A method, device and equipment for adaptive control of a wire cutting machining process

Abstract

The application relates to the field of workpiece machining, in particular to a wire cutting machining process adaptive control method, device and equipment. The method comprises the following steps: the application realizes active judgment of machining quality by monitoring the workpiece state (satisfying / unsatisfying) in real time, avoids waste loss caused by traditional post-detection, automatically collects key machining data (voltage, current and speed) when the workpiece is found to be unqualified, establishes a rapid traceability channel from quality problems to process parameters, and generates optimal machining parameters by using a dynamic analysis technology and feeds back the optimal machining parameters to a machining system in real time, so that a closed-loop control of "detection-analysis-optimization" is formed, the cost of manual intervention is reduced, the machining system always maintains an optimal working state through continuous optimization, and the production efficiency and product quality are comprehensively improved.

Description

Technical Field

[0001] The present application relates to the field of workpiece processing, and in particular to a method, device and equipment for adaptive control of a wire cutting process. Background Art

[0002] In wire electrical discharge machining (WEDM), workpiece quality is highly dependent on the stability of discharge parameters. Because WEDM is a non-contact process, the material removal process is strongly influenced by factors such as the discharge gap, electrode wear, and the state of the working fluid. This necessitates dynamic adjustment of machining parameters (such as pulse width, current, and voltage) based on the machining state.

[0003] Existing WEDM control systems mostly use preset parameters. During precision mold machining, as workpiece height increases, chip removal conditions deteriorate and discharge becomes unstable. Continuing to use fixed parameters can easily lead to problems such as reduced surface quality and excessive geometric accuracy. Traditional methods often rely on operator experience and manual intervention, making it difficult to guarantee workpiece quality. Therefore, a method to improve workpiece quality is urgently needed. Summary of the Invention

[0004] In order to improve the quality of processed workpieces, the present application provides a method, device and equipment for adaptive control of a wire cutting process.

[0005] In a first aspect, the present application provides a method for adaptive control of a wire cutting process, which adopts the following technical solutions:

[0006] A method for adaptive control of a wire cutting process, comprising:

[0007] Determining a workpiece state corresponding to a current workpiece, wherein the current workpiece is a workpiece generated during a current machining process, and the workpiece state is either satisfied or unsatisfied;

[0008] When the workpiece state of the current workpiece is unsatisfactory, obtaining processing data corresponding to the current processing process, the processing data including processing voltage, processing current and processing speed;

[0009] Dynamically analyze the processing data to determine optimal processing data, and send the optimal processing data to a corresponding processing system.

[0010] By adopting the above technical solution, active judgment of processing quality is achieved through real-time monitoring of the workpiece status (satisfied / unsatisfied), avoiding the waste loss caused by traditional post-inspection. When the workpiece is found to be unqualified, key processing data (voltage, current, speed) is automatically collected, and a rapid traceability channel from quality problems to process parameters is established. Dynamic analysis technology is used to automatically generate optimal processing parameters and provide real-time feedback to the processing system, forming a "detection-analysis-optimization" closed-loop control, thereby reducing the cost of manual intervention and keeping the processing system in the best working state through continuous optimization, comprehensively improving production efficiency and product quality.

[0011] In one possible implementation, determining the workpiece status corresponding to the current workpiece includes:

[0012] Acquire the inspection data corresponding to the current workpiece and obtain the standard data corresponding to the current workpiece, wherein the inspection data includes machining accuracy, surface quality, machining efficiency and material damage,

[0013] Comparing the test data with the standard data to obtain a comparison result, wherein the comparison result is consistent or inconsistent;

[0014] If the comparison result is consistent, determining that the workpiece state corresponding to the current workpiece is satisfied;

[0015] If the comparison result is inconsistent, it is determined that the workpiece status corresponding to the current workpiece is unsatisfactory.

[0016] In one possible implementation, dynamically analyzing the processing data to determine optimal processing data includes:

[0017] Determine defect parameters corresponding to the current workpiece, and obtain defect processing data corresponding to the defect parameters, wherein the defect parameters are one or more data in the detection data, and the defect processing data are one or more data in the detection data;

[0018] Determining, based on the defect processing data, standard processing parameters corresponding to the defect parameters meeting the standards;

[0019] Based on the standard processing parameters, optimal processing data is generated.

[0020] In a possible implementation, when the defect parameter includes multiple data, determining, based on the defect processing data, the standard processing parameter corresponding to the defect parameter meeting the standard includes:

[0021] Obtaining a fuzzy control rule corresponding to the defect parameter, wherein the fuzzy control rule associates a fuzzy mapping relationship between the defect parameter and the processing parameter;

[0022] Performing fuzzy processing on the defect processing data to obtain a fuzzy input value of the defect parameter;

[0023] Determining a fuzzy output value of the processing parameter through fuzzy reasoning based on the fuzzy input value and the fuzzy control rule;

[0024] The fuzzy output value is defuzzified to obtain the standard processing parameters corresponding to the defect parameters meeting the standards.

