Optimization method of process parameters for rotary ultrasonic hole machining of ceramic composite armor

Abstract

The present invention provides a method for optimizing process parameters of rotary ultrasonic hole machining of ceramic composite armor, which relates to the technical field of rotary ultrasonic hole machining. The specific steps include: establishing a kinematic model of a drill bit, analyzing its motion trajectory under different conditions to obtain displacement and applied external excitation force data; then, using Newton's law to establish a dynamic equation, calculate the natural frequency of the drill bit, and determine the resonant frequency region; based on these analyses, setting different cutting frequencies and vibration amplitude combinations for machining experiments, constructing a wear test model, and using a genetic algorithm to optimize the rotation speed, vibration frequency and feed speed to obtain the optimal combination value of the rotation speed, vibration frequency and feed speed. The present invention avoids the resonant frequency region, maintains the stable operation of the drill bit, enhances the controllability of the machining process, reduces the negative impact of vibration on machining quality, and at the same time, optimizes the optimal process parameters and reduces machining risks.

Description

Technical Field

[0001] The invention relates to the technical field of rotary ultrasonic hole machining, and in particular to a method for optimizing process parameters of rotary ultrasonic hole machining of ceramic composite armor. Background Art

[0002] The optimization of rotary ultrasonic hole machining process parameters for ceramic composite armor refers to adjusting and optimizing the key process parameters (such as cutting frequency, vibration amplitude, and feed speed) during rotary ultrasonic machining on ceramic composite materials through system analysis and experimental design to achieve the best machining effect. This includes improving the accuracy and surface quality of hole machining, increasing material removal rate, reducing tool wear during machining, and improving overall machining efficiency.

[0003] In the prior art, there is a lack of analysis and selection of the natural frequency and resonant frequency of the drill bit. When the vibration frequency of the drill bit is close to its natural frequency, resonance will occur in the system, resulting in a significant increase in the vibration amplitude of the drill bit. The increased vibration will lead to instability in the machining process, affecting the positioning accuracy of the drill bit and the continuity of the cutting process, thereby affecting the machining stability and product quality. In addition, the optimization of process parameters has not received sufficient attention, and there is a lack of a systematic method that integrates the natural frequency and process parameters.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide a method for optimizing process parameters of rotary ultrasonic hole machining of ceramic composite armor to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for optimizing process parameters of rotary ultrasonic hole machining of ceramic composite armor, the specific steps comprising:

[0008] S1. Collect the rotation speed, vibration frequency and feed speed of the drill bit, establish a kinematic model of the drill bit, perform motion trajectory analysis based on the kinematic model, and obtain the data of the drill bit under different processing conditions, including the displacement of the drill bit and the external excitation force applied to the drill bit;

[0009] S2. Obtain the property parameters of the drill bit, including elastic modulus, mass, diameter and length, and use Newton's law to establish the dynamic equation of the drill bit during vibration according to the displacement of the drill bit and the external excitation force applied to the drill bit. Based on the dynamic equation, obtain the natural frequency of the drill bit;

[0010] S3. According to the natural frequency of the drill bit, the resonant frequency region is identified, and the vibration frequency is selected outside the resonant frequency region. The rotation speed, vibration frequency and feed speed are set as constant values, and different cutting frequency and vibration amplitude combinations are set. A processing experiment is performed under each group to obtain the surface roughness and aperture accuracy of the rotary ultrasonic holes of different groups, and the surface roughness and aperture accuracy of the rotary ultrasonic holes of different groups are processed to obtain the quality coefficients of the rotary ultrasonic holes of different groups. The quality coefficients of the rotary ultrasonic holes of different groups are compared, and the optimal combination value of the cutting frequency and the vibration amplitude is determined according to the comparison results;

[0011] S4. Taking the optimal combination of cutting frequency and vibration amplitude as a fixed value, selecting a vibration frequency outside the resonance frequency region, and setting different combinations of rotation speed, vibration frequency and feed speed, performing processing experiments under each combination, obtaining the wear amount of the drill under different combinations, and constructing a wear amount test model. Taking the optimal combination of cutting frequency and vibration amplitude, rotation speed, vibration frequency and feed speed combination as input, and the corresponding drill wear amount as a label, the wear amount test model is trained;

[0012] S5. Taking the minimization of wear as the optimization goal, the rotation speed, vibration frequency and feed speed are optimized based on the genetic algorithm to obtain the best combination value of the rotation speed, vibration frequency and feed speed.

