A multi-stage control method and system for workpiece grinding in the field of aviation

Abstract

This application provides a multi-level control method and system for workpiece grinding in the aerospace field, belonging to the field of aerospace manufacturing technology. The method includes: determining a first control strategy for the grinding equipment based on the material properties of the target workpiece and the grinding task requirements; acquiring physical state signals of the grinding area of ​​the target workpiece when the grinding equipment is controlled based on the first control strategy; the physical state signals include one or more of grinding force, grinding temperature, vibration signals, acoustic emission signals, and workpiece surface morphology; selecting a control strategy generation mode based on the deviation index between the physical state signals and a preset target state of the target workpiece; generating a target control strategy based on the control strategy generation mode; and controlling the grinding equipment to grind the target workpiece based on the target control strategy. The multi-level control method and system for workpiece grinding in the aerospace field provided by this application achieves precise control of the aerospace workpiece grinding process.

Description

Technical Field

[0001] This application relates to the field of aerospace manufacturing technology, and in particular to a multi-level control method and system for workpiece grinding in the aerospace field. Background Technology

[0002] In the aerospace manufacturing process, workpiece grinding is a critical machining step, and its quality directly affects the performance and reliability of aerospace components. However, due to the special materials (such as titanium alloys and high-temperature alloys), complex structures, and extremely high precision requirements of workpieces in the aerospace field, existing grinding control methods are difficult to adapt to changes in working conditions during the grinding process in real time. This can easily lead to problems such as uneven grinding force, excessively high grinding temperature, and poor workpiece surface quality, which in turn affect the machining accuracy and service life of the workpiece.

[0003] Furthermore, existing control methods lack flexible multi-level control strategies and cannot dynamically adjust the control scheme according to different grinding conditions, resulting in low processing efficiency and serious waste of resources.

[0004] Therefore, there is an urgent need for a multi-stage control method for workpiece grinding in the aerospace field that can effectively solve the above problems. Summary of the Invention

[0005] To address the aforementioned technical problems, this application provides a multi-level control method and system for workpiece grinding in the aerospace field. By dynamically adjusting the multi-level control strategy, precise control of the aerospace workpiece grinding process is achieved, thereby improving the workpiece's processing quality and efficiency.

[0006] A first aspect of this application provides a multi-level control method for workpiece grinding in the aerospace field, comprising:

[0007] Based on the material properties of the target workpiece and the grinding task requirements, determine the first control strategy for the grinding equipment;

[0008] When the grinding equipment is controlled based on the first control strategy, the physical state signal of the grinding area of ​​the target workpiece is obtained; the physical state signal includes one or more of the following: grinding force, grinding temperature, vibration signal, acoustic emission signal, and workpiece surface morphology.

[0009] Based on the deviation index between the physical state signal and the preset target state of the target workpiece, a control strategy generation mode is selected.

[0010] Based on the control strategy generation mode, a target control strategy is generated;

[0011] The grinding equipment is controlled to grind the target workpiece based on the target control strategy.

[0012] A second aspect of this application provides a multi-level control system for workpiece grinding in the aerospace field, comprising:

[0013] The first strategy module is used to determine the first control strategy of the grinding equipment based on the material properties of the target workpiece and the grinding task requirements.

[0014] The data acquisition module is used to acquire the physical state signal of the grinding area of ​​the target workpiece when the grinding equipment is controlled based on the first control strategy; the physical state signal includes one or more of the following: grinding force, grinding temperature, vibration signal, acoustic emission signal, and workpiece surface morphology;

[0015] The mode selection module is used to select a control strategy generation mode based on the deviation index between the physical state signal and the preset target state of the target workpiece.

[0016] The control strategy module is used to generate a target control strategy based on the control strategy generation mode.

[0017] An execution module is used to control the grinding equipment to grind the target workpiece based on the target control strategy.

[0018] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the multi-level control method for workpiece grinding in the aerospace field described above.

[0019] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the aforementioned multi-level control system for workpiece grinding in the aerospace field.

[0020] The beneficial effects of the multi-level control method and system for workpiece grinding in the aerospace field provided in this application are as follows: First, this application determines the first control strategy based on the material properties of the target workpiece and the requirements of the grinding task, achieving precise adaptation of the grinding equipment control, avoiding workpiece damage caused by improper strategies, and improving the processing qualification rate. Second, by acquiring physical state signals of the grinding area in real time, such as grinding force and temperature, the state of the grinding process can be dynamically grasped, providing reliable data support for the generation of subsequent target control strategies. Then, the control strategy generation mode is selected based on the deviation index between the physical state signals and the preset target state, thereby generating the target control strategy and forming a dynamic adjustment mechanism to correct deviations in the grinding process, ensuring that the grinding process is always in an optimal state, effectively improving the machining accuracy and surface quality of the workpiece. In addition, the multi-level control method of this application enhances the stability and reliability of the grinding process, meeting the stringent requirements of the aerospace field for high precision and high quality of workpieces. Attached Figure Description

[0021] Figure 1 A flowchart illustrating a multi-level control method for workpiece grinding in the aerospace field, provided as an embodiment of this application;

[0022] Figure 2 A structural block diagram of a multi-level control system for workpiece grinding in the aerospace field is provided as an embodiment of this application;

[0023] Figure 3 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0024] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0025] To make the purpose, technical solution, and advantages of this application clearer, the following will be described in conjunction with the appendix. Figure 1-3 The following is an explanation using specific examples.

