Chemical process fault detection method based on one-dimensional convolution attention mechanism network

Abstract

The invention discloses a chemical process fault detection method based on a one-dimensional convolution attention mechanism network, and particularly relates to the field of chemical process fault diagnosis. The method comprises the following steps: firstly, performing simulation by matlab software to obtain chemical process data, preprocessing the chemical process data, and performing standardization and sliding window processing; establishing a chemical process data set, performing label labeling on the obtained chemical process data, and dividing the chemical process data set into a training set and a test set; then constructing a one-dimensional convolution attention mechanism network model, wherein the one-dimensional convolution attention mechanism network model is formed by connecting a one-dimensional convolution layer, a Relu activation layer, a pyramid extrusion attention mechanism layer, a full connection layer and a Softmax layer in sequence; then training the chemical process data training set by using the constructed network model, and storing the network model with trained parameters; and finally, carrying out fault detection on the chemical process data test set by using the stored network model so as to obtain a fault classification result of the chemical process. The method is suitable for fault diagnosis in the chemical process.

Description

Technical Field

[0001] The present invention relates to the technical field of chemical process fault diagnosis, and in particular to a chemical process fault detection method based on a one-dimensional convolutional attention mechanism network. Background Art

[0002] With the rapid development of the chemical industry, chemical process systems are becoming increasingly complex, involving large amounts of sensor data and dynamic changes in multiple variables. Fault detection has become a key technology for ensuring production safety and improving system stability. Traditional fault detection methods, which rely heavily on mathematical modeling and expert experience, struggle to adapt to the demands of complex, nonlinear, and variable operating conditions. Furthermore, the model construction process is cumbersome and lacks adaptability. In recent years, with the advancement of deep learning technology, neural network-based fault detection methods have become a research hotspot due to their powerful feature extraction and pattern recognition capabilities.

[0003] One-dimensional convolutional neural network (1D-CNN) is an important branch of deep learning. It can directly process time series data and extract local time series features. It has low computational complexity and is suitable for processing high-dimensional sensor data in chemical processes. Compared with two-dimensional convolutional networks, 1D-CNN avoids sensitivity to the order of variable arrangement, is more stable and efficient, and has achieved good results in fault detection in multiple industrial processes. However, simple convolutional networks have certain limitations in capturing long-distance dependencies and global information, which may lead to the neglect of key features. Against this background, the present invention proposes a chemical process fault detection method based on a one-dimensional convolutional attention mechanism network. This method combines a one-dimensional convolutional network with a pyramid squeezing attention mechanism. Through multi-scale feature fusion, it can effectively capture important information at different scales, enhance the model's ability to focus on key fault features, and improve the accuracy and robustness of chemical process fault detection. Summary of the Invention

[0004] In response to the shortcomings of the existing technology, the present invention proposes a chemical process fault detection method based on a one-dimensional convolutional attention mechanism network, which improves the accuracy of chemical process fault diagnosis.

[0005] The present invention is achieved by adopting the following technical solutions:

[0006] A chemical process fault detection method based on a one-dimensional convolutional attention mechanism network is implemented using the following steps:

[0007] Step 1: Use MATLAB software to simulate the Tennessee Eastman Chemical process data, preprocess the data, and perform normalization and sliding window processing;

[0008] Step 2: Create a chemical process data set, label the simulated chemical process data, and divide the chemical process data into training and test sets according to the proportion;

[0009] Step 3: Construct a one-dimensional convolutional attention mechanism network model, which consists of a one-dimensional convolutional layer, a Relu activation layer, a pyramid squeeze attention mechanism layer, a fully connected layer, and a Softmax layer;

[0010] Step 4: Use the constructed network model to train the chemical process data training set and save the network model with the trained parameters;

[0011] Step 5: Use the saved network model to perform fault detection on the chemical process data test set to obtain the fault classification results of the chemical process data.