[0025] In a possible implementation, performing fuzzy processing on the defect processing data to obtain a fuzzy input value of the defect parameter includes:

[0026] For each defect parameter, convert the actual value of the defect parameter into the corresponding fuzzy set membership, and select the fuzzification strategy corresponding to the defect parameter;

[0027] Perform weighted processing on multi-dimensional defect parameters and assign different weight coefficients according to the degree of influence of each defect parameter on the processing quality;

[0028] The membership values ​​of each defect parameter under different fuzzy sets are output to form a multi-dimensional fuzzy input vector to obtain the fuzzy input value of the defect parameter.

[0029] In a possible implementation, defuzzification is performed on the fuzzy output value to obtain standard processing parameters corresponding to the defect parameters meeting the standard, including:

[0030] Defuzzifying the fuzzy output value to obtain preliminary parameters;

[0031] Performing simulated machining based on the preliminary parameters and predicting machining results;

[0032] Calculate the error function between the predicted effect and the standard parameter;

[0033] When the error function does not converge, the weight coefficients of the fuzzy rules are iteratively updated using the gradient descent method;

[0034] When the error function reaches a minimum value or the number of iterations exceeds a threshold, a processing parameter combination is output, and based on the processing parameter combination, a standard processing parameter is obtained.

[0035] In a possible implementation, based on the combination of processing parameters, standard processing parameters are obtained, including:

[0036] Check whether the combination of machining parameters exceeds the safe operating range of the machine tool;

[0037] If the combination of machining parameters does not exceed the safe operating range of the machine tool, virtual machining verification is performed through the digital twin system;

[0038] If the verification fails, the preliminary parameters are iterated again.

[0039] In a second aspect, the present application provides a wire cutting process adaptive control device, which adopts the following technical solution:

[0040] A wire cutting process adaptive control device, comprising:

[0041] a determination module, configured to determine a workpiece status corresponding to a current workpiece, wherein the current workpiece is a workpiece generated during a current machining process, and the workpiece status is either satisfied or unsatisfied;

[0042] an acquisition module, configured to acquire processing data corresponding to the current processing process when the workpiece state of the current workpiece is unsatisfactory, the processing data including processing voltage, processing current, and processing speed;

[0043] The sending module is used to dynamically analyze the processing data, determine the optimal processing data, and send the optimal processing data to the corresponding processing system.

[0044] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0045] An electronic device, comprising:

[0046] at least one processor;

[0047] Memory;

[0048] At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the method described in any one of the first aspects above.

[0049] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0050] A computer-readable storage medium, comprising: storing a computer program that can be loaded by a processor and execute any one of the methods described in the first aspect above.

[0051] In summary, this application has the following beneficial technical effects:

[0052] By real-time monitoring of the workpiece status (satisfied / unsatisfied), active judgment of processing quality is achieved, avoiding the waste loss caused by traditional post-inspection. When the workpiece is found to be unqualified, key processing data (voltage, current, speed) is automatically collected, and a rapid traceability channel from quality problems to process parameters is established. Dynamic analysis technology is used to automatically generate optimal processing parameters and provide real-time feedback to the processing system, forming a "detection-analysis-optimization" closed-loop control, thereby reducing the cost of manual intervention and keeping the processing system in the best working state through continuous optimization, comprehensively improving production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a flow chart of a method for adaptive control of a wire cutting process provided by an embodiment of the present application;

[0054] Figure 2 1 is a block diagram of an adaptive control device for a wire cutting process provided by an embodiment of the present application;

[0055] Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The following is combined with Figure 1 -Attached Figure 3 This application is described in further detail.

[0057] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0058] In order to facilitate understanding of the technical solutions proposed in this application, several elements that will be introduced in the description of this application are first introduced here. It should be understood that the following introduction is only for the convenience of understanding these elements, so as to understand the content of the embodiments of this application, and does not necessarily cover all possible situations.

[0059] In the field of electrical discharge machining (WEDM), the quality of workpiece processing is highly dependent on the stability of the discharge parameters. Since WEDM is a non-contact process, its material removal process is strongly affected by factors such as the discharge gap, electrode loss, and the state of the working fluid. As a result, the processing parameters (such as pulse width, current, and voltage) need to be dynamically adjusted according to the processing state. However, most existing WEDM control systems use preset parameters for processing, which makes it difficult to adapt to dynamic changes in the processing process in real time. For example, when processing precision mold cavities, as the processing depth increases, the chip removal conditions deteriorate and the discharge state becomes unstable. If fixed parameters are still used for processing, it is very easy to cause problems such as reduced surface quality and excessive geometric accuracy. Traditional methods usually rely on operator experience for manual intervention, which not only lags in adjustment, but also makes it difficult to ensure the scientific nature of process optimization.

[0060] The typical WEDM control method currently employs an "offline programming + online fine-tuning" model: initial parameters are set based on a process database of material-electrode combinations, and during processing, only simple threshold protection is implemented for extreme abnormalities (such as short circuits). This single parameter adjustment approach is difficult to fully optimize the processing state, especially when processing complex structures such as high-quality materials and tapered surfaces, and defects such as dimensional deviations may still occur.

[0061] In view of this, see Figure 1 The embodiment of the present application provides a method for adaptively controlling a wire cutting process, which is executed by an electronic device. The method includes:

[0062] Step S101: Determine the workpiece state corresponding to the current workpiece.

