A machining part production management method and system

Abstract

The present application is suitable for the field of manufacturing information technology, and provides a machining part production management method and system, a blade wear data sharing platform module, a wear data analysis and blade performance evaluation module, a cost control optimization strategy development module, and a knowledge sharing and decision support system module. Through the deployment of sensors and data acquisition systems and the development of an online platform, systematic collection and sharing of blade wear data are realized, data islands are broken, and data utilization efficiency is improved. By establishing a blade wear life model and a performance evaluation system using data on the sharing platform, scientific evaluation of blade performance is realized, and the accuracy of blade selection and replacement decisions is improved. By constructing a model of the relationship between blade wear and production cost, analyzing the impact of wear on cost, and developing optimization strategies, effective control of production cost is realized, and overall production cost is reduced.

Description

Technical Field

[0001] This invention belongs to the field of information technology in the manufacturing industry, and in particular relates to a method and system for production management of machined parts. Background Technology

[0002] The manufacturing industry is undergoing a digital transformation, with more and more companies adopting digital technologies such as the Internet of Things (IoT), big data analytics, cloud computing, and artificial intelligence (AI) to improve production efficiency, optimize supply chains, and enhance product quality. Smart manufacturing is one of the main trends in information technology within the manufacturing sector. By integrating advanced sensors, automated equipment, and intelligent systems, manufacturing companies can achieve intelligent production processes and equipment management. With technological advancements, information technology in manufacturing is constantly innovating. For example, the application of 5G technology enables faster data transmission speeds and lower latency, thereby supporting more complex industrial automation and smart manufacturing applications.

[0003] In traditional machining, tool wear data is often difficult to collect and share systematically, resulting in significant data silos between different equipment and factories, hindering efficient information flow and utilization. Without systematic data support, tool performance evaluation often relies on experience, lacking scientific basis, leading to inaccurate tool selection and replacement decisions. Tool procurement, use, and replacement account for a significant proportion of overall production costs, but the lack of systematic optimization strategies makes it difficult to effectively control these costs. Summary of the Invention

[0004] The purpose of this invention is to provide a method for production management of machined parts, which aims to solve the technical problems existing in the prior art as identified in the background art.

[0005] This invention is implemented as follows: a method for production management of machined parts, the method comprising:

[0006] The wear data of the cutting blades in the processing equipment is collected by sensors and uploaded to a sharing platform;

[0007] By utilizing data from a shared platform, the performance and durability of blades are evaluated based on wear data, a blade wear life model is established, and performance evaluations are conducted on blades of different brands and materials to generate an evaluation report.

[0008] Construct an optimized production cost model for blades to determine the relationship between blade wear and production costs. Analyze the impact of blade wear on costs. Based on the analysis results, formulate optimization strategies for blade procurement, use, and replacement. Integrate cost control strategies into the production management system, automate the execution of optimization strategies, and monitor the effectiveness of strategy execution.

[0009] Based on wear data analysis and cost control strategies, a knowledge base is built to provide users with decision-making suggestions on blade selection, procurement timing, and usage cycle.

[0010] As a further embodiment of the present invention, the step of collecting wear data of the cutting blade during the use of the processing equipment through sensors and uploading it to the sharing platform specifically includes:

[0011] Various types of sensors are installed on cutting tools to monitor their usage status and wear in real time. A data acquisition system is configured to convert the collected data into a unified format, and then the data is cleaned, standardized, and stored in a database.

[0012] The processed data is uploaded to the sharing platform periodically.

[0013] As a further aspect of the present invention, the method of utilizing data from a shared platform to evaluate the performance and durability of the blade based on wear data and establishing a blade wear life model specifically includes:

[0014] Wear data from a data sharing platform is centralized in a data warehouse, from which wear rate, wear type, and processing parameter characteristics are extracted.

[0015] A blade wear life model is established based on the data warehouse, the model is trained using the training set data, and the model parameters are adjusted.

[0016] As a further aspect of the present invention, the step of constructing a blade optimization production cost model relating blade wear to production costs, analyzing the impact of blade wear on costs, formulating optimization strategies for blade procurement, use, and replacement based on the analysis results, integrating cost control strategies into the production management system, automating the execution of optimization strategies, and monitoring the effectiveness of strategy execution, specifically includes:

[0017] By summarizing wear and cost data, and based on the data exploration results, we selected feature variables that are highly correlated with blade wear and cost. We then analyzed the correlation between the selected features and cost to identify cost drivers, analyzed the trend relationship between blade wear and cost, identified patterns of cost change, and constructed a blade optimization production cost model based on the analysis results.

[0018] Verify the accuracy and practicality of the results, assess the relationship between actual wear and cost, design strategies to optimize the procurement, use and replacement of cutting tools to reduce wear costs, evaluate the potential economic benefits of the designed strategies through simulation experiments, develop a detailed strategy implementation plan based on simulation results and strategy evaluation, integrate the implementation plan into the existing production management system, implement a strategy monitoring mechanism, track the strategy implementation results, and adjust the strategy and implementation plan based on feedback.

[0019] As a further aspect of the present invention, the construction of a knowledge base, which provides users with decision-making suggestions regarding blade selection, procurement timing, and usage cycle, specifically includes:

[0020] By integrating wear data, cost data, and blade performance evaluation results, decision rules are extracted from the data. The extracted rules and patterns are then structured, knowledge base content is encoded using appropriate data structures and storage technologies, and decision support tools are developed.

