Automatic input and collection system for tool parameter of machining center

Abstract

The present application relates to the technical field of mechanical manufacturing, in particular to a machining center tool setting parameter automatic input acquisition system, the machining center tool setting parameter automatic input acquisition system is composed of intelligent tool identification module, real-time error correction module, process automation module, tool condition monitoring module, intelligent learning module, tool cloud database module, image processing and pattern recognition module, adaptive parameter optimization module, in the present application, based on the deep learning of convolutional neural network, special tools are rapidly and accurately automatically identified, and manual input error is reduced, error correction is carried out by using gradient descent, and tool setting parameters are optimized, automatic process improves production efficiency, production plan is adjusted according to live conditions, and resource utilization is enhanced, tool state is monitored in real time to provide data for maintenance, and the service life of the tool is prolonged, the learning of historical data makes the parameters more accurate, and the efficiency and quality are improved, cloud database connection guarantees real-time updating and retrieval of tool parameters, and various working conditions are met.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of mechanical manufacturing, in particular to a machining center tool setting parameter automatic input and acquisition system. BACKGROUND

[0002] The technical field of mechanical manufacturing covers manufacturing and processing technologies related to mechanical equipment, tools, automation systems, etc. In this field, people strive to develop various mechanical equipment and systems to improve production efficiency, quality and precision.

[0003] Among them, in the tool setting work, the most advanced tool setting in the numerical control industry is the automatic tool setting instrument, which needs to be purchased and added. The operator only needs to call the code to realize the automatic movement of the machine tool to the tool setting point, and write the automatic machine tool tool compensation value, but it has limitations and cannot realize automatic tool setting for special tools, such as T-shaped tools with the tool tip upward. At present, most of the machine tools on the market are not equipped with automatic tool setting instruments, and manual tool setting is required, which involves manual operation throughout the process, needs to be manually moved to the tool setting point, and the corresponding tool compensation number in the machine tool parameter table needs to be eliminated. After calculating the tool block height, it is input again. In the process, too many manual operations are involved, the risk points are too large, and the probability of errors is also large. SUMMARY

[0004] The purpose of the application is to solve the shortcomings in the prior art and provide a machining center tool setting parameter automatic input and acquisition system.

[0005] In order to achieve the above-mentioned purpose, the application adopts the following technical scheme: a machining center tool setting parameter automatic input and acquisition system is composed of an intelligent tool recognition module, a real-time error correction module, a process automation module, a tool condition monitoring module, an intelligent learning module, a tool cloud database module, an image processing and pattern recognition module, and a self-adaptive parameter optimization module.

[0006] The intelligent tool recognition module adopts a deep learning algorithm based on a convolutional neural network, automatically recognizes special tools, and automatically generates tool setting parameters to establish a tool recognition report.

[0007] The real-time error correction module is based on the tool recognition report and uses a gradient descent algorithm for real-time error correction to generate an error correction report and a precision guarantee report.

[0008] The process automation module is based on the error correction report and uses workflow management technology for process automation to automatically adjust the production plan and form an automated process.

[0009] The tool condition monitoring module is based on the automated process and uses sensor data analysis technology to monitor the health of the tool in real time and form a tool health report.

[0010] The intelligent learning module adopts a reinforcement learning algorithm to automatically optimize tool-to-tool parameters according to historical data based on the tool health report, and generates a parameter optimization report;

[0011] The tool cloud database module establishes a cloud tool database based on the parameter optimization report, and automatically retrieves parameters according to the current tool type to form a cloud tool database connection;

[0012] The image processing and pattern recognition module adopts an image processing and pattern recognition algorithm to automatically identify the tool type and position of the machine tool working area based on the cloud tool database connection, and generates a tool position and type report;

[0013] The adaptive parameter optimization module adopts an adaptive parameter optimization algorithm based on gradient reinforcement learning to generate a parameter optimization scheme based on the tool position and type report.

[0014] As a further scheme of the application, the intelligent tool recognition module includes a tool type sub-module, a tool orientation sub-module, and a tool parameter generation sub-module;

[0015] The real-time error correction module includes a real-time detection sub-module, an error correction sub-module, and a precision guarantee sub-module;

[0016] The process flow automation module includes a parameter adjustment sub-module, a seamless switching sub-module, and a process automation sub-module;

[0017] The tool condition monitoring module includes a wear monitoring sub-module, a health condition sub-module, and a maintenance reminder sub-module;

[0018] The intelligent learning module includes a historical data processing sub-module, a tool parameter optimization sub-module, and a learning effect feedback sub-module;

[0019] The tool cloud database module includes a database establishment sub-module, a system connection sub-module, and an automatic retrieval sub-module;

[0020] The image processing and pattern recognition module includes an image capture sub-module, a tool type recognition sub-module, and a tool position recognition sub-module;

[0021] The adaptive parameter optimization module includes a dynamic adjustment sub-module, a material adaptation sub-module, and a process condition adaptation sub-module.

