Intelligent manufacturing adaptive processing system and real-time quality detection method

Abstract

The invention discloses an intelligent manufacturing adaptive processing system and a real-time quality detection method, and relates to the technical field of intelligent manufacturing, and the system comprises an initialization module which is used for carrying out parameter initialization and communication configuration on a processing equipment control system, and obtaining equipment operation state data and processing technology initial parameters; and the data acquisition module is used for performing real-time data acquisition on the workpiece machining process by using the multi-sensor array to obtain real-time data of the machining process. Through self-adaptive machining parameter adjustment, the adaptability of the machining process to different working conditions is improved, the stability of product quality is guaranteed, quality problems are found and processed in time through real-time quality detection, unqualified products are reduced, data interaction and cooperative work among the modules are reduced, and the production efficiency is improved. Integration of the machining process and quality detection is achieved, and the production efficiency and the intelligent level are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing technology, and in particular to an intelligent manufacturing adaptive processing system and a real-time quality inspection method. Background Technology

[0002] Traditional intelligent manufacturing processing systems have many shortcomings in practical applications, making it difficult to meet complex and ever-changing production demands. On the one hand, existing systems lack effective adaptive adjustment mechanisms when processing workpieces of different materials and specifications. Processing parameters often use fixed preset values ​​and cannot be dynamically optimized based on the real-time processing status of the workpiece, equipment operating conditions, and environmental factors. This leads to problems such as substandard workpiece surface roughness and large dimensional accuracy deviations during processing, seriously affecting the stability of product quality. For example, when milling metal materials of varying hardness, if the spindle speed and feed rate cannot be adjusted in real time according to the material hardness, it will exacerbate tool wear, and the workpiece processing quality will be difficult to guarantee.

[0003] On the other hand, most existing quality inspection methods rely on offline inspection or periodic sampling, which cannot achieve real-time quality monitoring of the processing process. This lagging inspection method makes it difficult to detect and deal with quality problems in a timely manner. Defective products are often only detected after mass production, resulting in a huge waste of raw materials, manpower, and time. Moreover, offline inspection cannot form a closed-loop feedback with the processing process, making it difficult to correct processing parameters in a timely manner. For example, in the turning of precision parts, if the diameter of the part cannot be detected in real time and fed back to the processing system, the cutting depth cannot be adjusted in time, leading to the production of a large number of defective parts.

[0004] Furthermore, the existing system has weak data interaction and collaborative capabilities between processing equipment and quality inspection equipment. A large amount of real-time data generated during processing, such as cutting force, vibration signals, and temperature, has not been fully utilized for quality inspection and processing parameter optimization. The quality data obtained by the inspection equipment cannot be transmitted to the processing system in a timely manner, which makes the processing process and the quality inspection process isolated from each other and unable to achieve true intelligent manufacturing.

[0005] Therefore, it is necessary to invent an intelligent manufacturing adaptive processing system and a real-time quality inspection method to solve the above problems. Summary of the Invention

[0006] The purpose of this invention is to provide an intelligent manufacturing adaptive processing system and a real-time quality inspection method. By adjusting the adaptive processing parameters, the system improves the adaptability of the processing process to different working conditions, ensuring the stability of product quality. Real-time quality inspection enables the timely detection and handling of quality problems, reducing the generation of defective products. Data interaction and collaborative work between modules realize the integration of the processing process and quality inspection, improving production efficiency and intelligence level, thereby solving the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: an intelligent manufacturing adaptive processing system, comprising...

[0008] The initialization module is used to initialize parameters and configure communication in the control system of the processing equipment, and to obtain equipment operating status data and initial parameters of the processing technology.

[0009] The data acquisition module is used to acquire real-time data of the workpiece processing process using a multi-sensor array, and obtain real-time data of the processing process.

[0010] The parameter optimization module is used to dynamically optimize and adjust the processing parameters based on the real-time data of the processing process using an adaptive algorithm, so as to obtain the optimized processing parameters.

[0011] The quality inspection module is used to perform online quality inspection on the workpiece during processing through a real-time quality inspection module, and to obtain quality inspection data.

[0012] The feedback control module is used to perform feedback control on the processing process based on the quality inspection data and preset quality standards, adjusting processing parameters or triggering anomaly handling mechanisms; and

[0013] The management module is used to classify and trace the quality of completed workpieces, and generate quality reports and optimization suggestions for processing parameters.

[0014] This invention also provides a real-time quality detection method for an intelligent manufacturing adaptive processing system, specifically including the following steps:

[0015] S1. Initialize parameters and configure communication for the control system of the processing equipment to obtain equipment operating status data and initial parameters of the processing technology.

[0016] S2. Use a multi-sensor array to collect real-time data on the workpiece processing process and obtain real-time data on the processing process.

