A quality prediction method, device and medium for multi-stage manufacturing systems

Abstract

The present invention relates to a quality prediction method, device, and medium for multi-stage manufacturing systems, comprising the following steps: obtaining initial quality index values ​​of raw materials and equipment status parameters for each manufacturing stage, preprocessing and splicing them through a broadcast mechanism, and then inputting a trained quality prediction model for the multi-stage manufacturing system to obtain quality prediction results for each manufacturing stage; the model includes a full-quantity attention module and a feedforward neural network, as well as an encoder and decoder constructed based on a bidirectional long short-term memory network, the encoder is used to generate an output vector for each manufacturing stage based on input data; the full-quantity attention module is used to calculate the attention weight of the output vector based on the decoder's hidden vector; the decoder is used to decode the weighted output vector, and the decoding result is output as a quality sequence through the feedforward neural network. Compared with the existing technology, the present invention improves the accuracy of quality prediction in complex multi-stage manufacturing processes.

Description

Technical Field

[0001] The present invention belongs to the technical field of industrial production quality control, and in particular relates to a quality prediction method, device and medium for a multi-stage manufacturing system. Background Art

[0002] Multistage manufacturing systems (MMS) are common in modern production processes. They consist of multiple, sequential production stages, with products undergoing processing or assembly in sequence until the entire manufacturing process is complete. The production of complex products, such as aircraft siding and automotive assembly, are typical examples of MMS. These products often experience varying degrees of quality deviation during stages such as unit assembly and system assembly. These deviations accumulate during subsequent processing, collectively impacting the quality of the final product. In MMS, factors such as the condition of equipment in intermediate processes and the quality of initial raw materials significantly influence final product quality. By predicting quality in advance, manufacturers can adjust production plans and optimize the manufacturing process. Therefore, studying the quality transfer mechanisms and prediction methods within MMS is of great significance.

[0003] Chinese invention patent publication number CN118552092A proposes a multi-process quality prediction method based on an attention mechanism. Using a training set, a feature encoding network based on the attention mechanism is trained for multi-process quality prediction, resulting in a quality prediction model. This model captures the mapping between process parameters and quality indicators, providing support for intelligent optimization of process parameters and demonstrating strong practicality. Chinese patent application publication number CN116757545A proposes a quality prediction method for multi-stage manufacturing systems based on multi-task deep learning. This method constructs a multi-scale convolutional network with a control gate network based on feature extraction of the influence of each stage. While considering the influence of each stage, it also outputs prediction results for multiple quality indicators in parallel. This method effectively transfers the influence of each stage, and the parallel output of multiple quality indicators is highly accurate. However, these methods ignore the cumulative and interactive impact of different stages on final product quality, resulting in a waste of resources and time. Furthermore, most quality prediction models require input of all process deviations, making it difficult to achieve the accuracy and generalization performance of parameter estimation in complex production scenarios. Therefore, a redesigned quality prediction method for multi-stage manufacturing systems is needed to further improve the accuracy of quality prediction in complex multi-stage manufacturing processes. Summary of the Invention

[0004] The purpose of the present invention is to overcome the defects of the above-mentioned existing technologies and provide a quality prediction method, equipment and medium for multi-stage manufacturing systems with good generalization performance, taking into account the cumulative and interactive effects of different stages on the quality of the final product, and further improving the accuracy of quality prediction in complex multi-stage manufacturing processes.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] The present invention provides a quality prediction method for a multi-stage manufacturing system, comprising the following steps:

[0007] Obtain the initial quality index values ​​of raw materials and equipment status parameters at each manufacturing stage, perform preprocessing, and then splice them through a broadcast mechanism. Then, input them into the trained quality prediction model for multi-stage manufacturing systems to obtain the quality prediction results for each manufacturing stage.

[0008] Among them, the quality prediction model for multi-stage manufacturing systems includes an encoder, a full attention module, a decoder and a feedforward neural network connected in sequence. The encoder is constructed based on a bidirectional long short-term memory network, and is used to generate an output vector for each manufacturing stage based on input data; the full attention module is used to calculate the attention weight of the output vector of each manufacturing stage based on the hidden vector of the decoder, and input the weighted output vector into the decoder; the decoder is constructed based on a bidirectional long short-term memory network, and is used to decode the weighted output vector. The decoding results are integrated through the feedforward neural network and output as a quality prediction sequence. The quality prediction results of each manufacturing stage are obtained based on the quality prediction sequence.