[0021] Monitor the performance of decision support tools, regularly collect user feedback on tool usage, and provide feedback based on the latest blade wear and cost control data, as well as usage and effectiveness.

[0022] Another object of the present invention is to provide a production management system for machined parts, the system comprising:

[0023] The blade wear data sharing platform module is used to collect wear data of the cutting blades of the processing equipment during use through sensors and upload it to the sharing platform;

[0024] The wear data analysis and blade performance evaluation module is used to evaluate the performance and durability of blades based on wear data using data from the shared platform, establish a blade wear life model, evaluate the performance of blades of different brands and materials, and generate an evaluation report.

[0025] The cost control optimization strategy development module is used to build an optimized production cost model for the relationship between blade wear and production costs, analyze the impact of blade wear on costs, formulate optimization strategies for blade procurement, use and replacement based on the analysis results, integrate cost control strategies into the production management system, automate the execution of optimization strategies, and monitor the effectiveness of strategy execution.

[0026] The knowledge sharing and decision support system module is used to build a knowledge base based on wear data analysis and cost control strategies, and to provide users with decision-making suggestions on blade selection, procurement timing, and usage cycle.

[0027] As a further embodiment of the present invention, the blade wear data sharing platform module specifically includes:

[0028] The data acquisition and preprocessing unit is used to monitor the usage status and wear of the cutting tool in real time by using various types of sensors installed on the cutting tool machine, configure the data acquisition system, convert the acquired data into a unified format, and store it in the database after cleaning and standardization.

[0029] The data sharing platform unit is used to periodically upload processed data to the sharing platform.

[0030] As a further embodiment of the present invention, the wear data analysis and blade performance evaluation module specifically includes:

[0031] The data analysis and processing unit is used to centralize wear data from the data sharing platform into a data warehouse and extract wear rate, wear type and processing parameter characteristics from the data;

[0032] Establish a blade wear life model and evaluation unit to build the blade wear life model based on the data warehouse, train the model using training set data, and adjust the model parameters.

[0033] As a further embodiment of the present invention, the cost control optimization strategy development module specifically includes:

[0034] The cost and wear data analysis unit is used to summarize wear and cost data. Based on the data exploration results, it selects feature variables that are highly correlated with blade wear and cost, identifies cost drivers by analyzing the correlation between the selected features and costs, analyzes the trend relationship between blade wear and cost, identifies patterns of cost change, and constructs an optimized blade production cost model based on the analysis results.

[0035] The optimization strategy formulation and execution unit is used to verify the accuracy and practicality of the results, assess the relationship between actual wear and cost, design strategies for optimizing the procurement, use and replacement of cutting tools to reduce wear costs, evaluate the potential economic benefits of the designed strategies through simulation experiments, formulate detailed strategy execution plans based on simulation results and strategy evaluation, integrate the execution plans into the existing production management system, implement a strategy monitoring mechanism, track strategy execution results, and adjust strategies and execution plans based on feedback.

[0036] As a further embodiment of the present invention, the knowledge sharing and decision support system module specifically includes:

[0037] The knowledge base building unit is used to integrate wear data, cost data, and blade performance evaluation results, extract decision rules from the data, structure the extracted rules and patterns, encode the knowledge base content using appropriate data structures and storage technologies, and develop decision support tools.

[0038] The decision support system maintenance and optimization unit is used to monitor the operational performance of decision support tools, regularly collect user feedback on tool usage, and provide feedback based on the latest blade wear and cost control data, as well as usage and effectiveness.

[0039] The beneficial effects of this invention are as follows: By deploying sensors and data acquisition systems and developing an online platform, systematic collection and sharing of blade wear data are achieved, breaking down data silos and improving data utilization efficiency. Utilizing data from the shared platform, a blade wear life model and performance evaluation system are established, enabling scientific evaluation of blade performance and improving the accuracy of blade selection and replacement decisions. By constructing a model of the relationship between blade wear and production costs, the impact of wear on costs is analyzed, optimization strategies are formulated, and effective control of production costs is achieved, reducing overall production costs. Attached Figure Description

[0040] Figure 1 A flowchart illustrating a method for managing the production of machined parts, provided as an embodiment of the present invention;

[0041] Figure 2 A flowchart illustrating the specific steps involved in collecting wear data of machining equipment blades during use via sensors and uploading it to a sharing platform, as provided in this embodiment of the invention.

[0042] Figure 3 A flowchart for establishing a blade wear life model provided in an embodiment of the present invention;

[0043] Figure 4 A flowchart for constructing a blade optimization production cost model provided in an embodiment of the present invention;

[0044] Figure 5 The flowchart for constructing a knowledge base provided in the embodiments of the present invention, which uses the knowledge base to provide users with decision-making suggestions on blade selection, procurement timing, and usage cycle;

[0045] Figure 6 A structural block diagram of a machining parts production management system provided in an embodiment of the present invention;

[0046] Figure 7 This is a structural block diagram of the blade wear data sharing platform module provided in an embodiment of the present invention;

[0047] Figure 8 This is a structural block diagram of the wear data analysis and blade performance evaluation module provided in an embodiment of the present invention;

[0048] Figure 9 A structural block diagram of the cost control optimization strategy development module provided in this embodiment of the invention;

[0049] Figure 10 This is a structural block diagram of the knowledge sharing and decision support system module provided in an embodiment of the present invention. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0051] It is understood that the terms "first," "second," etc., used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are used only to distinguish one element from another. For example, without departing from the scope of this application, a first script may be referred to as a second script, and similarly, a second script may be referred to as a first script.

