Adaptive machine tool processing method and system based on intelligent perception

Abstract

The present invention discloses an adaptive machine tool processing method and system based on intelligent perception, which relates to the field related to intelligent manufacturing. The method includes: deploying intelligent perception equipment; acquiring processing tasks, parsing processing tasks, and constructing stage partitions of processing stages; configuring intelligent perception equipment, completing initialization, aligning with the zero point of the machine tool, and activating the intelligent perception equipment when executing processing tasks; performing time series data monitoring, and feeding back the time series data monitoring results to the processing center for processing and analysis; after optimizing the processing parameters of the machine tool by generating response compensation according to the processing and analysis results, performing early warning monitoring of the machine tool based on the processing early warning window, and performing processing management according to the early warning monitoring results. The technical problem of low precision of processing process control existing in the existing machine tool processing method is solved, and the technical effect of improving the precision of the processing process is achieved.

Description

Technical Field

[0001] The present application relates to fields related to intelligent manufacturing, and in particular to an adaptive machine tool processing method and system based on intelligent perception. Background Art

[0002] With the rapid development of the manufacturing industry, the requirements for machine tool processing accuracy, efficiency and safety are getting higher and higher. In the existing machine tool processing methods, the processing tasks are usually completed by operators manually setting machine tool parameters according to processing drawings and process requirements. During the processing, workers need to constantly observe the operating status of the machine tool and make necessary adjustments based on experience. However, this method often has errors due to manual judgment and experience adjustments, and it is difficult to ensure the accuracy of the processing process.

[0003] In the current related technologies, the machine tool processing method has the technical problem of low control accuracy of the processing process. Summary of the invention

[0004] The present application provides an adaptive machine tool processing method and system based on intelligent perception, deploys intelligent sensing equipment, monitors various data in the machine tool processing process in real time, performs intelligent analysis and processing through a processing center, and other technical means. By real-time monitoring and analysis of data in the machine tool processing process, the processing parameters are adjusted in real time, thereby achieving the technical effect of improving the accuracy of the processing process.

[0005] The present application provides an adaptive machine tool processing method based on intelligent perception, including:

[0006] Deploy intelligent sensing devices, which include a sensor group for monitoring and an IOT device for transmission; obtain a processing task of a machine tool, which includes processing product information and processing strategy information, parse the processing task, and construct a stage partition of the processing stage, wherein each stage partition maps a compensation response subnetwork; configure the intelligent sensing device based on the processing task, complete the initialization of the intelligent sensing device, and align the zero point of the intelligent sensing device and the machine tool, and synchronously activate the intelligent sensing device when the machine tool performs the processing task; monitor the time series data through the sensor group, and feed back the time series data monitoring results to the processing center through the IOT device, and process and analyze the time series data monitoring results through the processing center to obtain the processing analysis results, wherein the processing center stores all the compensation response subnetworks; generate response compensation according to the processing analysis results, and establish a processing warning window, after optimizing the processing parameters of the machine tool based on the response compensation, perform early warning monitoring of the machine tool based on the processing warning window, and perform processing management according to the early warning monitoring results.

[0007] In a possible implementation, the processing center performs processing and analysis on the time series data monitoring results, obtains the processing and analysis results, and performs the following processing:

[0008] Parse the time series data monitoring results to obtain monitoring time nodes; match and activate the compensation response subnetwork through the monitoring time nodes; establish a time period, which is the processing period of the activated compensation response subnetwork, and perform an end approximation evaluation of the current processing stage based on the monitoring time nodes and the time period, and construct an approximation evaluation coefficient; initialize the activated compensation response subnetwork through the approximation evaluation coefficient, process the time series data monitoring results according to the initialized compensation response subnetwork, and generate a compensation result; obtain the processing analysis result according to the compensation result.

[0009] In a possible implementation, the end approximation evaluation of the current processing stage is performed based on the monitoring time node and the time period, an approximation evaluation coefficient is constructed, and the following processing is performed:

[0010] The approximate evaluation coefficient is constructed as follows: Among them, C is the approximation evaluation coefficient, δ is the adjustment coefficient used to control the approximation rate, t is the monitoring time node, and t s is the starting time node of the current processing stage, and T is the time period of the current processing stage.

[0011] In a possible implementation, the time series data monitoring result is processed according to the initialized compensation response sub-network to generate a compensation result, and the following processing is performed:

[0012] The timing data monitoring result is extracted by a preprocessing unit, and a unit feed error is constructed according to the extracted result. The preprocessing unit is a processing unit of the compensation response subnetwork; a cumulative error is constructed based on the timing data monitoring result, and the post-processing task of the current processing stage is reconstructed based on the cumulative error and the processing task; the approximation evaluation coefficient is called, and a step compensation fitting is performed based on the approximation evaluation coefficient and the post-processing task to obtain a step compensation fitting result; the step compensation fitting result is optimized by the unit feed error to generate the compensation result.

