and reducing production waste, unexpected shutdown waste, defective rate and inventory waste;
continuous improvement: according to the effect of the improvement measures, the production flow and the quality management system are continuously adjusted and perfected, and continuous improvement and optimization are realized.
Preferably, the data in the production process includes:
production efficiency data: production speed, yield, production cycle and production capacity utilization rate are used for measuring production efficiency and production capacity;
device status data: the equipment running state, the equipment on-off time and the equipment maintenance time are used for knowing the running condition and the maintenance condition of the equipment;
quality data: the product percent of pass, defective rate and rework rate are used for evaluating the quality of products and the problems in the production process;
logistics data: material supply, stock quantity and material consumption for optimizing logistics management and reducing stock waste;
human resource data: the working time length, the staff efficiency and the staff attendance are used for evaluating the working performance of staff and managing human resources;
environmental data: temperature, humidity and air quality for monitoring the safety and stability of the production environment.
Preferably, the data processing includes, data cleansing: unnecessary data is removed, invalid, repeated and missing through data cleaning, and reliable and accurate data is reserved so as to improve the quality and usability of the data;
data conversion: the collected original data is converted, a digital signal or an analog signal is converted into a data format which can be identified by a computer, or different data types are subjected to uniform format conversion so as to process and analyze the data.
Preferably, the model establishment includes feature selection of data after data processing, and before the model establishment, data features need to be selected and extracted to determine input variables and output variables of the model, namely, an object and a method for model establishment; selecting a proper modeling method and tool according to the data characteristics and the predicted requirements; after the modeling methods and tools are determined, the model needs to be trained and tested to verify the accuracy and usability of the model; evaluating the performance and reliability of the model through the model evaluation index, and adjusting and optimizing the model; and (3) applying the established model to the production process, and carrying out prediction and trend analysis on the production data to find problems and potential risks in the production process, thereby providing basis for management decisions.
Preferably, the modeling method comprises regression analysis, a neural network and a decision tree, and a prediction model and a trend analysis model are established.
By adopting the scheme, the invention has the beneficial effects that: the production efficiency is improved: the digital lean diagnosis platform can discover problems and bottlenecks in the production process through real-time monitoring and analysis of the production process, optimize the production flow and improve the production efficiency and the yield. Meanwhile, through monitoring and analysis of the human resource data, the work performance of staff can be estimated, and the staff efficiency and the work quality are improved.
The product quality is improved: the digital lean diagnosis platform can evaluate the quality of products and the problems in the production process through monitoring and analysis of quality data, and provides improvement measures, reduces defective rate and rework rate, and improves the quality of the products and customer satisfaction.
Cost and risk are reduced: the digital lean diagnosis platform can optimize logistics management through monitoring and analysis of logistics data, reduces inventory waste and reduces material consumption and purchasing cost. Meanwhile, through monitoring and analyzing the equipment state data, the operation condition and the maintenance condition of the equipment are known, the equipment faults and the maintenance requirements are found in advance, and the maintenance cost and the production downtime are reduced.
The decision effect is improved: the digital lean diagnosis platform can provide decision support for an enterprise management layer through data visualization, report early warning and other modes, quickly discover problems and risks, take measures in time, optimize production and management, and improve decision-making effect and enterprise competitiveness.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
Description of the embodiments
The present invention will be described in further detail below in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1: a digital lean diagnosis method of a lean production control platform comprises the following steps: and (3) data acquisition: collecting data in the production process through sensor equipment;
and (3) data processing: uploading the acquired data to a data warehouse, and cleaning, processing and analyzing the data to find potential problems and rules in the data;
and (3) establishing a model: selecting proper modeling methods and tools according to data characteristics and requirements, establishing a prediction model and a trend analysis model, and predicting problems in the production process;
and (3) real-time monitoring: the production process is monitored in real time in a data visualization, report form and early warning mode, and abnormal production conditions are found timely to perform early warning and reminding.
Analysis improvement: according to the model prediction and real-time monitoring results, analyzing problems and bottlenecks existing in the production process, providing improvement measures, optimizing the production flow, and reducing production waste, unexpected shutdown waste, defective rate and inventory waste;
continuous improvement: according to the effect of the improvement measures, the production flow and the quality management system are continuously adjusted and perfected, and continuous improvement and optimization are realized.
In the present embodiment, the following is described. The main objective of the digital lean diagnosis method is to optimize the production flow and reduce the production cost through the steps of data acquisition, processing, modeling, real-time monitoring, analysis, improvement and the like, so as to realize continuous improvement and optimization.