[0052] Figure 1 A flowchart of a machining parts production management method provided in an embodiment of the present invention is shown below. Figure 1 As shown, a method for production management of machined parts includes:

[0053] S100 collects wear data of the cutting blades during the use of the processing equipment through sensors and uploads it to a sharing platform;

[0054] This step utilizes advanced sensor technology, enabling more real-time and precise monitoring of blade wear. This provides reliable data for proactive maintenance and replacement planning, thereby reducing the risk of production failures such as sudden blade breakage. Automated data cleaning and standardization processes ensure data quality and consistency, reduce human error, and improve the efficiency and accuracy of data processing. Standardized data formats support data compatibility and exchange between different brands and models of machinery, achieving interoperability of equipment data.

[0055] This step, through the establishment of registration, authentication, and access control mechanisms, ensures the security of data access and the protection of data privacy on the data sharing platform. The platform's data upload and download interfaces lower the technical barrier for users, enabling even non-technical personnel to easily manipulate data. Data is presented in chart form, making complex data more intuitive and easier to understand, helping users quickly comprehend the data and make appropriate decisions. The implemented data update mechanism and regular maintenance maintain the timeliness and accuracy of the data, enhancing the platform's reliability.

[0056] This step integrates advanced data analytics and machine learning algorithms to provide blade wear prediction services. This helps users predict blade life and optimize replacement schedules, reducing unexpected downtime. Leveraging cloud technology, the blade wear data sharing platform can integrate data from multiple plants, providing macro-level data analysis to uncover broader manufacturing trends and insights. The platform can automatically generate wear reports and maintenance logs, providing users with historical data and trend analysis to help them understand long-term wear patterns and cost-effectiveness. Users can customize data analysis reports to meet specific production and analysis needs. Integrated online collaboration tools enable engineers, suppliers, and managers to communicate and collaborate in real time regarding blade use and maintenance. Integrating these functionalities into the blade wear data sharing platform module not only enhances existing production management systems but also drives the transformation towards smart manufacturing and Industry 4.0.

[0057] S200 utilizes data from a shared platform to evaluate the performance and durability of blades based on wear data, establishes a blade wear life model, conducts performance evaluations on blades of different brands and materials, and generates an evaluation report.

[0058] This step acquires data from a cutting tool wear data sharing platform, including but not limited to workpiece material, cutting speed, feed rate, depth of cut, coolant usage, wear type, wear amount, wear rate, service life, cutting tool material, cutting tool type, and specifications. Missing and outlier values ​​are handled, and data standardization and normalization are performed to ensure data quality and lay a solid foundation for subsequent analysis. The processed data is stored in a unified data warehouse for easy analysis and modeling. Features, such as wear rate, wear type, and machining parameters, are extracted from the raw data, and feature selection and dimensionality reduction are performed to improve model training efficiency and predictive performance. Time series analysis is conducted on the cutting tool wear data to capture the dynamic changes in cutting tool wear and improve the model's predictive capabilities.

[0059] This step employs various machine learning models (such as linear regression, decision trees, random forests, support vector machines, and neural networks) for modeling, selecting the optimal model. The model is trained using training data, its parameters are optimized, and cross-validation and other methods are used to evaluate its generalization ability. Finally, the model's predictive performance is improved through hyperparameter tuning, feature selection, and ensemble learning.

[0060] This step involves collecting and analyzing a large amount of blade wear data. The system can then perform blade performance evaluation in a data-driven manner, significantly improving the scientific rigor and accuracy of the evaluation and reducing the impact of human factors. Utilizing advanced machine learning technology, a highly efficient predictive model is established, accurately predicting blade wear life and providing a reliable basis for blade selection, procurement, and replacement during the production process. By monitoring and analyzing blade wear data in real time, the system can dynamically adjust blade usage strategies, promptly identify and respond to anomalies, optimize the production process, and reduce production costs. Integrating blade performance evaluation with cost control and production management systems enables automated management and optimization of the entire process, improving production efficiency and reducing manual intervention. By building a knowledge base, the system can accumulate and share experience and knowledge gained during blade usage, enhancing the overall technical level and decision-making capabilities of the factory and bringing long-term competitive advantages to the enterprise.

[0061] S300 constructs an optimized production cost model for blades, establishing the relationship between blade wear and production costs. It analyzes the impact of blade wear on costs, and based on the analysis results, formulates optimization strategies for blade procurement, use, and replacement. It integrates cost control strategies into the production management system, automates the execution of optimization strategies, and monitors the effectiveness of strategy execution.

[0062] This step involves acquiring wear data from a blade wear data sharing platform and cost data from ERP or other financial systems. Missing and outlier values ​​are handled to ensure data integrity and accuracy. The cleaned data is stored in a data warehouse for subsequent analysis and modeling. Feature variables highly correlated with blade wear and cost are selected from the dataset, such as blade unit price, total blade usage time, and labor cost rate. Statistical methods (such as Pearson correlation coefficient and Spearman correlation coefficient) are used to analyze the correlation between features and cost, identifying key cost drivers. Time series analysis and regression analysis are used to analyze the trend relationship between blade wear and cost, identifying patterns of cost change. Cluster analysis and classification analysis are used to identify cost change characteristics under different wear patterns, providing a basis for strategy formulation.