[0013] Furthermore, a kinematic model of the drill bit is established, and the motion trajectory analysis is performed based on the kinematic model to obtain the displacement of the drill bit under different processing conditions and the external excitation force applied to the drill bit. The specific process is as follows:

[0014] The movement of the drill bit is considered as a combined motion, including rotational motion and vibration motion. Assuming that the path of the drill bit is described by a combination of circular motion and simple harmonic vibration, the displacement of the drill bit is expressed as:

[0015] ;

[0016] in, is the displacement of the drill bit at time t, is the radius of the circular trajectory of the drill bit when it rotates, is the angular velocity, is the vibration amplitude, is the vibration frequency, is the time variable;

[0017] Assuming that the external excitation force is expressed as a function related to the vibration characteristics of the drill bit, it is estimated by the dynamic equation, applying Newton's second law:

[0018] ;

[0019] in, is the mass of the abrasive particles, is the acceleration at time t;

[0020] Acceleration By taking the derivative of the displacement function, we get:

[0021] ;

[0022] The acceleration Substituting into the force formula, we get the external excitation force applied to the drill bit:

[0023] ;

[0024] in, is the external excitation force at time t.

[0025] Furthermore, according to the displacement of the drill bit and the external excitation force applied to the drill bit, the dynamic equation of the drill bit during vibration is established using Newton's law. Based on the dynamic equation, the natural frequency of the drill bit is obtained. The specific process is as follows:

[0026] Assume that the external excitation force is expressed as some simple harmonic vibration:

[0027] ;

[0028] in, is the stiffness of the drill bit;

[0029] Substituting into the kinetic equation:

[0030] ;

[0031] The above kinetic equation is converted into the characteristic equation as follows:

[0032] ;

[0033] Solve for characteristic roots:

[0034] ;

[0035] in, is an imaginary unit;

[0036] The natural frequency of the drill bit is the frequency of the natural vibration of the system without external force. According to the solution of the characteristic root, the natural frequency is calculated by the following formula:

[0037] ;

[0038] ;

[0039] ;

[0040] in, is the natural frequency of the drill bit, is the elastic modulus, is the area of ​​the circular cross section, is the length of the drill bit, is the diameter of the drill bit.

[0041] Furthermore, according to the natural frequency of the drill bit, the process of identifying the resonant frequency region is as follows:

[0042] Perform a frequency response test, apply an excitation of known frequency to the drill system, and use an accelerometer to measure the vibration of the drill at different frequencies. Vibration response under

[0043] Record different vibration frequencies The vibration amplitude under , forming a vibration frequency and vibration amplitude Relationship diagram;

[0044] Based on vibration frequency and vibration amplitude The average value of the vibration amplitude is obtained from the relationship diagram of the vibration amplitude, the average value of the vibration amplitude is used as the preset threshold, and the vibration amplitude greater than the preset threshold is The frequency region is taken as the resonant frequency.

[0045] Furthermore, the vibration frequency is selected outside the resonance frequency region, and the rotation speed, vibration frequency and feed speed are set as constant values. Different cutting frequency and vibration amplitude combinations are set, and processing experiments are carried out under each group to obtain the surface roughness and aperture accuracy of the rotary ultrasonic holes of different groups. The specific process is as follows:

[0046] set up Group cutting frequency and The vibration amplitude of the group is formed The cutting frequency and vibration amplitude combination of the i-th experimental group is used as the experimental group. The processing experiment is carried out by combining the experimental group with the fixed rotation speed, vibration frequency and feed speed to obtain the corresponding surface roughness and aperture accuracy. The surface roughness and aperture accuracy corresponding to the i-th experimental group are calibrated as , , i is the index of the experimental group, .

[0047] Furthermore, the surface roughness and aperture accuracy are processed to obtain the quality coefficient of the rotating ultrasonic hole, based on the following formula:

[0048] ;

[0049] in, For the The mass coefficient of the rotating ultrasonic hole corresponding to the experimental group, is a constant, is the weight coefficient of the surface roughness of the rotating ultrasonic hole, is the weight coefficient of the aperture accuracy of the rotating ultrasonic hole, , .

