A method and system for analyzing efficiency of can production line

Abstract

The present invention discloses an efficiency analysis method and system for a canning production line, and relates to the field of data analysis technology. The method comprises: collecting production line data to construct a production data set; preprocessing the data in the production data set; constructing a bottleneck identification model, a comprehensive equipment efficiency model and a process analysis model based on the preprocessed production data set; performing bottleneck identification, multi-dimensional efficiency analysis and full process efficiency analysis of the production line based on the above models, and generating corresponding optimization decisions; performing analysis and evaluation based on big data; and establishing a production line monitoring system to monitor and track various indicators of the production line in real time. The present invention systematically evaluates and optimizes the canning production line through a variety of analysis methods, can deeply understand the operation status of the production line and discover potential inefficient links, improve production efficiency, reduce production costs and ensure product quality by optimizing the operation of equipment, thereby enhancing market competitiveness.

Description

Technical Field

[0001] The invention belongs to the technical field of data analysis, and in particular relates to an efficiency analysis method and system for a canning production line. Background Art

[0002] In modern manufacturing, with the continuous improvement of production automation level and the increasing complexity of production processes, how to improve the overall efficiency of the production line has become the focus of major companies' continuous attention. The canning production line usually consists of multiple processes, covering multiple links such as metal sheet stamping, forming, welding, painting, testing, and packaging. The production process involves a large number of mechanical equipment and automation systems, such as stamping machines, forming machines, welding equipment, paint spraying systems, etc. These equipment are under high load and high speed working environment. Performance problems in any link may lead to a decrease in production efficiency or fluctuations in product quality. Therefore, for the efficiency analysis of the canning production line, it is necessary to comprehensively consider multiple factors such as equipment, personnel, and process flow, and conduct comprehensive and dynamic evaluation and optimization. Since the canning production line is a key industrial manufacturing system, its efficiency is directly related to production costs, delivery cycles, and product quality. Therefore, improving the efficiency of the canning production line is one of the core tasks of optimizing production processes and enhancing corporate competitiveness.

[0003] At present, the efficiency analysis method of canning production lines usually adopts the traditional method of regular inspection and manual recording. This method has many shortcomings, such as untimely data collection, single analysis method, inability to fully reflect production bottlenecks and lack of intelligent analysis. Therefore, in order to improve the efficiency of canning production lines, enterprises urgently need an efficient efficiency analysis method that can monitor in real time, intelligently analyze and provide decision support. Summary of the invention

[0004] The object of the present invention is to provide an efficiency analysis method and system for a canning production line, which can be achieved by the following technical solutions: In a first aspect, an embodiment of the present application provides an efficiency analysis method for a canning production line, comprising the following steps: Collect production line data, production equipment parameters, and production process data of each process in the production line at each stage of the production process and use them to build a production data set; Preprocessing the data in the production data set; A bottleneck analysis method is used to build a bottleneck identification model based on the preprocessed production data set; a comprehensive equipment efficiency analysis method is used to build a comprehensive equipment efficiency model based on the preprocessed production data set; a time analysis method is used to build a process analysis model based on the preprocessed production data set; Based on the bottleneck identification model, bottleneck identification is performed and bottleneck optimization decisions are generated; based on the comprehensive equipment efficiency model, multi-dimensional efficiency analysis is performed and efficiency optimization decisions are generated; based on the process analysis model, full process efficiency analysis of the production line is performed and process optimization decisions are generated; Analyze and evaluate the production efficiency of can production lines based on big data; Establish a production line monitoring system and monitor and track various production line indicators in real time; adjust the production line operation mode and optimize production scheduling, equipment utilization and process flow based on real-time monitoring data and analysis feedback results.

[0005] Preferably, the production line data includes production line start-up time, fault frequency and process parameters; the production equipment parameters include equipment operating status, equipment operating speed, equipment operating time, and downtime; the production process data includes working time, total production time, output, production rate and production quality. Preferably, the preprocessing includes data cleaning, data smoothing, outlier correction, data standardization, and duplicate and missing value processing.