[0013] In a possible implementation, the following processing is performed:

[0014] A tool timing data set based on machine vision acquisition is established; perspective recognition is performed on the tool timing data set, and tool wear is established according to the perspective recognition result; and unit feed error compensation is performed according to the tool wear.

[0015] In a possible implementation, the processing and analysis result is obtained according to the compensation result, and the following processing is performed:

[0016] Analyze the time series data monitoring results to obtain the time series thermal monitoring data; evaluate the heat accumulation in the area through the time series thermal monitoring data and establish the heat accumulation anomaly; perform coolant-based heat accumulation anomaly response optimization, and obtain the processing analysis result according to the response optimization result and the compensation result.

[0017] In a possible implementation, the execution is based on the coolant heat accumulation abnormal response optimization, the processing analysis result is obtained according to the response optimization result and the compensation result, and the following processing is performed:

[0018] Determine whether the response optimization result cannot adapt to the thermal accumulation anomaly; if the response optimization result cannot adapt to the thermal accumulation anomaly, generate a path reconstruction instruction; re-plan the cutting path through the path reconstruction instruction, generate parameter compensation according to the re-planned cutting path, and obtain the processing analysis result according to the parameter compensation, the response optimization result and the compensation result.

[0019] The present application also provides an adaptive machine tool processing system based on intelligent perception, including:

[0020] An intelligent sensing device deployment module, the intelligent sensing device deployment module is used to deploy intelligent sensing devices, the intelligent sensing devices include a sensor group for monitoring and an IOT device for transmission; a stage partition construction module, the stage partition construction module is used to obtain a processing task of a machine tool, the processing task includes processing product information and processing strategy information, parse the processing task, and construct a stage partition of the processing stage, wherein each stage partition maps a compensation response subnetwork; an intelligent sensing device activation module, the intelligent sensing device activation module is used to configure the intelligent sensing device based on the processing task, complete the initialization of the intelligent sensing device, and align the zero point of the intelligent sensing device and the machine tool, and execute the processing on the machine tool. When a task is performed, the intelligent sensing device is synchronously activated; a monitoring result processing and analysis module, the monitoring result processing and analysis module is used to monitor the time series data through the sensor group, and feed back the time series data monitoring results to the processing center through the IOT device, and the processing center processes and analyzes the time series data monitoring results to obtain processing and analysis results, wherein the processing center stores all compensation response sub-networks; a processing management module, the processing management module is used to generate response compensation according to the processing and analysis results, and establish a processing early warning window, after optimizing the processing parameters of the machine tool based on the response compensation, perform early warning monitoring of the machine tool based on the processing early warning window, and perform processing management according to the early warning monitoring results.

[0021] The adaptive machine tool processing method and system based on intelligent perception proposed in this application first deploy intelligent perception equipment, including a sensor group for monitoring and an IOT device for transmission, then obtain the processing task of the machine tool, including processing product information and processing strategy information, parse the processing task, and construct a stage partition of the processing stage, wherein each stage partition maps a compensation response subnetwork, then configure the intelligent perception device based on the processing task, complete the initialization of the intelligent perception device, and align the zero point of the intelligent perception device and the machine tool, when the machine tool performs the processing task, the intelligent perception device is synchronously activated, and then the time series data is monitored through the sensor group, and the time series data monitoring results are fed back to the processing center through the IOT device, and the processing center performs processing and analysis of the time series data monitoring results to obtain the processing analysis results, wherein the processing center stores all the compensation response subnetworks, and finally generates response compensation according to the processing analysis results, and establishes a processing warning window, after the processing parameters of the machine tool are optimized based on the response compensation, the machine tool is early warning monitored based on the processing warning window, and the processing management is performed according to the early warning monitoring results, thereby achieving the technical effect of improving the accuracy of the processing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0023] Figure 1 A schematic flow chart of an adaptive machine tool processing method based on intelligent perception provided in an embodiment of the present application.

[0024] Figure 2 A schematic diagram of the structure of an adaptive machine tool processing system based on intelligent perception provided in an embodiment of the present application.

[0025] Explanation of the reference numerals: intelligent sensing device deployment module 10 , stage partition construction module 20 , intelligent sensing device activation module 30 , monitoring result processing and analysis module 40 , processing management module 50 . DETAILED DESCRIPTION

[0026] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0027] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0028] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0029] The present application embodiment provides an adaptive machine tool processing method based on intelligent perception, such as Figure 1 As shown, the method includes:

[0030] Step S100, deploy intelligent sensing devices, which include a sensor group for monitoring and an IOT device for transmission. Specifically, the sensor group is a collection of multiple sensors, which are used to monitor various physical quantities in the machine tool processing process; the IOT device is an Internet of Things device, which is used to transmit the data collected by the sensor to the processing center. Specifically, according to the characteristics and requirements of the machine tool processing, select suitable sensor types and quantities, including temperature sensors, vibration sensors, pressure sensors, etc., to monitor various physical quantities of the machine tool during the processing process. The selected sensors are installed on the machine tool in a predetermined position and manner, and the installation position can maximize the reflection of the state changes in the machine tool processing process. According to the selected sensor type and quantity, configure the corresponding IOT device, connect the IOT device with the sensor, and realize real-time data collection and transmission. The connection method can include wired connection and wireless connection, depending on the actual situation and requirements of the machine tool.

