Cut tobacco dryer health degree evaluation method and system based on data enhancement and integrated learning

Abstract

The invention discloses a cut-tobacco drier health degree evaluation method and system based on data enhancement and integrated learning. The method comprises the steps of cut-tobacco drier data preprocessing and feature analysis, data pseudo label marking and data screening, data feature importance calculation and feature sorting and screening. And calculating the health degree value of the single model of the cut-tobacco dryer, and realizing data enhancement of the monitoring data by respectively establishing a health degree value calculation model based on a long short-term memory network and a health degree value calculation model based on an adversarial auto-encoder. And calculating and evaluating the health degree of the combined model of the cut-tobacco drier, and establishing a health degree value calculation integrated model of the cut-tobacco drier through an index correlation weighting method and a fuzzy evaluation method so as to realize health degree evaluation of the cut-tobacco drier. According to the method, the problem that the health condition of the cut-tobacco dryer is difficult to evaluate effectively under the conditions of unbalanced sample labels and insufficient data volume can be solved.

Description

Technical Field

[0001] The present invention belongs to the fields of electronic engineering and computer science, and specifically relates to a tofu drying machine health assessment method and system based on data enhancement and integrated learning. Background Art

[0002] As an important link in tobacco production, the drying process directly affects the quality of tobacco, and the drying machine is the key equipment for the intelligent production of the drying process. The drying machine adjusts the moisture content of the dried tobacco leaves and other tobacco quality indicators by setting process parameters, which directly affects the quality of the tobacco. However, if a failure occurs during the operation of the drying machine, it will cause the equipment to operate poorly or even shut down, and the quality of the products produced will decline or even fail to meet the standards, causing safety accidents and economic losses.

[0003] In order to evaluate the health of complex equipment (such as tofu drying machines), various technologies and methods are needed. These include advanced technologies such as data mining, machine learning, and artificial intelligence. These technologies can analyze a large amount of historical data, explore the inherent connections and rules between the data, and thus evaluate the health of complex equipment.

[0004] Equipment health assessment has been applied, but the problems of multiple data feature dimensions, insufficient data labels, and difficulty in real-time and accurate fault monitoring always exist. The existing methods are not ideal for concrete tofu drying equipment, because these models do not fully match the tofu drying machine monitoring data and the actual situation of the tofu drying machine. Therefore, a method with higher matching degree and able to solve problems such as multiple data feature dimensions and insufficient data labels is needed. Summary of the invention

[0005] In order to solve the technical problem that it is difficult to accurately evaluate the health of the tofu drying machine, the present invention first preprocesses the data, extracts pseudo labels and performs feature analysis; a health value calculation model based on a bidirectional long short-term memory network and a health value calculation model based on an adversarial autoencoder are proposed respectively; through ensemble learning, a fuzzy evaluation of the health of the tofu drying machine is performed based on this.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] The present invention provides a method for evaluating the health of a tofu drying machine based on data enhancement and ensemble learning, comprising the following steps:

[0008] Step (1), preprocessing and feature analysis of the tofu drying machine data; realizing data pseudo-label marking and data screening, calculation of data feature importance, and feature sorting and screening;

[0009] Step (2), calculating the health value of a single model of the tofu drying machine, by respectively establishing a health value calculation model based on a long short-term memory network and a health value calculation model based on an adversarial autoencoder, thereby achieving data enhancement of the monitoring data;

[0010] Step (3), calculating and evaluating the health of the combined model of the tofu drying machine, establishing an integrated model for calculating the health value of the tofu drying machine, thereby realizing the health evaluation of the tofu drying machine.

[0011] The present invention provides a tofu drying machine health evaluation system based on data enhancement and integrated learning, comprising:

[0012] The tofu drying machine data preprocessing and feature analysis module realizes data pseudo-label marking and data screening, data feature importance calculation, and feature sorting and screening;

[0013] The single model health value calculation module of the tofu drying machine realizes data enhancement of monitoring data by establishing health value calculation models based on long short-term memory network and adversarial autoencoder respectively;

[0014] The health calculation and evaluation module of the combined model of the tofu drying machine establishes an integrated model for calculating the health value of the tofu drying machine, thereby realizing the health evaluation of the tofu drying machine.

