Multi-source data fusion-based pressure parameter optimization method in microsphere polishing process

Abstract

The invention provides a pressure parameter optimization method in a microsphere grinding and polishing process based on multi-source data fusion. The pressure parameter optimization method specifically comprises the following steps that 1, vibration signals and non-vibration signals in the microsphere grinding and polishing process are collected through a plurality of sensors; the collected vibration signals are processed, and main features are extracted; then, the extracted vibration signal features and non-vibration signals are integrated, and it is ensured that data dimensions are consistent; step 2, inputting the integrated data into a DAE-MMR prediction model, and predicting an optimal pressure value in a current processing state; the prediction model is constructed based on an automatic encoder and a BP neural network, and is obtained by training historical data of multi-source data collected by a plurality of sensors; thirdly, the predicted pressure value is input into a control system, the pressure in the grinding and polishing process is adjusted through the control system, and precise optimization of pressure parameters is achieved; therefore, the processing precision and the processing efficiency of the microspheres can be improved.

Description

Technical Field

[0001] The invention belongs to the field of micro-ball grinding and polishing, and in particular relates to a method for optimizing pressure parameters in a micro-ball grinding and polishing process based on multi-source data fusion. Background Art

[0002] Diamond-coated microspheres play a huge role in ignition engineering. They are not only related to the research process of laser inertial confinement fusion (ICF), but also important components in high-end optical instruments, high-quality bearings, and high-precision measuring instruments. They play a very important role in basic components and play an important strategic supporting role in the development of the country's high-end manufacturing industry. At present, my country can achieve mass production of G5-level ceramic balls and steel balls; but for G3-level high-precision microspheres with SФ0.5~2.5mm, spherical error better than 0.08μm, and surface roughness better than 0.01μm, especially microspheres made of extremely hard and brittle materials such as diamond and silicon, it is difficult to ensure the quality of microsphere processing during the production process, and it is impossible to achieve mass production, which cannot make up for the gap in the relevant market in my country, which makes it necessary to import high-end microspheres from abroad.

[0003] In the process of micro-ball grinding and polishing, precise control of pressure parameters is crucial to ensure product quality. Traditional pressure control methods rely on mechanical systems and static measurements, and it is difficult to achieve real-time adjustment. In recent years, with the development of vibration signal processing technology, pressure parameter control methods based on vibration signals have gradually become a research hotspot. This method analyzes the characteristic parameters of the equipment vibration signal and establishes a corresponding mathematical model to achieve precise control of pressure parameters; it has the advantages of real-time, precision and intelligence, and is particularly suitable for manufacturing fields with high-precision requirements, such as optical components, semiconductors and aerospace; at the same time, it can also be combined with automated production lines to improve production efficiency and product quality, providing new ideas and broad application prospects for intelligent manufacturing and automated control. Then, if the above-mentioned pressure parameter control method can be applied to the field of micro-ball grinding and polishing, and a pressure parameter optimization method in the process of micro-ball grinding and polishing is studied, it will be of great significance to improve the quality of micro-ball processing and realize the mass production of high-end micro-spheres. Summary of the invention

[0004] In response to the above-mentioned problems existing in the existing microsphere processing technology, the present invention provides a method for optimizing pressure parameters in the microsphere grinding and polishing process based on multi-source data fusion; the optimization method collects multiple data sources such as vibration signals and non-vibration signals in the microsphere grinding and polishing process, and inputs them into the DAE-MMR prediction model to predict the optimal pressure value under the current processing state, and then the control system adjusts the pressure to achieve accurate optimization of the pressure parameters in the microsphere grinding and polishing process, thereby improving the microsphere processing accuracy and efficiency; wherein, the DAE-MMR prediction model is constructed based on an autoencoder and a BP neural network, combining the feature fusion capability of the autoencoder and the linear regression learning capability of the BP neural network, and can effectively fuse multi-source data with high prediction accuracy.