[0050] Furthermore, the quality coefficients of the rotary ultrasonic holes of different groups were compared, and the optimal combination of cutting frequency and vibration amplitude was determined based on the comparison results. The process is as follows:

[0051] The quality coefficients corresponding to each experimental group are arranged from large to small, and the cutting frequency and vibration amplitude combination corresponding to the maximum quality coefficient is taken as the best combination of cutting frequency and vibration amplitude, and the cutting frequency and vibration amplitude in the best combination are calibrated as , , i1 represents the index of the best combination in the experimental group, and .

[0052] Furthermore, the wear amount experimental model adopts a convolutional neural network model, and the convolutional neural network model is composed of a deep neural network based on a multilayer perceptron. The deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer. The first hidden layer, the second hidden layer and the third hidden layer all have at least two neurons, and all use ReLU as the activation function.

[0053] Furthermore, the expression of the wear amount of the drill bit is specifically as follows:

[0054] ;

[0055] in, is the wear of the drill bit, is the proportionality constant, is the rotation speed, is the feed speed, is the vibration frequency, is the index of cutting frequency, , for The index of , is the index of the rotation speed, , is the weight coefficient of feed speed, , is the weight coefficient of vibration frequency, , is the exponent of the vibration frequency, ;

[0056] The wear test model is trained by taking the optimal combination of cutting frequency and vibration amplitude, rotation speed, vibration frequency and feed speed as input, and the corresponding drill wear as output label. , , , , and Optimize and use the mean square error as the loss function. When the mean square error is When it is within the range, the training of the wear test model is completed.

[0057] Furthermore, with the minimization of wear as the optimization goal, the rotation speed, vibration frequency and feed speed are optimized based on the genetic algorithm to obtain the optimal combination of rotation speed, vibration frequency and feed speed. The specific process is as follows:

[0058] An initial population is randomly generated based on the set rotation speed, vibration frequency and feed speed combination. The initial population includes multiple individuals, each of which has three gene bits for storing the rotation speed, vibration frequency and feed speed values. The optimal combination value of the individual and the cutting frequency and vibration amplitude is input into the trained wear test model to obtain the drill wear corresponding to the individual. The individuals in the initial population are sorted from small to large according to the drill wear, and the individuals in the top 50% are selected as the parent generation. Through the crossover operation, the genes of the parent individuals are exchanged and combined to generate new individuals. After the mutation operation is performed on the newly generated individuals, the drill wear calculation, selection, crossover and mutation operations are repeated until the preset number of iterations is reached. The individual with the smallest drill wear is selected as the optimal individual. The rotation speed, vibration frequency and feed speed corresponding to the optimal individual are the optimal combination values ​​of the rotation speed, vibration frequency and feed speed.

[0059] Compared with the prior art, the present invention has the following beneficial effects:

[0060] The present invention collects the rotation speed, vibration frequency and feed speed of the drill bit, establishes a kinematic model, analyzes the motion trajectory of the drill bit under different conditions, obtains the attribute parameters of the drill bit, establishes a dynamic equation using Newton's law, calculates the natural frequency of the drill bit, identifies the resonant frequency area, and sets different vibration frequency and vibration amplitude combinations for processing experiments to avoid the resonant frequency area, maintain stable operation of the drill bit, enhance the controllability of the processing process, and reduce the negative impact of vibration on the processing quality. By obtaining the surface roughness, aperture accuracy and wear, and performing data processing and comparison to determine the optimal cutting frequency and vibration amplitude, the genetic algorithm is used to optimize the rotation speed, vibration frequency and feed speed to minimize the wear amount, thereby optimizing the optimal process parameters and reducing the processing risk. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0062] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0063] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0064] Example:

[0065] See also Figure 1 , the present invention provides a technical solution:

[0066] A method for optimizing process parameters of rotary ultrasonic hole machining of ceramic composite armor, the specific steps comprising:

[0067] S1. Collect the rotation speed, vibration frequency and feed speed of the drill bit, establish a kinematic model of the drill bit, perform motion trajectory analysis based on the kinematic model, and obtain the data of the drill bit under different processing conditions, including the displacement of the drill bit and the external excitation force applied to the drill bit;

[0068] S2. Obtain the property parameters of the drill bit, including elastic modulus, mass, diameter and length, and use Newton's law to establish the dynamic equation of the drill bit during vibration according to the displacement of the drill bit and the external excitation force applied to the drill bit. Based on the dynamic equation, obtain the natural frequency of the drill bit;