[0026] Please refer to Figure 1 , Figure 1 A flowchart illustrating a multi-level control method for workpiece grinding in the aerospace field, provided in one embodiment of this application, includes:

[0027] S101: Determine the first control strategy for the grinding equipment based on the material properties of the target workpiece and the grinding task requirements;

[0028] In this embodiment, in the aerospace field, workpiece materials typically have characteristics such as high strength, high temperature resistance, and low density, such as titanium alloys and carbon fiber composite materials. The grinding processes for different materials vary significantly.

[0029] In this embodiment, the material properties of the target workpiece include physical parameters such as hardness, toughness, thermal conductivity, and elastic modulus. For example, titanium alloys have high hardness and poor thermal conductivity, which easily leads to high temperatures and tool wear during grinding; carbon fiber composites are prone to delamination, tearing, and other problems.

[0030] According to the preset grinding task requirements, such as grinding accuracy, grinding efficiency and machining allowance, grinding accuracy includes dimensional accuracy, shape accuracy and surface roughness.

[0031] Based on material properties and grinding task requirements, suitable grinding parameters are matched from a pre-established grinding process database to determine the primary control strategy for the grinding equipment. These grinding parameters include: wheel linear speed, feed rate, depth of cut, and coolant flow rate. The grinding process database contains optimal combinations of process parameters for different materials and grinding requirements; it is built upon extensive grinding test data and practical production experience.

[0032] S102: When controlling the grinding equipment based on the first control strategy, acquire the physical state signal of the grinding area of ​​the target workpiece; the physical state signal includes one or more of the following: grinding force, grinding temperature, vibration signal, acoustic emission signal, and workpiece surface morphology;

[0033] In this embodiment, when the grinding equipment is controlled to grind the target workpiece based on the first control strategy, a high-precision sensor is used to acquire the physical state signal of the grinding area of ​​the target workpiece in real time. Specifically:

[0034] A force gauge mounted on the spindle of the grinding equipment or the workpiece fixture measures the tangential and normal grinding forces generated during the grinding process in real time. The magnitude and changes in these grinding forces reflect the stability of the grinding process, the wear of the grinding wheel, and the material removal efficiency. An infrared thermometer or thermocouple is used to measure the temperature of the grinding area. High temperatures can cause surface burns and changes in material properties, so real-time monitoring of the grinding temperature is crucial for ensuring workpiece quality. An accelerometer collects vibration signals from the grinding equipment and workpiece during the grinding process. Excessive vibration indicates problems such as grinding wheel imbalance, unreasonable grinding parameters, or insecure workpiece clamping. An acoustic emission sensor receives elastic wave signals generated by material deformation and fracture during grinding. Acoustic emission signals can predict the generation and development of internal material defects, such as crack initiation. Optical microscopes and profilometers are used to inspect the workpiece surface morphology online, obtaining information such as surface roughness and texture.

[0035] S103: Select the control strategy generation mode based on the deviation index between the physical state signal and the preset target state of the target workpiece;

[0036] In this embodiment, the preset target state is determined based on the workpiece's design requirements and quality standards, including the ideal range of various physical state signals. For example, for grinding temperature, the preset target temperature range would be 60-80℃; for surface roughness, the preset target value would be Ra0.6μm.

[0037] S104: Generate the target control strategy based on the control strategy generation mode;

[0038] In this embodiment, a corresponding target control strategy is generated based on the determined control strategy generation mode. When the deviation is large: a replanning mode is selected, and the control strategy is re-formulated based on the current physical state signal and the remaining machining allowance of the workpiece. Specifically, an intelligent algorithm is used to search for the optimal control strategy within the feasible domain of process parameters, based on the current physical state signal and the remaining machining requirements. The intelligent algorithm includes genetic algorithms and particle swarm optimization algorithms, etc. Taking the genetic algorithm as an example, grinding parameters are used as gene encoding, and workpiece quality indicators (such as surface roughness, dimensional accuracy, etc.) are used as the fitness function. Through selection, crossover, mutation, and other operations, the optimal control strategy is continuously evolved.

[0039] When abnormal signals occur, such as excessive vibration or abnormal acoustic emission signals that may lead to workpiece scrapping or equipment damage, the emergency intervention mode should be selected to immediately stop the grinding process and take appropriate measures. Specifically, depending on the type of abnormal signal, a pre-set emergency handling procedure should be invoked; for example, when excessive vibration is detected, the feed rate should be reduced first. If the vibration does not decrease, grinding should be stopped, the equipment and workpiece clamping should be checked, and a new control strategy should be formulated after troubleshooting.

[0040] S105: Based on the target control strategy, control the grinding equipment to grind the target workpiece.

[0041] In this embodiment, the generated target control strategy is transmitted to the control system of the grinding equipment, and the equipment grinds the target workpiece according to the new control strategy. During the grinding process, the physical state signal is continuously monitored, and the above steps S102 to S104 are repeated to form a closed-loop control, ensuring that the entire grinding process is always in the optimal state until the grinding of the workpiece is completed. This application, through the above multi-level control method, can effectively improve the grinding quality and processing efficiency of workpieces in the aerospace field, meeting the stringent requirements of aerospace manufacturing for high-precision and high-reliability workpieces.