[0005] The technical solution of this application is:

[0006] The pressure parameter optimization method in the micro-ball grinding and polishing process based on multi-source data fusion specifically includes the following steps: Step 1, first collect the vibration signal and non-vibration signal in the micro-ball grinding and polishing process through multiple sensors; then process the collected vibration signal to extract the main features to distinguish the difference of vibration signals in different processing stages; then, integrate the extracted vibration signal features with the non-vibration signal to ensure the consistency of data dimension; Step 2, input the integrated data into the DAE-MMR prediction model to predict the optimal pressure value under the current processing state; the prediction model is constructed based on the autoencoder and BP neural network, and is trained with historical data of multi-source data collected by multiple sensors; the specific training process is as follows: a. The vibration signals and non-vibration signals collected by multiple sensors are divided into rough polishing stage and fine polishing stage according to the time period, and further divided into training set and test set; b. Use the training set data to train the autoencoder, extract the encoding part of the autoencoder, and use the BP neural network for regression prediction training until the loss function converges or reaches the predetermined number of training times; c. Input the data in the test set into the trained prediction model, output the prediction result, and then according to the formula Calculate the mean absolute error MAE to evaluate the performance of the prediction model; where y i is the true pressure value, y′ i To predict the pressure value, N represents the number of samples; if MAE is not greater than the set threshold, the training is completed, otherwise, repeat step b; in step three, the predicted pressure value is input into the control system, and the control system adjusts the pressure during the grinding and polishing process to achieve accurate optimization of the pressure parameters.

[0007] Compared with the prior art, the pressure parameter optimization method in the micro-ball grinding and polishing process based on multi-source data fusion of the present application collects multiple data sources such as vibration signals and non-vibration signals (including temperature, rotation speed, torque, etc.) in the micro-ball grinding and polishing process, and inputs them into the DAE-MMR prediction model to predict the optimal pressure value under the current processing state, and then the control system adjusts the pressure to achieve accurate optimization of the pressure parameters in the micro-ball grinding and polishing process, thereby improving the micro-ball processing accuracy and processing efficiency; wherein, the DAE-MMR prediction model is constructed based on the autoencoder and the BP neural network, combining the feature fusion capability of the autoencoder and the linear regression learning capability of the BP neural network, and can effectively fuse multi-source data with high prediction accuracy. Moreover, after the prediction model has been used for a period of time, the vibration signal, non-vibration signal and predicted pressure parameters within the time period can be input into the prediction model, and the prediction model can be trained again to obtain a new prediction model, thereby achieving regular updating and optimization of the prediction model, and continuously improving the accuracy of the prediction model to make it more adaptable to changes in the processing process.

[0008] As an optimization, in the aforementioned pressure parameter optimization method during micro-ball polishing based on multi-source data fusion, the autoencoder includes multiple neural network hidden layers, and the calculation of each layer is as follows: h = σ(Wx+b); wherein x is the input data, W is the encoding weight matrix, b is the encoding bias matrix, σ is the activation function, and h is the hidden layer output matrix; the decoding formula of the autoencoder is: x′ = σ'(W′x+b′), wherein x' is the reconstructed output, W' is the decoding weight matrix, b' is the decoding bias matrix, and σ' is the activation function; in the training step b, the specific process of autoencoder training is as follows: first, initialize the weight matrices W and W' of the encoder and decoder and the bias matrices b and b'; then, input data x to calculate the hidden layer h, and then calculate the reconstructed output x' through the decoding formula; finally, use the mean square error as the loss function: The autoencoder is trained until the error between the input data x and the reconstructed output x' is minimized. Autoencoders can be used for data fusion and dimensionality reduction, which can optimize the training of prediction models and improve their prediction performance and stability.

[0009] Furthermore, in the training step b, the specific process of regression prediction training is as follows: first, initialize the weight matrix and bias vector of the BP neural network (to prevent all neurons from learning the same features and prevent gradient explosion from causing unstable training); then, calculate the output of the hidden layer and the output layer; taking the first layer as an example, the output of the hidden layer is: 1 =W 1 x+b 1 , a 1 =f(z 1 ), where x is the input feature vector, W1 is the weight matrix of the first hidden layer, f is the activation function, a 1 is the activation output of the first hidden layer, b 1 is the bias vector of the first hidden layer; the output of the output layer is: y'=W o a L +b o , where W o is the weight matrix of the output layer, b o is the bias vector of the output layer, a L is the activation output of the last hidden layer, and y′ is the pressure prediction value; finally, the weight of the BP neural network is adjusted by back-propagation to calculate the error gradient to optimize the prediction ability of the prediction model. The BP neural network is used for feature extraction in the present invention, which can effectively extract features from the autoencoder and map them to pressure parameters to achieve accurate regression prediction. Furthermore, the present invention adopts a random initialization method to facilitate breaking the symmetry and avoid the initial value being too large or too small.