[0031] Step S200, obtaining the processing task of the machine tool, the processing task includes processing product information and processing strategy information, parsing the processing task, and constructing the stage partition of the processing stage, wherein each stage partition maps a compensation response subnetwork. Specifically, the processing task of the machine tool is obtained from the production planning system, task management system or manual input, that is, the specific processing operation that the machine tool needs to perform, including processing product information and processing strategy information, wherein the processing product information is information describing the material, size, shape and other characteristics of the product to be processed, and the processing strategy information is information describing the details of the cutting conditions, processing sequence, processing path and the like during the processing, such as cutting speed, feed rate, cutting depth and the like. The obtained processing task is parsed in detail to determine the specific requirements and goals of the processing, that is, the processing product information is analyzed to determine the key parameters such as the material properties and geometric shape of the product, and the processing strategy information is analyzed to clarify the details such as the cutting conditions, processing sequence, processing path and the like. According to the complexity of the processing task and the performance of the machine tool, the processing process is divided into several logically continuous but different stage partitions. Each stage partition represents a specific processing operation or a group of related processing operations. The start and end conditions of each stage partition and the conversion logic between stage partitions are determined. For each processing stage partition, a compensation response subnetwork is designed. The compensation response subnetwork is an algorithm or model for adjusting processing parameters according to real-time monitoring data. Each stage partition is mapped with the corresponding compensation response subnetwork to ensure that these compensation response subnetworks can be correctly called and applied during the processing process.

[0032] Step S300, configure the intelligent sensing device based on the processing task, complete the initialization of the intelligent sensing device, align the zero point of the intelligent sensing device and the machine tool, and synchronously activate the intelligent sensing device when the machine tool performs the processing task. Specifically, analyze the specific requirements of the processing task, such as processing materials, processing accuracy, processing speed, etc., determine the key parameters that the intelligent sensing device needs to monitor, and adjust the configuration parameters of the sensor group according to the requirements of the processing task, such as sampling frequency, range, sensitivity, etc., to ensure that the sensor can accurately capture the key changes in the machine tool processing process. Configure the communication parameters of the IOT device, such as IP address, port number, data transmission format, etc., to ensure unimpeded communication between the sensor group and the processing center. Start the intelligent sensing device, perform self-test and initialization operations on it, check whether the working status of the sensor is normal, such as whether there is damage, drift, etc.; check whether the communication status of the IOT device is normal, such as whether it can be successfully connected to the processing center. Align the zero point of the intelligent sensing device with the machine tool to ensure data synchronization and accuracy between the two. When the machine tool starts to perform processing tasks, the intelligent sensing device is started and activated synchronously. The sensor group monitors the key parameters of the machine tool processing process in real time and transmits the data to the processing center in real time through the IOT device.

[0033] Step S400, monitor the time series data through the sensor group, and feed back the time series data monitoring results to the processing center through the IOT device, and process and analyze the time series data monitoring results through the processing center to obtain the processing and analysis results, wherein the processing center stores all the compensation response subnetworks. Specifically, the sensor group monitors various physical quantities such as temperature, vibration, pressure, etc. in the machine tool processing process in real time according to the preset sampling frequency and range. The sensor group transmits the collected time series data (data arranged in time order, used to describe the change of a physical quantity over time) to the processing center in real time through the IOT device. The processing center is a computer system or server for receiving, storing and processing data from intelligent sensing devices, which has powerful computing power and storage capacity and can support complex data processing and analysis tasks. The processing center processes and analyzes the received time series data according to the preset algorithms and models, and calls the corresponding compensation response subnetwork to process the time series data according to the stage partition of the processing task, including data cleaning, feature extraction, pattern recognition, etc., to obtain the processing and analysis results. Among them, the compensation response subnetwork adjusts the processing parameters according to the real-time data to improve the processing accuracy and efficiency.

[0034] In a possible implementation, the processing and analysis of the time series data monitoring results are performed by the processing center to obtain the processing and analysis results, and step S400 further includes step S410, parsing the time series data monitoring results and obtaining the monitoring time nodes. Specifically, the time series data monitoring results are read from the data source, and the time series data monitoring results include a timestamp and a corresponding monitoring value. The timestamp information, i.e., the monitoring time node, is extracted from the read data. The monitoring time node indicates the specific time point when the data is collected or monitored. Step S420, matching and activating the compensation response subnetwork is performed through the monitoring time node. Specifically, each compensation response subnetwork is used to optimize different time nodes, and according to the acquired monitoring time node, a matching compensation response subnetwork is found and activated.