[0009] Furthermore, the preprocessing includes feature dimensionality reduction and data normalization.

[0010] Furthermore, feature dimensionality reduction is performed through principal component analysis.

[0011] Furthermore, the broadcast mechanism is specifically as follows:

[0012]

[0013] Concat means concatenating the input data in the second to last dimension, n is the total number of manufacturing stages, x is the number of j is the equipment status parameter of the jth manufacturing stage, x j，m is the mth equipment status parameter in the jth manufacturing stage, n x，j represents the total amount of equipment state parameters in the jth manufacturing stage, and C is the common input.

[0014] Furthermore, the attention weight α of the output vector of the i-th manufacturing stage is iThe calculation formula is as follows:

[0015]

[0016] in, represents the unnormalized attention weight, n is the total number of manufacturing stages;

[0017] Calculate the attention weight α i and the encoder's i-th output vector The dot product of Send to the decoder:

[0018]

[0019] Furthermore, the unnormalized attention weights Calculated using the following formula:

[0020]

[0021] Among them, v is the parameter vector, v T is the transpose of the vector, w is the weight matrix, represents the jth hidden vector of the decoder, Represents the encoder's i-th output vector.

[0022] Furthermore, the specific expression of the quality sequence output by the feedforward neural network is as follows:

[0023] y=W2(σ(W1x+b1)+b2)

[0024] Where y is the quality sequence, x is the multidimensional output of the decoder, σ is the activation function, W1 and W2 are two linear transformation layers, and b1 and b2 are the bias parameters of the linear transformation layers respectively.

[0025] Furthermore, the activation function σ is ReLU.

[0026] The present invention also provides an electronic device, comprising a memory, a processor, and a program stored in the memory, wherein the processor implements the above method when executing the program.

[0027] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the program implements the above method when executed by a processor.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] 1. The present invention proposes a quality prediction method for a multi-stage manufacturing system. First, the initial quality index values ​​of raw materials and equipment status parameters of each manufacturing stage are obtained, pre-processed and spliced ​​through a broadcast mechanism, and then the trained quality prediction model for the multi-stage manufacturing system is input to obtain the quality prediction results of each manufacturing stage; the sequence-to-sequence quality prediction model for the multi-stage manufacturing system specifically includes an encoder, a full-quantity attention module, a decoder and a feedforward neural network connected in sequence, wherein the encoder is constructed based on a bidirectional long short-term memory network, which can effectively process the dependencies between features with a large number of input intervals, and the encoder generates an output vector for each manufacturing stage according to the input data; the full-quantity attention module is used to calculate the attention weight of the output vector of each manufacturing stage according to the hidden vector of the decoder, and input the weighted output vector into the decoder; the decoder is constructed based on a bidirectional long short-term memory network, which is used to decode the weighted output vector, and the decoding results are integrated through a feedforward neural network and output as a quality prediction sequence, based on which the quality prediction results of each manufacturing stage can be obtained; the above method takes into account the cumulative and interactive effects of different stages on product quality, and can meet the accuracy and generalization performance of product quality estimation in complex production scenarios.

[0030] 2. The present invention uses a broadcast mechanism to combine the initial quality index values ​​of raw materials and the equipment status parameters of each manufacturing stage. The composition takes into account the performance and initial stage of the raw materials, and can cover complex situations such as returning workpieces and restarting processing, thereby improving the practicality of the model.

[0031] 3. The present invention dynamically pays attention to the weight of each stage through the full attention mechanism, thereby improving the prediction accuracy, realizing the weight control of the impact of key stages on the final quality output, and effectively improving the accuracy of quality estimation in complex multi-stage manufacturing processes. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 Schematic diagram of the process of the present invention;

[0033] Figure 2 Schematic diagram of the quality prediction model for multi-stage manufacturing systems;

[0034] Figure 3 This is a loss convergence diagram of the multi-stage prediction model obtained from the simulation experiment of the embodiment;

[0035] Figure 4 2 is a comparison chart of the prediction accuracy indicators of various methods in the simulation experiment of the embodiment. DETAILED DESCRIPTION

[0036] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0037] Example:

[0038] This embodiment provides a quality prediction method for a multi-stage manufacturing system. Figure 1 As shown, the following steps are included:

[0039] S1. Obtain the initial quality indicators of raw materials in the historical processing stage and the equipment status parameters of each manufacturing stage, pre-process them, and then splice them through the broadcast mechanism to construct a training set.