[0010] Furthermore, the specific adjustment process of the weight of the BP neural network is as follows: First, the error of the output layer and the hidden layer is calculated; the error of the output layer is: δ o =y′-y, where y is the actual pressure value; taking the lth layer as an example, the error of the hidden layer is: δ l =(W l+1 ) T δ (l+1) ⊙f′(z l ), where f′ is the derivative of the activation function and ⊙ represents element-by-element multiplication; then, the partial derivative is calculated based on the gradient of the error function with respect to the weights of each layer in the BP neural network: Finally, according to the update formula: Update weights and biases, where η is the learning rate. The learning rate η is usually selected to a suitable value to ensure that the neural network can converge quickly without oscillation.

[0011] Furthermore, during the regression prediction training process, GA is used to tune the hyperparameters of the BP neural network. GA (genetic algorithm) can automatically adjust hyperparameters and perform global searches in complex high-dimensional hyperparameter spaces, avoiding local optimality, thereby improving the efficiency and robustness of the prediction model and making the prediction model perform better in practical applications.

[0012] As an optimization, in the aforementioned method for optimizing pressure parameters in the micro-ball polishing process based on multi-source data fusion, in step one, the main frequency domain features of the vibration signal data are extracted by fast Fourier transform, specifically: first use a low-pass filter to obtain the signal in the required frequency domain range, and then reduce spectrum leakage through signal truncation and period extension to extract more accurate frequency domain features, and on this basis, use a window function to reduce the impact of boundary effects on frequency domain feature extraction. The present invention uses a fast Fourier transform algorithm, the core function of which is to efficiently convert time domain signals to frequency domain, which is convenient for frequency analysis, filtering and signal processing; it significantly improves the efficiency of processing large-scale data by reducing computational complexity.

[0013] Furthermore, in step 1, a Butterworth low-pass filter is used to remove high-frequency noise and low-frequency drift in the signal, and the main frequency components of the signal are retained. The transfer function of the Butterworth low-pass filter is: Where n is the order, f c is the cut-off frequency, ω C =2πf c is the angular frequency of the cutoff frequency; the truncated signal is expressed as: Where x[n] is a given discrete signal, n0 is the sample point index where truncation starts, and n1 is the sample point index where truncation ends. The periodic extension signal is expressed as: extended [n] = x[mmod N], where n mod N is the modulo operation, which is the signal length x. cut [n]; the mathematical expression of the window function is: Where ω[n] is the value of the window function, n is the sample index point of the window function, N is the number of samples of the window function, and α and β are used to balance the main lobe width and side lobe attenuation; the calculation formula of the fast Fourier transform is: X[k] = FFT(x extended [n]), where X[k] is the kth frequency component of the frequency domain signal.

[0014] As an optimization, in the aforementioned pressure parameter optimization method in the micro-ball grinding and polishing process based on multi-source data fusion, a deterministic polishing device is used to grind and polish the micro-balls; the deterministic polishing device includes a workbench and a polishing tank arranged on the workbench; a polishing disc is arranged in the polishing tank, and a polishing head is arranged above the polishing tank; the polishing disc is driven to rotate by a servo motor; the polishing head is connected to a DD motor and driven to rotate by the DD motor; the DD motor is connected to a cylinder and driven to move up and down by the cylinder; a pressure sensor 5 is arranged between the DD motor and the cylinder; during the grinding and polishing process, the micro-balls to be polished are installed on the polishing disc, and polishing liquid is filled into the polishing tank so that the micro-balls are completely immersed in the polishing liquid; the polishing head is then driven downward by the cylinder until the polishing head is pressed on the micro-ball with a certain pressure; then, the servo motor is started to drive the polishing disc to rotate, and the DD motor is started to drive the polishing head to rotate at the same time, so as to grind and polish the micro-balls. The micro-ball grinding and polishing experiment is carried out by using the polishing device with the above structure, which is easy to implement and easy to obtain various polishing process parameters. In order to ensure the validity and accuracy of the vibration signal, in the present application, the collected vibration signal includes the vibration signal of the polishing plate and the vibration signal of the polishing head.