[0063] The current workpiece is a workpiece generated in the current machining process, and the workpiece status is satisfied or unsatisfied.

[0064] Specifically, the electronic device automatically collects key data about the workpiece, such as its geometry, surface roughness, and hardness, by connecting to testing instruments (such as a three-dimensional coordinate measuring machine, roughness tester, or hardness tester). It then compares this data with standard data stored in a database. If all collected data is within the allowable error range of the standard data, the workpiece status is considered "satisfactory." If any data item falls outside this error range, the workpiece status is considered "unsatisfactory."

[0065] More specifically, in this embodiment, determining the workpiece state corresponding to the current workpiece includes:

[0066] Obtain the inspection data corresponding to the current workpiece and obtain the standard data corresponding to the current workpiece. The inspection data includes processing accuracy, surface quality, processing efficiency and material damage.

[0067] Compare the test data with the standard data to obtain a comparison result, which is consistent or inconsistent;

[0068] If the comparison result is consistent, it is determined that the workpiece state corresponding to the current workpiece is satisfied;

[0069] If the comparison result is inconsistent, it is determined that the workpiece status corresponding to the current workpiece is unsatisfactory.

[0070] Among them, standard data include standard processing accuracy, standard surface quality, standard processing efficiency and standard material damage.

[0071] Specifically, the electronic device automatically collects relevant data about the current workpiece by connecting to various testing instruments, such as a three-dimensional coordinate measuring machine, surface roughness tester, hardness tester, and infrared thermal imager. The three-dimensional coordinate measuring machine measures the workpiece's geometric dimensions, form and position tolerances, and other machining accuracy data. The surface roughness tester detects microscopic undulations on the workpiece surface and obtains surface quality data. Machining efficiency data is calculated by calculating the amount of material removed per unit time or the time it takes to complete a machining process. An infrared thermal imager detects the workpiece's surface temperature distribution, and a metallographic microscope is used to observe changes in the material's microstructure to determine whether there is material damage. Simultaneously, the electronic device retrieves the corresponding standard data for the workpiece from the machining database, including the tolerance range for machining accuracy, the upper limit for surface roughness, specified machining efficiency indicators, and the qualified standards for material properties.

[0072] Furthermore, the collected test data are compared with the standard data one by one. For numerical data, such as processing dimensions and surface roughness values, it is determined whether the test data falls within the tolerance range specified by the standard data; for non-numerical data, such as the determination results of material damage (whether there are cracks or whether the structure is abnormal), a direct comparison is made to see whether it is consistent with the standard description. By traversing all test items, the comparison results of each data are generated, and finally the overall comparison conclusion is summarized, and the result is "consistent" (all test data meet the standard) or "inconsistent" (there is at least one data that exceeds the standard range). Furthermore, if the comparison results of all test data and standard data are "consistent", the workpiece status corresponding to the current workpiece is determined to be "satisfied", that is, the workpiece is qualified; if the comparison results of any one or more test data and standard data are "inconsistent", the workpiece status corresponding to the current workpiece is determined to be "unsatisfied", that is, the workpiece is unqualified.

[0073] Step S102: When the workpiece status of the current workpiece is unsatisfactory, obtain processing data corresponding to the current processing process.

[0074] The processing data includes processing voltage, processing current and processing speed.

[0075] The machining voltage is the voltage applied between the workpiece and the tool (such as the electrode wire) during the machining process, which directly affects the energy input and material removal efficiency.

[0076] The machining current is the current flowing through the workpiece and tool during the machining process, which is related to the discharge energy and the amount of material removed.

[0077] The machining speed is the relative movement rate of the workpiece or tool during the machining process, such as the electrode wire feed speed in EDM, the water spray speed in machining, or the worktable movement speed.

[0078] Specifically, when a workpiece's status is determined to be "unsatisfactory," the system uses a built-in data acquisition module to read data from sensors connected to the processing equipment (such as voltage sensors, current sensors, and displacement sensors) in real time, obtaining the current processing voltage, current, and speed. These sensors continuously monitor equipment operating parameters and transmit electrical signals to the electronic equipment, which then undergo analog-to-digital conversion to generate processable digital signals.

[0079] It is worth noting that when the artifact status of the current artifact is satisfied, no operation is performed.

[0080] Step S103: Dynamically analyze the processing data to determine the optimal processing data, and send the optimal processing data to the corresponding processing system.

[0081] Specifically, it can identify abnormal data patterns (such as excessive current fluctuations causing surface burns) and then calculate a corrected parameter combination based on preset rules or models to form "optimal processing data." Furthermore, the electronic device transmits this optimal processing data to the processing system controller via a communication interface (such as RS-485 or Ethernet), automatically adjusting the equipment's operating parameters and achieving real-time optimization of the processing process.

[0082] More specifically, in this embodiment, dynamically analyzing the processing data to determine the optimal processing data includes:

[0083] Determine defect parameters corresponding to the current workpiece, and obtain defect processing data corresponding to the defect parameters, where the defect parameters are one or more data in the detection data, and the defect processing data are one or more data in the detection data;

[0084] Based on the defect processing data, determine the standard processing parameters corresponding to the defect parameters meeting the standards;

[0085] Generate optimal processing data based on standard processing parameters.