Specifically, the method comprises the following steps:
and (3) data acquisition: data in the production process is collected through sensor equipment, including the running state of the production equipment, key parameters and indexes of the production process and the like. These data may be collected in real time by various sensor devices, such as temperature, humidity, pressure, vibration, current, etc.
And (3) data processing: the collected data is uploaded to a data warehouse and the data is cleaned, processed and analyzed to find potential problems and laws in the data. The data processing may use various data processing tools and techniques, such as data mining, machine learning, and the like.
And (3) establishing a model: and selecting proper modeling methods and tools according to the data characteristics and the requirements, establishing a prediction model and a trend analysis model, and predicting the problems in the production process. For example, time series analysis, regression analysis, neural network, etc. may be used to build a model to predict possible problems in production, such as equipment failure, defective rate in production, etc.
And (3) real-time monitoring: the production process is monitored in real time in a data visualization, report form and early warning mode, and abnormal production conditions are found timely to perform early warning and reminding. For example, key indexes in the production process can be monitored in real time by using modes such as an instrument panel and a report, and abnormal conditions are found and early warning is carried out.
Analysis improvement: according to the model prediction and real-time monitoring results, problems and bottlenecks existing in the production process are analyzed, improvement measures are provided, the production flow is optimized, and production waste, unexpected shutdown waste, defective product rate and inventory waste are reduced. For example, the production cost can be reduced and the production efficiency can be improved by optimizing the production plan, improving the equipment maintenance and the like.
Continuous improvement: according to the effect of the improvement measures, the production flow and the quality management system are continuously adjusted and perfected, and continuous improvement and optimization are realized. For example, continuous improvements and optimizations can be achieved by continuously improving the production process and quality management system by collecting feedback, periodic evaluations, and the like.
The digital lean diagnosis method helps enterprises to optimize production flow, reduce production cost, improve production efficiency and reduce production risk through steps such as data acquisition, processing, modeling, real-time monitoring, analysis, improvement and the like, so that continuous improvement and optimization are realized, and higher competitiveness and sustainable development are provided for the enterprises. Meanwhile, the method can promote the digitalized transformation and intelligent upgrading of enterprises, improve the production management level of the enterprises, improve the production efficiency and quality and reduce the cost and risk.
In addition, the digital lean diagnosis method can be combined with other digital technologies and tools, such as the technologies of the Internet of things, cloud computing, big data and the like, so that more refined production management and control can be realized. For example, the sensor equipment data can be uploaded to a cloud platform, and data analysis and mining are performed by utilizing cloud computing and big data technology, so that more accurate prediction and decision are realized.
In a word, the digital lean diagnosis method is an important production control platform, can help enterprises to realize digital transformation and intelligent upgrading, improves production efficiency and quality, reduces cost and risk, realizes continuous improvement and optimization, and provides higher competitiveness and sustainable development for the enterprises.
Further, the data in the production process includes:
production efficiency data: production speed, yield, production cycle and production capacity utilization rate are used for measuring production efficiency and production capacity;
device status data: the equipment running state, the equipment on-off time and the equipment maintenance time are used for knowing the running condition and the maintenance condition of the equipment;
quality data: the product percent of pass, defective rate and rework rate are used for evaluating the quality of products and the problems in the production process;
logistics data: material supply, stock quantity and material consumption for optimizing logistics management and reducing stock waste;
human resource data: the working time length, the staff efficiency and the staff attendance are used for evaluating the working performance of staff and managing human resources;
environmental data: temperature, humidity and air quality for monitoring the safety and stability of the production environment.
In the present embodiment, the following is described. The data can help enterprises to know the actual condition of the production process, discover potential problems and make improvement measures. Specific:
production efficiency data: including production speed, yield, production cycle, and throughput utilization. Production speed refers to the number of products produced per unit time, yield refers to the number of products produced, production cycle refers to the time required to produce a batch of products, and throughput utilization refers to the ratio of actual throughput to theoretical throughput. The indexes can help enterprises to know actual conditions of production efficiency and production capacity, find bottlenecks and problems in the production process and formulate corresponding improvement measures.
Device status data: including equipment operating conditions, equipment on-off time, and equipment maintenance time. These metrics may help businesses understand the operating conditions and maintenance of equipment, discover equipment failures and maintenance needs, and formulate corresponding maintenance and equipment update plans.