[0015] Since the polishing disc and the polishing head need to rotate, in the present application, a signal slip ring is arranged on the polishing disc and the polishing head, and an acceleration sensor is arranged on the signal slip ring, so that the acceleration sensor is connected to an external signal collector through the signal slip ring, and is used to divide the collected vibration signal into three directions of X, Y and Z axes and transmit it to the signal collector. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of the optimization method of the present application;

[0017] Figure 2 is a schematic structural diagram of a polishing device in an embodiment of the present application;

[0018] The markings in the attached drawings are: 1-polishing disc; 2-polishing groove; 3-polishing head; 4-DD motor; 5-pressure sensor; 6-cylinder; 7-driving shaft; 8-workbench. DETAILED DESCRIPTION

[0019] The present application is further described below in conjunction with the accompanying drawings and embodiments, but they are not intended to limit the present application.

[0020] In the process of micro-ball grinding and polishing, in view of the problem that traditional pressure control methods rely on mechanical systems and static measurements and are difficult to achieve real-time adjustment, the present invention provides a method for optimizing pressure parameters in the process of micro-ball grinding and polishing based on multi-source data fusion. The method collects multiple data sources such as vibration signals and non-vibration signals (including temperature, rotation speed, torque, etc.) in the process of micro-ball grinding and polishing, and inputs them into the DAE-MMR prediction model to predict the optimal pressure value under the current processing state. The control system then adjusts the pressure to achieve accurate optimization of pressure parameters in the process of micro-ball grinding and polishing, thereby improving the micro-ball processing accuracy and processing efficiency. The DAE-MMR prediction model is constructed based on an autoencoder and a BP neural network, and is obtained through historical data training of multi-source data collected by multiple sensors.

[0021] Example:

[0022] In this embodiment, a deterministic polishing device is used to grind and polish the microspheres. Figure 2 The deterministic polishing device includes a workbench 8 and a polishing tank 2 arranged on the workbench 8; a polishing disc 1 is arranged in the polishing tank 2, and a polishing head 3 is arranged above the polishing tank 2; the polishing disc 1 is driven to rotate by a servo motor; the polishing head 3 is connected to a DD motor 4 and can be driven to rotate by the DD motor 4; the DD motor 4 is connected to a driving shaft 7 of a cylinder 6 and is driven to move up and down by the cylinder 6; a pressure sensor 5 is arranged between the DD motor 4 and the cylinder 6. During the grinding and polishing process, the microsphere to be polished is installed on the polishing disc 1, and the polishing liquid is filled in the polishing tank 2 so that the microsphere is completely immersed in the polishing liquid; then the polishing head 3 is driven downward by the cylinder 6 until it is pressed on the microsphere with a certain pressure; then, the servo motor is started to drive the polishing disc 1 to rotate, and the DD motor 4 is started to drive the polishing head 3 to rotate, so as to grind and polish the microsphere. During the polishing process, the polishing liquid is added every 20 minutes, and the polishing liquid is used to cool down and take away the waste generated.

[0023] See also Figure 2 The pressure parameter optimization method in the micro-ball polishing process based on multi-source data fusion specifically includes the following steps.

[0024] Step 1: First, use multiple sensors to collect vibration signals and non-vibration signals during the micro-ball grinding and polishing process, where the non-vibration signals include temperature, rotation speed, and torque (specifically, the rotation speed of the polishing disc 1 and the polishing head 3, and the torque of the motor output shaft); then process the collected vibration signals and extract the main features to distinguish the differences in vibration signals at different processing stages; then, integrate the extracted vibration signal features with the non-vibration signals to ensure consistent data dimensions.