[0022] As a further scheme of the application, the tool type sub-module adopts a convolutional neural network deep learning algorithm combined with feature map layer visualization to perform feature extraction on input images, recognize tool types, and generate a tool type recognition report;

[0023] The tool orientation identification submodule identifies the orientation of the tool based on the tool type identification report, using image rotation correction technology and edge detection, and generates a tool orientation identification report.

[0024] The tool parameter generation submodule estimates and generates a tool parameter report based on the tool orientation identification report, using data fitting and regression techniques.

[0025] As a further solution of the present application: the real-time detection submodule uses high-speed ADC sampling technology to capture the running state of the tool in real time and detect errors, generating a real-time detection report;

[0026] The error correction submodule corrects errors based on the real-time detection report, combined with gradient descent algorithm and dynamic adjustment strategy, and generates an error correction report;

[0027] The precision guarantee submodule ensures that the machining precision is not affected by external factors based on the error correction report, through fault-tolerant encoding and redundancy strategy, and generates a precision guarantee report.

[0028] As a further solution of the present application: the parameter adjustment submodule uses fuzzy logic control to dynamically adjust the process parameters according to environmental changes based on the precision guarantee report, and generates a parameter adjustment report;

[0029] The seamless switching submodule uses state machine logic control to ensure smooth switching and continuity of the production line based on the parameter adjustment report, and generates a seamless switching report;

[0030] The process automation submodule uses PID control technology and encoding and decoding technology to schedule process nodes based on the seamless switching report, realizing process automation, and generating an automated process flow.

[0031] As a further solution of the present application: the wear monitoring submodule uses vibration spectrum analysis and ultrasonic detection technology to monitor the wear condition of the tool in real time based on the automated process flow, and generates a wear monitoring report;

[0032] The health status submodule evaluates the current health status of the tool based on the wear monitoring report, combined with statistical health models and Bayesian inference, and generates a tool health report;

[0033] The maintenance reminder submodule predicts the maintenance cycle of the tool through a time series prediction model based on the tool health report, and generates a maintenance reminder.

[0034] As a further solution of the present application: the historical data processing submodule uses time series analysis method combined with data normalization technology to deeply clean, integrate and classify historical tool data, and generates an integrated historical data report;

[0035] The tool parameter optimization submodule generates a parameter optimization report by using a Q-learning reinforcement learning algorithm and Bayesian optimization based on the integrated historical data report to finely optimize tool alignment parameters.

[0036] The learning effect feedback submodule generates a learning effect feedback report by using a K-fold cross-validation method and mean square error analysis to evaluate the learning effect based on the parameter optimization report.

[0037] As a further scheme of the application, the database establishment submodule generates a tool cloud database structure by using association rule mining and clustering analysis techniques to structurally construct a cloud tool database based on the parameter optimization report.

[0038] The system connection submodule forms a cloud tool database connection by using RESTful API technology and a secure connection protocol based on the tool cloud database structure.

[0039] The automatic retrieval submodule generates a tool parameter retrieval result by using a hash retrieval algorithm to perform parameter retrieval for the current tool type based on the cloud tool database connection.

[0040] As a further scheme of the application, the image capture submodule generates a machine tool working area image by using high-speed image acquisition technology combined with HDR technology to capture tool images of the machine tool working area in real time.

[0041] The tool type identification submodule generates a tool type identification result by using deep convolutional neural network technology based on the machine tool working area image.

[0042] The tool position identification submodule generates a tool position report by using ORB feature matching technology to determine the position of the tool on the machine tool based on the tool type identification result.

[0043] As a further scheme of the application, the dynamic adjustment submodule generates a dynamic parameter adjustment scheme by using online adaptive learning and simulated annealing algorithm to instantaneously fine-tune tool parameters based on the tool position report.

[0044] The material adaptation submodule generates a material adaptation parameter scheme by using a material science knowledge base and a machine learning prediction model to adjust tool parameters based on materials based on the dynamic parameter adjustment scheme.