[0042] As can be seen from the above, the application determines the first control strategy based on the material properties of the target workpiece and the requirements of the grinding task, achieving precise adaptation of the grinding equipment control. This avoids workpiece damage caused by improper strategies and improves the processing qualification rate. Secondly, by acquiring physical state signals of the grinding area in real time, such as grinding force and temperature, the state of the grinding process can be dynamically monitored, providing reliable data support for the subsequent generation of the target control strategy. Then, based on the deviation index between the physical state signals and the preset target state, the control strategy generation mode is selected, thereby generating the target control strategy and forming a dynamic adjustment mechanism. This corrects deviations in the grinding process, ensuring that the grinding process is always in an optimal state, effectively improving the machining accuracy and surface quality of the workpiece. Furthermore, the multi-level control method of this application enhances the stability and reliability of the grinding process, meeting the stringent requirements of the aerospace field for high precision and high quality workpieces.

[0043] For example, taking the grinding of an aero-engine blade as an example, the blade material is titanium alloy, and the grinding task requires a surface roughness of Ra0.8μm and a machining accuracy of ±0.01mm.

[0044] Based on the characteristics of titanium alloy materials and the requirements of the grinding task, the first control strategy is determined as follows: grinding wheel speed 2000 r / min, feed rate 0.5 mm / min, and grinding depth 0.02 mm.

[0045] During grinding based on the first control strategy, the physical state signals of the grinding area are acquired in real time by sensors. These physical state signals include grinding force, grinding temperature, and vibration signals.

[0046] Calculate the deviation index between the physical state signal and the preset target state (e.g., ideal grinding force range, temperature range, etc.). If the deviation index is less than the first deviation threshold, select the strategy library matching mode.

[0047] The acquired physical state signal is input into the working condition identification model to determine that the current grinding working condition is a normal grinding working condition.

[0048] Select a second control strategy optimized for normal grinding conditions from the preset target strategy library. For example, adjust the grinding wheel speed to 2200 r / min, keep the feed rate unchanged, and adjust the grinding depth to 0.015 mm.

[0049] The overlapping parameters in the first control strategy and the second control strategy are weighted and fused, while the non-overlapping parameters retain the set values ​​of the first control strategy to generate the target control strategy.

[0050] The grinding equipment is controlled to grind the blades based on the generated target control strategy.

[0051] During the grinding process, the second physical state signal is acquired in real time, and the control effect index is calculated. If the surface roughness does not meet the expectations, the control strategy generation mode is redefined and a new target control strategy is generated until the processing requirements are met.

[0052] Assuming the deviation index is greater than a first deviation threshold and less than a second deviation threshold, an intelligent optimization algorithm generation mode is selected. An optimization objective function is constructed based on the physical state signal, aiming to minimize grinding force and surface roughness. Using the parameters corresponding to the first control strategy as the initial solution, a genetic algorithm is used for iterative optimization under the conditions of satisfying process constraints (machining accuracy requirements) and safety constraints (equipment load limits). During the iteration process, a fitness function is constructed based on the physical state signal and the optimization objective function to determine the fitness value of individuals in the population. The parameters in the first control strategy are used as individuals, and the target crossover probability is determined based on the variance of the individual fitness values. The target mutation probability is determined based on the accuracy of the genetic algorithm, and the parameters are iteratively optimized. When the convergence condition is met, the optimal solution of the optimization objective function is taken as the target control strategy.

[0053] In one embodiment of this application, the control policy generation mode includes: a policy library matching mode and an intelligent optimization algorithm generation mode;

[0054] Based on the deviation index between the physical state signal and the preset target state, a control strategy generation mode is selected, including:

[0055] Calculate the difference between the physical state signal and the preset target state, and the deviation index;

[0056] If the deviation index is less than or equal to the first deviation threshold, then the strategy library matching mode is selected;

[0057] If the deviation index is greater than the first deviation threshold and less than or equal to the second deviation threshold, then the intelligent optimization algorithm generation mode is selected.

[0058] If the deviation index exceeds the second deviation threshold, the grinding equipment will be shut down.

[0059] In this embodiment, the deviation index between the physical state signal and the preset target state of the target workpiece is calculated. The preset target state is determined according to the design requirements and quality standards of the workpiece, and includes the ideal range of various physical state signals.

[0060] In this embodiment, the formula for calculating the deviation index is:

[0061]

[0062] in, This is a deviation index; The number of signals is the number of types of physical parameters being monitored. For the first Class of monitoring signals; This refers to the actual measured value, which is the physical quantity collected by the sensor in real time. The target value is the ideal state value required by the process. The tolerance standard deviation is the allowable range of process fluctuations. It is a nonlinear transformation function; The weights are dynamic and determined based on the signal importance coefficients. This is the coupling penalty coefficient; It is a set of coupled signals, that is, a combination of signals that have physical interaction effects; For the first in the coupling set One signal; It is a non-negative cutoff, penalizing only positive deviations (out of tolerance), used to prevent negative deviations from offsetting the risk; For a chain multiplication operator, only if all Activated when exceeding tolerance.

