Reactor cooler performance evaluation and predictive maintenance method and device

Abstract

The application provides an electric reactor cooler performance evaluation and predictive maintenance method and device, relates to the technical field of performance evaluation, and comprises the following steps: collecting historical data of an electric reactor cooler in real time; acquiring an input variable feature set; inputting a prediction model and combining real-time monitoring data to cooperatively predict cooling efficiency and future energy consumption data, so that a performance degradation curve of the electric reactor cooler is obtained; a temperature difference is calculated, input into a support vector regression model and the prediction model respectively, and corresponding predicted electric reactor cooler temperature difference values are generated; a final electric reactor cooler temperature difference prediction value is obtained, and a service life curve of the electric reactor cooler is calculated in combination with the cooling efficiency; the performance evaluation grade of the electric reactor cooler is determined, and a maintenance time point and a maintenance strategy are determined according to the performance evaluation grade. Through efficient data processing and feature extraction, the performance evaluation grade of the electric reactor cooler is determined, and the accuracy of electric reactor cooler performance determination is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of performance evaluation, and in particular to a method and device for performance evaluation and predictive maintenance of a reactor cooler. BACKGROUND

[0002] As a key component in the power system, the stability and reliability of the performance of the reactor cooler are crucial to the safe operation of the entire power grid. However, during long-term operation, the reactor cooler may experience performance degradation and potential failures due to continuous load and environmental factors, which directly affects the stability of the power system and the reliability of power supply. SUMMARY

[0003] The present application aims to at least partially solve one of the technical problems in the related art.

[0004] To this end, a first object of the present application is to provide a method for performance evaluation and predictive maintenance of a reactor cooler.

[0005] A second object of the present application is to provide a device.

[0006] A third object of the present application is to provide an electronic device.

[0007] A fourth object of the present application is to provide a computer-readable storage medium.

[0008] A fifth object of the present application is to provide a computer program product.

[0009] To achieve the above objects, a first aspect of the present application provides a method for performance evaluation and predictive maintenance of a reactor cooler, comprising:

[0010] collecting historical data of the reactor cooler in real time using a sensor, the historical data including a process variable data set and an operating variable data set;

[0011] performing denoising processing on the historical data, and filtering data in the operating variable data set to obtain an input variable feature set according to mutual information values between each variable in the operating variable data set and a target variable;

[0012] inputting the input variable feature set into a prediction model, and cooperatively predicting cooling efficiency and future energy consumption data in combination with real-time monitoring data to obtain a performance degradation curve of the reactor cooler;

[0013] calculating a first temperature difference and a second temperature difference from data in the process variable data set, inputting the first temperature difference and the second temperature difference into a support vector regression model and the prediction model respectively, and generating corresponding predicted reactor cooler temperature difference values;

[0014] integrating the predicted reactor cooler temperature difference to obtain a final reactor cooler temperature difference prediction value, and combining the cooling efficiency of the performance degradation curve to calculate a service life curve of the reactor cooler;

[0015] determining a performance evaluation grade of the reactor cooler in combination with the performance degradation curve and the service life curve, and determining a maintenance time point and a maintenance strategy according to the performance evaluation grade.

[0016] Optionally, the process variable data set includes operating temperature, ambient temperature, current, and reactor thermal resistance, and the operation variable data set includes flow rate, energy consumption data, operating state, and maintenance record.

[0017] The operating temperature and the ambient temperature belong to a first sub-data set of the process variable data set.

[0018] The current and the reactor thermal resistance belong to a second sub-data set of the process variable data set.

[0019] Optionally, the denoising processing of the historical data includes screening data in the operation variable data set to obtain an input variable feature set according to mutual information values between each variable in the operation variable data set and a target variable, including:

[0020] performing wavelet transform on the historical data through a wavelet base function, and adjusting a scale factor and a translation factor in the wavelet base function;

[0021] calculating mutual information values between variables in the operation variable set after wavelet transform and the target variable;

[0022] retaining variables with mutual information values greater than a preset threshold value to construct the input variable feature set.