[0045] The process condition adaptation submodule generates a parameter optimization scheme by using environmental perception technology and genetic algorithm optimization to optimize tool parameters based on process conditions based on the material adaptation parameter scheme.

[0046] Compared with the prior art, the application has the following advantages and positive effects:

[0047] In the present application, based on the deep learning algorithm of convolutional neural network, the system can quickly and accurately identify special tools automatically, reducing the time of manual input and possible human errors. Through error correction by gradient descent algorithm, the system can adjust and optimize the tool parameters in real time, ensuring the machining precision and efficiency. Through the automatic process flow, not only the production efficiency is improved, but also the production plan can be automatically adjusted according to the real-time situation, improving the resource utilization. Real-time monitoring of tool condition provides strong data support for equipment maintenance, prolongs the tool life and ensures the production safety. Learning and optimization according to historical data make the tool parameters more accurate, gradually improving the production efficiency and quality. Through the connection of cloud database, the tool parameters can be updated and retrieved in real time, meeting the needs of different working conditions. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 is a system flowchart of the present application;

[0049] Figure 2 is a system framework schematic diagram of the present application;

[0050] Figure 3 is a smart tool identification module flowchart of the present application;

[0051] Figure 4 is a real-time error correction module flowchart of the present application;

[0052] Figure 5 is a process flow automation module flowchart of the present application;

[0053] Figure 6 is a tool condition monitoring module flowchart of the present application;

[0054] Figure 7 is a smart learning module flowchart of the present application;

[0055] Figure 8 is a tool cloud database module flowchart of the present application;

[0056] Figure 9 is an image processing and pattern recognition module flowchart of the present application;

[0057] Figure 10 is an adaptive parameter optimization module flowchart of the present application. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical scheme and advantages of the present application more clear and explicit, the present application will be further described in detail below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application.

[0059] In the description of the present application, it should be understood that the terms "length", "width", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, in the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0060] Embodiment: please refer to Figure 1 A machining center tool setting parameter automatic input and acquisition system is composed of an intelligent tool recognition module, a real-time error correction module, a process automation module, a tool condition monitoring module, an intelligent learning module, a tool cloud database module, an image processing and pattern recognition module, and a self-adaptive parameter optimization module.

[0061] The intelligent tool recognition module adopts a deep learning algorithm based on convolutional neural network, automatically recognizes special tools, and automatically generates tool setting parameters to establish a tool recognition report.

[0062] The real-time error correction module is based on the tool recognition report and uses gradient descent algorithm for real-time error correction to generate error correction report and precision guarantee report.

[0063] The process automation module is based on the error correction report and uses workflow management technology for process automation to realize automatic adjustment of production plan and form an automatic process.

[0064] The tool condition monitoring module is based on the automatic process and uses sensor data analysis technology to monitor the health status of the tool in real time to form a tool health report.

[0065] The intelligent learning module is based on the tool health report and uses reinforcement learning algorithm to automatically optimize tool setting parameters according to historical data to generate parameter optimization report.

[0066] The tool cloud database module is based on the parameter optimization report and establishes a cloud tool database, and automatically retrieves parameters according to the current tool type to form a cloud tool database connection.

[0067] The image processing and pattern recognition module is based on the cloud tool database connection and uses image processing and pattern recognition algorithm to automatically identify the tool type and position of the machine tool working area to generate tool position and type report.

[0068] The adaptive parameter optimization module generates parameter optimization schemes based on tool position and type reports using gradient boosting learning-based adaptive parameter optimization algorithms.

[0069] Firstly, the system can automatically identify special tools and generate tool setting parameters through the intelligent tool recognition module, improving work efficiency. The real-time error correction module implements real-time error correction through gradient descent algorithm based on tool recognition reports, ensuring high-precision machining. The process automation module automatically adjusts production plans based on error correction reports, improving the intelligent and automated level of the production process.

[0070] The tool condition monitoring module monitors the health status of the tool in real time, which helps to prevent tool failure and reduce production interruptions. The intelligent learning module automatically optimizes tool setting parameters using tool health reports and historical data, improving machining efficiency and quality. The tool cloud database module establishes a cloud tool database, making tool parameter management more convenient and efficient. The image processing and pattern recognition module automatically identifies the type and position of tools in the machine tool working area, further optimizing tool usage. Finally, the adaptive parameter optimization module generates parameter optimization schemes based on tool position and type reports using gradient boosting learning algorithms, improving the flexibility and efficiency of machining.