[0063] In this embodiment, the control strategy generation mode is selected according to the following rules based on the deviation index: when the deviation index is less than or equal to a first deviation threshold, the strategy library matching mode is selected. The first deviation threshold is set based on a large number of grinding tests and actual production experience. It indicates that the current grinding state deviates little from the ideal state and can be quickly adjusted using existing experience data. In the strategy library matching mode, the control system uses the current physical state signal as a search condition and matches it in a pre-built target control strategy library, prioritizing the selection of the strategy that best matches the current state as the target control strategy.

[0064] When the deviation index is greater than the first deviation threshold and less than or equal to the second deviation threshold, the intelligent optimization algorithm generation mode is selected. The second deviation threshold is also set based on experience; deviation within this range means that relying solely on strategy library matching is insufficient to meet optimization requirements, necessitating more intelligent algorithms for in-depth optimization. In the intelligent optimization algorithm generation mode, intelligent algorithms such as genetic algorithms or particle swarm optimization algorithms are used, taking the current physical state signal and the remaining machining allowance of the workpiece as inputs, to search for the optimal control strategy within the feasible domain of process parameters. Taking particle swarm optimization as an example, grinding parameters (such as grinding wheel linear speed, feed rate, etc.) are used as particle position parameters, and workpiece quality indicators (such as surface roughness, dimensional accuracy, etc.) are used as fitness functions. Through information sharing and iterative updates among particles, the parameter combination is continuously adjusted until the optimal or near-optimal control strategy is found.

[0065] When the deviation index exceeds the second deviation threshold, the grinding equipment is shut down. At this point, the grinding process has seriously deviated from the preset target state, and continued processing may lead to workpiece scrap or even equipment damage. After shutdown, the operator needs to conduct a comprehensive inspection of the equipment, workpiece, and grinding process, troubleshoot the problem, and replan the control strategy.

[0066] In one embodiment of this application, when the policy library matching mode is selected, generating a target control policy includes:

[0067] Input the physical state signal into the working condition identification model to obtain the grinding working condition category;

[0068] Based on the grinding condition category, a matching second control strategy is selected from a preset target strategy library; wherein, the target strategy library stores a set of control strategies optimized for different grinding conditions;

[0069] The second control strategy is merged with the first control strategy to generate the target control strategy.

[0070] In this embodiment, the acquired physical state signals are input into a pre-trained condition recognition model. This model is built based on machine learning algorithms, including convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. This embodiment uses a CNN model, trained with a large number of samples containing physical state signal data under different grinding conditions, enabling it to automatically extract features from the signals and classify the grinding conditions. The grinding condition categories in this embodiment include: normal grinding, wheel wear, workpiece surface burns, and cutting chatter.

[0071] In this embodiment, based on the grinding condition category output by the condition identification model, a matching selection is made from a preset target strategy library. This target strategy library is constructed through extensive experimentation and accumulation of actual production data, storing sets of control strategies optimized for different grinding conditions. Each control strategy set contains a complete combination of grinding parameters, such as wheel linear speed, feed rate, grinding depth, and coolant flow rate. For example, when the condition is identified as "grinding wheel wear," the corresponding control strategy set in the target strategy library includes a parameter combination that reduces the wheel linear speed, decreases the feed rate, and increases the coolant flow rate to reduce the impact of grinding wheel wear on machining quality and extend grinding wheel life. A second control strategy matching the current grinding condition category is then accurately retrieved from the target strategy library.

[0072] In this embodiment, the selected second control strategy is fused with the initially determined first control strategy. The fusion process employs a weighted average method, assigning weights to different parameters based on their impact on machining quality and efficiency. For example, the grinding wheel linear velocity parameter, which significantly affects surface roughness, is assigned a higher weight; while the feed rate parameter, which significantly affects machining efficiency, is assigned a moderate weight. Through weighted calculation, a new parameter combination is obtained, thereby generating the target control strategy. For instance, if the grinding wheel linear velocity is 30 m / s in the first control strategy and adjusted to 25 m / s in the second control strategy due to grinding wheel wear, and if the grinding wheel linear velocity is assigned a weight of 0.7, after weighted calculation, the grinding wheel linear velocity in the target control strategy might be 30 × 0.3 + 25 × 0.7 = 26.5 m / s.

[0073] In this embodiment, the operations related to the intelligent optimization algorithm generation mode and when the deviation index is greater than the second deviation threshold (such as equipment shutdown processing) still follow the rules and procedures of the original method.

[0074] In summary, this embodiment can more accurately handle different grinding conditions, further improving the control accuracy and processing quality of workpiece grinding in the aerospace field.

[0075] In one embodiment of this application, the second control strategy and the first control strategy are fused together, including:

[0076] For the overlapping parameters in the first control strategy and the second control strategy, a weighted fusion is performed according to the first formula;

[0077] For non-overlapping parameters in the first and second control strategies, the settings of the first control strategy are retained.