[0012] The beneficial effects of the present invention are:

[0013] The one-dimensional convolutional neural network proposed in the present invention is suitable for processing multivariate sensor data in chemical processes and can capture local temporal variation characteristics. However, the traditional 1D-CNN has the problem of limited receptive field, which makes it difficult to effectively capture long-distance dependencies and global contextual information, which may lead to insufficient recognition of key fault signals in complex chemical fault detection. The present invention introduces a pyramid squeezing attention mechanism. This mechanism effectively captures key information at different time scales through multi-scale feature fusion, and enhances the model's perception of complex fault signals. The pyramid structure combined with the squeezing operation not only reduces the feature dimension and computational complexity, but also enables the model to automatically focus on the most important time periods and features by dynamically adjusting the attention weights. At the same time, the pyramid squeezing attention mechanism enhances the model's ability to model global information, makes up for the limitations of the local receptive field of the traditional 1D-CNN, and improves the generalization ability and robustness of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 Schematic diagram of the overall process of the present invention

[0015] Figure 2 Network model architecture diagram of the present invention

[0016] Figure 3 TEP simulation system structure diagram DETAILED DESCRIPTION

[0017] The present invention is described in detail below with reference to specific embodiments.

[0018] A chemical process fault detection method based on a one-dimensional convolutional attention mechanism network is implemented using the following steps:

[0019] Step 1: Use MATLAB software to simulate the Tennessee Eastman Chemical process data, preprocess the data, and perform normalization and sliding window processing;

[0020] Step 2: Create a chemical process data set, label the simulated chemical process data, and divide the chemical process data into training and test sets according to the proportion;

[0021] Step 3: Construct a one-dimensional convolutional attention mechanism network model, which consists of a one-dimensional convolutional layer, a Relu activation layer, a pyramid squeeze attention mechanism layer, a fully connected layer, and a Softmax layer;

[0022] Step 4: Use the constructed network model to train the chemical process data training set and save the network model with the trained parameters;

[0023] Step 5: Use the saved network model to perform fault detection on the chemical process data test set to obtain the fault classification results of the chemical process data.

[0024] In the step 1, the specific steps include:

[0025] (1) Obtain chemical process data under different faults in MATLAB software, and obtain 20 different fault data sets and normal state data sets.

[0026] (2) All the above data sets are normalized. In this implementation, the function expression of the normalization process is shown in formula (1-1):

[0027]

[0028] In the above formula, x scale is the data after the chemical process data x is standardized, x mean is the mean value of the chemical process data x, and std is the standard deviation of the chemical process data x.

[0029] (3) Sliding window processing is performed on each data set under different fault conditions and normal conditions. Assume that the chemical process data x=[x1,x2,x3,…,x n ], where x i The shape of the sliding window is (1,50), the sliding window length is 50, and the sliding step size is 1. The data processed by the sliding window is d1=[x1,x2,…,x 50 ],d2=[x2,x3,…,x 51 ],…,d n =[x n-49 x n-48 …x n ], that is, the data x after the sliding window is processed i The shape is (50,50).

[0030] In the step 2, the specific steps include:

[0031] (1) All data sets obtained in step 1 are labeled according to the One-Hot encoding rule.

[0032] (2) Then divide the dataset into test set and training set in a 3:7 ratio.

[0033] In the step three, the specific steps include:

[0034] (1) Construct a one-dimensional convolutional attention mechanism network model. The constructed network model structure first undergoes convolution processing consisting of two layers of one-dimensional convolutional layers plus a Relu layer, then passes through a pyramid squeeze attention mechanism layer, and then is sent to a fully connected layer, and finally passes through a Softmax layer to obtain the probability of the fault category.

[0035] In the step 4, the specific steps include:

[0036] (1) After the network model of step 3 is constructed, the mean square error function is selected as the loss function in the present invention. The expression of the mean square error function is shown in formula (1-2):

[0037]

[0038] Where N is the number of samples, y i is the true value of the i-th sample, is the predicted value of the i-th sample.

[0039] (2) In the present invention, Adam is selected as the optimizer, the learning rate parameter is set to 0.00001, the BatchSize is set to 128, the number of iterations is 500, and the shape of the input chemical process data is [128, 50, 50].

[0040] (3) Once the loss function, optimizer, and parameters are set, the training set data can be fed into the constructed network model for training. During the training process, backpropagation is used to adjust and update the entire network parameters, thereby reducing the loss function value and improving the model accuracy. Finally, the network model with the trained parameters is saved.

[0041] In the step 5, the specific steps include:

[0042] (1) Load the network model saved in step 4, then send the test set data into the loaded network model for fault detection, and finally generate the fault detection classification results.