[0086] Defect parameters refer to one or more indicators in the inspection data that do not meet standard requirements and are the direct cause of workpiece failure, such as dimensional deviation, excessive surface roughness, and insufficient material hardness. Defective processing data refers to processing data associated with defect parameters. It covers the real-time values ​​and changes of parameters such as processing voltage, processing current, and processing speed during the period when the defect occurs, and is used to analyze the cause of the defect.

[0087] After determining the current workpiece's "unsatisfactory" status, the inspection data is first classified and screened. Using a pre-set rule base, the key factors leading to workpiece failure are identified. For example, if the workpiece dimensions are out of tolerance, "machining accuracy - dimensional error" is marked as a defect parameter; if burn marks are present on the surface, "surface quality - burn condition" is listed as a defect parameter. After determining the defect parameters, historical and current data associated with these defect parameters are extracted from the real-time processing data (such as processing voltage, current, speed, etc.) to generate defect processing data.

[0088] Furthermore, after obtaining defective machining data, pre-set data analysis algorithms (such as fuzzy control algorithms and neural network algorithms) can be used to conduct in-depth mining of this data. For example, if the defect parameter is "machining accuracy - small aperture size," the voltage, current, and feed speed combinations for acceptable apertures can be analyzed in historical data. Combined with the abnormal characteristics of the current defective machining data (such as low machining current leading to insufficient discharge energy), the algorithm can simulate the impact of different parameter adjustments on aperture size. Ultimately, the specific values ​​of machining parameters such as voltage, current, and feed speed that achieve the standard aperture size can be calculated, which are referred to as the standard machining parameters.

[0089] Furthermore, after obtaining the standard processing parameters corresponding to the respective defect parameters, the standard processing parameters are combined, and the specific values ​​of the parameters except those corresponding to the defect parameters are integrated to obtain the optimal processing data.

[0090] In this embodiment, when the defect parameter includes multiple data, the standard processing parameters corresponding to the defect parameter meeting the standard are determined based on the defect processing data, including:

[0091] Obtaining fuzzy control rules corresponding to defect parameters, wherein the fuzzy control rules associate fuzzy mapping relationships between defect parameters and processing parameters;

[0092] Perform fuzzy processing on defect processing data to obtain fuzzy input values ​​of defect parameters;

[0093] Based on the fuzzy input value and fuzzy control rules, the fuzzy output value of the processing parameter is determined through fuzzy reasoning;

[0094] The fuzzy output value is defuzzified to obtain the standard processing parameters corresponding to the defect parameters reaching the standard.

[0095] Specifically, after identifying multiple defect parameters (such as dimensional deviation and surface roughness exceeding the specified value), the system retrieves fuzzy control rules related to these defect parameters from a built-in fuzzy rule library. The rule library is pre-stored in an "IF-THEN" format, for example: IF (dimensional deviation is "positive") AND (surface roughness is "neutral") THEN (processing voltage should be "increased") AND (processing current should be "decreased"). The electronic device uses keyword matching to filter out all rules that encompass the current defect parameter, forming a rule subset. For example, when the defect parameters include both "dimensional deviation" and "surface roughness," all rules involving these two parameters are extracted for subsequent reasoning. Fuzzy control rules are logical rules that describe the nonlinear mapping relationship between defect parameters and processing parameters. They are expressed using fuzzy linguistic variables (such as "positive" and "negative") and are acquired through expert knowledge or historical data training. The fuzzy rule library is a collection of all fuzzy control rules stored in the electronic device and serves as the knowledge base for the fuzzy control system.

[0096] Furthermore, the actual measured value of each defect parameter (e.g., a dimensional deviation of +0.05mm, a surface roughness of Ra = 3.2μm) is converted into a membership value of a fuzzy set. Specifically, fuzzy sets are defined: for each defect parameter, multiple fuzzy sets are predefined. For example, "dimensional deviation" is divided into {negative large, negative medium, zero, positive medium, positive large}, and each set corresponds to a membership function (e.g., triangular or trapezoidal function). The actual measured value is substituted into the membership function, and the membership of the value to each fuzzy set is calculated. For example, a dimensional deviation of +0.05mm may have a membership of 0.7 to the "positive medium" set and a membership of 0.3 to the "positive large" set. The membership values ​​of all defect parameters are combined into a multidimensional vector, which serves as the input for subsequent fuzzy reasoning.

[0097] Furthermore, a fuzzy logic inference algorithm is used to perform a composite operation on the fuzzy input values ​​and control rules to determine the direction and degree of adjustment of the processing parameters. Specifically, the fuzzy input values ​​are substituted into each selected fuzzy control rule, and the activation degree of each rule is calculated. For all activated rules, the conclusions of each rule are combined through a "smaller" (AND operation) or "larger" (OR operation) operation to obtain the output membership of the processing parameters under each fuzzy set. For example, multiple rules may each produce different degrees of membership for "voltage increase," which are then combined through a composite operation to form a comprehensive membership distribution. The fuzzy conclusions of all processing parameters (such as voltage, current, and speed) are combined into a fuzzy output vector.