[0078] In this embodiment, overlapping parameters are weighted and fused: overlapping parameters in the first and second control strategies, such as grinding wheel linear speed, feed rate, grinding depth, and coolant flow rate, are weighted and fused according to the first formula. Assume the first formula is:

[0079]

[0080] in, These are the parameter values ​​after fusion; The parameter value for the first control strategy. This is the parameter value for the second control strategy. The first credibility coefficient, The second credibility coefficient is dynamically calculated based on the historical success rate of the strategy, and ; To integrate the sensitivity factor, the k-value is used to achieve adaptive switching of the fusion strategy under different operating conditions; The intensity of conflict punishment; A tolerance threshold for parameter differences is used to apply attenuation to conflicting parameters, preventing system oscillations caused by policy contradictions.

[0081] Non-overlapping parameter handling: For non-overlapping parameters in the first and second control strategies, the setpoints of the first control strategy are directly retained. For example, if the first control strategy includes a setting for the spindle speed of the grinding equipment, but the second control strategy does not involve this parameter, then the spindle speed will use the setpoint of the first control strategy when generating the target control strategy. Operations related to the intelligent optimization algorithm generation mode and when the deviation index exceeds the second deviation threshold (such as equipment shutdown) still follow the rules and procedures of the original method.

[0082] In one embodiment of this application, when the intelligent optimization algorithm generation mode is selected, the target control strategy is generated, including:

[0083] Construct an optimization objective function based on physical state signals;

[0084] Using the parameters corresponding to the first control strategy as the initial solution, the genetic algorithm is used to iteratively optimize the solution under the conditions of satisfying process constraints and safety constraints.

[0085] When the convergence condition or optimization objective is met, the optimal solution of the objective function is used as the target control strategy.

[0086] In this embodiment, a multi-objective optimization function is constructed based on the acquired physical state signal, combined with grinding process requirements and quality indicators. The multi-objective optimization function includes the following key objectives:

[0087] Machining quality objectives: These are measured by indicators such as workpiece surface roughness and shape accuracy. For example, regarding surface roughness, minimizing the mean square error of surface roughness improves surface machining quality. Machining efficiency objectives: These are measured by material removal rate, maximizing this rate increases machining efficiency. Equipment wear objectives: These are assessed by monitoring grinding force and other signals, minimizing wheel wear extends equipment life. Energy consumption objectives: Based on the power consumption of various components of the grinding equipment, such as spindle power and coolant pump power, the goal is to minimize total energy consumption. These objectives are weighted and fused to obtain an optimization objective function. The weight coefficients for each objective can be set according to the priority of the specific grinding task.

[0088] In this embodiment, the grinding parameters are encoded to form individual chromosomes. For example, a binary encoding method is used to map the range of grinding wheel linear velocity [20, 40] m / s to 8-bit binary numbers, with each binary string representing a combination of grinding parameters.

[0089] Using the parameter values ​​corresponding to the first control strategy as the initial solution, a certain number of individuals are randomly generated to form the initial population; each individual represents a possible control strategy.

[0090] Fitness calculation: Each individual is substituted into the optimization objective function for calculation, and the result is converted into a fitness value. The larger the fitness value, the better the control strategy corresponding to that individual.

[0091] Genetic operations: A new generation of population is generated through three genetic operations: selection, crossover, and mutation.

[0092] Selection process: Using methods such as roulette wheel selection, superior individuals are selected in proportion to enter the next generation based on their fitness level, so that superior genes can be preserved and passed on.

[0093] Crossover operation: Selected individuals are crossed over, exchanging partial gene segments to generate new individual combinations and increase population diversity. For example, single-point or multi-point crossover can be used, randomly selecting crossover points on the chromosomes of two individuals and exchanging genes at the corresponding positions.

[0094] Mutation operation: Randomly altering the genes of an individual with a certain mutation probability to prevent the algorithm from getting trapped in local optima and to ensure the evolutionary vitality of the population. For example, flipping 0-1 bits in binary encoded gene positions.

[0095] In this embodiment, process constraints and safety constraints must always be met during the iteration process. Process constraints include ensuring that the range of grinding parameters meets the processing requirements of the equipment and workpiece, such as the grinding wheel speed not exceeding the rated speed of the equipment; safety constraints ensure that dangerous situations such as equipment overload and workpiece damage do not occur during the grinding process, such as the grinding force not exceeding the upper limit of the equipment's load capacity.

[0096] In this embodiment, convergence judgment and result output: A convergence condition is set, and iteration stops when one of the following conditions is met:

[0097] Reaching the maximum number of iterations: A maximum number of iterations is preset, such as 100 iterations. When this number is reached, the algorithm stops running.

[0098] Fitness value change less than threshold: When the rate of change of the fitness value of the best individual in the population over several consecutive generations is less than the set threshold, the algorithm is considered to have converged.

[0099] When the convergence condition is met, the individual with the highest fitness value is selected from the final population, and the parameter combination obtained after decoding it is used as the optimal solution of the objective function, i.e., the objective control strategy.

[0100] In one embodiment of this application, iterative optimization is performed using a genetic algorithm under conditions that satisfy process constraints and safety constraints, including:

[0101] The fitness function of the genetic algorithm is constructed based on the physical state signal and the optimization objective function;

[0102] The fitness value of an individual in the population is determined based on the fitness function;

[0103] The parameters in the first control strategy are used as individuals in the genetic algorithm;

[0104] The target crossover probability of the genetic algorithm is determined based on the variance of the fitness values ​​of individuals in the population.