[0040] The training set contains input variables (i.e., influencing factors) and output variables (i.e., quality indicators) at different stages. The input variable x is defined as {x1, ..., x J}, output variable index y={y1,...,y I},in is the input variable of stage j, x j，m is the mth equipment status parameter in the jth manufacturing stage, n x，j represents the total amount of equipment status parameters at the jth manufacturing stage, y i represents the quality indicator output of the i-th stage. Taking into account the multiple impacts of multiple stages, this embodiment designs an encoder-decoder structure based on BiLSTM and designs an attention mechanism based on state weights to address the impact of different stages on the output variables.

[0041] Preprocessing includes feature dimensionality reduction and data normalization based on data distribution. Specifically, PCA (Principal Component Analysis) is used for dimensionality reduction to reduce redundant features, avoid overfitting, and improve the model's performance on new data. Normalization is performed on the reduced data to eliminate the impact of different feature dimensions on the prediction results. The features of each stage in a multi-stage manufacturing system are aligned, and the data of each stage is combined with the common input variables through a broadcast mechanism:

[0042]

[0043] Concat represents concatenating the input data along the penultimate dimension, n represents the total number of manufacturing stages, and C represents the common input.

[0044] S2. Build and train a quality prediction model (Seq2Seq-FA) for multi-stage manufacturing systems.

[0045] like Figure 2As shown in the figure, the basic structure of the quality prediction model for multi-stage manufacturing systems consists of an encoder and a decoder. The encoder uses a bidirectional long short-term memory neural network to capture inter-sequence features, and then outputs a hidden vector through a feedforward neural network. A full attention module is added between the encoder and decoder to capture the correlation between stages, allocate more attention to stage features that are more important for subsequent predictions, and enhance the model's focus on key features. The encoder output is weighted and summed with the attention mechanism, and then sent to the decoder for decoding into a quality output sequence. Finally, the bidirectional long short-term memory neural network in the decoder is input to restore the hidden vector to the quality indicator output of each stage, and the feedforward neural network increases the model's expressiveness. The detailed description of each part of the model is as follows:

[0046] (1) Encoder

[0047] The encoder BiLSTM has n time steps, each time step corresponds to a production stage in the model, and the latent vector of the jth stage can be expressed as h j , the output vector is y j , j = 1, 2, ..., n, latent vector h j Can be used to assist the next stage hidden vector h j+1 and the output vector y j+1 As the time step increases, j can be as large as n, that is, the latent vector of the last time step is h n , the output vector is y n .

[0048] The data spliced ​​by the broadcast mechanism is passed through multiple BiLSTM blocks to capture features, and the output sequence of the last BiLSTM is passed through the feedforward neural network module (FFN) to obtain the feature hidden state h n and the output sequence y n BiLSTM can effectively handle the dependencies between features with a large number of input intervals based on LSTM. Among them, the forget gate, input gate, and output gate play a vital role in updating the information state of the storage unit at a given time. The calculation formula of BiLSTM is as follows:

[0049] Calculate the forward LSTM formula:

[0050] u j =σ(W uj x j +W uh h j-1 +b u )

[0051] f j =σ(W fx x j +W fh hj-1 +b f )

[0052]

[0053] o j =σ(W ox x j +W oh h j-1 +b o )

[0054] h j =o j ⊙tanh(C j )

[0055] Among them, u j 、f j 、o j They are input gate, forget gate, and output gate respectively; C j represents the cell state of the forward LSTM at the jth time step, σ represents the sigmoid activation function; tanh represents the tanh activation function; W is the parameter matrix of the gate and storage unit; x j represents the representation of the j-th time step of the input sequence; b represents the bias, and ⊙ represents element-by-element multiplication.