[0015] The present invention has the following beneficial effects:

[0016] Aiming at the monitoring data of the tofu drying machine with insufficient label information, the present invention proposes a method of pseudo-label extraction and data screening based on the semi-supervised learning idea, which solves the problem of insufficient data set labels to a certain extent and improves the operation speed of the health assessment model.

[0017] The present invention proposes a data enhancement method for torrefied tobacco drying machine equipment. An adversarial autoencoder is used to generate monitoring data of torrefied tobacco drying machine after screening in real time, and reconstruction error is calculated in real time, which improves the diversity of data set patterns and the generalization performance of the health assessment model. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a structural block diagram of the tofu drying machine health assessment method based on data enhancement and ensemble learning of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in each embodiment of the present invention described below can be combined with each other as long as they do not conflict with each other. To achieve the above-mentioned purpose, the present invention adopts the following technical scheme.

[0020] The invention discloses a method for evaluating the health of a torrefied paper-cutting machine based on data enhancement and integrated learning, comprising: data preprocessing, which includes processing missing values, abnormal values ​​and preliminary processing with strong interpretability for collected data; pseudo label marking, which includes preliminary label marking of data using a clustering algorithm; a feature extraction module that uses extreme gradient boosting to calculate, sort and screen the importance of data features; a torrefied paper-cutting machine health value calculation, which includes calculating the health value based on a bidirectional long short-term memory network and an adversarial autoencoder model according to specific torrefied paper-cutting machine monitoring data; and a torrefied paper-cutting machine health value evaluation block, which includes obtaining an integrated health value calculation method through integrated learning and performing fuzzy evaluation based on the health value to achieve real-time evaluation of the health status of the torrefied paper-cutting machine.

[0021] The structural block diagram of the method for evaluating the health of a tofu drying machine based on data enhancement and ensemble learning of the present invention is as follows: Figure 1 As shown, it includes data preprocessing and feature analysis of the health evaluation of the tofu drying machine, calculation of the health value of the health evaluation of the tofu drying machine, and health evaluation of the tofu drying machine. The specific steps are as follows:

[0022] Step (1), data preprocessing and feature analysis of the tofu drying machine, is specifically implemented as follows:

[0023] Step (1.1), data preprocessing: Data preprocessing specifically includes missing value processing, outlier processing, preliminary feature processing, data standardization and normalization, and filtering.

[0024] Among them, missing value processing is to fill the missing data with the average of the five data before and after the missing data as the value of the missing data. Outlier processing is to check whether there is abnormal data in the original data. The method is to replace the missing data with the average of the five data before and after the missing data as the replacement data. The specific processing includes the missing value and outlier value formulas as follows:

[0025] (1)

[0026] In the above formula, N is the total number of data. is the i+jth data, is the data used to supplement or replace the i-th position.

[0027] On this basis, the original features are preliminarily merged, added, and deleted according to prior knowledge. For the monitoring of the tofu drying machine, the "hot air speed setting value" and the "hot air speed actual value" are merged into the feature "hot air speed working deviation" which is of practical significance for health assessment, the "BBHS_area 1 barrel temperature setting value" and the "BBHS_area 1 barrel temperature actual value" are merged into "BBHS_area 1 barrel temperature", and the "BBHS_area 2 barrel temperature setting value" and the "BBHS_area 2 barrel temperature actual value" are merged into "BBHS_area 2 Cylinder temperature", "BBHS_Pressure setting value at discharge hood" and "BBHS_Pressure actual value at discharge hood" are merged into "BBHS_Pressure at discharge hood", "BBHS_Final tobacco moisture setting value" and "BBHS_Final tobacco moisture actual value" are merged into "BBHS_Final tobacco moisture working deviation", "HT_Steam pressure preferred setting value" and "HT_Steam pressure preferred actual value" are merged into "HT_Steam pressure preferred working deviation", "Drying wire cylinder wall 2 temperature preferred (set) value" and "Drying wire cylinder wall 2 temperature preferred (set) value" are merged into "Drying wire cylinder wall 2 temperature preferred working deviation", "Drying wire cylinder wall 1 temperature preferred (set) value" and "Drying wire cylinder wall 1 temperature preferred (set) value" are merged into "Drying wire cylinder wall 1 temperature preferred working deviation", delete the feature "Cumulative amount of tobacco flow" and other monitoring data features that have little relationship with the actual fault. Data standardization and normalization is to process data with different characteristics so that the data are all on the same scale to prevent certain characteristics from occupying too dominant a position. The specific formula is as follows:

[0028] (2)

[0029] In the above formula, is the i-th data, and are the minimum and maximum data values, respectively. is the normalized result of the i-th data.

[0030] Then, the noise interference is eliminated by using the data of the five previous and next time steps for sliding average filtering;

[0031] Step (1.2), pseudo-label extraction: This step is to solve the problem of insufficient labeling. A small number of partial features are selected based on prior knowledge, and the labels are initially calibrated and updated through the k-means clustering algorithm. Clusters n_clusters=2 and n_clusters=4 are selected as coarse labels and fine labels respectively. Each cluster is set to correspond to different label values ​​according to its degree of deviation from the healthy operation state. The greater the deviation of the cluster center from the healthy operation state, the larger the label value is set. Judgment, where d is the degree of deviation, , They are the clustering clusters and the corresponding data of healthy operation. Each clustering cluster corresponds to a different label size. The coarse label is set to 0 (healthy) and 1 (faulty). The label sizes of the four fine labeling clusters are set to 0, 0.4, 0.7, and 1. Run the k-means model training results under the two clustering cluster parameters to obtain the corresponding two sets of labels. Then, the confidence evaluation and screening are performed based on the distance between the clustering sample points and the cluster center. The confidence is set to α=0.05, and the clustering results are screened. The monitoring data corresponding to the clustering results after screening is used as available data and recorded as AD;

[0032] Step (1.3), feature analysis and screening: For the problems of high feature dimension of monitoring data and unclear impact on health, feature screening method is used to solve them. Data feature mining and analysis and feature importance calculation are performed through the extreme gradient boosting algorithm. This algorithm has superior performance and accuracy compared with algorithms such as gradient boosting tree, and can perform data feature mining and analysis and feature importance calculation. First, input the corresponding features of the original tofu drying machine monitoring data, and set the tree depth max_depth, number of trees (ie, number of iterations) n_estimators, and learning rate learning_rate related parameters. For the XGBoost model with set parameters, perform model pre-training and parameter adjustment, and save the training results. Calculate the feature importance of the trained model and sort it from large to small according to the feature importance. Select the feature screening number n, and select the corresponding features of the largest n feature importance as the filtered features based on this, and retain the corresponding data of the filtered features as the subsequent model training data based on the feature screening results;

[0033] Step (2), the single model health value calculation module of the tofu drying machine is specifically implemented as follows:

[0034] Step (2.1), calculation of the health value of the bidirectional long short-term memory network model: to calculate the health value of the tofu drying machine. For the historical time series characteristics of the data, a Bi-LSTM method is used to utilize this characteristic. First, it is necessary to analyze and set the specific network structure and hyperparameters of Bi-LSTM. Bi-LTSM mainly includes three layers of input layer, hidden layer, and output layer. The hidden layer contains three gated unit structures: forget gate, input gate, and output gate, which can be regarded as three fully connected layers. The input gate is used to control the proportion of information flowing into the hidden layer, the forgetting layer is used to control the proportion of information that needs to be forgotten, and the output layer is used to calculate the output value at the current moment. The Bi-LSTM network structure is pre-set based on empirical knowledge, and the model is pre-trained through the available data AD obtained in step (1.2) to obtain the corresponding results and parameters of the model. Then, based on the comparison of the training results with the available data AD, the specific network structure and hyperparameters of Bi-LSTM are further adjusted. Finally, a four-layer Bi-LSTM structure and a one-layer fully connected layer structure were determined as the basic structure of the training model (32 layers, 16 layers, 16 layers, and 8 layers, respectively), and the input feature dimension was set to 14 to match the dimension of the monitoring data. By training the Bi-LSTM model, the temporal characteristics and patterns of the original data can be learned, so as to learn the corresponding relationship between the monitoring data of the tofu drying machine and its health value. By training the Bi-LSTM model, the temporal characteristics and patterns of the original data can be learned, so as to learn the corresponding relationship between the monitoring data of the tofu drying machine and its health value. The input is the filtered feature corresponding data, and the output is the real-time health value of the tofu drying machine. For the tofu drying machine time series monitoring data, each Bi-LTSM layer can capture the time series characteristics of the data. Then determine the model hyperparameters, and modify the model hyperparameters appropriately according to the training situation. The specific structure is shown in Table 1. Train the Bi-LSTM model again, and save the trained model parameters, denoted as M1. Finally, use the available data AD as the model input, and calculate the health value based on the trained model parameters M1, denoted as h1;

[0035] Table 1 Bi-LSTM network structure and hyperparameter settings

[0036]

[0037] Step (2.2), data enhancement of the adversarial autoencoder model: As a data generation model, the adversarial autoencoder, or AAE, has the characteristics of high training stability and rich types of generated data. It is suitable for the generation of high-dimensional, nonlinear monitoring data of the tofu drying machine, and solves the problem of insufficient data through data enhancement. Its structure specifically includes three parts: encoder, decoder, and discriminator. The encoder is used to reduce the dimension of the original data and encode it into abstract features; the decoder is used to decode and restore the encoded abstract features; the discriminator inputs Gaussian random distribution sampling and the original data dimensionality reduction results respectively, and needs to judge whether the input data is original data. Determine the model structure of the three parts respectively, and use the linear layer as the basic structure of the three modules. The AAE network structure is pre-set based on empirical knowledge, and the model is pre-trained with the available data AD obtained in step (1.2) to obtain the corresponding results and parameters of the model. Then, based on the comparison of the training results with the available data AD, the specific network structure and hyperparameters of AAE are further adjusted to obtain the final structure of AAE: a four-layer linear layer encoder, a four-layer decoder structure, a four-layer discriminator structure, and the input feature dimension is set to 14 (corresponding to the monitoring data dimension). Based on the selected loss function and learning rate, the model is trained and parameterized, and the trained results are saved. The specific model structure is shown in Table 2. For the AAE model with determined hyperparameters, further training is performed to establish the corresponding relationship between the drying machine monitoring data and the drying machine health value, and the trained model parameters are saved. Through the trained AAE model, normal data ND and fault data FD are generated to supplement and enhance the original data;

[0038] Step (2.3), calculation of health value based on adversarial autoencoder model: according to the formula , calculate the data reconstruction error e between the normal data ND obtained in step (2.2) and the available data AD, and normalize the reconstruction error to obtain the quantitative value (i.e., health value) that characterizes the health of the tofu drying machine, denoted as h2. Through the gradient descent algorithm, take the 14-dimensional feature data as input, the data reconstruction error as output, perform linear regression on the health value, and obtain the quantitative correspondence between the available data AD and the health value, denoted as M2.

[0039] Table 2 AAE network structure and hyperparameter settings

[0040]

[0041] Step (3), calculation and evaluation of the health of the combined model of the tofu drying machine, is specifically implemented as follows:

[0042] Step (3.1), calculation of health value based on integrated model: adopt the stacking method to integrate the model, and objectively assign weights through the indicator correlation weighting method (CRITIC method) of operations research. This method can not only reflect the relationship between data, but also comprehensively consider the relationship between various indicators of each single observation method and data volatility.