[0105] The target mutation probability of the genetic algorithm is determined based on the accuracy of the genetic algorithm.

[0106] The parameters in the first control strategy are iteratively optimized based on the fitness function, target crossover probability, and target mutation probability.

[0107] In this embodiment, when an individual's fitness value is higher than the average, the crossover probability decreases as the fitness value increases, protecting high-quality individuals; conversely, a higher crossover probability is used to promote population evolution. The mutation probability is dynamically adjusted based on the evolutionary accuracy of the genetic algorithm. As iterations proceed, the mutation probability gradually decreases; in the early stages, a higher mutation probability ensures search breadth, while in the later stages, a lower mutation probability maintains convergence stability.

[0108] This embodiment improves the search efficiency and optimization quality of the algorithm by dynamically adjusting the crossover and mutation probabilities and combining them with a constraint handling mechanism.

[0109] In one embodiment of this application, a multi-level control method for workpiece grinding in the aerospace field further includes:

[0110] During the grinding process of the grinding equipment based on the target control strategy to grind the target workpiece, the second physical state signal of the grinding area of ​​the target workpiece is acquired;

[0111] Calculate or determine the control effect index of the target control strategy based on the second physical state signal;

[0112] When the control effect index fails to reach the preset expected threshold range, or when the grinding condition changes based on the second physical state signal, the control strategy generation mode is re-determined based on the physical state signal and a new target control strategy is generated.

[0113] In this embodiment, a sensor system is used to collect the second physical state signal of the grinding area of ​​the target workpiece in real time, including dynamic data such as grinding force, temperature, vibration, and acoustic emission. A sliding window technique is employed to perform time-domain and frequency-domain analysis on the continuously acquired signals, extracting feature parameters (such as grinding force fluctuation frequency and temperature change gradient). The control effect indicators in this embodiment include: machining quality indicators and process stability indicators; wherein, the machining quality indicators include the predicted surface roughness and shape accuracy deviation; wherein, based on the spectral characteristics of the acoustic emission signal, the surface roughness is predicted in real time using a regression model; and the workpiece contour error is calculated through time-frequency analysis of the vibration signal.

[0114] Process stability indicators include grinding force fluctuation coefficient and temperature rise rate. The grinding force fluctuation coefficient is obtained by the standard deviation of grinding force and the average grinding force. If the grinding force fluctuation coefficient is greater than the preset fluctuation threshold, the grinding process is considered unstable. If the temperature rise rate is greater than the preset temperature threshold, it will cause surface burns.

[0115] This embodiment is based on multi-sensor data fusion and uses a Hidden Markov Model to identify changes in grinding conditions. It determines whether the condition has changed by comparing the similarity between the current feature vector and a predefined condition template. When the control performance index does not reach the expected threshold range, or when a change in the grinding condition is determined:

[0116] The control strategy regeneration process is triggered, using the current second physical state signal as the new input to reselect the control strategy generation mode (strategy library matching or intelligent optimization algorithm). If the change is small, the strategy library matching mode is used first to quickly adjust the parameters; if the change is significant, the intelligent optimization algorithm is activated for global optimization.

[0117] A multi-level control method for workpiece grinding in the aerospace field, corresponding to the above embodiment. Figure 2 This is a structural block diagram of a multi-level control method system for workpiece grinding in the aerospace field, provided as an embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 2 The multi-level control system 20 for workpiece grinding in the aerospace field includes: a first strategy module 21, a data acquisition module 22, a mode selection module 23, a control strategy module 24, and an execution module 25.

[0118] The first strategy module 21 is used to determine the first control strategy of the grinding equipment based on the material properties of the target workpiece and the grinding task requirements.

[0119] Data acquisition module 22 is used to acquire physical state signals of the target workpiece grinding area when the grinding equipment is controlled based on the first control strategy; the physical state signals include one or more of the following: grinding force, grinding temperature, vibration signal, acoustic emission signal and workpiece surface morphology;

[0120] The mode selection module 23 is used to select the control strategy generation mode based on the deviation index between the physical state signal and the preset target state of the target workpiece.

[0121] Control strategy module 24 is used to generate target control strategies based on control strategy generation mode;

[0122] The execution module 25 is used to control the grinding equipment to grind the target workpiece based on the target control strategy.

[0123] In one embodiment of this application, the mode selection module 23 is specifically used for:

[0124] Calculate the difference between the physical state signal and the preset target state, and the deviation index;

[0125] If the deviation index is less than or equal to the first deviation threshold, then the strategy library matching mode is selected;

[0126] If the deviation index is greater than the first deviation threshold and less than or equal to the second deviation threshold, then the intelligent optimization algorithm generation mode is selected.

[0127] If the deviation index exceeds the second deviation threshold, the grinding equipment will be shut down.

[0128] In one embodiment of this application, the control strategy module 24 is specifically used for: generating a target control strategy when the strategy library matching mode is selected, including:

[0129] Input the physical state signal into the working condition identification model to obtain the grinding working condition category;

[0130] Based on the grinding condition category, a matching second control strategy is selected from a preset target strategy library; wherein, the target strategy library stores a set of control strategies optimized for different grinding conditions;

[0131] The second control strategy is merged with the first control strategy to generate the target control strategy.