[0025] In order to ensure the validity and accuracy of the vibration signal, the vibration signals of the polishing disc 1 and the polishing head 3 are collected respectively in this embodiment; wherein, a signal slip ring is provided on the polishing disc 1 and the polishing head 3, and a three-axis acceleration sensor is provided on the signal slip ring, so that it can be connected to an external signal acquisition instrument through the signal slip ring, and is used to divide the collected vibration signal into three directions of X, Y, and Z axes and transmit it to the signal acquisition instrument, and then the signal acquisition instrument performs data processing. In order to collect temperature parameters, a pt100 platinum thermal resistor is embedded in the polishing disc 1, and the temperature of the grinding interface is measured during micro-ball polishing.

[0026] In this embodiment, the main frequency domain features of the vibration signal data are extracted by fast Fourier transform (i.e., the main frequency domain features in the X, Y, and Z axis vibration signals are extracted, and the vibration signals of each axis are Fourier transformed according to the time period to obtain the frequency amplitude distribution of each time period, and then the frequency features of each time period are extracted); first, a low-pass filter is used to obtain the signal in the required frequency domain range, and then the signal is truncated and the cycle is extended to reduce the spectrum leakage to extract more accurate frequency domain features, and on this basis, the window function is used to reduce the influence of boundary effects on the extraction of frequency domain features. The details are as follows:

[0027] First, a Butterworth low-pass filter is used to remove high-frequency noise and low-frequency drift in the signal and retain the main frequency components of the signal. The transfer function of the Butterworth low-pass filter is: Where n is the order, f c is the cut-off frequency, ω C =2πf c is the angular frequency of the cutoff frequency.

[0028] Next, in order to further process the filtered vibration signal, reduce spectrum leakage before Fourier transform, and improve the accuracy of frequency domain features, the present embodiment adopts the signal truncation and cycle extension method. For a given discrete signal x[n], the truncation operation selects the data of sample points n0 to n1; the truncated signal is expressed as: Among them, n0 is the sample point index where truncation starts, and n1 is the sample point index where truncation ends; then given the truncated signal x cut [n], its period extension signal is expressed as: extended [n] = x[n mod N], where n mod N is the modulo operation, which is the signal length x. cut [n] is repeated periodically. In order to further reduce the spectrum leakage in Fourier transform, the Hamming window is used to process the phase signal in this embodiment to make the edge of the signal smoother, thereby reducing the spectrum leakage; the mathematical expression of the Hamming window is: Among them, ω[n] is the value of the window function, n is the sample index point of the window function, N is the number of samples of the window function (the total length of the window function), α and β are used to balance the main lobe width and side lobe attenuation, and can be modified according to actual needs.

[0029] Finally, in order to further process the signal and extract frequency features, the fast Fourier transform (FFT) algorithm is used in this embodiment to efficiently convert the time domain signal to the frequency domain for frequency analysis, filtering and signal processing; FFT can significantly improve the efficiency of large-scale data processing by reducing computational complexity.

[0030] The signal data x obtained after the above cycle is extended extended [n] as the input signal, the frequency domain representation obtained is: X[k] = FFT(x extended [n]); FFT calculation is based on the discrete Fourier transform (DFT) formula: Where X[k] is the kth frequency component of the frequency domain signal, x extended [n] is the time domain signal after window function and period extension, is a complex exponential function representing the sine and cosine components in the frequency domain.

[0031] Step 2: Input the integrated data into the DAE-MMR prediction model to predict the optimal pressure value under the current processing state;

[0032] The prediction model is constructed based on an autoencoder and a BP neural network, and is trained through historical data of multi-source data collected by multiple sensors; the specific training process is as follows: a. The vibration signals and non-vibration signals collected by multiple sensors are divided into a rough polishing stage and a fine polishing stage according to time periods, and further divided into a training set and a test set;

[0033] b. Use the training set data to train the autoencoder, extract the encoding part of the autoencoder, and then perform regression prediction training through the BP neural network; the autoencoder includes multiple neural network hidden layers, and the calculation of each layer is as follows: h = σ (Wx + b); where x is the input data, W is the encoding weight matrix, b is the encoding bias matrix, σ is the activation function, and h is the hidden layer output matrix; the decoding formula of the autoencoder is: x′ = σ' (W′x + b′), where x' is the reconstructed output, W' is the decoding weight matrix, b' is the decoding bias matrix, and σ' is the activation function; specifically, the following steps are included:

[0034] S1, first perform autoencoder training: First, initialize the weight matrices W and W' and the bias matrices b and b' of the encoder and decoder; then, input data x to calculate the hidden layer h, and then calculate the reconstructed output x' through the decoding formula; finally, use the mean square error as the loss function: The autoencoder is trained until the error between the input data x and the reconstructed output x' is minimized.