[0063] This step verifies the accuracy of the optimization model using actual production data, ensuring it accurately reflects the relationship between blade wear and cost. It assesses the model's applicability and operability in a real production environment, ensuring the strategy's feasibility. Based on the cost model, it optimizes the blade procurement strategy, including procurement timing and quantity. It determines the optimal blade lifespan to reduce unnecessary replacements and cost increases. A blade replacement strategy is developed to ensure blades are replaced at the optimal time, minimizing downtime and production costs. Simulation experiments are conducted to evaluate the potential economic benefits of the designed strategy, identifying potential problems and areas for improvement. Based on the simulation results, the effectiveness and benefits of the strategy are evaluated, ensuring it achieves the expected cost savings. Based on the strategy evaluation results, a detailed strategy implementation plan is developed to ensure smooth implementation. The implementation plan is integrated into the existing production management system to automate strategy execution. A strategy monitoring mechanism is implemented to track strategy execution results, adjusting the strategy and implementation plan based on actual feedback to ensure continuous optimization.

[0064] This step, through in-depth analysis of blade wear and cost data, develops optimization strategies based on a data-driven approach, improving the scientific rigor and accuracy of decision-making. The cost control optimization strategy development module considers not only blade procurement costs but also replacement costs, quality costs, and downtime costs, achieving comprehensive cost control. Through real-time monitoring and analysis, the system can dynamically adjust optimization strategies based on actual conditions, ensuring the effectiveness and adaptability of the strategies. Automating the execution of optimization strategies reduces manual intervention, improves execution efficiency, and allows for timely problem detection and feedback through monitoring mechanisms, continuously optimizing the strategies. By implementing optimization strategies, enterprises can significantly improve production efficiency and achieve long-term economic benefits and competitive advantages.

[0065] S400, based on wear data analysis and cost control strategies, builds a knowledge base to provide users with decision-making suggestions on blade selection, procurement timing, and usage cycle.

[0066] Figure 2 The flowchart illustrating the specific steps of collecting wear data of machining equipment blades during use via sensors and uploading it to a sharing platform, as provided in this embodiment of the invention, is as follows: Figure 2 As shown, the process of collecting wear data of the cutting blade during use of the processing equipment via sensors and uploading it to the sharing platform specifically includes:

[0067] S110 installs various types of sensors on the cutting tool machine to monitor the tool's usage status and wear level in real time. It is equipped with a data acquisition system to convert the collected data into a unified format, and then stores it in the database after cleaning and standardization.

[0068] S120 processes the data and uploads it to the sharing platform periodically.

[0069] Figure 3 A flowchart illustrating how the performance and durability of a cutting tool are evaluated based on wear data from a shared platform, and how a cutting tool wear life model is established, is provided in this embodiment of the invention. Figure 2 As shown, the establishment of the blade wear life model specifically includes:

[0070] S210 centralizes wear data from the data sharing platform into a data warehouse and extracts wear rate, wear type and processing parameter characteristics from the data;

[0071] S220: Establish a blade wear life model based on the data warehouse, train the model using training set data, and adjust the model parameters.

[0072] The specific formula for the blade wear life model is as follows:

[0073] y = β0 + β1x1 + β2x2 + ... + β n x n +ε

[0074] Where y represents the wear life of the blade, x1, x2…x n This indicates the characteristic workpiece material, cutting speed, feed rate, depth of cut, coolant usage, wear type, wear amount, wear rate, service life, insert material, insert type, and insert specification in the above wear data. β0 is the intercept, and β1, β2…β n ε represents the coefficients of each feature, indicating the degree of influence of each feature on the wear life of the blade; ε is the error term, representing the unobserved variation in the data.

[0075] Figure 4 This invention provides an embodiment of an optimized production cost model for blades, which establishes the relationship between blade wear and production costs. It analyzes the impact of blade wear on costs, and based on the analysis results, formulates optimization strategies for blade procurement, use, and replacement. The cost control strategies are integrated into the production management system, automating the execution of these optimization strategies and monitoring their effectiveness. (See flowchart for example.) Figure 4 As shown, it specifically includes:

[0076] S310: Summarize wear and cost data, select feature variables that are highly correlated with blade wear and cost based on data exploration results, identify cost drivers by analyzing the correlation between selected features and costs, analyze the trend relationship between blade wear and cost, identify cost change patterns, and construct a blade optimization production cost model based on the analysis results.

[0077] The specific formula for the blade optimization production cost model is as follows:

[0078] C total =(P tool ·Dtool / y)+(T change ·L labour ·N change (y))+C quality (y)+(T downtime ·L downtime )

[0079] C total It optimizes the production cost of blades;

[0080] P tool That's the price per blade;

[0081] D tool / y represents the total blade usage time required;

[0082] y represents the blade wear life;

[0083] T change This is the time required to change the cutting tool;

[0084] L labour It is the cost rate of labor;

[0085] N change (y) represents the number of blade replacements calculated based on the blade life y;

[0086] C quality (y) represents the machining quality-related costs based on the blade life y;

[0087] T downtime This is the average downtime caused by tooling issues;

[0088] L downtime It is the cost rate of downtime.

[0089] S320 verifies the accuracy and practicality of the results, assesses the relationship between actual wear and cost, designs strategies for optimizing the procurement, use, and replacement of cutting tools to reduce wear costs, evaluates the potential economic benefits of the designed strategies through simulation experiments, and develops a detailed strategy implementation plan based on the simulation results and strategy evaluation. The implementation plan is then integrated into the existing production management system, a strategy monitoring mechanism is implemented, the strategy implementation results are tracked, and the strategy and implementation plan are adjusted based on feedback.