[0132] In one embodiment of this application, the control strategy module 24 is specifically used to: perform weighted fusion of overlapping parameters in the first control strategy and the second control strategy according to a first formula;

[0133] For non-overlapping parameters in the first and second control strategies, the settings of the first control strategy are retained.

[0134] In one embodiment of this application, the control strategy module 24 is specifically used to: generate a target control strategy when the intelligent optimization algorithm generation mode is selected, including:

[0135] Construct an optimization objective function based on physical state signals;

[0136] Using the parameters corresponding to the first control strategy as the initial solution, the genetic algorithm is used to iteratively optimize the solution under the conditions of satisfying process constraints and safety constraints.

[0137] When the convergence condition or optimization objective is met, the optimal solution of the objective function is used as the target control strategy.

[0138] In one embodiment of this application, the control strategy module 24 is specifically used to: construct the fitness function of the genetic algorithm based on the physical state signal and the optimization objective function;

[0139] The fitness value of an individual in the population is determined based on the fitness function;

[0140] The parameters in the first control strategy are used as individuals in the genetic algorithm;

[0141] The target crossover probability of the genetic algorithm is determined based on the variance of the fitness values ​​of individuals in the population.

[0142] The target mutation probability of the genetic algorithm is determined based on the accuracy of the genetic algorithm.

[0143] The parameters in the first control strategy are iteratively optimized based on the fitness function, target crossover probability, and target mutation probability.

[0144] In one embodiment of this application, the multi-level control system for workpiece grinding in the aerospace field further includes: a strategy update module, specifically used for:

[0145] During the grinding process of the grinding equipment based on the target control strategy to grind the target workpiece, the second physical state signal of the grinding area of ​​the target workpiece is acquired;

[0146] Calculate or determine the control effect index of the target control strategy based on the second physical state signal;

[0147] When the control effect index fails to reach the preset expected threshold range, or when the grinding condition changes based on the second physical state signal, the control strategy generation mode is re-determined based on the physical state signal and a new target control strategy is generated.

[0148] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of the modules in the aforementioned device embodiments, for example... Figure 2 The functions of the first strategy module 21, data acquisition module 22, mode selection module 23, control strategy module 24, and execution module 25 are shown.

[0149] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0150] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0151] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store device type information.

[0152] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation methods described in any embodiment of the multi-level control method for workpiece grinding in the aerospace field provided in the embodiments of this application, or they can execute the implementation methods of the electronic devices described in the embodiments of this application, which will not be repeated here.

[0153] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0154] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0155] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0156] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0157] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or units, or it may be an electrical, mechanical, or other form of connection.

[0158] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0159] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0160] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and such modifications or substitutions should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A multi-level control method for workpiece grinding in the aerospace field, characterized in that, include: Based on the material properties of the target workpiece and the grinding task requirements, determine the first control strategy for the grinding equipment; When controlling the grinding equipment based on the first control strategy, the physical state signal of the grinding area of ​​the target workpiece is acquired. The physical state signals include one or more of the following: grinding force, grinding temperature, vibration signal, acoustic emission signal, and workpiece surface morphology; Based on the deviation index between the physical state signal and the preset target state of the target workpiece, a control strategy generation mode is selected. Based on the control strategy generation mode, a target control strategy is generated; The grinding equipment is controlled to grind the target workpiece based on the target control strategy. The control strategy generation modes include: strategy library matching mode and intelligent optimization algorithm generation mode; The step of selecting a control strategy generation mode based on the deviation index between the physical state signal and the preset target state includes: Based on the difference between the physical state signal and the preset target state, the deviation index is calculated; If the deviation index is less than or equal to the first deviation threshold, then the strategy library matching mode is selected; If the deviation index is greater than the first deviation threshold and less than or equal to the second deviation threshold, then the intelligent optimization algorithm generation mode is selected. The first and second deviation thresholds are set based on a large number of grinding tests and actual production experience. The first deviation threshold indicates that the current grinding state deviates little from the ideal state. The deviation index within the range of the first and second deviation thresholds means that it is difficult to meet the optimization requirements by relying solely on strategy library matching, and a more intelligent algorithm is needed for in-depth optimization. If the deviation index is greater than the second deviation threshold, the grinding equipment is controlled to stop. The formula for calculating the deviation index is: in, This is a deviation index; The number of signals is the number of types of physical parameters being monitored. For the first Class of monitoring signals; This refers to the actual measured value, which is the physical quantity collected by the sensor in real time. The target value is the ideal state value required by the process. The tolerance standard deviation is the allowable range of process fluctuations. It is a nonlinear transformation function; The weights are dynamic and determined based on the signal importance coefficients. This is the coupling penalty coefficient; It is a set of coupled signals, that is, a combination of signals that have physical interaction effects; For the first in the coupling set One signal; It is a non-negative cutoff, penalizing only positive deviations (out of tolerance), used to prevent negative deviations from offsetting the risk; For a chain multiplication operator, only if all Activated when exceeding tolerance.