Quality data: including product yield, defective rate, and rework rate. The product yield refers to the proportion of qualified products in the produced products, the defective rate refers to the proportion of unqualified products in the produced products, and the reworking rate refers to the proportion of reworking required in the produced products. These metrics can help the enterprise evaluate the quality of the product and problems in the production process, discover bottlenecks and problems in the production process, and formulate corresponding improvement measures.
Logistics data: including material supply, inventory and material consumption. The material supply refers to the quantity and quality of material provided by the supplier, the stock quantity refers to the quantity of material stored in the enterprise, and the material consumption refers to the quantity of material consumed in the production process. These metrics can help enterprises optimize logistics management and reduce inventory wastage, discover material shortages and supply chain problems, and formulate corresponding improvement measures.
Human resource data: including working time, employee efficiency, and employee attendance. The working time length refers to the working time length of the staff, the staff efficiency refers to the workload completed in the staff unit time, and the staff attendance refers to the attendance condition of the staff. The indexes can help enterprises evaluate the work performance of staff and manage human resources, discover human resource problems and formulate corresponding improvement measures.
Environmental data: including temperature, humidity and air quality. The indexes can help enterprises monitor the safety and stability of the production environment, discover environmental problems and formulate corresponding improvement measures so as to ensure the stability of the production process and the safety of staff.
In summary, the data index in the production process can provide real-time, comprehensive and accurate production process data for enterprises, help the enterprises to know the bottleneck and the problem in the production process, formulate corresponding improvement measures, optimize the production process, reduce the cost, improve the production efficiency and the quality, and provide higher competitiveness and sustainable development for the enterprises.
Further, the data processing includes, data cleansing: unnecessary data is removed, invalid, repeated and missing through data cleaning, and reliable and accurate data is reserved so as to improve the quality and usability of the data;
data conversion: the collected original data is converted, a digital signal or an analog signal is converted into a data format which can be identified by a computer, or different data types are subjected to uniform format conversion so as to process and analyze the data.
In the present embodiment, the following is described. Unnecessary data is removed, invalid, repeated and missing through data cleaning, and reliable and accurate data is reserved, so that the data quality and usability are improved. The data cleaning can help enterprises filter out invalid data and noise data, and avoid interference to subsequent data processing and analysis. For example, duplicate data, missing data, abnormal data, etc. in the data can be removed, and reliable data can be reserved to improve data quality and usability.
The collected original data is converted, a digital signal or an analog signal is converted into a data format which can be identified by a computer, or different data types are subjected to uniform format conversion so as to process and analyze the data. Data conversion may help businesses convert raw data into data that can be analyzed and visualized for data analysis and decision making. For example, analog signals collected by the sensor device may be converted to digital signals, or different data formats may be converted to a unified data format to facilitate processing and analysis of the data.
The data processing is one of key steps in the digital lean diagnosis method, can help enterprises to improve data quality and usability, and provides reliable data support for subsequent data analysis and decision. Data cleansing and data transformation are two important steps in data processing, requiring careful design and implementation to ensure accuracy and availability of data.
Further, the model establishment includes feature selection of data after data processing, and before the model establishment, data features need to be selected and extracted to determine input variables and output variables of the model, namely, a model establishment target and a model establishment method; selecting a proper modeling method and tool according to the data characteristics and the predicted requirements; after the modeling methods and tools are determined, the model needs to be trained and tested to verify the accuracy and usability of the model; evaluating the performance and reliability of the model through the model evaluation index, and adjusting and optimizing the model; and (3) applying the established model to the production process, and carrying out prediction and trend analysis on the production data to find problems and potential risks in the production process, thereby providing basis for management decisions.
In the present embodiment, the following is described. Data feature selection: prior to modeling, data features need to be selected and extracted to determine the input and output variables of the model. The data feature selection can help enterprises determine the most useful data variables, reduce data noise and redundancy, and improve the accuracy and usability of the model.
Modeling method and tool selection: based on the data characteristics and the predicted requirements, a suitable modeling method and tool are selected. The modeling method and tool selection can be flexibly adjusted according to the specific requirements of enterprises so as to ensure the accuracy and usability of the model.
Model training and testing: after the modeling methods and tools are determined, the model needs to be trained and tested to verify the accuracy and usability of the model. Model training and testing can help enterprises evaluate the performance and reliability of models and discover problems and bottlenecks that exist with models.