[0006] Preferably, constructing the bottleneck identification model includes: Determine the goals of bottleneck identification, including increasing production capacity, balancing the capacity of different processes, improving equipment utilization, reducing waiting time, and reducing downtime; Select statistical analysis and machine learning as bottleneck analysis methods; Model training is performed based on the preprocessed production data set, and the effectiveness of the model is verified through cross-validation; Output the validated model as a bottleneck identification model; The bottleneck identification model is used to perform real-time or periodic bottleneck detection on the production line, so as to identify bottleneck equipment or bottleneck links in the production process. Preferably, constructing the comprehensive equipment efficiency model includes: Define the three dimensions of the OEE framework, including equipment availability, performance efficiency, and quality rate; The OEE index is obtained based on the preprocessed production data set, and the OEE index is expressed as: OEE = A × P × Q; Among them, A represents equipment availability; P represents performance efficiency; Q represents quality rate; forming the comprehensive equipment efficiency model based on the OEE indicator; Acquire real-time equipment data and real-time process data and calculate the OEE value based on the comprehensive equipment efficiency model; Optimizing the comprehensive equipment efficiency model based on the OEE value; The comprehensive equipment efficiency model is used to evaluate the overall health status of production equipment and perform predictive maintenance on the production equipment.

[0007] Preferably, in the OEE indicator, the equipment availability is the ratio of the actual equipment operation time to the planned operation time, expressed as: ; The performance efficiency is the ratio of the actual production rate of the equipment to the theoretical maximum rate, expressed as: ; The quality rate is the ratio of the number of qualified products to the total production quantity, expressed as: . Preferably, constructing the process analysis model includes: Define process time, including actual process time, standard time and efficiency deviation; Analyze the time relationship between different processes, including waiting time between processes and process handover time; Calculate process efficiency based on actual process time and standard process time; By analyzing the time data of each process, we can identify the bottleneck process that takes a long time. Building the process analysis model based on the process time, the process efficiency and the bottleneck process; The process analysis model is used to prioritize each process according to its time consumption and identify the processes that affect the production line; it is also used to reduce waiting time and idle time by optimizing the sequence or handover method of the processes, thereby optimizing the production line.

[0008] Preferably, the analysis and evaluation of the production efficiency of the canning production line based on big data includes: In the canning production line, the expected input index of a product is counted, and the operation data of the production line is grouped according to time to construct a matrix image; The abnormal point is obtained according to the grayscale information contained in the matrix image, the detection abnormal value of the column where the abnormal point is located is calculated according to the grayscale calculation information of the abnormal point and the column number, the detection abnormal point is obtained according to the detection abnormal value, and the error stop time is obtained by the influence of the detection abnormal point on time, wherein the time when the detection abnormal point is counted is recorded as the detection time, the time when the production line is restored is recorded as the recovery time, and the error stop time is the stop time obtained by subtracting the detection time from the recovery time; Each product is represented by multiple product quality indicators, and multiple products are sampled. The component weights are obtained according to the product quantity and product quality indicators. The defect degree value of the product is calculated by comparing the product quality indicators, the mean of each product quality indicator and the component weights. Defective products are detected using the defect degree value, and the product defect probability is obtained according to the ratio of the number of defective products to all products. The collected product quantity is corrected according to the error downtime of the production line and the product defect probability of the product, and the total number of cans produced of the product is calculated; The calculated total number of cans produced is used as the expected output index, and the production efficiency evaluation result of the product is obtained according to the expected input index and the expected output index; The production efficiency of the canning production line is judged based on the production efficiency evaluation results. Preferably, obtaining the abnormal point according to the grayscale information contained in the matrix image includes: A first difference between a maximum pixel value and a minimum pixel value in a matrix image is obtained. When the first difference is greater than a first preset threshold, a second difference between the pixel values ​​of two adjacent pixels in each row of the matrix image is obtained. All pixels on the row where the two adjacent pixels are located and whose horizontal coordinates are smaller than the two adjacent pixels are obtained in the matrix image. A first mean of the differences between the pixel values ​​of all the pixels is calculated, and an abnormal point is obtained according to the second difference and the first mean.