[0043] In this experiment, the Tennessee Eastman Chemical Process (TEP) data was selected as the data to verify the effect of the chemical process fault diagnosis model of the present invention. The data set used in the present invention was obtained by simulation using matlab software. The simulated TEP data includes normal data and 20 types of fault data. Each type of fault sample and normal sample involves 53 process parameters, including 22 process measurement variables, 19 component analysis variables and 12 operation variables. Since 3 of the 53 process parameters of the simulated data set are constants, these three variables have been deleted in the preprocessing. The shape of each sample in the preprocessed data set is (50, 50). The TEP data set was obtained by the TEP simulation model under 100h simulation, with sampling once every 3 minutes. The fault sample was introduced after 10h of simulation. The structure diagram of the TEP simulation system is shown in the figure. Figure 3 Finally, through comparative analysis of experimental results, it is concluded that the present invention has achieved a good fault classification accuracy in chemical process fault diagnosis.

Claims

1. A chemical process fault detection method based on a one-dimensional convolutional attention mechanism network, characterized in that: The following steps are involved: Step 1: Use MATLAB software to simulate the Tennessee Eastman Chemical process data, preprocess the data, and perform normalization and sliding window processing; Step 2: Create a chemical process data set, label the simulated chemical process data, and divide the chemical process data into training and test sets according to the proportion; Step 3: Construct a one-dimensional convolutional attention mechanism network model, which consists of a one-dimensional convolutional layer, a Relu activation layer, a pyramid squeeze attention mechanism layer, a fully connected layer, and a Softmax layer; Step 4: Use the constructed network model to train the chemical process data training set and save the network model with the trained parameters; Step 5: Use the saved network model to perform fault detection on the chemical process data test set to obtain the fault classification results of the chemical process data.

2. The chemical process fault detection method based on a one-dimensional convolutional attention mechanism network according to claim 1 is characterized by: In the step 1, the specific steps include: (1) Obtain chemical process data under different faults in MATLAB software, and obtain 20 different fault data sets and normal state data sets. (2) All the above data sets are normalized. In this implementation, the function expression of the normalization process is shown in formula (1-1): In the above formula, x scae is the data after the chemical process data x is standardized, x mean is the mean value of the chemical process data x, and std is the standard deviation of the chemical process data x. (3) Sliding window processing is performed on each data set under different fault conditions and normal conditions. Assume that the chemical process data x=[x1,x2,x3,…,x n ], where x i The shape of the sliding window is (1,50), the sliding window length is 50, and the sliding step size is 1. The data processed by the sliding window is d1=[x1,x2,…,x 50 ],d2=[x2,x3,…,x 51 ],…,d n =[x n-49 x n-48 …x n ], that is, the data x after the sliding window is processed i The shape is (50,50).

3. The chemical process fault detection method based on a one-dimensional convolutional attention mechanism network according to claim 1 is characterized by: In the step 2, the specific steps include: (1) All data sets obtained in step 1 are labeled according to the One-Hot encoding rule. (2) Then divide the dataset into test set and training set in a 3:7 ratio.

4. The chemical process fault detection method based on a one-dimensional convolutional attention mechanism network according to claim 1 is characterized by: In the step three, the specific steps include: (1) Construct a one-dimensional convolutional attention mechanism network model. The constructed network model structure first undergoes convolution processing consisting of two layers of one-dimensional convolutional layers plus a Relu layer, then passes through a pyramid squeeze attention mechanism layer, and then is sent to a fully connected layer, and finally passes through a Softmax layer to obtain the probability of the fault category.

5. The chemical process fault detection method based on a one-dimensional convolutional attention mechanism network according to claim 1, characterized in that: In the step 4, the specific steps include: (1) After the network model of step 3 is constructed, the mean square error function is selected as the loss function in the present invention. The expression of the mean square error function is shown in formula (1-2): Where N is the number of samples, y i is the true value of the i-th sample, is the predicted value of the i-th sample. (2) In the present invention, Adam is selected as the optimizer, the learning rate parameter is set to 0.00001, the BatchSize is set to 128, the number of iterations is 500, and the shape of the input chemical process data is [128, 50, 50]. (3) Once the loss function, optimizer, and parameters are set, the training set data can be fed into the constructed network model for training. During the training process, backpropagation is used to adjust and update the entire network parameters, thereby reducing the loss function value and improving the model accuracy. Finally, the network model with the trained parameters is saved.

6. The chemical process fault detection method based on a one-dimensional convolutional attention mechanism network according to claim 1, characterized in that: In the step 5, the specific steps include: (1) Load the network model saved in step 4, then send the test set data into the loaded network model for fault detection, and finally generate the fault detection classification results.

Images