Model evaluation and adjustment: and evaluating the performance and reliability of the model through the model evaluation index, and adjusting and optimizing the model. Model evaluation and adjustment can help enterprises further improve accuracy and usability of the model, find potential problems and bottlenecks, and provide more accurate data support for management decisions.
Model application: and (3) applying the established model to the production process, and carrying out prediction and trend analysis on the production data to find problems and potential risks in the production process, thereby providing basis for management decisions. The model application can help enterprises to realize lean production and lean management, improve production efficiency and quality, and reduce cost and risk.
The enterprise is helped to establish a reliable prediction model and a trend analysis model, and accurate data support is provided for management decisions. Data feature selection, modeling methods and tools selection, model training and testing, model evaluation and tuning, and model application are several important steps in model building, requiring careful design and implementation to ensure accuracy and usability of the model.
Further, the modeling method comprises regression analysis, a neural network and a decision tree, and a prediction model and a trend analysis model are established.
In this embodiment, regression analysis, a neural network, and a modeling method of a decision tree are used to build a prediction model and a trend analysis model.
Regression analysis, among other things, is a statistical method for building predictive models that predicts the value of one or more dependent variables by modeling the relationship between the variables. The regression analysis can select different regression models such as linear regression, multiple regression, logistic regression and the like according to different data types and model requirements so as to predict problems and potential risks in the production process.
Neural networks are artificial intelligence algorithms for building predictive models that predict the values of one or more dependent variables by training and learning the data to find complex relationships between the variables. The neural network may select different network structures and algorithms according to different data types and model requirements to predict problems and potential risks in the production process.
The decision tree is a machine learning algorithm for establishing a trend analysis model, which predicts future development trend by classifying and dividing data, finding the relation between variables. The decision tree may select different partitioning criteria and algorithms to predict trends and changes in the production process based on different data types and model requirements.
In this embodiment, regression analysis, neural networks, and decision trees are used as modeling methods for building prediction models and trend analysis models. The methods can be flexibly adjusted according to different data types and model requirements so as to ensure the accuracy and usability of the model. In practical applications, selection and optimization are required according to the specific conditions of enterprises so as to maximize the benefit and value of the model.
The previous description of the embodiments is provided to facilitate a person of ordinary skill in the art in order to make and use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles described herein may be applied to other embodiments without the use of the inventive faculty. Therefore, the present invention is not limited to the above-described embodiments. It will be understood by those skilled in the art that the foregoing and various other changes, modifications and variations can be made in the present invention without departing from the spirit and scope of the invention, and it is intended that the invention is limited only to the preferred embodiments of the invention.
Claims (5)
1. A digital lean diagnosis method for a lean production control platform is characterized by comprising the following steps: and (3) data acquisition: collecting data in the production process through sensor equipment;
and (3) data processing: uploading the acquired data to a data warehouse, and cleaning, processing and analyzing the data to find potential problems and rules in the data;
and (3) establishing a model: selecting proper modeling methods and tools according to data characteristics and requirements, establishing a prediction model and a trend analysis model, and predicting problems in the production process;
and (3) real-time monitoring: the production process is monitored in real time in a data visualization, report form and early warning mode, and abnormal production conditions are found in time to perform early warning and reminding;
analysis improvement: according to the model prediction and real-time monitoring results, analyzing problems and bottlenecks existing in the production process, providing improvement measures, optimizing the production flow, and reducing production waste, unexpected shutdown waste, defective rate and inventory waste;
continuous improvement: according to the effect of the improvement measures, the production flow and the quality management system are continuously adjusted and perfected, and continuous improvement and optimization are realized.
2. The digital lean diagnosis method of the lean production control platform according to claim 1, wherein the method is characterized by comprising the following steps of: the data in the production process comprises:
production efficiency data: production speed, yield, production cycle and production capacity utilization rate are used for measuring production efficiency and production capacity;
device status data: the equipment running state, the equipment on-off time and the equipment maintenance time are used for knowing the running condition and the maintenance condition of the equipment;
quality data: the product percent of pass, defective rate and rework rate are used for evaluating the quality of products and the problems in the production process;
logistics data: material supply, stock quantity and material consumption for optimizing logistics management and reducing stock waste;
human resource data: the working time length, the staff efficiency and the staff attendance are used for evaluating the working performance of staff and managing human resources;
environmental data: temperature, humidity and air quality for monitoring the safety and stability of the production environment.