[0009] In a second aspect, an embodiment of the present application provides an efficiency analysis system for a can production line, applying the efficiency analysis method as described above, including: Data collection module: collects production line data, production equipment parameters, and production process data of each process in the production line in each link of the production process and constructs a production data set based on this; Data processing module: pre-processing the production line data, the production equipment parameters and the production process data respectively; Model building module: adopt bottleneck analysis method and build bottleneck identification model based on pre-processed production line data; adopt comprehensive equipment efficiency analysis method and build comprehensive equipment efficiency model based on pre-processed production equipment parameters and production process data; adopt time analysis method and build process analysis model based on pre-processed production process data; Efficiency optimization module: performs bottleneck identification based on the bottleneck identification model and generates bottleneck optimization decisions; performs multi-dimensional efficiency analysis based on the comprehensive equipment efficiency model and generates efficiency optimization decisions; performs full process efficiency analysis of the production line based on the process analysis model and generates process optimization decisions; Efficiency evaluation module: Analyze and evaluate the production efficiency of the can production line based on big data; Monitoring and feedback module: Establish a production line monitoring system and monitor and track various indicators of the production line in real time; adjust the production line operation mode and optimize production scheduling, equipment utilization and process flow based on real-time monitoring data and analysis feedback results.

[0010] The beneficial effects of the present invention are as follows: the present invention uses a variety of analysis methods and data collection technologies to conduct systematic evaluation and optimization, covering the entire process from data collection, efficiency analysis to bottleneck identification and production optimization. Through the above steps, enterprises can gain an in-depth understanding of the operation status of the production line, discover potential inefficient links, and improve production efficiency, reduce production costs, and ensure product quality by optimizing equipment operation, improving the quality of the production process, reducing waste and downtime, and proposing feasible optimization plans, thereby enhancing market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] For better understanding and implementation, the technical solution of the present application is described in detail below with reference to the accompanying drawings.

[0012] Figure 1 A flowchart of a method for analyzing the efficiency of a can production line provided in an embodiment of the present application; Figure 2 A flowchart of the steps for constructing a bottleneck identification model provided in an embodiment of the present application; Figure 3 A flowchart of the steps of constructing a process analysis model provided in an embodiment of the present application; Figure 4 A structural flow chart of an efficiency analysis system for a canning production line provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] In order to further explain the technical means and effects taken by the present invention to achieve the predetermined invention purpose, exemplary embodiments will be described in detail here, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of methods and systems consistent with some aspects of the present application as detailed in the attached claims.

[0014] The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in this article refers to any or all possible combinations of one or more associated listed items.

[0015] The specific implementation methods, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0016] Example 1 See also Figure 1The present application embodiment provides an efficiency analysis method for a can production line, comprising the following steps: Collect production line data, production equipment parameters, and production process data of each process in the production line at each stage of the production process and use them to build a production data set; Preprocessing the data in the production data set; A bottleneck analysis method is used to build a bottleneck identification model based on the preprocessed production data set; a comprehensive equipment efficiency analysis method is used to build a comprehensive equipment efficiency model based on the preprocessed production data set; a time analysis method is used to build a process analysis model based on the preprocessed production data set; Based on the bottleneck identification model, bottleneck identification is performed and bottleneck optimization decisions are generated; based on the comprehensive equipment efficiency model, multi-dimensional efficiency analysis is performed and efficiency optimization decisions are generated; based on the process analysis model, full process efficiency analysis of the production line is performed and process optimization decisions are generated; Analyze and evaluate the production efficiency of can production lines based on big data; Establish a production line monitoring system and monitor and track various production line indicators in real time; adjust the production line operation mode and optimize production scheduling, equipment utilization and process flow based on real-time monitoring data and analysis feedback results.