[0090] Figure 5 The knowledge base provided in this embodiment of the invention includes a flowchart detailing the specific steps involved in constructing the knowledge base and providing users with decision-making suggestions regarding blade selection, procurement timing, and usage cycle. Figure 5 As shown, the construction of the knowledge base, which provides users with decision-making suggestions regarding blade selection, procurement timing, and usage cycle, specifically includes:

[0091] S410 integrates wear data, cost data, and blade performance evaluation results, extracts decision rules from the data, structures the extracted rules and patterns, encodes knowledge base content using appropriate data structures and storage technologies, and develops decision support tools.

[0092] In step S410, the steps of integrating wear data, cost data, and blade performance evaluation results to extract decision rules from the data are used to quantify the comprehensive performance index of the blade, so as to provide decision support for blade selection, procurement timing, and usage cycle.

[0093] The functional expression for the overall performance index of the blade is as follows:

[0094]

[0095] Where F represents the overall performance index of the blade, P represents the blade performance evaluation score, D represents the blade durability factor, and W represents the current wear of the blade. max C indicates the maximum allowable wear of the cutting blade. ceff C represents the blade utilization efficiency coefficient. init C represents the initial purchase cost of the blade. maint This indicates the maintenance cost of the blade.

[0096] As a supplementary explanation, in the functional expression of the above-mentioned blade comprehensive performance index, the blade comprehensive performance index F is used to evaluate the overall performance of the blade. The blade performance evaluation score P′ can be quantified based on a series of performance tests (such as cutting speed, accuracy, durability, etc.). The blade durability factor D′ can be estimated based on historical data and wear curves, representing the blade's durability under expected usage conditions. The maximum allowable wear amount W of the blade... max Exceeding this value usually means the blade needs to be replaced. For the blade efficiency coefficient C... ceff Consider the ratio of the actual efficiency to the theoretical efficiency of the blade during use.

[0097] Furthermore, P′×D′ represents a comprehensive consideration of the blade's basic performance and durability. (1-W / W) max ) is a wear factor used to quantify the remaining service life of the cutting tool. As the wear amount W increases, the wear factor gradually decreases, thus affecting the overall performance index of the cutting tool. C ceff The efficiency of the blade during use is taken into account; if the blade's efficiency decreases during use, this coefficient will decrease accordingly. Denominator C init +C maint The total cost of the blades was considered, including initial purchase costs and subsequent maintenance costs. Cost factors directly impact the overall performance index; higher costs result in a lower index.

[0098] By using a functional expression for the overall performance index of the cutting tool, a quantitative overall performance index F can be obtained. This index comprehensively considers the tool's performance, durability, wear, and cost factors, and can support decisions regarding tool selection, procurement timing, and service life. When the F value falls below a certain preset threshold, it may mean that the tool needs to be replaced or repaired.

[0099] The S420 monitors the performance of decision support tools, regularly collects user feedback on tool usage, and provides feedback based on the latest blade wear and cost control data, as well as usage and effectiveness.

[0100] Figure 6 A structural block diagram of a machining parts production management system provided in an embodiment of the present invention is shown below. Figure 6 As shown, a production management system for machined parts includes:

[0101] The blade wear data sharing platform module 100 is used to collect wear data of the cutting blades of the processing equipment during use through sensors and upload it to the sharing platform;

[0102] This module's advanced sensor technology enables more real-time and accurate monitoring of blade wear. This provides reliable data for proactive maintenance and replacement planning, thereby reducing the risk of production failures such as sudden blade breakage. Automated data cleaning and standardization processes ensure data quality and consistency, reduce human error, and improve data processing efficiency and accuracy. Standardized data formats support data compatibility and exchange between different brands and models of machinery, achieving interoperability of equipment data.

[0103] This module, through its registration, authentication, and access control mechanisms, ensures data access security and privacy protection for the data sharing platform. The platform's data upload and download interfaces lower the technical barrier for users, enabling even non-technical personnel to easily manipulate data. Data is presented in chart form, making complex data more intuitive and easier to understand, helping users quickly comprehend the data and make appropriate decisions. The implemented data update mechanism and regular maintenance maintain the timeliness and accuracy of the data, enhancing the platform's reliability.

[0104] This module integrates advanced data analytics and machine learning algorithms to provide blade wear prediction services. This helps users predict blade life and optimize replacement schedules, reducing unexpected downtime. Leveraging cloud technology, the blade wear data sharing platform can integrate data from multiple plants, providing macro-level data analysis to uncover broader manufacturing trends and insights. The platform can automatically generate wear reports and maintenance logs, providing users with historical data and trend analysis to help them understand long-term wear patterns and cost-effectiveness. Users can customize data analysis reports to meet specific production and analysis needs. Integrated online collaboration tools enable engineers, suppliers, and managers to communicate and collaborate in real time regarding blade use and maintenance. Integrating these functionalities into the blade wear data sharing platform module not only enhances existing production management systems but also drives the transformation towards smart manufacturing and Industry 4.0.

[0105] The Wear Data Analysis and Blade Performance Evaluation Module 200 is used to evaluate the performance and durability of blades based on wear data using data from a shared platform, establish a blade wear life model, evaluate the performance of blades of different brands and materials, and generate an evaluation report.