[0098] Convert the fuzzy output values ​​into precise adjustment values ​​for the machining parameters. Specifically, select a defuzzification method: Common methods include the centroid method and the maximum membership method. Defuzzify the fuzzy output of each machining parameter (such as voltage and current) to obtain a specific numerical adjustment value. This adjustment value is then added to the current machining parameter to obtain the final standard machining parameter.

[0099] In this embodiment, fuzzy processing is performed on the defect processing data to obtain fuzzy input values ​​of defect parameters, including:

[0100] For each defect parameter, the actual value of the defect parameter is converted into the corresponding fuzzy set membership, and the fuzzification strategy corresponding to the defect parameter is selected;

[0101] Perform weighted processing on multi-dimensional defect parameters and assign different weight coefficients according to the degree of influence of each defect parameter on the processing quality;

[0102] The membership values ​​of each defect parameter under different fuzzy sets are output to form a multi-dimensional fuzzy input vector to obtain the fuzzy input value of the defect parameter.

[0103] Based on the type of defect parameter (e.g., continuous numerical value, discrete classification), an adaptation scheme is selected from the preset fuzzy strategy library. For example: for continuous parameters (e.g., dimensional deviation, surface roughness): a triangular membership function or a trapezoidal membership function is used. The actual measured value (e.g., dimensional deviation +0.03mm) is substituted into the corresponding function to calculate its membership to different fuzzy sets (e.g., "negative small," "zero," and "positive small"). Assume that the dimensional deviation +0.03mm has a membership of 0.8 to the "positive small" set and a membership of 0.2 to the "zero" set; for discrete parameters (e.g., surface burn grade, crack status): a single-point membership function is used. If "minor burn" is detected on the workpiece surface, the device directly assigns it a membership of 1 to the "burn" fuzzy set, and the membership of the remaining sets is 0.

[0104] Furthermore, the system retrieves the priority rules for the current machining task from the machining database and assigns weight coefficients to each defect parameter. For example, if a workpiece's "dimensional accuracy" directly determines its assembly performance, the machine assigns a weight of 0.6; "surface roughness," which has a minor impact on function, is assigned a weight of 0.3; and other less important parameters (such as minor local scratches) are assigned a weight of 0.1.

[0105] Once the weight coefficient is determined, the membership value of each defect parameter can be multiplied by the corresponding weight to achieve weighted processing. For example, the membership value of dimensional deviation to the "positive small" set is 0.8, and after multiplying it by the weight of 0.6, the weighted membership value is 0.48; the membership value of surface roughness to the "rough" set is 0.7, and after multiplying it by the weight of 0.3, the weighted membership value is 0.21.

[0106] Furthermore, the weighted membership values ​​of all defect parameters are arranged in order and combined into a multidimensional vector, which is a multidimensional fuzzy input vector, to obtain the fuzzy input value of the defect parameter.

[0107] It is worth noting that when the defect parameter includes only one type of data, calculation can be performed according to the above-mentioned method of determining the standard processing parameters for each type of defect parameter, which is not described in detail in the embodiment of the present application.

[0108] In this embodiment, the fuzzy output value is defuzzified to obtain the standard processing parameters corresponding to the defect parameters meeting the standards, including:

[0109] Defuzzify the fuzzy output value to obtain preliminary parameters;

[0110] Perform simulated machining based on preliminary parameters and predict machining results;

[0111] Calculate the error function between the predicted effect and the standard parameter;

[0112] When the error function does not converge, the weight coefficients of the fuzzy rules are iteratively updated using the gradient descent method;

[0113] When the error function reaches a minimum value or the number of iterations exceeds a threshold, a processing parameter combination is output, and based on the processing parameter combination, a standard processing parameter is obtained.

[0114] After obtaining the fuzzy output value, the centroid method can be used to defuzzify it. Specifically, the membership distribution of each processing parameter (such as voltage, current, and speed) under each fuzzy set is converted into a precise numerical value. For example, the fuzzy output of the voltage adjustment value may be: a membership of 0.7 for the "increase" set and a membership of 0.3 for the "unchanged" set. The device calculates the centroid of the area under the membership function curve to obtain a preliminary voltage adjustment value (such as +2.5V). Furthermore, a pre-trained processing simulation model is called, and a preliminary parameter combination is input to simulate processing. The processing simulation model is constructed based on historical data and physical laws and can predict processing results (such as dimensional accuracy and surface roughness) under different parameters.

[0115] Furthermore, the predicted results can be compared with the target values ​​in the process standards to construct a multidimensional error function. If the error function value exceeds a preset threshold, a gradient descent algorithm can be initiated to optimize the weight coefficients of the fuzzy rules. Specifically, the partial derivative of the error function with respect to each weight coefficient is calculated to obtain a gradient vector, indicating the direction of the fastest error growth. The weights are adjusted in the opposite direction of the gradient, and fuzzy reasoning is re-performed using the new weight coefficients to generate a new combination of processing parameters. The processing is then simulated again and the error is calculated. These steps are repeated until the error function converges (for example, the error change is less than 0.001 after five consecutive iterations).