3. The digital lean diagnosis method of the lean production control platform according to claim 2, wherein the method is characterized by comprising the following steps of: the data processing comprises the steps of data cleaning: unnecessary data is removed, invalid, repeated and missing through data cleaning, and reliable and accurate data is reserved so as to improve the quality and usability of the data;
data conversion: the collected original data is converted, a digital signal or an analog signal is converted into a data format which can be identified by a computer, or different data types are subjected to uniform format conversion so as to process and analyze the data.
4. The digital lean diagnosis method of the lean production control platform according to claim 3, wherein the method comprises the following steps: the model establishment comprises the steps of carrying out feature selection by adopting data after data processing, and selecting and extracting data features before establishing the model so as to determine input variables and output variables of the model, namely, an object and a method for establishing the model; selecting a proper modeling method and tool according to the data characteristics and the predicted requirements; after the modeling methods and tools are determined, the model needs to be trained and tested to verify the accuracy and usability of the model; evaluating the performance and reliability of the model through the model evaluation index, and adjusting and optimizing the model; and (3) applying the established model to the production process, and carrying out prediction and trend analysis on the production data to find problems and potential risks in the production process, thereby providing basis for management decisions.
5. The digital lean diagnosis method of the lean production control platform according to claim 3, wherein the method comprises the following steps: the modeling method comprises regression analysis, a neural network and a decision tree, and a prediction model and a trend analysis model are established.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310499057.XA CN116483042A (en) | 2023-05-06 | 2023-05-06 | Digital lean diagnosis method for lean production control platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310499057.XA CN116483042A (en) | 2023-05-06 | 2023-05-06 | Digital lean diagnosis method for lean production control platform |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116483042A true CN116483042A (en) | 2023-07-25 |
Family
ID=87219357
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310499057.XA Pending CN116483042A (en) | 2023-05-06 | 2023-05-06 | Digital lean diagnosis method for lean production control platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116483042A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117389236A (en) * | 2023-12-11 | 2024-01-12 | 山东三岳化工有限公司 | Propylene oxide production process optimization method and system |
-
2023
- 2023-05-06 CN CN202310499057.XA patent/CN116483042A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117389236A (en) * | 2023-12-11 | 2024-01-12 | 山东三岳化工有限公司 | Propylene oxide production process optimization method and system |
CN117389236B (en) * | 2023-12-11 | 2024-02-13 | 山东三岳化工有限公司 | Propylene oxide production process optimization method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109886430B (en) | Equipment health state assessment and prediction method based on industrial big data | |
Wang et al. | Event-driven tool condition monitoring methodology considering tool life prediction based on industrial internet | |
CN112085261B (en) | Enterprise production status diagnosis method based on cloud fusion and digital twin technology | |
Liu et al. | Manufacturing system maintenance based on dynamic programming model with prognostics information | |
KR20180056900A (en) | Method for production control system using processing mining | |
Wang et al. | Innovative smart scheduling and predictive maintenance techniques | |
CN113760625B (en) | Evaluation method and monitoring system for model predictive controller performance | |
CN117389236B (en) | Propylene oxide production process optimization method and system | |
CN116483042A (en) | Digital lean diagnosis method for lean production control platform | |
Ungermann et al. | Data analytics for manufacturing systems–a data-driven approach for process optimization | |
CN110757510A (en) | Method and system for predicting remaining life of robot | |
CN116224947B (en) | Deep learning industrial control system capable of actively integrating domain rule knowledge | |
CN115526375A (en) | Space flight equipment predictive maintenance system | |
CN117194919A (en) | Production data analysis system | |
CN117393076B (en) | Intelligent monitoring method and system for heat-resistant epoxy resin production process | |
CN115114856A (en) | Intelligent manufacturing production line operation system based on digital twin | |
Li et al. | Integrated predictive maintenance approach for multistate manufacturing system considering geometric and non-geometric defects of products | |
KR102474332B1 (en) | Prediction method of machine health stability in smart factory system, and recording medium thereof | |
CN110794799A (en) | Big data system with fault diagnosis function applied to industrial production | |
Huang et al. | Tool remaining useful life prediction based on edge data processing and lstm recurrent neural network | |
CN115640980A (en) | Power grid engineering cost dynamic management system based on target control | |
Sharma et al. | Implementing Big Data Analytics and Machine Learning for Predictive Maintenance in Manufacturing Facilities in South Korea | |
Sadiki et al. | Intelligent sensor impact on predictive maintenance program costs | |
CN117234785B (en) | Centralized control platform error analysis system based on artificial intelligence self-query | |
TWM563108U (en) | Intelligent power management and self quality control 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 |