[0035] S2, then perform regression prediction training: In order to prevent all neurons from learning the same features and prevent gradient explosion from causing unstable training, it is necessary to initialize the weight matrix and bias vector of each layer of the BP neural network through the initialization function (in this embodiment, the random initialization method is used to break the symmetry and avoid the initial value being too large or too small); then, calculate the output of the hidden layer and the output layer; taking the first layer as an example, the output of the hidden layer is: z 1 =W 1 x+b 1 , a 1 =f(z 1 ), where x is the input feature vector, W 1 is the weight matrix of the first hidden layer, f is the activation function, a 1 is the activation output of the first hidden layer, b 1 is the bias vector of the first hidden layer; the output of the output layer is: y'=W o a L +b o , where W o is the weight matrix of the output layer, b o is the bias vector of the output layer, a L is the activation output of the last hidden layer, and y′ is the predicted pressure value;

[0036] S3, adjust the weight of BP neural network by back propagation to calculate the error gradient to optimize the prediction ability of the prediction model: First, calculate the error between the output layer and the hidden layer; the error of the output layer is: δ o =y′-y, where y is the actual pressure value; taking the lth layer as an example, the error of the hidden layer is: δ l =(W l+1 ) T δ (l+1) ⊙f′(z l ), where f′ is the derivative of the activation function and ⊙ represents element-by-element multiplication; then, the partial derivative is calculated based on the gradient of the error function with respect to the weights of each layer in the BP neural network: Finally, according to the update formula: Update weights and biases, where η is the learning rate;

[0037] S4, repeat steps S1-S3 until the loss function converges or reaches a predetermined number of training times.

[0038] The BP neural network is used to fit the features extracted by the autoencoder with the final regulated pressure parameters, and plays a key role in integrating features into the final prediction. In this embodiment, GA (genetic algorithm) is used to tune the hyperparameters of the BP (back propagation) neural network. GA (genetic algorithm) can perform global search in complex high-dimensional hyperparameter space by automatically adjusting hyperparameters, avoiding local optimality, thereby improving the efficiency and robustness of the prediction model, making the prediction model perform better in practical applications.

[0039] The specific calculation process is as follows:

[0040] I, initialize the population, the encoding of each individual is as follows: x = (a, L, N1, N2, ..., N L ), generate P individuals, each of which consists of random values ​​of the above hyperparameters, such as a∈[a min ,a max ],L∈[L min ,L max ], each N i ∈[N min ,N max ];

[0041] II, defined by training the BP neural network with a fitness function and evaluating its performance on the validation set, mainly looking at the negative value of the loss function, Fitness(x) = -Validation Loss;

[0042] III. The selection operation uses the roulette wheel selection method to calculate the individual selection probability:

[0043] IV, the crossover operation uses a single-point crossover method to generate a new individual by selecting the crossover point k:

[0044] V, the mutation operation applies mutation to each hyperparameter with a mutation probability of P m : Among them, Δα, ΔL and ΔN i is the random perturbation value;

[0045] VI, the replacement operation uses a full replacement strategy to completely replace individuals with low fitness with the newly generated individuals (or uses a partial replacement strategy to only replace a portion of individuals with the lowest fitness);

[0046] VII. The algorithm runs until it reaches the preset maximum number of iterations T or the fitness threshold Fitness threshold Through the above steps and formulas, the genetic algorithm can effectively optimize the hyperparameters of the BP neural network and improve its performance.

[0047] c. Input the data in the test set into the pre-trained prediction model and output the prediction results, then use the formula Calculate the mean absolute error MAE to evaluate the performance of the prediction model; where y i is the true pressure value, y′ i To predict the pressure value, N represents the number of samples; if the MAE is not greater than the set threshold, the training is completed, otherwise, repeat step b.

[0048] Step three, input the predicted pressure value into the control system, and the control system adjusts the pressure during the grinding and polishing process to achieve accurate optimization of the pressure parameters.