[0116] Furthermore, when the error function converges or the number of iterations reaches a limit (e.g., 100), the electronics terminate the optimization process and use the machining parameter combination obtained from the current iteration as the final result. For example, after 15 iterations, the error function decreases from an initial value of 0.03 to 0.005. The resulting parameter combination (voltage 88.2V, current 7.8A, speed 68%) is considered the optimal solution. The electronics then transmit this parameter combination to the machining system for execution and store it as the standard machining parameters for this type of workpiece.

[0117] In this embodiment, based on the combination of processing parameters, standard processing parameters are obtained, including:

[0118] Check whether the processing parameter combination exceeds the safe operating range of the machine tool;

[0119] If the combination of machining parameters does not exceed the safe operating range of the machine tool, virtual machining verification is performed through the digital twin system;

[0120] If the verification fails, the preliminary parameters are iterated again.

[0121] Among them, the machine tool has a safe operating range during operation, which is the safety threshold of various parameters set by the machine tool manufacturer. The safe operating range is related to the equipment itself. The processing database stores the safe operating range of the machine tool corresponding to the current processing process, including but not limited to the upper limit of the spindle speed, the feed speed limit, and the allowable range of current and voltage.

[0122] Specifically, the machine tool's various safety operating indicators, such as maximum spindle speed, maximum feed rate, maximum allowable machining current, and voltage range, are retrieved from the machining database. The optimized machining parameter combinations (such as voltage, current, and speed) are then compared against these safety indicators. For example, if the machine tool's maximum allowable machining current is 10A, and the current in the parameter combination is 12.5A, the parameter combination is considered to be outside the safe range. If all parameters are within the safety threshold, the parameter combination is considered to be within the safe operating range. If a parameter is detected to be out of range, the electronic equipment will issue an alarm, terminate the subsequent process, and prompt the operator to adjust the parameters or change the machining strategy.

[0123] Furthermore, once the electronic device confirms that the machining parameter combination is within a safe range, it inputs that parameter combination into the digital twin system. The digital twin system is a virtual environment constructed based on a three-dimensional model of the machine tool and machining process and physical simulation algorithms. During the virtual machining process, the system simulates physical phenomena such as the relative motion between the tool and the workpiece, the material removal process, changes in cutting forces, and thermal deformation, while simultaneously monitoring indicators such as machining accuracy and surface quality in real time. For example, the system simulates the final dimensions of the workpiece based on the parameter combination and compares them with the design requirements; it also predicts whether the surface roughness meets the standard by simulating the cutting process. The electronic device collects the simulation results output by the digital twin system and determines whether the virtual machining meets the quality requirements.

[0124] If, after analyzing the virtual machining results of the digital twin system, the electronic device finds that indicators such as machining accuracy and surface quality do not meet the standard requirements, the verification is determined to have failed. At this point, the electronic device will restart the optimization process and, based on the preliminary parameters, it will iteratively calculate the preliminary parameters again by adjusting the fuzzy rule weight coefficients, changing the defuzzification method, or optimizing the simulation machining model to generate a new combination of machining parameters. The electronic device will then repeat the above safety range check and virtual machining verification steps until the virtual machining verification is successful, obtaining standard machining parameters that meet quality requirements and are safe and feasible.

[0125] It is worth noting that when the defect parameter contains only one type of data, the fuzzy output is obtained and no iterative operation is performed.

[0126] The embodiment of the present application provides an adaptive control method for a wire cutting process, which realizes active judgment of the processing quality by real-time monitoring of the workpiece status (satisfied / unsatisfied), avoiding the waste loss caused by traditional post-detection. When the workpiece is found to be unqualified, key processing data (voltage, current, speed) is automatically collected, and a rapid traceability channel from quality problems to process parameters is established. Dynamic analysis technology is used to automatically generate optimal processing parameters and feed them back to the processing system in real time, forming a closed-loop control of "detection-analysis-optimization", thereby reducing the cost of manual intervention and keeping the processing system in the best working state at all times through continuous optimization, thereby comprehensively improving production efficiency and product quality.

[0127] The above embodiment introduces a wire cutting process adaptive control method from the perspective of method flow, and the following embodiment introduces a wire cutting process adaptive control device from the perspective of virtual module or virtual unit. For details, please refer to the following embodiment.

[0128] See also Figure 2The wire cutting process adaptive control device 20 may specifically include: a determination module 201, an acquisition module 202 and a sending module 203, wherein:

[0129] A wire cutting process adaptive control device 20, comprising:

[0130] Determination module 201, for determining a workpiece state corresponding to a current workpiece, where the current workpiece is a workpiece generated during a current machining process, and the workpiece state is either satisfied or unsatisfied;

[0131] An acquisition module 202 is configured to acquire processing data corresponding to a current processing process when the workpiece status of the current workpiece is unsatisfactory, the processing data including processing voltage, processing current, and processing speed;

[0132] The sending module 203 is used to dynamically analyze the processing data, determine the optimal processing data, and send the optimal processing data to the corresponding processing system.