[0043] The specific calculation method is as follows:

[0044] For the 2 single-item models M1 and M2 (evaluation objects), the root mean square error MSE, the mean absolute error MAE, and the decision coefficient R 2 , after fuzzy evaluation, the error rate J is judged and the four evaluation indicators are set up as the indicator evaluation matrix:

[0045] (3)

[0046] Among them, y ij It represents the evaluation value of the i-th evaluation indicator of the j-th single model, n is the total number of models (n=2), and m is the number of evaluation indicators (m=4).

[0047] For cost-based indicators (the smaller the better), normalize and calculate the mean:

[0048] (4)

[0049] (5)

[0050] u ij and are the standardized data and the mean data, respectively.

[0051] For the standard deviation S j and correlation coefficient r jj' (between the two indicators j and j') is calculated:

[0052] (6)

[0053] (7)

[0054] Then, for the conflict between the jth index and all the indexes, j Perform the calculation:

[0055] (8)

[0056] For the jth evaluation index, the amount of information C j Perform the calculation:

[0057] (9)

[0058] Weight the amount of information and calculate the objective weight w j :

[0059] (10)

[0060] This method assigns objective weights based on the degree of indicator difference and the correlation between indicators. The larger the standard deviation of the indicator, the more information the indicator provides when distinguishing different evaluation objects, and the stronger the corresponding objective weight; the greater the degree of negative correlation between two indicators, the stronger their conflict, the greater the difference in information provided when distinguishing different evaluation models, and the stronger the corresponding objective weight. The calculation formulas for some evaluation indicators are as follows:

[0061] Root mean square error MSE:

[0062] (11)

[0063] Mean absolute error MAE:

[0064] (12)

[0065] Decision coefficient R 2 :

[0066] (13)

[0067] In the above formulas (11), (12), and (13), is the true output value of the data corresponding to the i-th time point, is the predicted output value of the data corresponding to the i-th time point, and N is the total amount of data.

[0068] According to the above method, the corresponding models are calculated:

[0069] (14)

[0070] Among them, H is the total health value (i.e. the health value of the combined model), is the i-th model weight, Predict the health value for the i-th model, and n is the total number of models. Through the above steps, the overall health value of the tofu drying machine is obtained;

[0071] Step (3.2), health evaluation based on fuzzy evaluation: The fuzzy evaluation method is used to divide the health value into four levels: healthy, sub-healthy, degraded, and faulty. Based on the constructed health level, a membership function is established to determine the health value range as 0~1. When the health value is set to 0~0.2, the tofu drying machine is judged to be in a healthy state; when the health value is 0.2~0.5, the tofu drying machine is judged to be in a sub-healthy state; when the health value is 0.5~0.8, the tofu drying machine is judged to be in a degraded state; when the health value is 0.8~1.0, the tofu drying machine is judged to be in a faulty state. The combined model health value H calculated in step (3.1) is put into the membership function to obtain the qualitative health state of the tofu drying machine as the health evaluation result.

[0072] In summary, the present invention discloses a method for evaluating the health of a torrefied tofu drying machine based on data enhancement and ensemble learning, including: data preprocessing and feature analysis of torrefied tofu drying machine health evaluation, health value calculation of torrefied tofu drying machine health evaluation, and health evaluation of torrefied tofu drying machine health evaluation. The present invention can effectively solve the problem that the health status of a torrefied tofu drying machine is difficult to effectively evaluate during the operation of the torrefied tofu drying machine when sample labels are unbalanced and data volume is insufficient.

[0073] The contents not described in detail in the specification of the present invention belong to the prior art known to the professional and technical personnel in this field.

[0074] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for evaluating the health of a tofu drying machine based on data enhancement and ensemble learning, characterized in that: The steps include: Step (1), preprocessing and feature analysis of the tofu drying machine data; realizing data pseudo-label marking and data screening, calculation of data feature importance, and feature sorting and screening; Step (2), calculating the health value of a single model of the tofu drying machine, by respectively establishing a health value calculation model based on a long short-term memory network and a health value calculation model based on an adversarial autoencoder, thereby achieving data enhancement of the monitoring data; Step (3), calculating and evaluating the health of the combined model of the tofu drying machine, establishing an integrated model for calculating the health value of the tofu drying machine, thereby realizing the health evaluation of the tofu drying machine.