[0071] Please refer to Figure 2 , the intelligent tool recognition module includes a tool type submodule, a tool orientation submodule, and a tool parameter generation submodule.

[0072] The real-time error correction module includes a real-time detection submodule, an error correction submodule, and a precision guarantee submodule.

[0073] The process automation module includes a parameter adjustment submodule, a seamless switching submodule, and a process automation submodule.

[0074] The tool condition monitoring module includes a wear monitoring submodule, a health status submodule, and a maintenance reminder submodule.

[0075] The intelligent learning module includes a historical data processing submodule, a tool parameter optimization submodule, and a learning effect feedback submodule.

[0076] The tool cloud database module includes a database establishment submodule, a system connection submodule, and an automatic retrieval submodule.

[0077] The image processing and pattern recognition module includes an image capture submodule, a tool type identification submodule, and a tool position identification submodule.

[0078] The adaptive parameter optimization module includes a dynamic adjustment submodule, a material adaptation submodule, and a process condition adaptation submodule.

[0079] Smart Tool Recognition Module:

[0080] The Tool Type Submodule automatically identifies the type of tool, ensuring that the correct cutting tool is used at the right time.

[0081] The Tool Orientation Submodule identifies the orientation of the tool, aiding in precise cutting direction.

[0082] The Tool Parameter Generation Submodule generates appropriate tool parameters to ensure an efficient cutting process, which will improve production efficiency and product quality.

[0083] Real-Time Error Correction Module:

[0084] The Real-Time Detection Submodule monitors tool status and cutting errors, identifying issues in a timely manner.

[0085] The Error Correction Submodule uses gradient descent algorithms for real-time error correction, ensuring high-precision machining.

[0086] The Precision Assurance Submodule provides reports and records, ensuring traceability and controllability of the production process.

[0087] Process Flow Automation Module:

[0088] The Parameter Adjustment Submodule automatically adjusts process parameters based on tool status and error conditions to achieve optimal production efficiency.

[0089] The Seamless Switching Submodule allows seamless switching between different processes, improving production flexibility.

[0090] The Process Automation Submodule ensures automatic adjustment of production plans, improving the intelligence of the production process.

[0091] Tool Condition Monitoring Module:

[0092] The Wear Monitoring Submodule monitors tool wear in real time, helping to predict maintenance needs.

[0093] The Health Status Submodule provides comprehensive tool health reports, helping to extend tool life and improve production efficiency.

[0094] The Maintenance Reminder Submodule timely reminds the maintenance team to perform necessary tool maintenance.

[0095] Intelligent Learning Module:

[0096] The Historical Data Processing Submodule analyzes past data to provide a basis for optimization.

[0097] The Tool Parameter Optimization Submodule uses reinforcement learning algorithms to automatically optimize tool parameters, improving machining efficiency.

[0098] The learning effect feedback sub-module continuously improves the learning algorithm to ensure system adaptability and intelligence.

[0099] The tool cloud database module:

[0100] The database establishment sub-module creates a cloud tool database for easy parameter management and sharing.

[0101] The system connection sub-module ensures the collaborative work and data sharing between various modules.

[0102] The automatic retrieval sub-module provides fast parameter retrieval to improve production efficiency.

[0103] The image processing and pattern recognition module:

[0104] The image capture sub-module is responsible for collecting image data related to the tool. This process can monitor the working environment in real time, capture visual information of the tool, and help to grasp the state and position of the tool in time.

[0105] The tool type recognition sub-module can identify different types of tools, including the type and model of the tool, which is very important for adjusting the work flow and managing the tool.

[0106] The tool position recognition sub-module can determine the specific position of the tool in the working area, which helps to improve work safety and efficiency.

[0107] The adaptive parameter optimization module:

[0108] The dynamic adjustment sub-module dynamically adjusts the parameters according to the actual working conditions to ensure the best machining effect.

[0109] The material adaptation sub-module considers the characteristics of different materials and automatically adjusts the parameters to adapt to different machining requirements.

[0110] The process condition adaptation sub-module automatically optimizes the parameters according to the changes of process conditions to maintain high-quality machining.

[0111] Please refer to Figure 3 , the tool type sub-module uses convolutional neural network deep learning algorithm combined with feature map layer visualization to extract features from input images, identify tool types, and generate tool type recognition report;

[0112] The tool orientation sub-module uses image rotation correction technology and edge detection based on the tool type recognition report to determine the orientation of the tool and generate a tool orientation recognition report.

[0113] The tool parameter generation sub-module uses data fitting and regression technology based on the tool orientation recognition report to estimate and generate a tool parameter report.