[0069] S3. According to the natural frequency of the drill bit, the resonant frequency region is identified, and the vibration frequency is selected outside the resonant frequency region. The rotation speed, vibration frequency and feed speed are set as constant values, and different cutting frequency and vibration amplitude combinations are set. A processing experiment is performed under each group to obtain the surface roughness and aperture accuracy of the rotary ultrasonic holes of different groups, and the surface roughness and aperture accuracy of the rotary ultrasonic holes of different groups are processed to obtain the quality coefficients of the rotary ultrasonic holes of different groups. The quality coefficients of the rotary ultrasonic holes of different groups are compared, and the optimal combination value of the cutting frequency and the vibration amplitude is determined according to the comparison results;

[0070] S4. Taking the optimal combination of cutting frequency and vibration amplitude as a fixed value, selecting a vibration frequency outside the resonance frequency region, and setting different combinations of rotation speed, vibration frequency and feed speed, performing processing experiments under each combination, obtaining the wear amount of the drill under different combinations, and constructing a wear amount test model. Taking the optimal combination of cutting frequency and vibration amplitude, rotation speed, vibration frequency and feed speed combination as input, and the corresponding drill wear amount as a label, the wear amount test model is trained;

[0071] S5. Taking the minimization of wear as the optimization goal, the rotation speed, vibration frequency and feed speed are optimized based on the genetic algorithm to obtain the best combination value of the rotation speed, vibration frequency and feed speed.

[0072] On the basis of the above embodiment, the equipment and method for collecting the rotation speed, vibration frequency, feed speed and elastic modulus of the drill bit are as follows:

[0073] Use photoelectric sensors to detect the rotation speed of the drill bit;

[0074] By installing an accelerometer on the drill bit, the vibration signal is measured and converted into vibration frequency;

[0075] The feed rate is calculated by measuring the displacement of the drill bit through a linear displacement sensor;

[0076] A universal mechanical testing machine is used to measure the stress and strain of the material during stretching, and then the elastic modulus is calculated.

[0077] On the basis of the above embodiment, a kinematic model of the drill bit is established, and motion trajectory analysis is performed according to the kinematic model to obtain the displacement of the drill bit under different processing conditions and the external excitation force applied to the drill bit. The specific process is as follows:

[0078] The movement of the drill bit is considered as a combined motion, including rotational motion and vibration motion. Assuming that the path of the drill bit is described by a combination of circular motion and simple harmonic vibration, the displacement of the drill bit is expressed as:

[0079] ;

[0080] in, is the displacement of the drill bit at time t, is the radius of the circular trajectory of the drill bit when it rotates, is the angular velocity, is the vibration amplitude, is the vibration frequency, is the time variable;

[0081] Assuming that the external excitation force is expressed as a function related to the vibration characteristics of the drill bit, it is estimated by the dynamic equation, applying Newton's second law:

[0082] ;

[0083] in, is the mass of the abrasive particles, is the acceleration at time t;

[0084] Acceleration By taking the derivative of the displacement function, we get:

[0085] ;

[0086] The acceleration Substituting into the force formula, we get the external excitation force applied to the drill bit:

[0087] ;

[0088] in, is the external excitation force at time t.

[0089] On the basis of the above embodiment, according to the displacement of the drill bit and the external excitation force applied to the drill bit, Newton's law is used to establish the dynamic equation of the drill bit during vibration. According to the dynamic equation, the natural frequency of the drill bit is obtained. The specific process is as follows:

[0090] Assume that the external excitation force is expressed as some simple harmonic vibration:

[0091] ;

[0092] in, is the stiffness of the drill bit;

[0093] Substituting into the kinetic equation:

[0094] ;

[0095] The above kinetic equation is converted into the characteristic equation as follows:

[0096] ;

[0097] Solve for characteristic roots:

[0098] ;

[0099] in, is an imaginary unit;

[0100] The natural frequency of the drill bit is the frequency of the natural vibration of the system without external force. According to the solution of the characteristic root, the natural frequency is calculated by the following formula:

[0101] ;

[0102] ;

[0103] ;

[0104] in, is the natural frequency of the drill bit, is the elastic modulus, is the area of ​​the circular cross section, is the length of the drill bit, is the diameter of the drill bit.