2. According to the method for evaluating the health of a tofu drying machine based on data enhancement and ensemble learning in claim 1, it is characterized in that: Step (1) is implemented as follows: Step (1.1), data preprocessing: Data preprocessing includes missing value processing, outlier processing, and feature preliminary processing steps; Among them, the missing value processing is to fill the gap with the average value of multiple data before and after the missing data as the value of the missing data; Outlier processing is to check whether there are abnormal data in the original data, and the method is to replace the missing data with the average value of multiple data before and after the missing data as the replacement data; The initial feature processing is to merge, add and delete the original features of the tofu drying machine. The "hot air speed setting value" and "hot air speed actual value" are merged into the feature "hot air speed working deviation", "BBHS_area 1 barrel temperature setting value" and "BBHS_area 1 barrel temperature actual value" are merged into "BBHS_area 1 barrel temperature", and "BBHS_area 2 barrel temperature setting value" and "BBHS_area 2 barrel temperature actual value" are merged into "BBHS_area 2 "BBHS_Pressure setting value at discharge hood" and "BBHS_Pressure actual value at discharge hood" are merged into "BBHS_Pressure at discharge hood", "BBHS_Final tobacco moisture setting value" and "BBHS_Final tobacco moisture actual value" are merged into "BBHS_Final tobacco moisture working deviation", "HT_Steam pressure optimization setting value" and "HT_Steam pressure optimization actual value" are merged into "HT_Steam pressure optimization working deviation", "Drying wire cylinder wall 2 temperature optimization setting value" and "Drying wire cylinder wall 2 temperature optimization setting value" are merged into "Drying wire cylinder wall 2 temperature optimization working deviation", "Drying wire cylinder wall 1 temperature optimization setting value" and "Drying wire cylinder wall 1 temperature optimization setting value" are merged into "Drying wire cylinder wall 1 temperature optimization working deviation"; delete the feature "Cumulative amount of tobacco flow", and normalize the filtered data; Step (1.2), pseudo-label extraction: select features with high correlation with the health of the tofu drying machine, and preliminarily label the monitoring data through the clustering algorithm; then select clusters n_clusters=2 as coarse labels and n_clusters=4 as fine labels, and each cluster is based on the formula: , calculate the degree of deviation from the healthy operating state, where d is the degree of deviation, , The corresponding data of clusters and healthy operation are respectively, and then the corresponding label values ​​are set according to the label categories according to the degree of deviation of the cluster center. The coarse label is set to 0, which means healthy, and 1 means fault. The value of the fine label is set to 0, 0.4, 0.7, and 1. Finally, the confidence is set to α=0.05, that is, the confidence interval is set. The confidence evaluation is performed by the distance between the cluster sample point and the cluster center to screen the data of each cluster in turn. The monitoring data corresponding to the clustering result after screening is used as the available data and recorded as AD. Step (1.3), feature analysis and feature screening: Use the available data of the tofu drying machine in n0 dimensions as the model input, and use the labels extracted from the pseudo-labels as the model output. Perform XGBoost model training, use the trained XGBoost model to calculate and sort the feature importance, and select the first several features with higher feature importance as the input features of the health value calculation model.