[0023] Optionally, the input variable feature set is input into a prediction model, and cooling efficiency and future energy consumption data are cooperatively predicted in combination with real-time monitoring data to obtain a performance degradation curve of the reactor cooler, including:

[0024] inputting the variable feature set into a prediction model to obtain a prediction output variable, the prediction output variable including predicted cooling efficiency and predicted energy consumption;

[0025] calculating overall mean values of the predicted cooling efficiency and the predicted energy consumption;

[0026] calculating inter-group sum of squares according to the number of observations and the mean values at each time point and the overall mean values, and calculating inter-group mean square according to the inter-group sum of squares;

[0027] calculating a within-group sum of squares according to the mean values of each time point and the predicted output variable, and calculating a within-group mean square according to the within-group sum of squares;

[0028] querying a corresponding significance level in a test critical value table according to the between-group mean square and the within-group mean square, and constructing the performance degradation curve according to the significance level, the predicted cooling efficiency and the predicted energy consumption.

[0029] Optionally, the first temperature difference and the second temperature difference are calculated according to data in the process variable data set, and the method comprises:

[0030] subtracting the ambient temperature from the operating temperature in the first sub-data set to obtain the first temperature difference;

[0031] obtaining a resistance loss according to the current in the second sub-data set and the resistance value of the reactor cooler, and dividing the resistance loss by the reactor thermal resistance to obtain the second temperature difference.

[0032] Optionally, the final reactor cooler temperature difference prediction value is obtained by integrating the predicted reactor cooler temperature difference, and the service life curve of the reactor cooler is calculated in combination with the cooling efficiency of the performance degradation curve, and the method comprises:

[0033] integrating the predicted reactor cooler temperature difference value generated by the support vector regression model and the predicted reactor cooler temperature difference value generated by the prediction model to generate a final reactor cooler temperature difference prediction value;

[0034] calculating the service life curve of the reactor cooler according to the final reactor cooler temperature difference value, the predicted energy consumption and the predicted cooling efficiency by the Monte-Carlo life law, and the formula is:

[0035]

[0036] wherein, T is the service life, A is a constant related to the insulation material grade, a is a preset constant, Tr is the final reactor cooler temperature difference value, y1 is the predicted cooling efficiency, and y2 is the predicted energy consumption.

[0037] Optionally, the performance evaluation level comprises:

[0038] a first degradation level: good performance, long remaining service life, and no immediate maintenance is required;

[0039] a second degradation level: stable performance, medium remaining service life, and regular inspection is recommended;

[0040] a third degradation level: performance starts to degrade, short remaining service life, and planned maintenance is recommended;

[0041] Level 4 degradation: significant performance degradation, very short remaining life, immediate maintenance required;

[0042] The maintenance time and maintenance strategy include:

[0043] Level 1 degradation: monitor performance, no maintenance required;

[0044] Level 2 degradation: schedule inspection within the next operating cycle, including visual inspection and basic functional testing;

[0045] Level 3 degradation: develop a detailed maintenance plan, including cleaning, component replacement and performance testing;

[0046] Level 4 degradation: immediately perform emergency maintenance measures to avoid potential failure and downtime.

[0047] To achieve the above purpose, the second aspect of the present application proposes an electric reactor cooler performance evaluation and predictive maintenance device, comprising:

[0048] A collection module for collecting historical data of the electric reactor cooler in real time using sensors, the historical data including a process variable data set and an operating variable data set;

[0049] A preprocessing module for denoising the historical data, and filtering data in the operating variable data set to obtain an input variable feature set according to mutual information values between each variable in the operating variable data set and a target variable;

[0050] A curve prediction module for inputting the input variable feature set into a prediction model and cooperatively predicting cooling efficiency and future energy consumption data in combination with real-time monitoring data to obtain a performance degradation curve of the electric reactor cooler;

[0051] A temperature difference prediction module for calculating a first temperature difference and a second temperature difference from data in the process variable data set, inputting the first temperature difference and the second temperature difference into a support vector regression model and the prediction model respectively, and generating corresponding predicted electric reactor cooler temperature difference values;

[0052] A life prediction module for integrating the predicted electric reactor cooler temperature difference to obtain a final electric reactor cooler temperature difference prediction value, and combining the cooling efficiency of the performance degradation curve to calculate a service life curve of the electric reactor cooler;

[0053] A performance evaluation module for determining a performance evaluation level of the electric reactor cooler in combination with the performance degradation curve and the service life curve, and determining a maintenance time point and a maintenance strategy according to the performance evaluation level.