[0105] Based on the above embodiment, the process of identifying the resonant frequency region according to the natural frequency of the drill bit is as follows:

[0106] Frequency response testing applies a known frequency stimulus to the drill system and uses a sensor (such as an accelerometer) to measure the drill's vibration response at different frequencies. Vibration response under

[0107] Record different vibration frequencies The vibration amplitude under , forming a vibration frequency and vibration amplitude Relationship diagram;

[0108] Based on vibration frequency and vibration amplitude The average value of the vibration amplitude is obtained from the relationship diagram of the vibration amplitude, the average value of the vibration amplitude is used as the preset threshold, and the vibration amplitude greater than the preset threshold is The frequency region is taken as the resonant frequency.

[0109] On the basis of the above embodiment, the vibration frequency is selected outside the resonance frequency region, the rotation speed, the vibration frequency and the feed speed are set as constant values, and different cutting frequencies and vibration amplitude combinations are set. A processing experiment is carried out under each group to obtain the surface roughness and aperture accuracy of the rotary ultrasonic holes of different groups. The specific process is as follows:

[0110] set up Group cutting frequency and The vibration amplitude of the group is formed The cutting frequency and vibration amplitude combination of the i-th experimental group is used as the experimental group. The processing experiment is carried out by combining the experimental group with the fixed rotation speed, vibration frequency and feed speed to obtain the corresponding surface roughness and aperture accuracy. The surface roughness and aperture accuracy corresponding to the i-th experimental group are calibrated as , , i is the index of the experimental group, .

[0111] On the basis of the above embodiment, the surface roughness and the aperture accuracy are processed to obtain the quality coefficient of the rotating ultrasonic hole, according to the following formula:

[0112] ;

[0113] in, For the The mass coefficient of the rotating ultrasonic hole corresponding to the experimental group, is a constant, is the weight coefficient of the surface roughness of the rotating ultrasonic hole, is the weight coefficient of the aperture accuracy of the rotating ultrasonic hole, , .

[0114] In the formula, surface roughness The increase in the denominator will result in Increase, which means the quality factor will decrease, reflecting the surface roughness The increase in the roughness will reduce the quality, which is in line with the actual situation, because the higher the roughness Usually it will lead to more wear and friction, thus affecting the product quality. Therefore, the surface roughness and the quality coefficient of the rotary ultrasonic hole are negatively correlated;

[0115] Aperture accuracy The increase in will reduce the influence of the denominator, which will reduce the denominator and increase , which reflects that the improvement of aperture accuracy improves the processing quality. Therefore, there is a positive correlation between aperture accuracy and the quality coefficient of rotary ultrasonic hole.

[0116] Surface roughness requires a larger weight because the negative impact of roughness on quality is very significant, so a larger weight needs to be given to surface roughness in the formula to accurately reflect its influence on the quality coefficient; relatively speaking, the influence of aperture accuracy on quality is usually indirect, and in some cases its importance is not as obvious as roughness. Therefore, a smaller weight is given to aperture accuracy in the formula.

[0117] In summary, setting When only surface roughness and aperture accuracy have an effect on the quality coefficient of the rotary ultrasonic hole, set .

[0118] On the basis of the above-mentioned embodiment, the quality coefficients of the rotating ultrasonic holes of different groups are compared, and the optimal combination of the cutting frequency and the vibration amplitude is determined according to the comparison result, and the process is as follows:

[0119] The quality coefficients corresponding to each experimental group are arranged from large to small, and the cutting frequency and vibration amplitude combination corresponding to the maximum quality coefficient is taken as the best combination of cutting frequency and vibration amplitude, and the cutting frequency and vibration amplitude in the best combination are calibrated as , , i1 represents the index of the best combination in the experimental group, and .

[0120] On the basis of the above embodiment, the wear amount experimental model adopts a convolutional neural network model, and the convolutional neural network model is composed of a deep neural network based on a multilayer perceptron. The deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer. The first hidden layer, the second hidden layer and the third hidden layer all have at least two neurons, and all use ReLU as the activation function.

[0121] In this embodiment, the input features of the deep neural network of the multilayer perceptron include five features: cutting frequency, vibration amplitude, rotation speed, vibration frequency and feed speed.