[0035] Step S430, establish a time period, the time period is the processing period of the activated compensation response subnetwork, perform an approximation evaluation of the end of the current processing stage based on the monitoring time node and the time period, and construct an approximation evaluation coefficient. Specifically, set a processing period (a fixed time length, used to define the processing period of the compensation response subnetwork) for each activated compensation response subnetwork, and this time period can be set according to actual needs and the characteristics of the compensation response subnetwork. According to the current monitoring time node and the set time period, judge whether the current processing stage is close to the end, for example, by calculating the difference or ratio between the monitoring time node and the time period to evaluate whether the current processing stage is close to the end. Based on the result of the end approximation evaluation, construct an approximation evaluation coefficient to indicate the degree of approximation to the end of the current processing stage. Step S440, initialize the activated compensation response subnetwork through the approximation evaluation coefficient, perform time series data monitoring result processing according to the initialized compensation response subnetwork, and generate compensation results. Specifically, the constructed approximation evaluation coefficient is used to initialize the activated compensation response subnetwork, including adjusting the parameters, weights or other configurations of the subnetwork, and the initialized compensation response subnetwork is used to process the time series data monitoring results, including filtering, prediction, interpolation and other operations, and based on the processed data, a compensation result is generated, and the compensation result is used to correct the anomaly or fluctuation in the original data. Step S450, the processing analysis result is obtained according to the compensation result. Specifically, the generated compensation result is integrated with the original time series data monitoring result, and the integrated data is further analyzed and interpreted to generate the final processing analysis result. This implementation method evaluates the end approximation degree of the current processing stage by monitoring the time node and time period, and constructs the approximation evaluation coefficient. This evaluation method enables the progress and status of the processing process to be more accurately grasped, and provides an accurate information basis for subsequent compensation processing, thereby achieving the technical effect of improving the accuracy of the compensation result.

[0036] In a possible implementation, the end approximation evaluation of the current processing stage is performed based on the monitoring time node and the time period to construct an approximation evaluation coefficient. Step S430 further includes step S431, and the approximation evaluation coefficient is constructed as follows:

[0037]

[0038] Among them, C is the approximation evaluation coefficient, δ is the adjustment coefficient used to control the approximation rate, t is the monitoring time node, and t sis the start time node of the current processing stage, and T is the time period of the current processing stage. Specifically, the approximation evaluation coefficient is a coefficient used to quantify the degree to which the current processing stage is close to the end. The closer the approximation evaluation coefficient is to 1, the closer the current processing stage is to the end; the closer the approximation evaluation coefficient is to 0, the current processing stage has just begun; the adjustment coefficient is a parameter used to control the approximation rate, which can be adjusted according to actual needs to control the growth rate of the approximation evaluation coefficient over time; the monitoring time node refers to the monitoring time at the current moment; the start time node of the current processing stage refers to the moment when the current processing stage starts; the time period of the current processing stage refers to the total time required for the current processing stage. This implementation method quantifies the degree to which the current processing stage is close to the end by constructing the approximation evaluation coefficient, thereby achieving the technical effect of providing an accurate information basis for subsequent compensation processing.

[0039] In a possible implementation, the instantaneous data monitoring result is processed according to the initialized compensation response subnetwork to generate a compensation result. Step S440 further includes step S441, extracting the instantaneous data monitoring result through a preprocessing unit, and constructing a unit feed error according to the extracted result. The preprocessing unit is a processing unit of the compensation response subnetwork. Specifically, the preprocessing unit extracts key information such as position, speed, acceleration, etc. from the instantaneous data monitoring result, calculates the error value within each unit time or unit distance according to the extracted information, and constructs a unit feed error. Step S442, constructs a cumulative error based on the instantaneous data monitoring result, and reconstructs the post-processing task of the current processing stage based on the cumulative error and the processing task. Specifically, the unit feed error in the instantaneous data monitoring result is accumulated to obtain the cumulative error, that is, the total error from the current processing stage to the current time point. According to the cumulative error and the original processing task, the impact on the subsequent processing is analyzed, and the post-processing task of the current processing stage is reconstructed, that is, the subsequent processing task that needs to be performed in the current processing stage. By reconstructing the post-processing task, the impact of the cumulative error is offset. Step S443, calling the approximation evaluation coefficient, performing step compensation fitting based on the approximation evaluation coefficient and the post-processing task, and obtaining the step compensation fitting result. Specifically, calling the approximation evaluation coefficient, the approximation evaluation coefficient reflects the degree to which the current processing stage is close to the end, and performing step compensation fitting according to the approximation evaluation coefficient and the reconstructed post-processing task. The step compensation fitting is a compensation strategy, and the compensation value is calculated in a step-by-step manner according to the approximation evaluation coefficient and the requirements of the post-processing task. Step S444, optimizing the step compensation fitting result by the unit feed error, and generating the compensation result. Specifically, the unit feed error is used as an optimization factor, and the unit feed error reflects the real-time error of the processing process. The step compensation fitting result is fine-tuned by the unit feed error to generate the final compensation result. This implementation method constructs unit feed error and cumulative error by extracting time series data monitoring results, accurately determines the error situation in the machining process, and performs step compensation fitting based on the approximation evaluation coefficient and post-machining tasks. It can perform compensation processing in real time according to the progress and status of the machining process, achieving the technical effect of improving the accuracy and real-time performance of compensation.