[0114] Firstly, through efficient tool recognition and orientation determination, the system will improve production quality, reduce scrap rates, and reduce manual intervention, thereby improving product consistency. Secondly, accurate tool parameter generation will improve production efficiency, speed up the adjustment of cutting tools, and reduce downtime on the production line. This will bring significant improvements in production efficiency and cost savings. At the same time, automated tool recognition and parameter generation reduce the burden on operators and improve the convenience of operation.

[0115] In addition, these modules also provide support for data-driven decision-making, through the generated identification reports and parameter reports, enterprises can better manage production processes, optimize resource utilization, and improve the maintainability of production lines. Ultimately, this comprehensive implementation will upgrade the tool parameter automatic input and acquisition system of machining centers to an intelligent level, enabling enterprises to better respond to market demand, improve competitiveness, while reducing human errors and losses in the production process, bringing comprehensive benefits.

[0116] Please refer to Figure 4 , the real-time detection submodule uses high-speed ADC sampling technology to capture the running state of the tool in real time and detect errors, generating a real-time detection report;

[0117] The error correction submodule, based on the real-time detection report, combines gradient descent algorithm and dynamic adjustment strategy to correct errors, generating an error correction report;

[0118] The precision guarantee submodule, based on the error correction report, uses fault-tolerant encoding and redundancy strategies to ensure that machining precision is not affected by external factors, generating a precision guarantee report.

[0119] Firstly, the real-time detection submodule uses high-speed ADC sampling technology to capture the running state of the tool in real time and detect errors, generating a real-time detection report. This helps to discover and respond to changes in tool state in a timely manner, ensuring controllability of the production process.

[0120] Secondly, the error correction submodule, based on the real-time detection report, combines gradient descent algorithm and dynamic adjustment strategy to correct errors, generating an error correction report. Through real-time error correction, the system can continuously improve the precision of cutting tools and reduce errors in machining, thereby improving the quality level of products.

[0121] The precision guarantee submodule, based on the error correction report, uses fault-tolerant encoding and redundancy strategies to ensure that machining precision is not affected by external factors, generating a precision guarantee report. This means that even in unstable working environments, the system can still maintain a certain level of production precision, reducing the potential impact of external interference on product quality.

[0122] Please refer to Figure 5, the parameter adjustment submodule uses fuzzy logic control based on the precision guarantee report to dynamically adjust process parameters according to environmental changes, generating a parameter adjustment report;

[0123] The seamless switching submodule uses state machine logic control based on the parameter adjustment report to ensure smooth switching and continuity of the production line, generating a seamless switching report;

[0124] The process automation submodule uses PID control technology and encoding and decoding technology based on the seamless switching report to schedule process nodes, achieving process automation and generating an automated process flow.

[0125] First, the parameter adjustment submodule uses fuzzy logic control based on the precision guarantee report to dynamically adjust process parameters, generating a parameter adjustment report. This step ensures that process parameters can be optimally configured under different environmental changes, improving the stability and efficiency of the production process.

[0126] Second, the seamless switching submodule uses state machine logic control based on the parameter adjustment report to ensure smooth switching and continuity of the production line, generating a seamless switching report. This means that in production, the system can quickly adapt to different product requirements or process flow changes without large-scale downtime or major intervention, improving production flexibility and response speed.

[0127] The process automation submodule uses PID control technology and encoding and decoding technology based on the seamless switching report to schedule process nodes, achieving process automation and generating an automated process flow. This means that the entire manufacturing process can be carried out without human intervention, reducing the need for operators, reducing labor costs, and improving manufacturing consistency and controllability.

[0128] Please refer to Figure 6 , the wear monitoring submodule uses vibration spectrum analysis and ultrasonic detection technology based on the automated process flow to monitor tool wear in real time, generating a wear monitoring report;

[0129] The health status submodule uses statistical health models and Bayesian inference based on the wear monitoring report to assess the current health status of the tool, generating a tool health report;

[0130] The maintenance reminder submodule uses a time series prediction model based on the tool health report to predict the tool's maintenance cycle and generate a maintenance reminder.

[0131] First, the wear monitoring submodule uses vibration spectrum analysis and ultrasonic detection technology based on the automated process flow to monitor tool wear in real time, generating a wear monitoring report. This helps to track the status of the tool in real time, detects wear or damage problems in advance, reduces unnecessary downtime and maintenance time, and improves production efficiency.