[0017] Specifically, since the efficiency analysis methods of canning production lines in the prior art usually adopt traditional periodic inspections and manual recording methods, these methods often have the following limitations: untimely data collection: traditional analysis methods rely on manual recording, and there is a lag in data collection, making it difficult to achieve real-time monitoring and response; single analysis means: existing efficiency analysis mostly focuses on the performance evaluation of a single link, such as equipment failure rate, output statistics, etc., and lacks a comprehensive analysis of the production line as a whole; unable to fully reflect production bottlenecks: traditional methods find it difficult to track the coordination and bottlenecks between processes in real time, and are unable to provide accurate bottleneck identification and improvement measures; lack of intelligent analysis: with the continuous development of production technology, traditional analysis methods can no longer make full use of technologies such as big data and artificial intelligence, and are unable to provide dynamic and intelligent decision support; therefore, in order to solve the above problems and improve the efficiency of the canning production line, the present application provides an efficient method that can monitor in real time, perform intelligent analysis, and provide decision support, the specific contents of which include: first, collecting production line data from each link in the production process; and production equipment parameters, as well as the production process data of each process in the production line; then the production line data, the production equipment parameters and the production process data are preprocessed respectively; then the bottleneck analysis method is adopted and a bottleneck identification model is constructed based on the preprocessed production line data; the comprehensive equipment efficiency analysis method is adopted and a comprehensive equipment efficiency model is constructed based on the preprocessed production equipment parameters; the time analysis method is adopted and a process analysis model is constructed based on the preprocessed production process data; then bottleneck identification is performed based on the bottleneck identification model and bottleneck optimization decisions are generated; multi-dimensional efficiency analysis is performed based on the comprehensive equipment efficiency model and efficiency optimization decisions are generated; full process efficiency analysis of the production line is performed based on the process analysis model and process optimization decisions are generated; then the production efficiency of the canning production line is analyzed and evaluated based on big data; finally, a production line monitoring system is established and various indicators of the production line are monitored and tracked in real time; according to the real-time monitoring data and analysis feedback results, the production line operation mode is adjusted and production scheduling, equipment utilization and process flow are optimized. This application uses a variety of analysis methods and data acquisition technologies to conduct systematic evaluation and optimization, covering the entire process from data acquisition, efficiency analysis to bottleneck identification and production optimization. Through the above steps, enterprises can gain in-depth understanding of the operation status of the production line, discover potential inefficient links, and enhance market competitiveness by optimizing equipment operation, improving the quality of the production process, reducing waste and downtime, and proposing practical optimization plans, thereby improving production efficiency, reducing production costs and ensuring product quality.

[0018] In an embodiment provided in the present application, the production line data includes production line startup time, fault frequency and process parameters; the production equipment parameters include equipment operating status, equipment operating speed, equipment operating time, and downtime; the production process data includes working time, total production time, output, production rate and production quality.

[0019] In an embodiment provided in the present application, the preprocessing includes data cleaning, data smoothing, outlier correction, data standardization, and duplicate and missing value processing.

[0020] Specifically, data preprocessing includes data cleaning, data smoothing, outlier correction, data standardization, duplicate and missing value processing, etc. Through these preprocessing steps, noise can be effectively removed, data quality can be improved, and an accurate and reliable data foundation can be provided for subsequent data analysis, modeling and optimization.

[0021] like Figure 2 As shown, in one embodiment provided in the present application, constructing the bottleneck identification model includes: Determine the goals of bottleneck identification, including increasing production capacity, balancing the capacity of different processes, improving equipment utilization, reducing waiting time, and reducing downtime; Select statistical analysis and machine learning as bottleneck analysis methods; Model training is performed based on the preprocessed production data set, and the effectiveness of the model is verified through cross-validation; Output the validated model as a bottleneck identification model; The bottleneck identification model is used to perform real-time or periodic bottleneck detection on the production line, so as to identify bottleneck equipment or bottleneck links in the production process.

[0022] Specifically, this embodiment builds a bottleneck identification model based on preprocessed production line data, which is a systematic work, including data preprocessing, bottleneck analysis method selection, bottleneck target setting, model establishment and training, bottleneck detection and continuous feedback, etc. Through scientific bottleneck identification and optimization methods, the overall efficiency of the production line can be effectively improved, costs can be reduced, and product quality can be improved.

[0023] In an embodiment provided in the present application, constructing the comprehensive equipment efficiency model includes: Define the three dimensions of the OEE framework, including equipment availability, performance efficiency, and quality rate; The OEE index is obtained based on the preprocessed production data set, and the OEE index is expressed as: OEE = A × P × Q; Among them, A represents equipment availability; P represents performance efficiency; Q represents quality rate; forming the comprehensive equipment efficiency model based on the OEE indicator; Acquire real-time equipment data and real-time process data and calculate the OEE value based on the comprehensive equipment efficiency model; Optimizing the comprehensive equipment efficiency model based on the OEE value; The comprehensive equipment efficiency model is used to evaluate the overall health status of production equipment and perform predictive maintenance on the production equipment.

[0024] In an embodiment provided in the present application, in the OEE indicator, the equipment availability is the ratio of the actual operating time of the equipment to the planned operating time, expressed as: ; The performance efficiency is the ratio of the actual production rate of the equipment to the theoretical maximum rate, expressed as: ; The quality rate is the ratio of the number of qualified products to the total production quantity, expressed as: .