[0049] In this embodiment, the DAE-MMR prediction model is integrated into the control system, the optimal value under the current processing state is predicted online, and the actual output value of the cylinder is adjusted by controlling the solenoid valve to realize the automatic regulation of the pressure parameters during the processing. At the same time, the control system stores the obtained new state parameters and process parameters (i.e., the detected vibration signal, non-vibration signal and predicted pressure parameter); thus, after the prediction model has been used for a period of time, the vibration signal, non-vibration signal and predicted pressure parameter within the time period can be input into the prediction model, and the prediction model can be trained again to obtain a new prediction model, so as to realize the regular updating and optimization of the prediction model, thereby continuously improving the accuracy of the prediction model and making it more adaptable to changes in the processing process.

[0050] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, a person skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some or all of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing pressure parameters in the micro-ball polishing process based on multi-source data fusion, characterized in that: The specific steps include: Step 1: First, multiple sensors are used to collect vibration signals and non-vibration signals during micro-ball grinding and polishing. Then, the collected vibration signals are processed to extract the main features to distinguish the differences in vibration signals at different processing stages. Then, the extracted vibration signal features are integrated with the non-vibration signals to ensure the consistency of data dimensions. Step 2: Input the integrated data into the DAE-MMR prediction model to predict the optimal pressure value under the current processing state; the prediction model is constructed based on an autoencoder and a BP neural network, and is trained with historical data of multi-source data collected by multiple sensors; The specific process of training is as follows: a. The vibration signals and non-vibration signals collected by multiple sensors are divided into rough polishing stage and fine polishing stage according to the time period, and further divided into training set and test set; b. The training set data is used to train the autoencoder, and the encoding part of the autoencoder is extracted, and the BP neural network is used for regression prediction training until the loss function converges or the predetermined number of training times is reached; c. Input the data in the test set into the trained prediction model and output the prediction results, then use the formula Calculate the mean absolute error MAE to evaluate the performance of the prediction model; where y i is the true pressure value, y′ i To predict the pressure value, N represents the number of samples; if MAE is not greater than the set threshold, the training is completed, otherwise, repeat step b; Step three, input the predicted pressure value into the control system, and the control system adjusts the pressure during the grinding and polishing process to achieve accurate optimization of the pressure parameters.

2. The method for optimizing pressure parameters in the micro-ball polishing process based on multi-source data fusion according to claim 1, characterized in that: The autoencoder includes multiple neural network hidden layers, and the calculation of each layer is as follows: h = σ (Wx + b); where x is the input data, W is the encoding weight matrix, b is the encoding bias matrix, σ is the activation function, and h is the hidden layer output matrix; the decoding formula of the autoencoder is: x′ = σ' (W′x + b′), where x' is the reconstructed output, W' is the decoding weight matrix, b' is the decoding bias matrix, and σ' is the activation function; in the training step b, the specific process of the autoencoder training is as follows: first, initialize the weight matrices W and W' of the encoder and decoder and the bias matrices b and b'; then, input data x to calculate the hidden layer h, and then calculate the reconstructed output x' through the decoding formula; finally, use the mean square error as the loss function: The autoencoder is trained until the error between the input data x and the reconstructed output x' is minimized.

3. The method for optimizing pressure parameters in the micro-ball polishing process based on multi-source data fusion according to claim 2, characterized in that: In the training step b, the specific process of regression prediction training is as follows: first, initialize the weight matrix and bias vector of the BP neural network; then, calculate the output of the hidden layer and the output layer; taking the first layer as an example, the output of the hidden layer is: 1 =W 1 x+b 1 , a 1 =f(z 1 ), where x is the input feature vector, W 1 is the weight matrix of the first hidden layer, f is the activation function, a 1 is the activation output of the first hidden layer, b 1 is the bias vector of the first hidden layer; the output of the output layer is: y'=W o a L +b o , where W o is the weight matrix of the output layer, b o is the bias vector of the output layer, a L is the activation output of the last hidden layer, and y′ is the predicted pressure value; finally, the weight of the BP neural network is adjusted by calculating the error gradient through back propagation to optimize the predictive ability of the prediction model.