[0056] Backward LSTM calculation formula:

[0057] u′ j =σ(W′ ux x j +W′ uh h′ j-1 +b′ u )

[0058] f′ j =σ(W′ fx x j +W′ fh h′ j-1 +b′ f )

[0059]

[0060] o′ j =σ(W′ ox x j +W′ oh h j-1 +b′ o )

[0061] h′ j =o′ j ⊙tanh(C′ j )

[0062] Similar to the forward LSTM, u′ j 、f′ j 、o′ j are the states of input gate, forget gate, and output gate respectively, C′ j is the cell variable of the jth time step of the backward LSTM; h j is the hidden state variable of the jth time step of the forward LSTM; h′ j is the hidden state variable of the jth time step of the backward LSTM, σ represents the sigmoid activation function; tanh represents the tanh activation function; W is the parameter matrix of the gate and storage unit; x j represents the representation of the j-th time step of the input sequence; b represents the bias, and ⊙ represents element-by-element multiplication.

[0063] (2) Full-Attention Module (FA)

[0064] The feature hidden state output by the decoder The output characteristics of the encoder The sequence attention score is obtained through a full-attention (FA) module

[0065] The attention mechanism is used to capture the correlation between stages, allocate more attention to the stage features that are more important for subsequent predictions, and enhance the model's attention to key features. The encoder output is weighted and summed with the attention mechanism and then sent to the decoder for decoding into a quality output sequence. i and Element-wise multiplication to obtain the hidden state with attention weights Attention weight α i is generated by the decoder hidden state and all encoder outputs. The relevant equation is as follows:

[0066]

[0067] Among them, v is the parameter vector, v T is the transpose of the vector, which is used to map the calculation result to an attention weight to generate the attention score. w is the weight matrix used to transform the hidden state and output of the decoder. The parameter Represents the mutual dependency between input and output, and uses the softmax function to ensure that the sum of all attention weights is 1. represents the i-th output vector of encoder e(encoder), Represents the jth hidden vector of the decoder d(decoder).

[0068] Then, calculate the dot product of the weight parameters and the encoder output Send to decoder:

[0069]

[0070] (3) Decoder

[0071] As the input of the first BiLSTM in the decoder, it passes through n BiLSTM modules at a time, and then through the FFN layer to integrate all features and finally output the quality prediction sequence. Specifically, the FFN layer consists of two linear transformation layers and an activation function. The activation function uses ReLU:

[0072] y=W2(σ(W1x+b1)+b2)

[0073] Wherein, y is the quality sequence, σ is the activation function. In this embodiment, ReLU is used, W1 and W2 are two linear transformation layers, and b1 and b2 are bias parameters of the linear transformation layers, respectively.

[0074] S3. Use the trained quality prediction model to predict the quality of the target data.

[0075] Compared with the prior art, the above method has the following beneficial effects:

[0076] 1. The cumulative and interactive effects of different stages on the quality of the final product are taken into account, ensuring the accuracy and generalization performance of parameter estimation in complex production scenarios.

[0077] 2. The performance and initial stage of raw materials are considered through the broadcast mechanism, and the process deviation is predicted using global state variables. This can cover complex situations such as returning workpieces to restart processing, thereby improving the practicality of the model.

[0078] 3. By establishing a sequence-to-sequence quality prediction model, we can effectively encode multi-level and multi-dimensional data, realize multi-stage quality prediction of different lengths, and effectively fit the quality transfer relationship between stages.

[0079] 4. By dynamically focusing on the weight mechanism of each stage through the full attention mechanism, the prediction accuracy is improved, and the weight control of the impact of key stages on the final quality output is achieved, effectively improving the accuracy of quality estimation in complex multi-stage manufacturing processes.