2. The multi-stage control method for workpiece grinding in the aerospace field according to claim 1, characterized in that, When the policy library matching mode is selected, the generation of the target control policy includes: The physical state signal is input into the working condition identification model to obtain the grinding working condition category; Based on the grinding condition category, a matching second control strategy is selected from a preset target strategy library; wherein, the target strategy library stores a set of control strategies optimized for different grinding conditions; The second control strategy is fused with the first control strategy to generate the target control strategy.

3. The multi-stage control method for workpiece grinding in the aerospace field according to claim 2, characterized in that, The process of fusing the second control strategy with the first control strategy includes: For the overlapping parameters in the first control strategy and the second control strategy, a weighted fusion is performed according to the first formula; For non-overlapping parameters in the first control strategy and the second control strategy, the set value of the first control strategy is retained; The first formula is: in, These are the parameter values ​​after fusion; The parameter value for the first control strategy. This is the parameter value for the second control strategy. The first credibility coefficient, The second credibility coefficient is dynamically calculated based on the historical success rate of the strategy, and ; To integrate the sensitivity factor, the k-value is used to achieve adaptive switching of the fusion strategy under different operating conditions; The intensity of conflict punishment; This is the parameter difference tolerance threshold, used to apply attenuation to conflicting parameters.

4. The multi-stage control method for workpiece grinding in the aerospace field according to claim 1, characterized in that, When the intelligent optimization algorithm generation mode is selected, the generation target control strategy includes: Construct an optimization objective function based on the physical state signal; Using the parameters corresponding to the first control strategy as the initial solution, the genetic algorithm is used to iteratively optimize the solution under the conditions of satisfying process constraints and safety constraints. When the convergence condition or optimization objective is met, the optimal solution of the objective function is taken as the objective control strategy.

5. The multi-stage control method for workpiece grinding in the aerospace field according to claim 4, characterized in that, The iterative optimization using a genetic algorithm under the conditions of satisfying process and safety constraints includes: The fitness function of the genetic algorithm is constructed based on the physical state signal and the optimization objective function; The fitness value of an individual in the population is determined based on the fitness function. The parameters in the first control strategy are used as individuals in the genetic algorithm; The target crossover probability of the genetic algorithm is determined based on the variance of the fitness values ​​of individuals in the population. The target mutation probability of the genetic algorithm is determined based on the accuracy of the genetic algorithm. The parameters in the first control strategy are iteratively optimized based on the fitness function, the target crossover probability, and the target mutation probability.

6. The multi-stage control method for workpiece grinding in the aerospace field according to claim 1, characterized in that, Also includes: During the grinding process of the grinding equipment to grind the target workpiece based on the target control strategy, the second physical state signal of the grinding area of ​​the target workpiece is acquired; Calculate or determine the control effect index of the target control strategy based on the second physical state signal; When the control effect index fails to reach the preset expected threshold range, or when the grinding condition changes based on the second physical state signal, the control strategy generation mode is re-determined based on the physical state signal and a new target control strategy is generated.

7. A multi-level control system for workpiece grinding in the aerospace field, characterized in that, include: The first strategy module is used to determine the first control strategy of the grinding equipment based on the material properties of the target workpiece and the grinding task requirements. The data acquisition module is used to acquire the physical state signal of the grinding area of ​​the target workpiece when controlling the grinding equipment based on the first control strategy; The physical state signals include one or more of the following: grinding force, grinding temperature, vibration signal, acoustic emission signal, and workpiece surface morphology; The mode selection module is used to select a control strategy generation mode based on the deviation index between the physical state signal and the preset target state of the target workpiece. The control strategy module is used to generate a target control strategy based on the control strategy generation mode. An execution module is configured to control the grinding equipment to grind the target workpiece based on the target control strategy. The control strategy generation modes include: strategy library matching mode and intelligent optimization algorithm generation mode; The step of selecting a control strategy generation mode based on the deviation index between the physical state signal and the preset target state includes: Based on the difference between the physical state signal and the preset target state, the deviation index is calculated; If the deviation index is less than or equal to the first deviation threshold, then the strategy library matching mode is selected; If the deviation index is greater than the first deviation threshold and less than or equal to the second deviation threshold, then the intelligent optimization algorithm generation mode is selected; the first deviation threshold and the second deviation threshold are set based on a large number of grinding tests and actual production experience. The first deviation threshold indicates that the current grinding state deviates little from the ideal state; the deviation index within the range of the first deviation threshold and the second deviation threshold means that it is difficult to meet the optimization requirements by relying solely on strategy library matching, and in-depth optimization is required. If the deviation index is greater than the second deviation threshold, the grinding equipment is controlled to stop. The formula for calculating the deviation index is: in, This is a deviation index; The number of signals is the number of types of physical parameters being monitored. For the first Class of monitoring signals; This refers to the actual measured value, which is the physical quantity collected by the sensor in real time. The target value is the ideal state value required by the process. The tolerance standard deviation is the allowable range of process fluctuations. It is a nonlinear transformation function; The weights are dynamic and determined based on the signal importance coefficients. This is the coupling penalty coefficient; It is a set of coupled signals, that is, a combination of signals that have physical interaction effects; For the first in the coupling set One signal; It is a non-negative cutoff, penalizing only positive deviations (out of tolerance), used to prevent negative deviations from offsetting the risk; For a chain multiplication operator, only if all Activated when exceeding tolerance.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 6.

Images