[0040] In a possible implementation, step S441 further includes step S4411, establishing a tool timing data set based on machine vision acquisition. Specifically, during the processing, a machine vision system (such as a camera) is used to capture the image of the tool in real time, and the captured image data is organized in time series to form a tool timing data set. Step S4412, perspective recognition is performed on the tool timing data set, and tool wear is established based on the perspective recognition result. Specifically, perspective recognition processing is performed on each image in the tool timing data set to extract key information such as the shape and size of the tool, wherein the perspective recognition is an image processing technology for extracting three-dimensional information such as depth and shape from a two-dimensional image. Compare and analyze the tool information at different time points, calculate the wear of the tool, and establish a tool wear model or data table based on the calculation results to record the wear of the tool at different time points. Step S4413, perform unit feed error compensation based on the tool wear. Specifically, according to the tool wear model or data table, the wear amount of the current tool is queried, and the unit feed error compensation value is calculated based on the wear amount, wherein the greater the wear amount, the greater the compensation value. The calculated compensation value is applied to the processing process to correct the unit feed error to offset the error caused by tool wear. This implementation method accurately evaluates the wear of the tool by establishing a tool time series data set and performing perspective recognition, and performs unit feed error compensation accordingly, achieving the technical effect of ensuring that the unit feed error is corrected in a timely manner.

[0041] In a possible implementation, the processing and analysis results are obtained according to the compensation results, and step S450 further includes step S451, parsing the time series data monitoring results to obtain time series heat monitoring data. Specifically, data related to heat changes are extracted from the time series data monitoring results, and the extracted data is preprocessed, such as denoising, smoothing, etc., to obtain accurate time series heat monitoring data. Step S452, the heat accumulation in the area is evaluated through the time series heat monitoring data, and the heat accumulation anomaly is established. Specifically, according to the time series heat monitoring data, the accumulation of heat in a specific area is analyzed, and a heat accumulation threshold is set. When the heat accumulation exceeds the threshold, it is considered that there is a heat accumulation anomaly, that is, the heat accumulation anomaly refers to an abnormal state caused by continuous heat accumulation in a certain area, which may have an adverse effect on equipment performance or product quality. Record the location, time and other information of the heat accumulation anomaly for subsequent analysis and processing. Step S453, perform heat accumulation anomaly response optimization based on coolant, and obtain the processing and analysis result according to the response optimization result and the compensation result. Specifically, when abnormal heat accumulation is detected, a response optimization process based on coolant is started, wherein coolant is a liquid used to reduce the temperature of equipment or workpieces, and removes heat through circulating flow. The current use of coolant, such as flow rate, temperature, etc., is analyzed, and the parameters of the coolant are adjusted according to the analysis results, such as increasing the flow rate, lowering the temperature, etc., to accelerate heat dissipation, reduce heat accumulation, and obtain response optimization effects. Combined with the previous compensation results, a comprehensive analysis is performed to obtain the final processing analysis results. This implementation method can timely detect abnormal heat accumulation of equipment or workpieces during the processing process through the analysis of time-series heat monitoring data. By adjusting the use parameters of the coolant, the heat dissipation effect is optimized, and the heat accumulation problem is effectively solved, achieving the technical effect of preventing abnormal heat accumulation from adversely affecting equipment performance or product quality, and ensuring that the equipment or workpiece maintains stable performance during the processing process.

[0042] In a possible implementation, the execution is based on the heat accumulation abnormal response optimization of the coolant, and the processing analysis result is obtained according to the response optimization result and the compensation result. Step S453 further includes step S4531, judging whether the response optimization result cannot adapt to the heat accumulation abnormality; step S4532, if the response optimization result cannot adapt to the heat accumulation abnormality, then generating a path reconstruction instruction. Specifically, the real-time monitoring data after the coolant response optimization is collected, including temperature, heat accumulation, etc., and the data before and after the optimization are compared to evaluate whether the heat accumulation abnormality is effectively controlled or reduced. Based on the set evaluation criteria (such as the temperature drop rate, the degree of heat accumulation reduction, etc.), it is judged whether the response optimization result is adapted to the current heat accumulation abnormality, that is, whether the response optimization measures can effectively solve or alleviate the heat accumulation abnormality. When it is judged that the response optimization result cannot adapt to the heat accumulation abnormality, the path reconstruction process is triggered, and the path reconstruction instruction is generated based on the current processing state, material characteristics, equipment performance and other factors, that is, during the processing process, due to the heat accumulation abnormality, the original cutting path is no longer applicable, and the cutting path needs to be replanned. The path reconstruction instruction is used to guide how to replan the cutting path. Instructions or parameter settings. Step S4533, re-plan the cutting path through the path reconstruction instruction, generate parameter compensation according to the re-planned cutting path, and obtain the processing analysis result according to the parameter compensation, response optimization result and the compensation result. Specifically, according to the path reconstruction instruction, re-plan the cutting path to ensure that the new path can reduce the risk of heat accumulation. Based on the new cutting path, recalculate or adjust the processing parameters (such as feed speed, cutting depth, etc.) to generate parameter compensation. Comprehensively analyze the parameter compensation, response optimization results and previous compensation results to obtain the final processing analysis result. In this implementation method, when the coolant response optimization cannot effectively adapt to the heat accumulation anomaly, the heat accumulation risk is reduced through path reconstruction and parameter compensation, and the technical effect of taking corresponding optimization and compensation measures for different heat accumulation situations to enhance the robustness and adaptability of the system is achieved.