[0122] The structure of a deep neural network with a multilayer perceptron is:

[0123] Input layer: receives input of 5 features;

[0124] The first hidden layer has 128 neurons and uses ReLU as the activation function.

[0125] The second hidden layer has 256 neurons and also uses the ReLU activation function.

[0126] The third hidden layer has 128 neurons and uses the ReLU activation function.

[0127] Output layer: has a single neuron, the amount of wear on the drill bit.

[0128] On the basis of the above embodiment, taking the optimal combination of cutting frequency and vibration amplitude as a constant, a functional expression of drill wear and cutting frequency, vibration amplitude, rotation speed, vibration frequency and feed speed is established in the following form:

[0129] ;

[0130] in, is the wear of the drill bit, is the proportionality constant, is the rotation speed, is the feed speed, is the vibration frequency, is the index of cutting frequency, , for The index of , is the index of the rotation speed, , is the weight coefficient of feed speed, , is the weight coefficient of vibration frequency, , is the exponent of the vibration frequency, ;

[0131] A data set including the best combination of cutting frequency and vibration amplitude, rotation speed, vibration frequency and feed speed was constructed. The entire data set was divided into a training set and a validation set. 80% of the data was used for training and 20% for validation. The best combination of cutting frequency and vibration amplitude, rotation speed, vibration frequency and feed speed were used as input, and the corresponding drill wear was used as the output label to train the wear test model. The back propagation algorithm was used to train the wear test model. , , , , and Optimize and use the mean square error as the loss function. When the mean square error is When the wear test model is trained, the obtained , , , , and It can be used to predict the wear amount under new cutting conditions.

[0132] In the normal range, a higher cutting frequency means that the drill bit performs more cutting times per unit time, which will lead to more wear. Frequent cutting actions increase the frequency of contact between the drill bit and the material, leading to accelerated wear. Therefore, the cutting frequency is proportional to the wear of the drill bit;

[0133] A larger vibration amplitude means that the drill generates a greater impact force during the cutting process, making the material removal more intense. This intense cutting will accelerate wear because the contact strength between the drill material and the cut material increases, resulting in more material wear. Therefore, the vibration amplitude is directly proportional to the amount of drill wear;

[0134] Increasing the rotation speed means that the drill cuts the material at a faster rate, which also results in a higher grinding effect. High rotation speeds usually increase cutting efficiency, but also increase wear because the friction and impact forces on the drill bit increase. Therefore, the rotation speed and the amount of wear on the drill bit are directly proportional;

[0135] A higher feed rate means that the drill cuts thinner material per unit time. Although this can speed up the process, it may also lead to less wear on the drill bit, because the contact time between the drill bit and the material is reduced, and the opportunity for wear accumulation is also reduced. Therefore, the feed rate and the amount of drill wear are inversely proportional;

[0136] A higher vibration frequency may mean that the drill moves more frequently during the cutting process, generating stronger impact forces, but if the vibration frequency is too high, it may cause the overall stability of the drill to decrease, but reduce wear. When the vibration frequency is too high, the contact strength between the drill and the material may be weakened, thereby reducing wear. Therefore, the vibration frequency and the amount of drill wear are inversely proportional.

[0137] Taking the minimization of wear as the optimization goal, the rotation speed, vibration frequency and feed speed are optimized based on the genetic algorithm to obtain the best combination of rotation speed, vibration frequency and feed speed. The specific process is as follows:

[0138] An initial population is randomly generated based on the set rotation speed, vibration frequency and feed speed combination. The initial population includes multiple individuals, each of which has three gene bits for storing the rotation speed, vibration frequency and feed speed values. The optimal combination value of the individual and the cutting frequency and vibration amplitude is input into the trained wear test model to obtain the drill wear corresponding to the individual. The individuals in the initial population are sorted from small to large according to the drill wear, and the individuals in the top 50% are selected as the parent generation. Through the crossover operation, the genes of the parent individuals are exchanged and combined to generate new individuals. After the mutation operation is performed on the newly generated individuals, the drill wear calculation, selection, crossover and mutation operations are repeated until the preset number of iterations is reached. The individual with the smallest drill wear is selected as the optimal individual. The rotation speed, vibration frequency and feed speed corresponding to the optimal individual are the optimal combination values ​​of the rotation speed, vibration frequency and feed speed.