4. The method for optimizing pressure parameters in the micro-ball polishing process based on multi-source data fusion according to claim 3, characterized in that: The specific adjustment process of the weight of the BP neural network is as follows: First, the error of the output layer and the hidden layer is calculated; the error of the output layer is: δ o =y′-y, where y is the actual pressure value; taking the lth layer as an example, the error of the hidden layer is: δ l =(W l+1 ) T δ (l+1) ⊙f′(z l ), where f' is the derivative of the activation function and ⊙ represents element-by-element multiplication; then, the partial derivative is calculated based on the gradient of the error function with respect to the weights of each layer in the BP neural network: Finally, according to the update formula: Update weights and biases, where η is the learning rate.

5. The method for optimizing pressure parameters in the micro-ball polishing process based on multi-source data fusion according to claim 4, characterized in that: During the regression prediction training process, GA is used to tune the hyperparameters of the BP neural network.

6. The method for optimizing pressure parameters in the micro-ball polishing process based on multi-source data fusion according to claim 1, characterized in that: In the step 1, the main frequency domain features of the vibration signal data are extracted by fast Fourier transform, specifically: first use a low-pass filter to obtain the signal in the required frequency domain range, then reduce spectrum leakage through signal truncation and period extension to extract more accurate frequency domain features, and on this basis, use a window function to reduce the influence of boundary effects on frequency domain feature extraction.

7. The method for optimizing pressure parameters in the micro-ball polishing process based on multi-source data fusion according to claim 6, characterized in that: In the step 1, a Butterworth low-pass filter is used to remove high-frequency noise and low-frequency drift in the signal, and the main frequency components of the signal are retained. The transfer function of the Butterworth low-pass filter is: Where n is the order, f c is the cut-off frequency, ω C =2πf c is the angular frequency of the cutoff frequency; the truncated signal is expressed as: Where x[n] is a given discrete signal, n0 is the sample point index where truncation starts, and n1 is the sample point index where truncation ends. The periodic extension signal is expressed as: extended [n] = x[n mod N], where nmod N is a modulo operation, which is the signal length x. cut [n]; the mathematical expression of the window function is: Where ω[n] is the value of the window function, n is the sample index point of the window function, N is the number of samples of the window function, and α and β are used to balance the main lobe width and side lobe attenuation; the calculation formula of the fast Fourier transform is: X[k] = FFT(x extended [n]), where X[k] is the kth frequency component of the frequency domain signal.

8. The method for optimizing pressure parameters in the micro-ball polishing process based on multi-source data fusion according to claim 1, characterized in that: The method uses a deterministic polishing device to grind and polish the microspheres; the deterministic polishing device comprises a workbench (8) and a polishing groove (2) arranged on the workbench (8); a polishing disc (1) is arranged in the polishing groove (2), and a polishing head (3) is arranged above the polishing groove (2); the polishing disc (1) is driven to rotate by a servo motor; the polishing head (3) is connected to a DD motor (4) and driven to rotate by the DD motor (4); the DD motor (4) is connected to a cylinder (6) and driven up and down by the cylinder (6) The DD motor (4) and the cylinder (6) are arranged to move; a pressure sensor (5) is arranged between the DD motor (4) and the cylinder (6); during the grinding and polishing process, the micro-balls to be polished are mounted on the polishing disc (1), and polishing liquid is added into the polishing groove (2) so that the micro-balls are completely immersed in the polishing liquid; the polishing head (3) is then driven downward by the cylinder (6) until the polishing head (3) is pressed on the micro-balls with a certain pressure; then, the servo motor is started to drive the polishing disc (1) to rotate, and the DD motor (4) is started to drive the polishing head (3) to rotate, so as to grind and polish the micro-balls.

9. The method for optimizing pressure parameters in the micro-ball polishing process based on multi-source data fusion according to claim 8, characterized in that: In the step 1, the vibration signals collected include the vibration signals of the polishing disc (1) and the vibration signals of the polishing head (3).

10. The method for optimizing pressure parameters in the micro-ball polishing process based on multi-source data fusion according to claim 9, characterized in that: The polishing disc (1) and the polishing head (3) are provided with signal slip rings; the signal slip rings are provided with acceleration sensors for dividing the collected vibration signals into three directions of X, Y and Z axes and transmitting them to the signal acquisition instrument.

Images