[0017] S3. Based on the real-time data of the processing process, an adaptive algorithm is used to dynamically optimize and adjust the processing parameters to obtain the optimized processing parameters;

[0018] S4. Perform online quality inspection on the workpiece during processing through the real-time quality inspection module to obtain quality inspection data;

[0019] S5. Based on the quality inspection data and preset quality standards, perform feedback control on the processing process, adjust processing parameters or trigger an abnormal handling mechanism;

[0020] S6. Perform quality classification and traceability management on the completed workpieces, and generate quality reports and processing parameter optimization suggestions.

[0021] Preferably, S3 includes:

[0022] A mapping model between processing parameters and processing quality indicators is established, and the mapping model is expressed as: Q=f(P,D)

[0023] Where Q is the processing quality index vector, P is the processing parameter vector, D is the real-time data vector of the processing process, and f is the mapping function;

[0024] Based on the real-time data vector D of the processing process and the preset quality index threshold, the processing parameter adjustment amount ΔP is calculated, and the calculation formula for the adjustment amount is:

[0025] ΔP=K·(Qtarget-Qcurrent)·g(D)

[0026] Where K is the adjustment coefficient matrix, Qtarget is the target quality index vector, Qvurrent is the current quality index vector, and g(D) is the adjustment factor function based on the processing data.

[0027] The current processing parameters are updated based on the processing parameter adjustment amount ΔP to obtain the optimized processing parameters Poptimized:

[0028] That is: Poptimized=Pcurrent+ΔP.

[0029] Preferably, S4 includes:

[0030] The surface morphology image data of the workpiece is acquired using a visual inspection sensor, and the surface roughness parameters are calculated using an image recognition algorithm.

[0031] The displacement sensor is used to measure the changes in workpiece dimensions in real time to obtain dimensional deviation data;

[0032] Force sensors are used to collect cutting force data, and the relationship between the trend of cutting force changes and machining quality is analyzed.

[0033] Preferably, S5 includes:

[0034] The quality inspection data is compared with the preset quality standard to calculate the quality deviation value;

[0035] When the quality deviation is within the preset allowable range, maintain the current processing parameters;

[0036] When the quality deviation exceeds the preset allowable range, the processing parameter adjustment amount is calculated according to S3 and the parameters are adjusted accordingly.

[0037] When the quality deviation value exceeds the critical threshold, the abnormal handling mechanism is triggered, including equipment shutdown, alarm, and resetting of processing parameters.

[0038] The technical effects and advantages of this invention are as follows:

[0039] This invention improves the adaptability of the processing process to different working conditions by adaptively adjusting processing parameters, ensuring the stability of product quality. Real-time quality detection enables timely detection and handling of quality problems, reducing the generation of defective products. Data interaction and collaborative work between modules realize the integration of processing and quality detection, improving production efficiency and intelligence level. Attached Figure Description

[0040] Figure 1 This is a schematic diagram of the system structure of the present invention;

[0041] Figure 2 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] This invention provides, for example Figure 1 The intelligent manufacturing adaptive machining system shown is characterized by: including an initialization module: the initialization module initializes the parameters and configures the communication of the machining equipment control system. First, it performs a power-on self-test on the hardware such as the motor and sensors of the machining equipment to obtain the equipment operating status data, including IO signal status and equipment interlock status. Then, according to the machining process requirements, it sets the initial parameters such as machining temperature, cutting speed, and feed rate. At the same time, it establishes a communication connection with the production execution system (MES) to obtain production work order information, including workpiece type and machining process requirements. Finally, it calibrates the coordinate system and calibrates the origin of the machining equipment to ensure machining accuracy.

[0044] Data Acquisition Module: The data acquisition module uses a multi-sensor array to collect real-time data on the workpiece machining process. For example, during milling, force sensors collect cutting force data, vibration sensors collect equipment vibration data, temperature sensors collect temperature data in the cutting area, and displacement sensors collect workpiece displacement data. The data collected by the sensors is converted from A / D and transmitted to the data processing unit via a communication bus to obtain real-time data on the machining process.

[0045] Parameter optimization module: Based on real-time machining data, the parameter optimization module uses an adaptive algorithm to dynamically optimize and adjust machining parameters. Taking cutting speed optimization in milling as an example, a mapping relationship model between cutting speed, surface roughness, and tool wear is established: Q=f(P,D)

[0046] Where Q is a quality index vector composed of surface roughness and tool wear, P is the cutting speed parameter, and D is a vector of collected machining process data such as cutting force and vibration.