[0139] Rotation speed Randomly generated from the range [100,1000], the vibration frequency Randomly generated from the range [0.1,10], the feed rate Randomly generated from the range of [0.1,5] to form the rotation speed , vibration frequency , Feed speed The range of the above parameters is verified through multiple simulations and tests.

[0140] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0141] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0142] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for optimizing process parameters of rotary ultrasonic hole machining of ceramic composite armor, characterized in that: The specific steps include: S1. Collect the rotation speed, vibration frequency and feed speed of the drill bit, establish a kinematic model of the drill bit, perform motion trajectory analysis based on the kinematic model, and obtain the data of the drill bit under different processing conditions, including the displacement of the drill bit and the external excitation force applied to the drill bit; S2. Obtain the property parameters of the drill bit, including elastic modulus, mass, diameter and length, and use Newton's law to establish the dynamic equation of the drill bit during vibration according to the displacement of the drill bit and the external excitation force applied to the drill bit. Based on the dynamic equation, obtain the natural frequency of the drill bit; S3. According to the natural frequency of the drill bit, the resonant frequency region is identified, and the vibration frequency is selected outside the resonant frequency region. The rotation speed, vibration frequency and feed speed are set as constant values, and different cutting frequency and vibration amplitude combinations are set. A processing experiment is performed under each group to obtain the surface roughness and aperture accuracy of the rotary ultrasonic holes of different groups, and the surface roughness and aperture accuracy of the rotary ultrasonic holes of different groups are processed to obtain the quality coefficients of the rotary ultrasonic holes of different groups. The quality coefficients of the rotary ultrasonic holes of different groups are compared, and the optimal combination value of the cutting frequency and the vibration amplitude is determined according to the comparison results; S4. Taking the optimal combination of cutting frequency and vibration amplitude as a fixed value, selecting a vibration frequency outside the resonance frequency region, and setting different combinations of rotation speed, vibration frequency and feed speed, performing processing experiments under each combination, obtaining the wear amount of the drill under different combinations, and constructing a wear amount test model. Taking the optimal combination of cutting frequency and vibration amplitude, rotation speed, vibration frequency and feed speed combination as input, and the corresponding drill wear amount as a label, the wear amount test model is trained; S5. Taking the minimization of wear as the optimization goal, the rotation speed, vibration frequency and feed speed are optimized based on the genetic algorithm to obtain the best combination value of the rotation speed, vibration frequency and feed speed; The kinematic model of the drill bit is established, and the motion trajectory analysis is performed based on the kinematic model to obtain the displacement of the drill bit under different processing conditions and the external excitation force applied to the drill bit. The specific process is as follows: The movement of the drill bit is considered as a combined motion, including rotational motion and vibration motion. Assuming that the path of the drill bit is described by a combination of circular motion and simple harmonic vibration, the displacement of the drill bit is expressed as: in, is the displacement of the drill bit at time t, is the radius of the circular trajectory of the drill bit when it rotates, is the angular velocity, is the vibration amplitude, is the vibration frequency, is the time variable; Assuming that the external excitation force is expressed as a function related to the vibration characteristics of the drill bit, it is estimated by the dynamic equation, applying Newton's second law: in, is the mass of the abrasive particles, is the acceleration at time t; Acceleration By taking the derivative of the displacement function, we get: The acceleration Substituting into the force formula, we get the external excitation force applied to the drill bit: in, is the external incentive force at time t; According to the displacement of the drill bit and the external excitation force applied to the drill bit, the dynamic equation of the drill bit during vibration is established using Newton's law. Based on this dynamic equation, the natural frequency of the drill bit is obtained. The specific process is as follows: Assume that the external excitation force is expressed as some simple harmonic vibration: in, is the stiffness of the drill bit; Substituting into the kinetic equation: The above kinetic equation is converted into the characteristic equation as follows: Solve for characteristic roots: in, is an imaginary unit; The natural frequency of the drill bit is the frequency of the natural vibration of the system without external force. According to the solution of the characteristic root, the natural frequency is calculated by the following formula: in, is the natural frequency of the drill bit, is the elastic modulus, is the area of ​​the circular cross section, is the length of the drill bit, is the diameter of the drill bit; Based on the natural frequency of the drill bit, the process of identifying the resonant frequency region is as follows: Perform a frequency response test, apply