3. The method for evaluating the health of a tofu drying machine based on data enhancement and ensemble learning according to claim 2 is characterized in that: Step (2) is implemented as follows: Step (2.1), calculation of the health value of the bidirectional long short-term memory network model: first, the Bi-LSTM network structure is preset based on empirical knowledge, and the model is pre-trained through the available data AD obtained in step (1.2) to obtain the corresponding results and parameters of the model; then, based on the comparison between the training results and the available data AD, the specific network structure and hyperparameters of the Bi-LSTM network structure are further adjusted, and the obtained four-layer Bi-LSTM network structure and one fully connected layer structure are used as the final structure of the model. The four-layer Bi-LSTM structure has 32 layers, 16 layers, 16 layers, and 8 layers respectively, and the input feature dimension is 14. Then, the extracted coarse labels and fine labels are used as the health value of the torrefied machine, and the Bi-LSTM network structure is re-trained to establish the corresponding relationship between the monitoring data of the torrefied machine and the health value of the torrefied machine, and the trained model parameters are saved, recorded as M1. Finally, the available data AD is used as the model input, and the health value is calculated based on the trained model parameters M1, recorded as h1; Step (2.2), data enhancement of the adversarial autoencoder model, i.e., AAE: first, the AAE network structure is preset based on empirical knowledge, and the model is pre-trained using the available data AD obtained in step (1.2) to obtain the corresponding results and parameters of the model. Then, based on the comparison between the training results and the available data AD, the specific network structure and hyperparameters of AAE are further adjusted to obtain the final structure of AAE: a four-layer linear encoder, a four-layer decoder structure, and a four-layer discriminator structure. The input feature dimension is 14. For the AAE model with the determined hyperparameters, training is performed to establish the corresponding relationship between the monitoring data of the tofu drying machine and the health value of the tofu drying machine, and the trained model parameters are saved. Through the trained AAE model, normal data ND and fault data FD are generated to supplement and enhance the original data. Step (2.3), calculation of health value based on adversarial autoencoder model: according to the formula , calculate the data reconstruction error e between the normal data ND obtained in step (2.2) and the available data AD, and normalize the reconstruction error to obtain the quantitative value characterizing the health of the tofu drying machine, namely the health value, denoted as h2. Through the gradient descent algorithm, the 14-dimensional feature data is taken as input and the data reconstruction error is taken as output. The health value calculation formula is linearly regressed to obtain the quantitative correspondence between the available data AD and the health value, denoted as M2.

4. The method for evaluating the health of a tofu drying machine based on data enhancement and ensemble learning according to claim 3 is characterized in that: Step (3) is implemented as follows: Step (3.1), calculation of health value based on integrated model: Based on the model M1 obtained in step (2.1) and the model M2 obtained in step (2.3), the root mean square error MSE, the mean absolute error MAE, and the decision coefficient R 2 , fuzzy evaluation after judgment error rate J There are 4 evaluation indicators in total, and the evaluation indicator matrix of the health calculation model is determined: , where y ij It represents the evaluation value of the i-th evaluation index of the j-th single model. The weights w1 and w2 corresponding to the models M1 and M2 are calculated respectively by the index correlation weighting method. The stacking method is used to integrate the models. Calculate the health value of the combined model, where H is the health value of the combined model, w j is the j-th model weight, h j Predict the health value for the jth model, n is the total number of models, n=2, m is the number of evaluation indicators, m=4; Step (3.2), health assessment based on fuzzy evaluation: using the fuzzy evaluation method, the health value is divided into four levels: healthy, sub-healthy, deteriorated, and faulty; According to the constructed health level, the membership function is established to determine the health value range as 0-1. When the health value is set between 0 and 0.2, the tofu drying machine is judged to be in a healthy state. When the health value is 0.2-0.5, the tofu drying machine is judged to be in a sub-healthy state; When the health value is between 0.5 and 0.8, the tofu drying machine is judged to be in a deteriorated state; When the health value is between 0.8 and 1.0, the tofu drying machine is judged to be in a fault state. The health value H of the combined model calculated in step (3.1) is put into the membership function to obtain the qualitative health state of the tofu drying machine as the health evaluation result.

5. A tofu drying machine health assessment system based on data enhancement and ensemble learning, characterized in that: include: The tofu drying machine data preprocessing and feature analysis module realizes data pseudo-label marking and data screening, data feature importance calculation, and feature sorting and screening; The single model health value calculation module of the tofu drying machine realizes data enhancement of monitoring data by establishing health value calculation models based on long short-term memory network and adversarial autoencoder respectively; The health calculation and evaluation module of the combined model of the tofu drying machine establishes an integrated model for calculating the health value of the tofu drying machine, thereby realizing the health evaluation of the tofu drying machine.

Images