[0043] Step S500, generate response compensation according to the processing and analysis results, and establish a processing warning window. After optimizing the processing parameters of the machine tool based on the response compensation, perform warning monitoring of the machine tool based on the processing warning window, and perform processing management according to the warning monitoring results. Specifically, based on the processing and analysis results of the time series data, generate corresponding response compensation for each processing stage according to preset rules and algorithms. The response compensation is an adjustment suggestion or optimization plan proposed for the deviation or abnormal situation in the machine tool processing process, including adjusting the processing parameters such as cutting speed, feed rate, cutting depth, or a suggestion for adjusting the machine tool state. According to the characteristics of the processing task and the analysis results of the time series data, establish a processing warning window. The processing warning window is a time range or condition range. When the processing state or time series data of the machine tool enters this range, an early warning will be triggered. The setting of the processing warning window is based on historical data, expert experience or machine learning model, which is used to discover potential processing problems or abnormal situations in advance. By adjusting the control system of the machine tool or sending a control command, the generated response compensation is applied to the processing parameters of the machine tool to optimize the parameters. The processing effect, processing accuracy and efficiency are improved through parameter optimization, while reducing deviations and abnormalities in the processing process. During the processing of the machine tool, the time series data and the machine tool status are continuously monitored. When the processing status of the machine tool or the time series data enters the processing warning window, the warning is triggered. The warning form can include sound alarm, screen display, sending notifications, etc. After the operator or system receives the warning, it takes corresponding management measures according to the warning monitoring results, including shutdown, adjustment of processing parameters, replacement of tools or fixtures, etc. By performing processing management according to the warning monitoring results, the stability of the machine tool processing process and product quality are ensured, while the failure rate and maintenance cost are reduced. The embodiment of the present application adopts the deployment of intelligent sensing equipment, real-time monitoring of various data in the machine tool processing process, and intelligent analysis and processing and other technical means through the processing center. By real-time monitoring and analysis of data in the machine tool processing process, the processing parameters are adjusted in real time, and the technical effect of improving the accuracy of the processing process is achieved.

[0044] In the above, refer to Figure 1 The adaptive machine tool processing method based on intelligent perception according to an embodiment of the present invention is described in detail. Figure 2 An adaptive machine tool processing system based on intelligent perception according to an embodiment of the present invention is described.

[0045] The adaptive machine tool processing system based on intelligent perception according to the embodiment of the present invention is used to solve the technical problem of low precision of processing control in the existing machine tool processing method, so as to achieve the technical effect of improving the precision of the processing process. The adaptive machine tool processing system based on intelligent perception includes: an intelligent perception device deployment module 10, a stage partition construction module 20, an intelligent perception device activation module 30, a monitoring result processing and analysis module 40, and a processing management module 50.

[0046] The intelligent sensing device deployment module 10 is used to deploy intelligent sensing devices, and the intelligent sensing devices include a sensor group for monitoring and an IOT device for transmission; the stage partition construction module 20 is used to obtain the processing task of the machine tool, and the processing task includes processing product information and processing strategy information, parse the processing task, and construct the stage partition of the processing stage, wherein each stage partition maps a compensation response subnetwork; the intelligent sensing device activation module 30 is used to configure the intelligent sensing device based on the processing task, complete the initialization of the intelligent sensing device, and align the zero point of the intelligent sensing device and the machine tool. When the machine tool performs the processing task, step, activating the intelligent sensing device; the monitoring result processing and analysis module 40 is used to monitor the time series data through the sensor group, and feed back the time series data monitoring results to the processing center through the IOT device, and the processing center processes and analyzes the time series data monitoring results to obtain processing and analysis results, wherein the processing center stores all compensation response sub-networks; the processing management module 50 is used to generate response compensation according to the processing and analysis results, and establish a processing early warning window, after optimizing the processing parameters of the machine tool based on the response compensation, perform early warning monitoring of the machine tool based on the processing early warning window, and perform processing management according to the early warning monitoring results.