[0025] Specifically, based on the above model, this embodiment uses sensors and equipment management systems to monitor the status of equipment in real time, obtain data such as operating time, downtime, production rate, and dynamically calculate the OEE value; evaluate the overall health of the equipment through the OEE model, and perform predictive maintenance on the equipment. For example, based on the trend of historical OEE data analysis, it predicts when the equipment may encounter bottlenecks or failures, and prepares for maintenance in advance. Bottleneck link identification: The OEE model combined with the bottleneck identification model can help identify bottleneck equipment or links in the production process. Usually, equipment with low OEE values ​​may be the bottleneck; by regularly evaluating OEE, inefficient links in the equipment can be effectively discovered and improved. Through the above content, enterprises can comprehensively evaluate the production efficiency of equipment, improve equipment utilization, reduce production costs, and achieve continuous improvement of the production process.

[0026] like Figure 3 As shown, in one embodiment provided in the present application, constructing the process analysis model includes: Define process time, including actual process time, standard time and efficiency deviation; Analyze the time relationship between different processes, including waiting time between processes and process handover time; Calculate process efficiency based on actual process time and standard process time; By analyzing the time data of each process, we can identify the bottleneck process that takes a long time. Building the process analysis model based on the process time, the process efficiency and the bottleneck process; The process analysis model is used to prioritize each process according to its time consumption and identify the processes that affect the production line; it is also used to reduce waiting time and idle time by optimizing the sequence or handover method of the processes, thereby optimizing the production line.

[0027] Specifically, this embodiment prioritizes processes based on time consumption: prioritize each process based on its time consumption, identify processes that have a greater impact on the production process, and take optimization measures for these processes (such as increasing manpower, improving equipment efficiency, shortening waiting time, etc.); optimize the order and handover method of the processes, reduce waiting time and idle time, and optimize the production process, for example, use parallel operations, parallel processing, etc. to shorten the overall production cycle; focus on the management of bottleneck processes, adopt reasonable scheduling and dispatching methods, reduce the impact of bottlenecks, and improve overall production efficiency. Through the above process analysis model, enterprises can gain an in-depth understanding of the time consumption of production processes, identify production bottlenecks, optimize resource allocation, and improve production efficiency.

[0028] In one embodiment provided in the present application, the analysis and evaluation of the production efficiency of the can production line based on big data includes: In the canning production line, the expected input index of a product is counted, and the operation data of the production line is grouped according to time to construct a matrix image; The abnormal point is obtained according to the grayscale information contained in the matrix image, the detection abnormal value of the column where the abnormal point is located is calculated according to the grayscale calculation information of the abnormal point and the column number, the detection abnormal point is obtained according to the detection abnormal value, and the error stop time is obtained by the influence of the detection abnormal point on time, wherein the time when the detection abnormal point is counted is recorded as the detection time, the time when the production line is restored is recorded as the recovery time, and the error stop time is the stop time obtained by subtracting the detection time from the recovery time; Each product is represented by multiple product quality indicators, and multiple products are sampled. The component weights are obtained according to the product quantity and product quality indicators. The defect degree value of the product is calculated by comparing the product quality indicators, the mean of each product quality indicator and the component weights. Defective products are detected using the defect degree value, and the product defect probability is obtained according to the ratio of the number of defective products to all products. The collected product quantity is corrected according to the error downtime of the production line and the product defect probability of the product, and the total number of cans produced of the product is calculated; The calculated total number of cans produced is used as the expected output index, and the production efficiency evaluation result of the product is obtained according to the expected input index and the expected output index; The production efficiency of the canning production line is judged based on the production efficiency evaluation results.

[0029] In an embodiment provided in the present application, obtaining an outlier point according to grayscale information contained in a matrix image includes: A first difference between a maximum pixel value and a minimum pixel value in a matrix image is obtained. When the first difference is greater than a first preset threshold, a second difference between the pixel values ​​of two adjacent pixels in each row of the matrix image is obtained. All pixels on the row where the two adjacent pixels are located and whose horizontal coordinates are smaller than the two adjacent pixels are obtained in the matrix image. A first mean of the differences between the pixel values ​​of all the pixels is calculated, and an abnormal point is obtained according to the second difference and the first mean.

[0030] Specifically, this embodiment corrects the production volume according to the production line error and the defect probability of the product, so that the expected output target is more accurate, and the production efficiency calculated thereby is also more accurate. With regard to the production volume, when an abnormality occurs in the equipment, it will affect the statistics of the final production volume, but the abnormality of the detection equipment should not affect the production volume, but it will also be affected by the production volume, so the production volume is corrected according to the error downtime of this part of the calculation to improve the accuracy. Defective products will be included in the statistical production volume, and defective products cannot be used in the calculation of production efficiency, so the defect probability of the product is calculated to correct the production volume and increase the accuracy of the production volume.