[0080] In order to prove the effectiveness of the above method, a verification experiment was carried out in this embodiment. The verification experiment was carried out on a computer with a CPU DELL R740Gold 5220R, a memory 32G 3200A, and a graphics card Nvidia TeslaV100 32G. The compiler used Pycharm and the compilation language used Python 3.11. The data set used in the verification experiment comes from the public data set https: / / www.kaggle.com / datasets / podsyp / production-quality / data. The sensor data of the discrete production process (RMDT) of multiple chambers of a roasting machine is used as historical data, with a total of 12,000 manufacturing data, which has sequential continuity in time. It is now divided into three stages according to time, where the initial state includes the initial original quality and the initial process. Each stage contains 17 sensor parameters P1, T x , ..., including pressure, humidity, water content and other characterization quantities. The quality index of stage i is S i-Quality , the data is randomly divided into 80% and 20% for training and testing, and the results are shown in Table 1.

[0081] Table 1 Multi-stage manufacturing raw dataset RMDT

[0082]

[0083] During data preprocessing, PCA was used for dimensionality reduction to remove variables with correlations greater than 0.9. This resulted in 15, 17, and 14 device state variables remaining for stages 1, 2, and 3, respectively. To align the sequence tensors when inputting into the Seq2Seq model, the vectors from different stages were padded with zeros to make them all 17-dimensional. Considering the impact of different initial distributions of different features on model performance, the remaining features were standardized by removing the mean and scaling to unit variance. The dataset was randomly split into three datasets: a training set (80%), a validation set (10%), and a test set (10%).

[0084] The characteristics of each stage in a multi-stage manufacturing system are aligned. The data from each stage is combined with common input variables to capture the common characteristics of all stages. In this verification experiment, there are two common input variables: initial pressure and temperature. Finally, the processed data is input into the model for training and validation.

[0085] This example uses eight popular regression algorithms for comparison, including state-of-the-art methods that can be reproduced on this dataset:

[0086] ① Polynomial regression (PR): Prediction is performed through a multidimensional combination of features, and the maximum degree of polynomial features is set to 2.

[0087] ② Support Vector Regression (SVR): One of the most robust prediction methods based on kernel learning and Vapnik-Chervonenkis theory (VC theory). The kernel type is the radial basis function (RBF), and the regularization parameter C = 1.0. The width of the ε-insensitive loss function in SVR is epsilon = 0.1.

[0088] ③ Lasso Regression: L1 regularization (Lasso penalty) is introduced to perform feature selection and prevent overfitting. The regularization strength alpha = 1.0.

[0089] ④ Random Forest (RF): An efficient gradient boosting method that uses squared error as the loss function, n_estimators = 100, max_depth = 5, random_state = 42.

[0090] ⑤ Extreme Gradient Boosting (Xgboost): The number of trees in the forest is assigned to 100, the maximum depth is 3, and the learning rate is 0.15.

[0091] ⑥K Nearest Neighbor (KNN): An instance-based learning algorithm that makes predictions by finding the nearest k data points and averaging their target values, where k is 5.

[0092] ⑦Long Short-Term Memory Network (LSTM): It can remember information in long time series and is suitable for processing data with long-term dependencies.

[0093] ⑧Transformer: A model architecture based on the self-attention mechanism. It does not rely on the sequential processing of sequences, but instead processes the input data through the self-attention mechanism task, which can capture global dependencies.

[0094] This example selects four indicators commonly used in regression tasks (mean square error RMSE, mean absolute error MAE, mean absolute percentage MAPE and determination coefficient R 2 ), among which, the smaller the RMSE, MAE, and MAPE, the better. 2 The bigger the better.

[0095] After multiple experiments, the experimental hyperparameters were adjusted, as shown in Table 2:

[0096] Table 2 Model hyperparameter settings

[0097] Batch size Learning rate Optimizer Number of training sessions Encoder hidden layer size 128 0.001 Adam 150 128

[0098] To avoid overfitting, early stopping was used and the MSE of the validation set was evaluated every 30 steps. The Adam optimizer was used to optimize the parameters in Seq2Seq-FA, where the training batch size batch_size was set to 128. Figure 3 As shown in Figure 3, the loss stabilizes after approximately 40 iterations, so the epoch is set to 150. The overall performance of the Seq2Seq-FA proposed in this example on the RMDT dataset, compared to the baseline method, is shown in Table 3. It can be observed that the proposed Seq2Seq-FA substantially outperforms the existing best methods, with the best indicators and methods indicated in bold.