[0054] To achieve the above object, the third aspect of the present application provides an electronic device, comprising a processor and a memory connected with the processor;

[0055] The memory stores computer execution instructions.

[0056] The processor executes the computer execution instructions stored in the memory to realize the method according to any one of the first aspect.

[0057] To achieve the above object, the fourth aspect of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by a processor to realize the method according to any one of the first aspect.

[0058] To achieve the above object, the fifth aspect of the present application provides a computer program product, wherein the computer program is executed by a processor to realize the method according to any one of the first aspect.

[0059] The reactor cooler performance evaluation and predictive maintenance method, device, electronic equipment and storage medium provided by the present application realize the performance evaluation grade determination of the reactor cooler through efficient data processing and feature extraction, and improve the accuracy of the performance determination of the reactor cooler.

[0060] Accurate performance degradation prediction: through the Sageformer prediction model combined with real-time monitoring data, the system can cooperatively predict cooling efficiency and energy consumption data, generate performance degradation curves using efficiency-energy consumption ratio and variance analysis method, and provide a scientific basis for performance evaluation.

[0061] Accurate remaining service life estimation: the system uses operating temperature, environmental temperature, current and reactor thermal resistance parameters, predicts temperature difference values through SVR and Sageformer model integration, and calculates service life T curve using the Monte-Carlo life law, thereby improving the accuracy of service life prediction.

[0062] Real-time and early warning capability: the system can respond to the operating state changes of the reactor cooler in real time, quickly diagnose the performance degradation condition, and timely issue early warning signals, thereby providing real-time support for maintenance decision-making.

[0063] Customized maintenance recommendations: according to the performance degradation curve and the service life T curve, the system divides different evaluation grades and proposes corresponding maintenance time points and content recommendations, thereby realizing the customization and optimization of maintenance activities.

[0064] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter in the description. BRIEF DESCRIPTION OF DRAWINGS

[0065] The above and / or additional aspects and advantages of the present application will become apparent and more readily appreciated from the following description, taken in conjunction with the following drawings of exemplary embodiments of the present application, wherein:

[0066] Figure 1 A flowchart of a method for performance evaluation and predictive maintenance of a reactor cooler according to an embodiment of the present application;

[0067] Figure 2 A structural diagram of a device for performance evaluation and predictive maintenance of a reactor cooler according to an embodiment of the present application. DETAILED DESCRIPTION

[0068] Embodiments of the present application are described in detail below with reference to the attached drawing figures, wherein the same or like reference numerals and letters throughout the drawings denote the same or functions elements, and embodiments of the present application described below are exemplary and are intended to explain the present application, and are not to be understood as limiting the present application.

[0069] As a key component in power systems, the stability and reliability of the performance of the reactor cooler are crucial to the safe operation of the entire power grid. However, during long-term operation, the reactor cooler will experience performance degradation and potential failures due to continuous load and environmental factors, which directly affects the stability of the power system and the reliability of power supply. Therefore, developing an effective performance evaluation and predictive maintenance system for the reactor cooler is of great significance for early identification of performance decline trends, prevention of failures, and optimization of maintenance plans.

[0070] Currently, the performance evaluation and predictive maintenance methods for the reactor cooler mainly rely on traditional time-based or periodic maintenance strategies, which are often based on experience and lack in-depth analysis and prediction of the real-time operating state of the equipment. In addition, although some existing predictive maintenance methods use sensor data and statistical analysis techniques, they mostly ignore the complexity and non-linear characteristics of the equipment operating data, making it difficult to achieve early identification and accurate prediction of performance degradation. At the same time, these methods also face challenges such as insufficient feature extraction, limited model generalization ability, and insufficient real-time performance when dealing with large amounts of, multi-dimensional, and high-noise data generated during actual equipment operation.

[0071] The main problems existing in the performance evaluation and predictive maintenance method of the existing reactor cooler include: limited data analysis capability: the traditional method is difficult to effectively process and analyze a large amount of multi-dimensional data generated in the operation of the reactor cooler. Low prediction accuracy: the prediction accuracy and reliability of the existing model for the performance degradation trend still need to be improved. Insufficient real-time performance: the speed of performance evaluation often cannot keep up with the demand of real-time monitoring. Insufficient maintenance strategy optimization: there is a lack of customized and optimized maintenance strategy based on the performance evaluation results.