an excitation of known frequency to the drill system, and use an accelerometer to measure the vibration of the drill at different frequencies. Vibration response under Record different vibration frequencies The vibration amplitude under , forming a vibration frequency and vibration amplitude Relationship diagram; Based on vibration frequency and vibration amplitude The average value of the vibration amplitude is obtained from the relationship diagram of the vibration amplitude, the average value of the vibration amplitude is used as the preset threshold, and the vibration amplitude greater than the preset threshold is The frequency region is taken as the resonance frequency; Select the vibration frequency outside the resonance frequency region, take the rotation speed, vibration frequency and feed speed as constant values, and set different cutting frequency and vibration amplitude combinations. Perform processing experiments under each group to obtain the surface roughness and aperture accuracy of the rotary ultrasonic holes of different groups. The specific process is as follows: set up Group cutting frequency and The vibration amplitude of the group is formed The cutting frequency and vibration amplitude combination of the i-th experimental group is used as the experimental group. The processing experiment is carried out by combining the experimental group with the fixed rotation speed, vibration frequency and feed speed to obtain the corresponding surface roughness and aperture accuracy. The surface roughness and aperture accuracy corresponding to the i-th experimental group are calibrated as , , i is the index of the experimental group, ; The surface roughness and aperture accuracy are processed to obtain the quality coefficient of the rotating ultrasonic hole, based on the following formula: in, For the The mass coefficient of the rotating ultrasonic hole corresponding to the experimental group, is a constant, is the weight coefficient of the surface roughness of the rotating ultrasonic hole, is the weight coefficient of the aperture accuracy of the rotating ultrasonic hole, , ; The quality coefficients of different groups of rotary ultrasonic holes are compared, and the optimal combination of cutting frequency and vibration amplitude is determined based on the comparison results. The process is as follows: The quality coefficients corresponding to each experimental group are arranged from large to small, and the cutting frequency and vibration amplitude combination corresponding to the maximum quality coefficient is taken as the best combination of cutting frequency and vibration amplitude, and the cutting frequency and vibration amplitude in the best combination are calibrated as , , i1 represents the index of the best combination in the experimental group, and ; The wear test model adopts a convolutional neural network model, and the convolutional neural network model is composed of a deep neural network based on a multilayer perceptron. The deep neural network of the multilayer perceptron includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer. The first hidden layer, the second hidden layer and the third hidden layer each have at least two neurons, and each uses ReLU as an activation function; The expression of the wear amount of the drill bit is as follows: in, is the wear of the drill bit, is the proportionality constant, is the rotation speed, is the feed speed, is the vibration frequency, is the index of cutting frequency, , for The index of , is the index of the rotation speed, , is the weight coefficient of feed speed, , is the weight coefficient of vibration frequency, , is the exponent of the vibration frequency, ; The wear test model is trained by taking the optimal combination of cutting frequency and vibration amplitude, rotation speed, vibration frequency and feed speed as input, and the corresponding drill wear as output label. , , , , and Optimize and use the mean square error as the loss function. When the mean square error is When it is within the range, the training of the wear test model is completed.

2. The method for optimizing process parameters of rotary ultrasonic hole machining of ceramic composite armor according to claim 1 is characterized in that: Taking the minimization of wear as the optimization goal, the rotation speed, vibration frequency and feed speed are optimized based on the genetic algorithm to obtain the best combination of rotation speed, vibration frequency and feed speed. The specific process is as follows: An initial population is randomly generated based on the set rotation speed, vibration frequency and feed speed combination. The initial population includes multiple individuals, each of which has three gene bits for storing the rotation speed, vibration frequency and feed speed values. The optimal combination value of the individual and the cutting frequency and vibration amplitude is input into the trained wear test model to obtain the drill wear corresponding to the individual. The individuals in the initial population are sorted from small to large according to the drill wear, and the individuals in the top 50% are selected as the parent generation. Through the crossover operation, the genes of the parent individuals are exchanged and combined to generate new individuals. After the mutation operation is performed on the newly generated individuals, the drill wear calculation, selection, crossover and mutation operations are repeated until the preset number of iterations is reached. The individual with the smallest drill wear is selected as the optimal individual. The rotation speed, vibration frequency and feed speed corresponding to the optimal individual are the optimal combination values ​​of the rotation speed, vibration frequency and feed speed.

Images