[0132] Secondly, the health condition sub-module assesses the current health condition of the tool based on the wear monitoring report, combining statistical health models with Bayesian inference, and generates a tool health report. Through this assessment, the production team can better understand the tool's life and performance, take appropriate measures to ensure that the tool remains in optimal condition throughout its life, and reduce the risk of sudden failure.

[0133] Finally, the maintenance reminder sub-module predicts the tool's maintenance cycle based on the tool health report and generates a maintenance reminder through a time series prediction model. This function helps manufacturing enterprises to make effective maintenance plans, ensuring that tools are timely maintained and replaced, extending the tool's service life and reducing unnecessary repair costs.

[0134] Please refer to Figure 7 , the historical data processing sub-module uses time series analysis methods combined with data normalization techniques to deeply clean, integrate, and classify historical tool data, generating an integrated historical data report.

[0135] The tool parameter optimization sub-module uses Q-learning reinforcement learning algorithms and Bayesian optimization based on the integrated historical data report to fine-tune tool parameters, generating a parameter optimization report.

[0136] The learning effect feedback sub-module evaluates the learning effect based on the parameter optimization report using K-fold cross-validation methods and mean square error analysis, generating a learning effect feedback report.

[0137] First, the historical data processing sub-module uses time series analysis methods combined with data normalization techniques to deeply clean, integrate, and classify historical tool data, generating an integrated historical data report. This provides a solid data foundation for tool performance analysis, helping to understand the tool's historical performance and trends.

[0138] Secondly, the tool parameter optimization sub-module uses Q-learning reinforcement learning algorithms and Bayesian optimization based on the integrated historical data report to fine-tune tool parameters, generating a parameter optimization report. This step uses intelligent algorithms to find the best tool parameter configuration to improve tool service life and performance.

[0139] Finally, the learning effect feedback sub-module evaluates the learning effect based on the parameter optimization report using K-fold cross-validation methods and mean square error analysis, generating a learning effect feedback report. This helps to evaluate the effectiveness of the optimization algorithm and provides feedback information for further improving tool performance.

[0140] Please refer to Figure 8, the database establishment submodule is based on parameter optimization report, using association rule mining and clustering analysis technology, structured construction of cloud tool database, generate tool cloud database structure;

[0141] The system connection submodule is based on the tool cloud database structure, using RESTful API technology and secure connection protocol, form cloud tool database connection;

[0142] The automatic retrieval submodule is based on the cloud tool database connection, using hash retrieval algorithm, for the current tool type parameter retrieval, generate tool parameter retrieval results.

[0143] First, the database establishment submodule is based on parameter optimization report, using association rule mining and clustering analysis technology, structured construction of cloud tool database, generate tool cloud database structure. This initiative will integrate historical and real-time data, establish a comprehensive, structured tool database. This enables enterprises to better manage and track the performance and use of tools, thereby improving the utilization and performance of tools.

[0144] Second, the system connection submodule is based on the tool cloud database structure, using RESTful API technology and secure connection protocol, form cloud tool database connection. This means that enterprises can access and manage the tool database through a secure network connection. This enables tool information to be quickly transmitted to where it is needed, such as production lines, management departments, etc., to achieve more efficient tool management and decision-making.

[0145] Finally, the automatic retrieval submodule is based on the cloud tool database connection, using hash retrieval algorithm, for the current tool type parameter retrieval, generate tool parameter retrieval results. This means that staff can easily obtain the relevant parameter information of the current tool without manual searching or calculation. This improves work efficiency and reduces possible errors.

[0146] Please refer to Figure 9 , the image capture submodule uses high-speed image acquisition technology combined with HDR technology to capture tool images in the machine tool working area in real time, generating machine tool working area images;

[0147] The tool type recognition submodule is based on the machine tool working area image, using deep convolutional neural network technology, generate tool type recognition results;

[0148] The tool position recognition submodule is based on the tool type recognition result, using ORB feature matching technology, determine the position of the tool on the machine tool, generate tool position report.

[0149] The image capture submodule uses high-speed image acquisition technology combined with HDR technology to capture tool images in the machine tool working area in real time, generating machine tool working area images;

[0150] The tool type identification submodule generates tool type identification results based on the machine tool working area image using deep convolutional neural network technology.

[0151] The tool position identification submodule determines the position of the tool on the machine tool based on the tool type identification results using ORB feature matching technology, and generates a tool position report.