[0031] Example 2 See also Figure 4 The present application embodiment provides an efficiency analysis system for a can production line, which uses the efficiency analysis method described above, including: Data collection module: collects production line data, production equipment parameters, and production process data of each process in the production line in each link of the production process and constructs a production data set based on this; Data processing module: pre-processing the production line data, the production equipment parameters and the production process data respectively; Model building module: adopt bottleneck analysis method and build bottleneck identification model based on preprocessed production data set; adopt comprehensive equipment efficiency analysis method and build comprehensive equipment efficiency model based on preprocessed production data set; adopt time analysis method and build process analysis model based on preprocessed production data set; Efficiency optimization module: performs bottleneck identification based on the bottleneck identification model and generates bottleneck optimization decisions; performs multi-dimensional efficiency analysis based on the comprehensive equipment efficiency model and generates efficiency optimization decisions; performs full process efficiency analysis of the production line based on the process analysis model and generates process optimization decisions; Efficiency evaluation module: Analyze and evaluate the production efficiency of the can production line based on big data; Monitoring and feedback module: Establish a production line monitoring system and monitor and track various indicators of the production line in real time; adjust the production line operation mode and optimize production scheduling, equipment utilization and process flow based on real-time monitoring data and analysis feedback results.

[0032] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0033] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0034] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0035] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. An efficiency analysis method for a can production line, characterized in that: The steps include: Collect production line data, production equipment parameters, and production process data of each process in the production line at each stage of the production process and use them to build a production data set; Preprocessing the data in the production data set; Adopt bottleneck analysis method and build bottleneck identification model based on preprocessed production data set; A comprehensive equipment efficiency analysis method is used to build a comprehensive equipment efficiency model based on the preprocessed production data set; a time analysis method is used to build a process analysis model based on the preprocessed production data set; Perform bottleneck identification based on the bottleneck identification model and generate bottleneck optimization decisions; Based on the comprehensive equipment efficiency model, a multi-dimensional efficiency analysis is performed and an efficiency optimization decision is generated; based on the process analysis model, an overall process efficiency analysis of the production line is performed and a process optimization decision is generated; Analyze and evaluate the production efficiency of can production lines based on big data; Establish a production line monitoring system and monitor and track various production line indicators in real time; adjust the production line operation mode and optimize production scheduling, equipment utilization and process flow based on real-time monitoring data and analysis feedback results.

2. The efficiency analysis method for a can production line according to claim 1, characterized in that: The production line data includes production line startup time, fault frequency and process parameters; the production equipment parameters include equipment operating status, equipment operating speed, equipment operating time, and downtime; the production process data includes working time, total production time, output, production rate and production quality.

3. The efficiency analysis method for a can production line according to claim 1, characterized in that: The preprocessing includes data cleaning, data smoothing, outlier correction, data standardization, and duplicate and missing value processing.

4. The efficiency analysis method for a can production line according to claim 1, characterized in that: Constructing the bottleneck identification model includes: Determine the goals of bottleneck identification, including increasing production capacity, balancing the capacity of different processes, improving equipment utilization, reducing waiting time, and reducing downtime; Select statistical analysis and machine learning as bottleneck analysis methods; Model training is performed based on the preprocessed production data set, and the effectiveness of the model is verified through cross-validation; Output the validated model as a bottleneck identification model; The bottleneck identification model is used to perform real-time or periodic bottleneck detection on the production line, so as to identify bottleneck equipment or bottleneck links in the production process.

5. The efficiency analysis method for a can production line according to claim 1, characterized in that: Constructing the comprehensive equipment efficiency model includes: Define the three dimensions of the OEE framework, including equipment availability, performance efficiency, and quality rate; The OEE index is obtained based on the preprocessed production data set, and the OEE index is expressed as: OEE = A × P × Q; Among them, A represents equipment availability; P represents performance efficiency; Q represents quality rate; forming the comprehensive equipment efficiency model based on the OEE indicator; Acquire real-time equipment data and real-time process data and calculate the OEE value based on the comprehensive equipment efficiency model; Optimizing the comprehensive equipment efficiency model based on the OEE value; The comprehensive equipment efficiency model is used to evaluate the overall health status of production equipment and perform predictive maintenance on the production equipment.