[0106] This module acquires data from a cutting tool wear data sharing platform, including but not limited to workpiece material, cutting speed, feed rate, depth of cut, coolant usage, wear type, wear amount, wear rate, service life, cutting tool material, cutting tool type, and specifications. It handles missing and outlier values, and performs data standardization and normalization to ensure data quality and lay a solid foundation for subsequent analysis. The processed data is stored in a unified data warehouse for convenient subsequent analysis and modeling. Features, such as wear rate, wear type, and machining parameters, are extracted from the raw data, and feature selection and dimensionality reduction are performed to improve model training efficiency and predictive performance. Time series analysis is conducted on the cutting tool wear data to capture the dynamic changes in cutting tool wear and improve the model's predictive capabilities.

[0107] This module employs various machine learning models (such as linear regression, decision trees, random forests, support vector machines, and neural networks) for modeling, selecting the optimal model. The model is trained using training data, its parameters are optimized, and cross-validation and other methods are used to evaluate its generalization ability. The predictive performance of the model is improved through hyperparameter tuning, feature selection, and ensemble learning.

[0108] This module collects and analyzes a large amount of blade wear data, enabling the system to perform blade performance evaluation in a data-driven manner. This significantly improves the scientific rigor and accuracy of the evaluation, reducing the impact of human factors. Utilizing advanced machine learning technology, it establishes a highly efficient predictive model that accurately predicts blade wear life, providing a reliable basis for blade selection, procurement, and replacement during the production process. By monitoring and analyzing blade wear data in real time, the system can dynamically adjust blade usage strategies, promptly identify and respond to anomalies, optimize the production process, and reduce production costs. Integrating blade performance evaluation with cost control and production management systems enables automated management and optimization of the entire process, improving production efficiency and reducing manual intervention. By building a knowledge base, the system can accumulate and share experience and knowledge gained during blade usage, enhancing the overall technical level and decision-making capabilities of the factory and bringing long-term competitive advantages to the enterprise.

[0109] The cost control optimization strategy development module 300 is used to build an optimized production cost model for the relationship between blade wear and production costs, analyze the impact of blade wear on costs, formulate optimization strategies for blade procurement, use and replacement based on the analysis results, integrate cost control strategies into the production management system, automate the execution of optimization strategies, and monitor the effectiveness of strategy execution.

[0110] This module acquires wear data from a blade wear data sharing platform and cost data from ERP systems or other financial systems. It handles missing and outlier values ​​to ensure data integrity and accuracy. The cleaned data is stored in a data warehouse for subsequent analysis and modeling. Feature variables highly correlated with blade wear and cost are selected from the dataset, such as blade unit price, total blade usage time, and labor cost rate. Statistical methods (such as Pearson correlation coefficient and Spearman correlation coefficient) are used to analyze the correlation between features and cost, identifying key cost drivers. Time series analysis and regression analysis are used to analyze the trend relationship between blade wear and cost, identifying patterns of cost change. Cluster analysis and classification analysis are used to identify cost change characteristics under different wear patterns, providing a basis for strategy formulation.

[0111] This module verifies the accuracy of the optimization model using actual production data, ensuring it accurately reflects the relationship between blade wear and cost. It evaluates the model's applicability and operability in real-world production environments, ensuring the strategy's feasibility. Based on the cost model, it optimizes blade procurement strategies, including timing and quantity. It determines the optimal blade lifespan to reduce unnecessary replacements and cost increases. A blade replacement strategy is developed to ensure timely replacement, minimizing downtime and production costs. Simulation experiments are used to assess the potential economic benefits of the designed strategy, identifying potential problems and areas for improvement. Based on simulation results, the effectiveness and benefits of the strategy are evaluated, ensuring it achieves the expected cost savings. A detailed strategy implementation plan is developed based on the evaluation results, ensuring smooth implementation. The implementation plan is integrated into the existing production management system for automated strategy execution. A strategy monitoring mechanism is implemented to track execution results and adjust the strategy and implementation plan based on feedback, ensuring continuous optimization.

[0112] This module, through in-depth analysis of blade wear and cost data, formulates optimization strategies based on a data-driven approach, improving the scientific rigor and accuracy of decision-making. The cost control optimization strategy development module considers not only blade procurement costs but also replacement costs, quality costs, and downtime costs, achieving comprehensive cost control. Through real-time monitoring and analysis, the system can dynamically adjust optimization strategies based on actual conditions, ensuring the effectiveness and adaptability of the strategies. Automating the execution of optimization strategies reduces manual intervention, improves execution efficiency, and allows for timely problem detection and feedback through monitoring mechanisms, continuously optimizing strategies. By implementing optimization strategies, enterprises can significantly improve production efficiency and achieve long-term economic benefits and competitive advantages.

[0113] The Knowledge Sharing and Decision Support System Module 400 is used to build a knowledge base based on wear data analysis and cost control strategies, and to provide users with decision-making suggestions on blade selection, procurement timing, and usage cycle using the knowledge base.

[0114] Figure 7 The structural block diagram of the blade wear data sharing platform module provided in the embodiments of the present invention is as follows: Figure 7 As shown, the blade wear data sharing platform module specifically includes:

[0115] The data acquisition and preprocessing unit 110 is used to monitor the usage status and wear of the cutting tool in real time by using various types of sensors installed on the cutting tool machine, configure the data acquisition system, convert the acquired data into a unified format, and store it in the database after cleaning and standardization.