[0133] In a possible implementation of the embodiment of the present application, when the determination module 201 determines the workpiece state corresponding to the current workpiece, the following steps are specifically performed:

[0134] Obtain the inspection data corresponding to the current workpiece and obtain the standard data corresponding to the current workpiece. The inspection data includes processing accuracy, surface quality, processing efficiency and material damage.

[0135] Compare the test data with the standard data to obtain a comparison result, which is consistent or inconsistent;

[0136] If the comparison result is consistent, it is determined that the workpiece state corresponding to the current workpiece is satisfied;

[0137] If the comparison result is inconsistent, it is determined that the workpiece status corresponding to the current workpiece is unsatisfactory.

[0138] In one possible implementation of the embodiment of the present application, the sending module 203 dynamically analyzes the processing data to determine the optimal processing data, specifically including:

[0139] Determine defect parameters corresponding to the current workpiece, and obtain defect processing data corresponding to the defect parameters, where the defect parameters are one or more data in the detection data, and the defect processing data are one or more data in the detection data;

[0140] Based on the defect processing data, determine the standard processing parameters corresponding to the defect parameters meeting the standards;

[0141] Generate optimal processing data based on standard processing parameters.

[0142] In one possible implementation of the embodiment of the present application, when the defect parameter includes multiple data, the sending module 203 determines, based on the defect processing data, that the defect parameter meets the standard processing parameter corresponding to the standard, specifically including:

[0143] Obtaining fuzzy control rules corresponding to defect parameters, wherein the fuzzy control rules associate fuzzy mapping relationships between defect parameters and processing parameters;

[0144] Perform fuzzy processing on defect processing data to obtain fuzzy input values ​​of defect parameters;

[0145] Based on the fuzzy input value and fuzzy control rules, the fuzzy output value of the processing parameter is determined through fuzzy reasoning;

[0146] The fuzzy output value is defuzzified to obtain the standard processing parameters corresponding to the defect parameters reaching the standard.

[0147] In a possible implementation of the embodiment of the present application, when the sending module 203 performs fuzzy processing on the defect processing data to obtain the fuzzy input value of the defect parameter, the following steps are specifically included:

[0148] For each defect parameter, the actual value of the defect parameter is converted into the corresponding fuzzy set membership, and the fuzzification strategy corresponding to the defect parameter is selected;

[0149] Perform weighted processing on multi-dimensional defect parameters and assign different weight coefficients according to the degree of influence of each defect parameter on the processing quality;

[0150] The membership values ​​of each defect parameter under different fuzzy sets are output to form a multi-dimensional fuzzy input vector to obtain the fuzzy input value of the defect parameter.

[0151] In a possible implementation of the embodiment of the present application, when the sending module 203 performs defuzzification processing on the fuzzy output value to obtain the standard processing parameter corresponding to the defect parameter meeting the standard, the following steps are specifically performed:

[0152] Defuzzify the fuzzy output value to obtain preliminary parameters;

[0153] Perform simulated machining based on preliminary parameters and predict machining results;

[0154] Calculate the error function between the predicted effect and the standard parameter;

[0155] When the error function does not converge, the weight coefficients of the fuzzy rules are iteratively updated using the gradient descent method;

[0156] When the error function reaches a minimum value or the number of iterations exceeds a threshold, a processing parameter combination is output, and based on the processing parameter combination, a standard processing parameter is obtained.

[0157] In a possible implementation of the embodiment of the present application, when the sending module 203 obtains the standard processing parameters based on the processing parameter combination, the steps specifically include:

[0158] Check whether the processing parameter combination exceeds the safe operating range of the machine tool;

[0159] If the combination of machining parameters does not exceed the safe operating range of the machine tool, virtual machining verification is performed through the digital twin system;

[0160] If the verification fails, the preliminary parameters are iterated again.

[0161] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0162] See also Figure 3 , the embodiment of the present application also introduces an electronic device from the perspective of a physical device, such as Figure 3 As shown, Figure 3 The electronic device 300 shown includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 300 may further include a transceiver 304. It should be noted that in actual applications, the number of transceivers 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0163] Processor 301 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0164] Bus 302 may include a path for transmitting information between the above components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. Bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0165] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0166] The memory 303 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the above method embodiment.

[0167] Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc., and can also be servers, etc. Figure 3 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0168] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding contents of the aforementioned method embodiment.