[0047] The specific configuration of the monitoring result processing and analysis module 40 will be described in detail below. As described above, the processing and analysis of the time series data monitoring results are performed through the processing center to obtain the processing and analysis results. The monitoring result processing and analysis module 40 may further include: a monitoring time node acquisition unit for parsing the time series data monitoring results and obtaining the monitoring time node; a compensation response subnetwork matching activation unit for matching and activating the compensation response subnetwork through the monitoring time node; an end approximation evaluation unit for establishing a time period, which is the processing period of the activated compensation response subnetwork, performing the end approximation evaluation of the current processing stage based on the monitoring time node and the time period, and constructing an approximation evaluation coefficient; a compensation result generation unit for initializing the activated compensation response subnetwork through the approximation evaluation coefficient, performing time series data monitoring result processing according to the initialized compensation response subnetwork, and generating a compensation result; a processing and analysis result acquisition unit for obtaining the processing and analysis result according to the compensation result.

[0048] Wherein, the end approximation evaluation of the current processing stage is performed based on the monitoring time node and the time period, and the approximation evaluation coefficient is constructed. The end approximation evaluation unit may further include: an approximation evaluation coefficient construction subunit is used to construct the approximation evaluation coefficient as follows: Among them, C is the approximation evaluation coefficient, δ is the adjustment coefficient used to control the approximation rate, t is the monitoring time node, and t s is the starting time node of the current processing stage, and T is the time period of the current processing stage.

[0049] Among them, the compensation response subnetwork after initialization processes the timing data monitoring results to generate compensation results, and the compensation result generating unit may further include: a unit feed error construction subunit for extracting the timing data monitoring results through a preprocessing unit, and constructing a unit feed error according to the extracted results, and the preprocessing unit is a processing unit of the compensation response subnetwork; a post-processing task reconstruction subunit for constructing a cumulative error based on the timing data monitoring results, and reconstructing the post-processing tasks of the current processing stage based on the cumulative error and the processing tasks; a step compensation fitting subunit for calling the approximation evaluation coefficient, and performing step compensation fitting based on the approximation evaluation coefficient and the post-processing tasks to obtain a step compensation fitting result; a step compensation fitting result optimization subunit for optimizing the step compensation fitting result through the unit feed error to generate the compensation result.

[0050] Among them, the unit feed error construction subunit may further include: a tool timing data set establishment microunit for establishing a tool timing data set based on machine vision acquisition; a tool wear establishment microunit for performing perspective recognition on the tool timing data set, and establishing tool wear according to the perspective recognition result; a unit feed error compensation microunit for performing unit feed error compensation according to the tool wear.

[0051] Among them, the processing and analysis result is obtained according to the compensation result, and the processing and analysis result acquisition unit may further include: a time series thermal monitoring data acquisition subunit for parsing the time series data monitoring result to obtain the time series thermal monitoring data; a thermal accumulation anomaly establishment subunit for evaluating the thermal accumulation in the area through the time series thermal monitoring data and establishing the thermal accumulation anomaly; a thermal accumulation anomaly response optimization subunit for performing coolant-based thermal accumulation anomaly response optimization, and obtaining the processing and analysis result according to the response optimization result and the compensation result.

[0052] Among them, the execution is based on the coolant-based thermal accumulation abnormality response optimization, and the processing analysis result is obtained according to the response optimization result and the compensation result. The thermal accumulation abnormality response optimization subunit may further include: a judgment microunit is used to judge whether the response optimization result cannot adapt to the thermal accumulation abnormality; a path reconstruction instruction generation microunit is used to generate a path reconstruction instruction if the response optimization result cannot adapt to the thermal accumulation abnormality; a parameter compensation generation microunit is used to re-plan the cutting path through the path reconstruction instruction, and generate parameter compensation according to the re-planned cutting path, and the processing analysis result is obtained according to the parameter compensation, the response optimization result and the compensation result.

[0053] The adaptive machine tool processing system based on intelligent perception provided by the embodiment of the present invention can execute the adaptive machine tool processing method based on intelligent perception provided by any embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method.