[0152] Please refer to Figure 10 The dynamic adjustment submodule adjusts the tool parameters in real time based on the tool position report, combining online adaptive learning and simulated annealing algorithm, and generates a dynamic parameter adjustment scheme.

[0153] The material adaptation submodule adjusts the tool parameters based on the material characteristics using a material science knowledge base and machine learning prediction model based on the dynamic parameter adjustment scheme, and generates a material adaptation parameter scheme.

[0154] The process condition adaptation submodule optimizes tool parameters based on process conditions using environmental perception technology and genetic algorithm optimization based on the material adaptation parameter scheme, and generates a parameter optimization scheme.

[0155] The dynamic adjustment submodule adjusts the tool parameters in real time based on the tool position report, combining online adaptive learning and simulated annealing algorithm, and generates a dynamic parameter adjustment scheme. This allows the system to adjust the parameters in real time according to the real-time position and state of the tool, to adapt to different processing conditions. The result is that the tool can maintain optimal performance in different situations, reducing the risk of tool wear and failure, and improving processing quality and efficiency.

[0156] The material adaptation submodule adjusts the tool parameters based on the material characteristics using a material science knowledge base and machine learning prediction model based on the dynamic parameter adjustment scheme, and generates a material adaptation parameter scheme. This means that the tool can be automatically adjusted according to the characteristics of different processing materials, maximizing processing efficiency and reducing material loss. This also helps to avoid excessive wear and extend the life of the tool.

[0157] The process condition adaptation submodule optimizes tool parameters based on real-time process conditions using environmental perception technology and genetic algorithm optimization based on the material adaptation parameter scheme, and generates a parameter optimization scheme. This step will take into account environmental changes and different production processes to ensure the best match of tool parameters. This improves the flexibility and adaptability of the production line, reduces the risk of processing errors, and improves production efficiency.

[0158] The above merely describes the preferred embodiments of the present application, and is not intended to limit the present application in other forms. Any skilled person in the art can modify or change the disclosed technical content into equivalent embodiments with equivalent changes, and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application, without departing from the technical solution content of the present application, still falls within the protection scope of the present application.

Claims

1. An automatic input and acquisition system for tool setting parameters in a machining center, characterized in that: The automatic tool setting parameter input and acquisition system of the machining center consists of an intelligent tool identification module, a real-time error correction module, a process automation module, a tool condition monitoring module, an intelligent learning module, a tool cloud database module, an image processing and pattern recognition module, and an adaptive parameter optimization module. The intelligent tool recognition module uses a deep learning algorithm based on convolutional neural networks to automatically identify special tools, automatically generate tool setting parameters, and establish a tool recognition report. The real-time error correction module uses the gradient descent algorithm to perform real-time error correction based on the tool identification report, and generates an error correction report and an accuracy assurance report. The process automation module, based on error correction reports, uses workflow management technology to automate the process flow, enabling automatic adjustment of production plans and forming an automated process flow. The tool condition monitoring module is based on an automated process flow and uses sensor data analysis technology to monitor the health status of the tool in real time and generate a tool health report. The intelligent learning module is based on the tool health report and uses a reinforcement learning algorithm to automatically optimize the tool setting parameters according to historical data and generate a parameter optimization report. The tool cloud database module establishes a cloud tool database based on the parameter optimization report, and automatically retrieves parameters according to the current tool type to form a cloud tool database connection; The image processing and pattern recognition module is based on a cloud-based tool database connection. It uses image processing and pattern recognition algorithms to automatically identify the tool type and position in the machine tool's working area and generate a tool position and type report. The adaptive parameter optimization module generates a parameter optimization scheme based on the tool position and type report and using an adaptive parameter optimization algorithm based on gradient reinforcement learning. The intelligent tool identification module includes a tool type submodule, a tool orientation submodule, and a tool parameter generation submodule; The real-time error correction module includes a real-time detection submodule, an error correction submodule, and an accuracy assurance submodule. The process automation module includes a parameter adjustment submodule, a seamless switching submodule, and a process automation submodule. The tool condition monitoring module includes a wear monitoring submodule, a health status submodule, and a maintenance reminder submodule; The intelligent learning module includes a historical data processing submodule, a tool parameter optimization submodule, and a learning effect feedback submodule. The tool cloud database module includes a database creation submodule, a system connection submodule, and an automatic retrieval submodule; The image processing and pattern recognition module includes an image capture submodule, a tool type recognition submodule, and a tool position recognition submodule; The adaptive parameter optimization module includes a dynamic adjustment submodule, a material adaptation submodule, and a process condition adaptation submodule.