[0169] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0170] The above are only some of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for adaptive control of a wire cutting process, characterized in that: include: Determining a workpiece state corresponding to a current workpiece, wherein the current workpiece is a workpiece generated during a current machining process, and the workpiece state is either satisfied or unsatisfied; When the workpiece state of the current workpiece is unsatisfactory, obtaining processing data corresponding to the current processing process, the processing data including processing voltage, processing current and processing speed; Dynamically analyzing the processing data to determine optimal processing data, and sending the optimal processing data to a corresponding processing system; Wherein, determining the workpiece state corresponding to the current workpiece includes: Acquire inspection data corresponding to the current workpiece and obtain standard data corresponding to the current workpiece, wherein the inspection data includes machining accuracy, surface quality, machining efficiency, and material damage; Comparing the test data with the standard data to obtain a comparison result, wherein the comparison result is consistent or inconsistent; If the comparison result is consistent, determining that the workpiece state corresponding to the current workpiece is satisfied; If the comparison result is inconsistent, determining that the workpiece state corresponding to the current workpiece is unsatisfactory; The dynamically analyzing the processing data to determine the optimal processing data includes: Determine defect parameters corresponding to the current workpiece, and obtain defect processing data corresponding to the defect parameters, wherein the defect parameters are one or more data in the detection data, and the defect processing data are one or more data in the detection data; Determining, based on the defect processing data, standard processing parameters corresponding to the defect parameters meeting the standards; generating optimal processing data based on the standard processing parameters; Wherein, when the defect parameter includes multiple data, determining the standard processing parameter corresponding to the standard at which the defect parameter meets the standard based on the defect processing data includes: Obtaining a fuzzy control rule corresponding to the defect parameter, wherein the fuzzy control rule associates a fuzzy mapping relationship between the defect parameter and the processing parameter; Performing fuzzy processing on the defect processing data to obtain a fuzzy input value of the defect parameter; Determining a fuzzy output value of the processing parameter through fuzzy reasoning based on the fuzzy input value and the fuzzy control rule; The fuzzy output value is defuzzified to obtain the standard processing parameters corresponding to the defect parameters meeting the standards.

2. The adaptive control method for wire cutting process according to claim 1, characterized in that: The fuzzy processing of the defect processing data to obtain the fuzzy input value of the defect parameter includes: For each defect parameter, convert the actual value of the defect parameter into the corresponding fuzzy set membership, and select the fuzzification strategy corresponding to the defect parameter; Perform weighted processing on multi-dimensional defect parameters and assign different weight coefficients according to the degree of influence of each defect parameter on the processing quality; The membership values ​​of each defect parameter under different fuzzy sets are output to form a multi-dimensional fuzzy input vector to obtain the fuzzy input value of the defect parameter.

3. The adaptive control method for wire cutting process according to claim 1, characterized in that: Defuzzification is performed on the fuzzy output value to obtain standard processing parameters corresponding to the defect parameters meeting the standards, including: Defuzzifying the fuzzy output value to obtain preliminary parameters; Performing simulated machining based on the preliminary parameters and predicting machining results; Calculate the error function between the predicted effect and the standard parameter; When the error function does not converge, the weight coefficients of the fuzzy rules are iteratively updated using the gradient descent method; When the error function reaches a minimum value or the number of iterations exceeds a threshold, a processing parameter combination is output, and based on the processing parameter combination, a standard processing parameter is obtained.

4. The adaptive control method for wire cutting process according to claim 3, characterized in that: The standard processing parameters are obtained based on the processing parameter combination, including: Check whether the combination of machining parameters exceeds the safe operating range of the machine tool; If the combination of machining parameters does not exceed the safe operating range of the machine tool, virtual machining verification is performed through the digital twin system; If the verification fails, the preliminary parameters are iterated again.

5. A wire cutting process adaptive control device, characterized in that: include: a determination module, configured to determine a workpiece status corresponding to a current workpiece, wherein the current workpiece is a workpiece generated during a current machining process, and the workpiece status is either satisfied or unsatisfied; an acquisition module, configured to acquire processing data corresponding to the current processing process when the workpiece state of the current workpiece is unsatisfactory, the processing data including processing voltage, processing current, and processing speed; a sending module, configured to dynamically analyze the processing data, determine optimal processing data, and send the optimal processing data to a corresponding processing system; Wherein, when determining the workpiece state corresponding to the current workpiece, the determination module is specifically used to: Acquire inspection data corresponding to the current workpiece and obtain standard data corresponding to the current workpiece, wherein the inspection data includes machining accuracy, surface quality, machining efficiency, and material damage; Comparing the test data with the standard data to obtain a comparison result, wherein the comparison result is consistent or inconsistent; If the comparison result is consistent, determining that the workpiece state corresponding to the current workpiece is satisfied; If the comparison result is inconsistent, determining that the workpiece state corresponding to the current workpiece is unsatisfactory; The sending module is specifically used to: Determine defect parameters corresponding to the current workpiece, and obtain defect processing data corresponding to the defect parameters, wherein the defect parameters are one or more data in the detection data, and the defect processing data are one or more data in the detection data; Determining, based on the defect processing data, standard processing parameters corresponding to the defect parameters meeting the standards; generating optimal processing data based on the standard processing parameters; When the defect parameter includes multiple data, the sending module is specifically configured to: Obtaining a fuzzy control rule corresponding to the defect parameter, wherein the fuzzy control rule associates a fuzzy mapping relationship between the defect parameter and the processing parameter; Performing fuzzy processing on the defect processing data to obtain a fuzzy input value of the defect parameter; Determining a fuzzy output value of the processing parameter through fuzzy reasoning based on the fuzzy input value and the fuzzy control rule; The fuzzy output value is defuzzified to obtain the standard processing parameters corresponding to the defect parameters meeting the standards.

6. An electronic device, characterized in that: The electronic device includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the wire cutting process adaptive control method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the wire cutting process adaptive control method according to any one of claims 1 to 4.

Images