[0047] Based on the currently collected machining process data D and the preset surface roughness threshold, calculate the cutting speed adjustment ΔP: ΔP=K·(Qtarget-Qcurrent)·g(D)

[0048] Where K is the adjustment coefficient, Qtarget is the target quality index, Qcurrent is the current quality index, and g(D) is the adjustment factor function based on cutting force and vibration data;

[0049] For example, g(D) = 1 + ek·F1, where F is the cutting force and k is a constant;

[0050] The current cutting speed is updated based on the calculated adjustment amount ΔP, resulting in the optimized cutting speed Poptimized:

[0051] That is: Poptimized=Pcurrent+ΔP;

[0052] Quality Inspection Module: The quality inspection module performs online quality inspection on the workpiece during processing using real-time quality inspection equipment. Taking visual inspection as an example, an industrial camera is used to acquire images of the workpiece surface morphology, and surface roughness parameters are calculated through image recognition algorithms. At the same time, a laser displacement sensor is used to measure the changes in workpiece dimensions in real time to obtain dimensional deviation data. The cutting force data collected by the force sensor can be used to analyze the relationship between the trend of cutting force changes and processing quality. For example, a sudden increase in cutting force may indicate tool wear or abnormal workpiece material.

[0053] Feedback control module: The feedback control module compares the quality inspection data with the preset quality standard, calculates the quality deviation value, and maintains the current cutting speed when the surface roughness deviation is within the preset allowable range. When the deviation exceeds the allowable range, the parameter optimization module is called to calculate the cutting speed adjustment amount and adjust the parameters. When the deviation exceeds the severe threshold, the abnormal handling mechanism is triggered, including equipment shutdown, alarm and processing parameter reset.

[0054] The management module classifies the finished workpieces by quality, classifying them into qualified, unprocessed, and unqualified products based on indicators such as surface roughness and dimensional accuracy. It also manages the traceability of workpieces, recording information such as processing parameters, quality inspection data, and processing equipment. Based on historical processing data and quality inspection results, it generates quality reports and processing parameter optimization suggestions to provide a reference for subsequent processing.

[0055] In summary, through the collaborative work of the above modules, this invention achieves intelligent manufacturing adaptive processing and real-time quality inspection, improving product quality and production efficiency, and has broad application prospects.

[0056] This invention also provides a real-time quality detection method for an intelligent manufacturing adaptive processing system, specifically including the following steps:

[0057] S1. Initialize parameters and configure communication for the control system of the processing equipment, obtain equipment operating status data and initial processing parameters. This step ensures that each module of the equipment works normally and establishes a data communication channel with other systems to provide basic data for subsequent processing and testing.

[0058] S2. Real-time data acquisition of the workpiece machining process is performed using a multi-sensor array, including physical quantities such as cutting force, vibration, temperature, and displacement, to obtain real-time machining process data. By deploying various types of sensors, comprehensive information is acquired during the machining process, providing data support for machining parameter optimization and quality inspection.

[0059] S3. Based on the real-time data of the processing process, an adaptive algorithm is used to dynamically optimize and adjust the processing parameters to obtain optimized processing parameters. By establishing a mapping relationship model between processing parameters and quality indicators, the parameter adjustment amount is calculated in real time to realize the dynamic optimization of processing parameters to adapt to different processing conditions.

[0060] Specifically, this includes establishing a mapping model between processing parameters and processing quality indicators, which is expressed as: Q = f(P, D)

[0061] Where Q is the processing quality index vector, P is the processing parameter vector, D is the real-time data vector of the processing process, and f is the mapping function;

[0062] Based on the real-time data vector D of the processing process and the preset quality index threshold, the processing parameter adjustment amount ΔP is calculated, and the calculation formula for the adjustment amount is:

[0063] ΔP=K·(Qtarget-Qcurrent)·g(D)

[0064] Where K is the adjustment coefficient matrix, Qtarget is the target quality index vector, Qcurrent is the current quality index vector, and g(D) is the adjustment factor function based on the processing data.

[0065] The current processing parameters are updated based on the processing parameter adjustment amount ΔP to obtain the optimized processing parameters Poptimized:

[0066] That is: Poptimized=Pcurrent+ΔP;

[0067] S4. The real-time quality inspection module performs online quality inspection on the workpiece during processing, obtains quality inspection data, and uses technologies such as vision inspection, displacement sensing, and force sensing to perform real-time inspection on key indicators such as surface quality and dimensional accuracy of the workpiece to ensure that quality problems are detected in a timely manner.

[0068] Specifically, this includes using visual inspection sensors to acquire image data of the workpiece surface morphology and calculating surface roughness parameters using image recognition algorithms;

[0069] The displacement sensor is used to measure the changes in workpiece dimensions in real time to obtain dimensional deviation data;

[0070] Force sensors are used to collect cutting force data, and the relationship between the trend of cutting force variation and machining quality is analyzed.