[0054] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0055] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. An adaptive machine tool processing method based on intelligent perception, characterized in that: The method comprises: Deploy intelligent sensing devices, which include a sensor group for monitoring and an IOT device for transmission; Acquire a processing task of a machine tool, the processing task including processing product information and processing strategy information, parse the processing task, and construct phase partitions of the processing phase, wherein each phase partition maps a compensation response subnetwork, the compensation response subnetwork is an algorithm or model for adjusting processing parameters according to real-time monitoring data, and each phase partition is mapped to a corresponding compensation response subnetwork for calling and processing during the processing; The intelligent sensing device is configured based on the processing task, the intelligent sensing device is initialized, and the zero point of the intelligent sensing device and the machine tool are aligned, and when the machine tool performs the processing task, the intelligent sensing device is synchronously activated; The sensor group is used to monitor the time series data, and the time series data monitoring results are fed back to the processing center through the IOT device. The processing center is used to process and analyze the time series data monitoring results to obtain the processing and analysis results, wherein the processing center stores all the compensation response sub-networks; The processing and analysis of the time series data monitoring results by the processing center to obtain the processing and analysis results includes: Analyze the time series data monitoring results to obtain the monitoring time nodes; Perform matching activation of the compensation response sub-network through the monitoring time node; Establishing a time period, the time period being a processing period of the activated compensation response subnetwork, performing an end approximation evaluation of the current processing stage based on the monitoring time node and the time period, and constructing an approximation evaluation coefficient; Initializing the activated compensation response sub-network by using the approximation evaluation coefficient, processing the time series data monitoring result according to the initialized compensation response sub-network, and generating a compensation result; Obtaining the processing and analysis result according to the compensation result; The processing of the time series data monitoring results according to the initialized compensation response sub-network to generate compensation results includes: Extracting the monitoring result of the time series data through a preprocessing unit, and constructing a unit feeding error according to the extracted result, wherein the preprocessing unit is a processing unit of the compensation response subnetwork; Constructing a cumulative error based on the time series data monitoring result, and reconstructing a post-processing task of the current processing stage based on the cumulative error and the processing task; Calling the approximation evaluation coefficient, performing step compensation fitting based on the approximation evaluation coefficient and the post-processing task, and obtaining a step compensation fitting result; Optimizing the step compensation fitting result by using the unit feed error to generate the compensation result; A response compensation is generated according to the processing and analysis results, and a processing warning window is established. After the processing parameters of the machine tool are optimized based on the response compensation, early warning monitoring of the machine tool is performed based on the processing warning window, and processing management is performed according to the early warning monitoring results.

2. The adaptive machine tool processing method based on intelligent perception according to claim 1, characterized in that: The step of performing an end approximation evaluation of the current processing stage based on the monitoring time node and the time period and constructing an approximation evaluation coefficient further includes: The approximate evaluation coefficient is constructed as follows: ； in, To approximate the evaluation coefficient, is the adjustment coefficient, used to control the approach rate, To monitor the time nodes, is the start time node of the current processing stage, It is the time period of the current processing stage.

3. The adaptive machine tool processing method based on intelligent perception according to claim 1, characterized in that: The method further comprises: Establish tool timing data set based on machine vision acquisition; Performing perspective recognition on the tool time series data set, and establishing tool wear according to the perspective recognition result; Unit feed error compensation is performed according to the tool wear.

4. The adaptive machine tool processing method based on intelligent perception according to claim 1, characterized in that: The obtaining the processing and analysis result according to the compensation result further includes: Analyze the time series data monitoring results to obtain the time series heat monitoring data; Conducting heat accumulation evaluation in the region through the time series heat monitoring data and establishing heat accumulation anomalies; Optimizing the response based on the abnormal heat accumulation of the coolant is performed, and the processing analysis result is obtained according to the response optimization result and the compensation result.

5. The adaptive machine tool processing method based on intelligent perception as claimed in claim 4, characterized in that: The performing of the coolant-based heat accumulation abnormal response optimization, and obtaining the processing analysis result according to the response optimization result and the compensation result, further includes: Determining whether the response optimization result cannot adapt to the heat accumulation anomaly; If the response optimization result cannot adapt to the heat accumulation anomaly, generating a path reconstruction instruction; The cutting path is replanned through the path reconstruction instruction, and parameter compensation is generated according to the replanned cutting path. The processing analysis result is obtained according to the parameter compensation, the response optimization result and the compensation result.

6. Adaptive machine tool processing system based on intelligent perception, characterized in that: The system is used to implement the adaptive machine tool processing method based on intelligent perception according to any one of claims 1 to 5, and the system comprises: An intelligent sensing device deployment module, wherein the intelligent sensing device deployment module is used to deploy intelligent sensing devices, wherein the intelligent sensing devices include a sensor group for monitoring and an IOT device for transmission; A phase partition construction module, the phase partition construction module is used to obtain a processing task of a machine tool, the processing task includes processing product information and processing strategy information, parse the processing task, and construct phase partitions of the processing phase, wherein each phase partition is mapped to a compensation response subnetwork, the compensation response subnetwork is an algorithm or model for adjusting processing parameters according to real-time monitoring data, and each phase partition is mapped to a corresponding compensation response subnetwork for calling and processing during the processing process; An intelligent sensing device activation module, the intelligent sensing device activation module is used to configure the intelligent sensing device based on the processing task, complete the initialization of the intelligent sensing device, and align the zero point of the intelligent sensing device and the machine tool, and synchronously activate the intelligent sensing device when the machine tool performs the processing task; A monitoring result processing and analysis module, which is used to monitor the time series data through the sensor group, and feed back the time series data monitoring results to the processing center through the IOT device, and process and analyze the time series data monitoring results through the processing center to obtain the processing and analysis results, wherein the processing center stores all the compensation response subnetworks; A processing management module, wherein the processing management module is used to generate response compensation according to the processing analysis results, and establish a processing warning window. After optimizing the processing parameters of the machine tool based on the response compensation, early warning monitoring of the machine tool is performed based on the processing warning window, and processing management is performed according to the early warning monitoring results.

Images