2. The machining center tool parameter automatic recording and collecting system according to claim 1, characterized in that: The tool type submodule uses a convolutional neural network deep learning algorithm combined with feature layer visualization to extract features from the input image, identify the tool type, and generate a tool type identification report. The tool orientation submodule determines the orientation of the tool based on the tool type identification report, using image rotation correction technology and edge detection, and generates a tool orientation identification report. The tool parameter generation submodule estimates and generates a tool parameter report based on the tool orientation identification report and using data fitting and regression techniques.

3. The machining center tool parameter automatic recording and collecting system according to claim 1, characterized in that: The real-time detection submodule uses high-speed ADC sampling technology to capture the tool's running status in real time and detect errors, generating a real-time detection report; The error correction submodule corrects errors based on real-time detection reports, combining gradient descent algorithm and dynamic adjustment strategy, and generates an error correction report. The accuracy assurance submodule, based on the error correction report, uses fault-tolerant coding and redundancy strategies to ensure that the machining accuracy is not affected by external factors and generates an accuracy assurance report.

4. The machining center tool parameter automatic recording and collecting system according to claim 1, characterized in that: The parameter adjustment submodule, based on the accuracy assurance report, uses fuzzy logic control to dynamically adjust the process parameters according to environmental changes and generate a parameter adjustment report. The seamless switching submodule, based on the parameter adjustment report, utilizes state machine logic control to ensure smooth switching and continuity of the production line, and generates a seamless switching report. The process automation submodule, based on seamless switching reports, uses PID control and encoding / decoding technologies to schedule process nodes, thereby achieving process automation and generating automated process flows.

5. The machining center tool parameter automatic recording and collecting system according to claim 1, characterized in that: The wear monitoring submodule is based on an automated process flow and uses vibration spectrum analysis and ultrasonic testing technology to monitor tool wear in real time and generate a wear monitoring report. The health status submodule assesses the current health status of the tool based on the wear monitoring report, combined with a statistical health model and Bayesian inference, and generates a tool health report. The maintenance reminder submodule uses the tool health report and a time series prediction model to predict the tool maintenance cycle and generate maintenance reminders.

6. The machining center tool parameter automatic recording and collecting system according to claim 1, characterized in that: The historical data processing submodule uses time series analysis methods combined with data normalization technology to perform in-depth cleaning, integration and classification of historical tool data, and generate an integrated historical data report. The tool parameter optimization submodule, based on the integrated historical data report, uses Q-learning reinforcement learning algorithm and Bayesian optimization to perform fine-grained optimization of tool setting parameters and generate a parameter optimization report. The learning performance feedback submodule evaluates the learning performance based on the parameter optimization report, using K-fold cross-validation and mean square error analysis, and generates a learning performance feedback report.

7. The automatic input and acquisition system for tool setting parameters of a machining center according to claim 1, characterized in that: The database establishment submodule, based on the parameter optimization report, uses association rule mining and cluster analysis techniques to structurally construct the cloud-based tool database and generate the tool cloud database structure. The system connection submodule is based on the tool cloud database structure and uses RESTful API technology and secure connection protocol to form a cloud tool database connection; The automatic retrieval submodule is based on a cloud-based tool database connection and uses a hash retrieval algorithm to perform parameter retrieval for the current tool type, generating tool parameter retrieval results.

8. The automatic input and acquisition system for tool setting parameters of a machining center according to claim 1, characterized in that: The image capture submodule uses high-speed image acquisition technology combined with HDR technology to capture tool images in the machine tool working area in real time and generate machine tool working area images; The tool type recognition submodule generates tool type recognition results based on the machine tool working area image and using deep convolutional neural network technology. The tool position recognition submodule determines the tool's position on the machine tool and generates a tool position report based on the tool type recognition result and ORB feature matching technology.

9. The automatic input and acquisition system for tool setting parameters of a machining center according to claim 1, characterized in that: The dynamic adjustment submodule, based on the tool position report and combined with online adaptive learning and simulated annealing algorithms, performs real-time fine-tuning of tool parameters to generate a dynamic parameter adjustment scheme. The material adaptation submodule is based on a dynamic parameter adjustment scheme. It applies a materials science knowledge base and a machine learning prediction model to adjust tool parameters based on materials and generate a material adaptation parameter scheme. The process condition adaptation submodule, based on the material adaptation parameter scheme, combines environmental perception technology and genetic algorithm optimization to optimize tool parameters based on process conditions and generate parameter optimization schemes.

Images