[0071] S5. Based on the quality inspection data and preset quality standards, feedback control is performed on the processing process, processing parameters are adjusted or an abnormal handling mechanism is triggered. By comparing the inspection data with the standards, closed-loop control of the processing process is achieved to ensure the stability of processing quality.

[0072] Specifically, this includes comparing the quality inspection data with a preset quality standard and calculating the quality deviation value;

[0073] When the quality deviation is within the preset allowable range, maintain the current processing parameters;

[0074] When the quality deviation exceeds the preset allowable range, the processing parameter adjustment amount is calculated according to S3 and the parameters are adjusted accordingly.

[0075] When the quality deviation value exceeds the critical threshold, the abnormal handling mechanism is triggered, including equipment shutdown, alarm, and resetting of processing parameters;

[0076] S6. Perform quality classification and traceability management on the finished workpieces, generate quality reports and processing parameter optimization suggestions, and provide reference for subsequent processing by analyzing historical data to continuously optimize the processing technology.

[0077] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An intelligent manufacturing adaptive processing system, characterized in that: include The initialization module is used to initialize parameters and configure communication in the control system of the processing equipment, and to obtain equipment operating status data and initial parameters of the processing technology. The data acquisition module is used to acquire real-time data of the workpiece processing process using a multi-sensor array, and obtain real-time data of the processing process. The parameter optimization module is used to dynamically optimize and adjust the processing parameters based on the real-time data of the processing process using an adaptive algorithm, so as to obtain the optimized processing parameters. The quality inspection module is used to perform online quality inspection on the workpiece during processing through the real-time quality inspection module and obtain quality inspection data. The feedback control module is used to perform feedback control on the processing process based on the quality inspection data and preset quality standards, and to adjust processing parameters or trigger an abnormal handling mechanism. as well as The management module is used to classify and trace the quality of completed workpieces, and generate quality reports and optimization suggestions for processing parameters.

2. A real-time quality inspection method for an intelligent manufacturing adaptive machining system, implemented using the intelligent manufacturing adaptive machining system as described in claim 1, characterized in that, Specifically, the following steps are included: S1. Initialize parameters and configure communication for the control system of the processing equipment to obtain equipment operating status data and initial parameters of the processing technology. S2. Use a multi-sensor array to collect real-time data on the workpiece processing process and obtain real-time data on the processing process. S3. Based on the real-time data of the processing process, an adaptive algorithm is used to dynamically optimize and adjust the processing parameters to obtain the optimized processing parameters; S4. Perform online quality inspection on the workpiece during processing through the real-time quality inspection module to obtain quality inspection data; S5. Based on the quality inspection data and preset quality standards, perform feedback control on the processing process, adjust processing parameters or trigger an abnormal handling mechanism; S6. Perform quality classification and traceability management on the completed workpieces, and generate quality reports and processing parameter optimization suggestions.

3. The real-time quality detection method for an intelligent manufacturing adaptive processing system according to claim 2, characterized in that: S3 includes: A mapping model between processing parameters and processing quality indicators is established, and the mapping model is expressed as: Q=f(P,D) Where Q is the processing quality index vector, P is the processing parameter vector, D is the real-time data vector of the processing process, and f is the mapping function; Based on the real-time data vector D of the processing process and the preset quality index threshold, the processing parameter adjustment amount ΔP is calculated, and the calculation formula for the adjustment amount is: ΔP=K·(Qtarget-Qcurrent)·g(D) Where K is the adjustment coefficient matrix, Qtarget is the target quality index vector, Qcurrent is the current quality index vector, and g(D) is the adjustment factor function based on the processing data. The current processing parameters are updated based on the processing parameter adjustment amount ΔP to obtain the optimized processing parameters Poptimized: That is: Poptimized=Pcurrent+ΔP.

4. The real-time quality detection method for an intelligent manufacturing adaptive processing system according to claim 3, characterized in that: S4 includes: The surface morphology image data of the workpiece is acquired using a visual inspection sensor, and the surface roughness parameters are calculated using an image recognition algorithm. The displacement sensor is used to measure the changes in workpiece dimensions in real time to obtain dimensional deviation data; Force sensors are used to collect cutting force data, and the relationship between the trend of cutting force changes and machining quality is analyzed.

5. The real-time quality detection method for an intelligent manufacturing adaptive processing system according to claim 4, characterized in that: S5 includes: The quality inspection data is compared with the preset quality standard to calculate the quality deviation value; When the quality deviation is within the preset allowable range, maintain the current processing parameters; When the quality deviation exceeds the preset allowable range, the processing parameter adjustment amount is calculated according to S3 and the parameters are adjusted accordingly. When the quality deviation value exceeds the critical threshold, the abnormal handling mechanism is triggered, including equipment shutdown, alarm, and resetting of processing parameters.

Images