[0116] The data sharing platform unit 120 is used to periodically upload processed data to the sharing platform.

[0117] Figure 8 This is a structural block diagram of the wear data analysis and blade performance evaluation module provided in an embodiment of the present invention, as shown below. Figure 8 As shown, the wear data analysis and blade performance evaluation module specifically includes:

[0118] The data analysis and processing unit 210 is used to centralize wear data from the data sharing platform into a data warehouse and extract wear rate, wear type and processing parameter characteristics from the data;

[0119] A blade wear life model and evaluation unit 220 are established to build a blade wear life model based on a data warehouse, train the model using training set data, and adjust the model parameters.

[0120] Figure 9 A structural block diagram of the cost control optimization strategy development module provided in the embodiments of the present invention is shown below. Figure 9 As shown, the cost control optimization strategy development module specifically includes:

[0121] The cost and wear data analysis unit 310 is used to summarize wear data and cost data. Based on the data exploration results, it selects feature variables that are highly correlated with blade wear and cost, identifies cost drivers by analyzing the correlation between the selected features and costs, analyzes the trend relationship between blade wear and cost, identifies the pattern of cost change, and constructs a blade optimization production cost model based on the analysis results.

[0122] The optimization strategy formulation and execution unit 320 is used to verify the accuracy and practicality of the results, assess the relationship between actual wear and cost, design strategies for optimizing the procurement, use and replacement of cutting tools to reduce wear costs, evaluate the potential economic benefits of the designed strategies through simulation experiments, formulate detailed strategy execution plans based on simulation results and strategy evaluation, integrate the execution plans into the existing production management system, implement a strategy monitoring mechanism, track strategy execution results, and adjust strategies and execution plans based on feedback.

[0123] Figure 10 This is a structural block diagram of the knowledge sharing and decision support system module provided in the embodiments of the present invention, such as... Figure 10 As shown, the knowledge sharing and decision support system module specifically includes:

[0124] The knowledge base building unit 410 is used to integrate wear data, cost data, and blade performance evaluation results, extract decision rules from the data, structure the extracted rules and patterns, encode the knowledge base content using appropriate data structures and storage technologies, and develop decision support tools.

[0125] The decision support system maintenance and optimization unit 420 is used to monitor the operational performance of decision support tools, regularly collect user feedback on tool usage, and provide feedback based on the latest blade wear and cost control data, as well as usage and effectiveness.

[0126] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0127] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0128] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0129] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0130] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for production management of machined parts, characterized in that, The method includes the following steps: The wear data of the cutting blades in the processing equipment is collected by sensors and uploaded to a sharing platform; By utilizing data from a shared platform, the performance and durability of blades are evaluated based on wear data, a blade wear life model is established, and performance evaluations are conducted on blades of different brands and materials to generate an evaluation report. Construct an optimized production cost model for blades to determine the relationship between blade wear and production costs. Analyze the impact of blade wear on costs. Based on the analysis results, formulate optimization strategies for blade procurement, use, and replacement. Integrate cost control strategies into the production management system, automate the execution of optimization strategies, and monitor the effectiveness of strategy execution. Based on wear data analysis and cost control strategies, a knowledge base is built to provide users with decision-making suggestions on blade selection, procurement timing, and usage cycle.

2. The method for production management of machined parts according to claim 1, characterized in that, The process of collecting wear data on the cutting blades of the processing equipment during use via sensors and uploading it to the sharing platform specifically includes: Various types of sensors are installed on cutting tools to monitor their usage status and wear in real time. A data acquisition system is configured to convert the collected data into a unified format, and then the data is cleaned, standardized, and stored in a database. The processed data is uploaded to the sharing platform periodically.

3. The method for production management of machined parts according to claim 2, characterized in that, The process of utilizing data from a shared platform to evaluate the performance and durability of the cutting blade based on wear data, and establishing a blade wear life model, specifically includes: Wear data from a data sharing platform is centralized in a data warehouse, from which wear rate, wear type, and processing parameter characteristics are extracted. A blade wear life model is established based on the data warehouse. The model is trained using the training set data, and the model parameters are adjusted. The specific formula for the blade wear life model is as follows: y=β0+β1x1+β2x2+…+β n x n +e Where y represents the wear life of the blade, x1, x2…x n This indicates the characteristic workpiece material, cutting speed, feed rate, depth of cut, coolant usage, wear type, wear amount, wear rate, service life, insert material, insert type, and insert specification in the above wear data. β0 is the intercept, and β1, β2…β n ε represents the coefficients of each feature, indicating the degree of influence of each feature on the wear life of the blade; ε is the error term, representing the unobserved variation in the data.