6. The efficiency analysis method for a can production line according to claim 5, characterized in that: In the OEE indicator, the equipment availability is the ratio of the actual equipment operation time to the planned operation time, expressed as: ; The performance efficiency is the ratio of the actual production rate of the equipment to the theoretical maximum rate, expressed as: ; The quality rate is the ratio of the number of qualified products to the total production quantity, expressed as: .

7. The efficiency analysis method for a can production line according to claim 1, characterized in that: Constructing the process analysis model includes: Define process time, including actual process time, standard time and efficiency deviation; Analyze the time relationship between different processes, including waiting time between processes and process handover time; Calculate process efficiency based on actual process time and standard process time; By analyzing the time data of each process, we can identify the bottleneck process that takes a long time. Building the process analysis model based on the process time, the process efficiency and the bottleneck process; The process analysis model is used to prioritize each process according to its time consumption and identify the processes that affect the production line; it is also used to reduce waiting time and idle time by optimizing the sequence or handover method of the processes, thereby optimizing the production line.

8. The efficiency analysis method for a can production line according to claim 1, characterized in that: The analysis and evaluation of the production efficiency of the can production line based on big data includes: In the canning production line, the expected input index of a product is counted, and the operation data of the production line is grouped according to time to construct a matrix image; The abnormal point is obtained according to the grayscale information contained in the matrix image, the detection abnormal value of the column where the abnormal point is located is calculated according to the grayscale calculation information of the abnormal point and the column number, the detection abnormal point is obtained according to the detection abnormal value, and the error stop time is obtained by the influence of the detection abnormal point on time, wherein the time when the detection abnormal point is counted is recorded as the detection time, the time when the production line is restored is recorded as the recovery time, and the error stop time is the stop time obtained by subtracting the detection time from the recovery time; Each product is represented by multiple product quality indicators, and multiple products are sampled. The component weights are obtained according to the product quantity and product quality indicators. The defect degree value of the product is calculated by comparing the product quality indicators, the mean of each product quality indicator and the component weights. Defective products are detected using the defect degree value, and the product defect probability is obtained according to the ratio of the number of defective products to all products. The collected product quantity is corrected according to the error downtime of the production line and the product defect probability of the product, and the total number of cans produced of the product is calculated; The calculated total number of cans produced is used as the expected output index, and the production efficiency evaluation result of the product is obtained according to the expected input index and the expected output index; The production efficiency of the canning production line is judged based on the production efficiency evaluation results.

9. The efficiency analysis method for a can production line according to claim 1, characterized in that: The step of obtaining the abnormal point according to the grayscale information contained in the matrix image includes: Obtain a first difference between a maximum pixel value and a minimum pixel value in a matrix image. When the first difference is greater than a first preset threshold, obtain a second difference between the pixel values ​​of two adjacent pixels in each row of the matrix image. Obtain all pixel points on the row where the two adjacent pixels are located and whose horizontal coordinates are smaller than the two adjacent pixels in the matrix image. Calculate a first mean of the differences between the pixel values ​​of all the pixels, and obtain an abnormal point based on the second difference and the first mean.

10. An efficiency analysis system for a can production line, using the efficiency analysis method according to any one of claims 1 to 9, characterized in that: include: Data collection module: collects production line data, production equipment parameters, and production process data of each process in the production line in each link of the production process and constructs a production data set based on this; Data processing module: pre-processing the production line data, the production equipment parameters and the production process data respectively; Model building module: Use bottleneck analysis method to build bottleneck identification model based on preprocessed production line data; A comprehensive equipment efficiency analysis method is used to build a comprehensive equipment efficiency model based on pre-processed production equipment parameters and production process data; a time analysis method is used to build a process analysis model based on pre-processed production process data; Efficiency optimization module: performs bottleneck identification based on the bottleneck identification model and generates bottleneck optimization decisions; Based on the comprehensive equipment efficiency model, a multi-dimensional efficiency analysis is performed and an efficiency optimization decision is generated; based on the process analysis model, an overall process efficiency analysis of the production line is performed and a process optimization decision is generated; Efficiency evaluation module: Analyze and evaluate the production efficiency of the can production line based on big data; Monitoring and feedback module: Establish a production line monitoring system and monitor and track various indicators of the production line in real time; adjust the production line operation mode and optimize production scheduling, equipment utilization and process flow based on real-time monitoring data and analysis feedback results.

Images