[0099] Table 3 Overall performance on the RMDT dataset

[0100]

[0101]

[0102] Draw the above results into a bar graph, as shown in Figure 4 As shown, it can be clearly seen that the loss values ​​of Seq2Seq-FA in the three stages are lower than those of other methods. In addition, LSTM, Transformer and Seq2Seq-FA are methods based on sequence prediction. Simple LSTM is not as good as Seq2Seq with an encoder structure. This embodiment believes that the structure of Seq2Seq-FA takes into account the attention of each element in the sequence and the output under variable length. Transformer is an attention-based sequence-to-sequence prediction, which is more advantageous in long-distance sequences. The current sequence length of 3 is prone to overfitting. Some machine learning-based methods PR, SVR, KNN, and XGBoost also show good performance on the current dataset. These models extract patterns in the data through feature extraction, which provides a good supplement in flexibility and interpretability, but still lack a certain fitting ability in the latent vector transfer of the sequence. Therefore, the structural advantages of Seq2Seq-FA enable it to have higher robustness and accuracy in complex sequence prediction tasks.

[0103] If the above method is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0104] The above description of the embodiments is intended to facilitate understanding and use of the invention by those skilled in the art. It will be apparent that those skilled in the art can readily make various modifications to these embodiments and apply the general principles described herein to other embodiments without requiring inventive effort. Therefore, the present invention is not limited to the above-described embodiments. Improvements and modifications made by those skilled in the art based on the disclosure of the present invention, without departing from the scope of the present invention, should be within the scope of protection of the present invention.

Claims

1. A quality prediction method for a multi-stage manufacturing system, characterized in that: The following steps are involved: Obtain the initial quality index values ​​of raw materials and equipment status parameters at each manufacturing stage, perform preprocessing, and then splice them through a broadcast mechanism. Then, input them into the trained quality prediction model for multi-stage manufacturing systems to obtain the quality prediction results for each manufacturing stage. The quality prediction model for a multi-stage manufacturing system includes an encoder, a full attention module, a decoder, and a feedforward neural network connected in sequence. The encoder is constructed based on a bidirectional long short-term memory network and is used to generate an output vector for each manufacturing stage based on input data. The full attention module is used to calculate the attention weight of the output vector of each manufacturing stage based on the hidden vector of the decoder and input the weighted output vector into the decoder. The decoder is constructed based on a bidirectional long short-term memory network and is used to decode the weighted output vector. The decoding results are integrated through the feedforward neural network and output as a quality prediction sequence. The quality prediction result for each manufacturing stage is obtained based on the quality prediction sequence. The broadcast mechanism is specifically as follows: in, Indicates that the input data is concatenated in the second-to-last dimension. is the total number of manufacturing stages, For the Equipment status parameters at each manufacturing stage, , For the The first stage of manufacturing Device status parameters, Indicates the The total amount of equipment status parameters in each manufacturing stage, For public input.

2. A quality prediction method for a multi-stage manufacturing system according to claim 1, characterized in that: The preprocessing includes feature dimension reduction and data normalization.

3. The quality prediction method for a multi-stage manufacturing system according to claim 2, characterized in that: Feature dimensionality reduction is performed through principal component analysis.

4. The quality prediction method for a multi-stage manufacturing system according to claim 1, characterized in that: No. The attention weights of the output vectors of the production stages The calculation formula is as follows: in, represents the unnormalized attention weight, is the total number of manufacturing stages; Calculating attention weights With encoder output vector The dot product of , sent to the decoder:

5. The quality prediction method for a multi-stage manufacturing system according to claim 4, characterized in that: Unnormalized attention weights Calculated using the following formula: in, is the parameter vector, is the transpose of this vector, is the weight matrix, Represents the encoder output vectors, Decoder hidden vectors.

6. The quality prediction method for a multi-stage manufacturing system according to claim 1, characterized in that: The specific expression of the quality prediction sequence output by the feedforward neural network is as follows: in, is the quality sequence, is the multi-dimensional output of the decoder, is the activation function, and are two linear transformation layers, and are the bias parameters of the linear transformation layer respectively.

7. The quality prediction method for a multi-stage manufacturing system according to claim 6, characterized in that: The activation function is ReLU.

8. An electronic device comprising a memory, a processor, and a program stored in the memory, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images