4. The method for production management of machined parts according to claim 3, characterized in that, The aforementioned blade optimization production cost model establishes the relationship between blade wear and production costs, analyzes the impact of blade wear on costs, and, based on the analysis results, formulates optimization strategies for blade procurement, use, and replacement. These cost control strategies are integrated into the production management system to automate the execution of these optimization strategies and monitor their effectiveness. Specifically, this includes: By summarizing wear and cost data, and based on the data exploration results, we select feature variables that are highly correlated with blade wear and cost. We identify cost drivers by analyzing the correlation between the selected features and costs, and analyze the trend relationship between blade wear and cost. We identify patterns of cost change and, based on the analysis results, we construct a blade optimization production cost model. The specific formula for the blade optimization production cost model is as follows: C total =(P tool ·D tool / y)+(T change ·L labour ·N change (y))+C quality (y)+(T downtime ·L downtime ) C total It optimizes the production cost of blades; P tool That's the price per blade; D tool / y represents the total blade usage time required; y represents the blade wear life; T change This is the time required to change the cutting tool; L labour It is the cost rate of labor; N change (y) represents the number of blade replacements calculated based on the blade life y; Cquality(y) is the machining quality-related cost based on the blade life y; T downtime This is the average downtime caused by tooling issues; L downtime It is the cost rate of downtime; Verify the accuracy and practicality of the results, assess the relationship between actual wear and cost, design strategies to optimize the procurement, use and replacement of cutting tools to reduce wear costs, evaluate the potential economic benefits of the designed strategies through simulation experiments, develop a detailed strategy implementation plan based on simulation results and strategy evaluation, integrate the implementation plan into the existing production management system, implement a strategy monitoring mechanism, track the strategy implementation results, and adjust the strategy and implementation plan based on feedback.

5. The method for production management of machined parts according to claim 4, characterized in that, The aforementioned knowledge base construction provides users with decision-making suggestions regarding blade selection, procurement timing, and usage cycle, specifically including: By integrating wear data, cost data, and blade performance evaluation results, decision rules are extracted from the data. The extracted rules and patterns are then structured, knowledge base content is encoded using appropriate data structures and storage technologies, and decision support tools are developed. Monitor the performance of decision support tools, regularly collect user feedback on tool usage, and provide feedback based on the latest blade wear and cost control data, as well as usage and effectiveness.

6. The method for production management of machined parts according to claim 5, characterized in that, In the step of integrating wear data, cost data, and blade performance evaluation results, and extracting decision rules from the data, the extracted decision rules are used to quantify the comprehensive performance index of the blade, so as to provide decision support for blade selection, procurement timing, and usage cycle. The functional expression for the overall performance index of the blade is as follows: Where F represents the overall performance index of the blade, P′ represents the blade performance evaluation score, D′ represents the blade durability factor, and W represents the current wear of the blade. max C indicates the maximum allowable wear of the cutting blade. ceff C represents the blade utilization efficiency coefficient. init C represents the initial purchase cost of the blade. maint This indicates the maintenance cost of the blade.

7. A production management system for machined parts, characterized in that, The system employs the machining parts production management method as described in any one of claims 1 to 6, wherein the system comprises: The blade wear data sharing platform module is used to collect wear data of the cutting blades of the processing equipment during use through sensors and upload it to the sharing platform; The wear data analysis and blade performance evaluation module is used to evaluate the performance and durability of blades based on wear data using data from the shared platform, establish a blade wear life model, evaluate the performance of blades of different brands and materials, and generate an evaluation report. The cost control optimization strategy development module is used to build an optimized production cost model for the relationship between blade wear and production costs, analyze the impact of blade wear on costs, formulate optimization strategies for blade procurement, use and replacement based on the analysis results, integrate cost control strategies into the production management system, automate the execution of optimization strategies, and monitor the effectiveness of strategy execution. The knowledge sharing and decision support system module is used to build a knowledge base based on wear data analysis and cost control strategies, and to provide users with decision-making suggestions on blade selection, procurement timing, and usage cycle.

8. The machining parts production management system according to claim 7, characterized in that, The blade wear data sharing platform module specifically includes: The data acquisition and preprocessing unit is used to monitor the usage status and wear of the cutting tool in real time by using various types of sensors installed on the cutting tool machine, configure the data acquisition system, convert the acquired data into a unified format, and store it in the database after cleaning and standardization. The data sharing platform unit is used to periodically upload processed data to the sharing platform.

9. A machining parts production management system according to claim 7, characterized in that, The wear data analysis and blade performance evaluation module specifically includes: The data analysis and processing unit is used to centralize wear data from the data sharing platform into a data warehouse and extract wear rate, wear type and processing parameter characteristics from the data; Establish a blade wear life model and evaluation unit, which is used to build a blade wear life model based on the data warehouse, train the model using training set data, and adjust the model parameters. The cost control optimization strategy development module specifically includes: The cost and wear data analysis unit is used to summarize wear data and cost data. Based on the data exploration results, it selects feature variables that are highly correlated with blade wear and cost, identifies cost drivers by analyzing the correlation between the selected features and costs, analyzes the trend relationship between blade wear and cost, identifies patterns of cost change, and constructs a blade optimization production cost model based on the analysis results. The optimization strategy formulation and execution unit is used to verify the accuracy and practicality of the results, assess the relationship between actual wear and cost, design strategies for optimizing the procurement, use and replacement of cutting tools to reduce wear costs, evaluate the potential economic benefits of the designed strategies through simulation experiments, formulate detailed strategy execution plans based on simulation results and strategy evaluation, integrate the execution plans into the existing production management system, implement a strategy monitoring mechanism, track strategy execution results, and adjust strategies and execution plans based on feedback.

10. A machining parts production management system according to claim 9, characterized in that, The knowledge sharing and decision support system module specifically includes: The knowledge base building unit is used to integrate wear data, cost data, and blade performance evaluation results, extract decision rules from the data, structure the extracted rules and patterns, encode the knowledge base content using appropriate data structures and storage technologies, and develop decision support tools. The decision support system maintenance and optimization unit is used to monitor the operational performance of decision support tools, regularly collect user feedback on tool usage, and provide feedback based on the latest blade wear and cost control data, as well as usage and effectiveness.

Images