[0072] To solve the above problems, the embodiment of the present application provides a reactor cooler performance evaluation and predictive maintenance method, Figure 1 A flowchart of a reactor cooler performance evaluation and predictive maintenance method provided by the embodiment of the present application is shown in Figure 1. Figure 1 As shown in the figure, the method comprises the following steps:

[0073] Step 101, real-time collection of historical data of the reactor cooler by using a sensor, wherein the historical data includes a process variable data set and an operating variable data set;

[0074] Step 102, denoising processing of the historical data, screening of data in the operating variable data set to obtain an input variable feature set according to the mutual information value between each variable in the operating variable data set and a target variable;

[0075] Step 103, inputting the input variable feature set into a prediction model, and cooperatively predicting cooling efficiency and future energy consumption data in combination with real-time monitoring data to obtain a performance degradation curve of the reactor cooler;

[0076] Step 104, calculation of a first temperature difference and a second temperature difference from the data in the process variable data set, inputting the first temperature difference and the second temperature difference into a support vector regression model and the prediction model respectively, and generating corresponding predicted reactor cooler temperature difference values;

[0077] Step 105, integration of the predicted reactor cooler temperature difference to obtain a final predicted reactor cooler temperature difference value, and calculation of a service life curve of the reactor cooler in combination with the cooling efficiency of the performance degradation curve;

[0078] Step 106, determination of a performance evaluation grade of the reactor cooler in combination with the performance degradation curve and the service life curve, and determination of a maintenance time point and a maintenance strategy according to the performance evaluation grade.

[0079] Optionally, the process variable data set includes operating temperature, ambient temperature, current, reactor thermal resistance, and the operating variable data set includes flow rate, energy consumption data, operating state and maintenance record.

[0080] The operating temperature and the ambient temperature belong to a first sub-data set of the process variable data set;

[0081] The current and the reactor thermal resistance belong to a second sub-data set of the process variable data set.

[0082] In this embodiment, the data set S1=(V1, V2) is constructed according to the operating temperature and the ambient temperature, the data set S2=(I, Φ) is constructed according to the current and the reactor thermal resistance, and the data set S3=(x1,..., x n ), where n is the number of the operation variable data sets.

[0083] Optionally, the step 102 performs denoising processing on the historical data, and screens the data in the operation variable data set according to the mutual information values between each variable in the operation variable data set and the target variable to obtain an input variable feature set, including:

[0084] Wavelet transformation is performed on the historical data through a wavelet base function, and a scale factor and a translation factor in the wavelet base function are adjusted;

[0085] The mutual information values between the variables in the operation variable set after the wavelet transformation and the target variable are calculated;

[0086] Variables with the mutual information values greater than a preset threshold value are reserved to construct the input variable feature set.

[0087] In this embodiment, the wavelet transformation algorithm is suitable for analyzing non-stationary signals, is suitable for capturing instantaneous events and local characteristics of signals, and is convenient for understanding and analyzing signal characteristics, and the specific implementation process is as follows:

[0088] f(s) is a signal of the process variable data set and the operation variable data set, and an expression of f(s) is obtained through wavelet transformation:

[0089]

[0090] Ψ(s) is a wavelet base, is a conjugate function of Ψ(s).

[0091] In the wavelet transformation process, the wavelet base function needs to be stretched and translated to cooperate with signal analysis, and after the wavelet base function is translated, there is:

[0092]

[0093] a represents a scale factor, affects the waveform width of Ψ(s), and a≠0; b represents a translation factor, and a, b∈R.

[0094] The wavelet transform has the characteristic of multi-resolution analysis. The wavelet base function is stretched and translated according to the scale factor a and the translation factor b, so that wavelet bases of different widths can be obtained to match any local time domain position of the signal, so as to achieve the purpose of obtaining the local time domain information of the signal.

[0095] The wavelet reconstruction signal (inverse transform) expression is as follows:

[0096]

[0097] Wherein, Ψf(a,b) is the coefficient of wavelet transform, that is, the inner product of f(s) and wavelet base function Ψ a,b (s), and C is a constant.

[0098] In this embodiment, the mutual information value (Mutual Information, MI) is a measure of the mutual dependence between two random variables, which can be used to measure the correlation between the features and the target variable. The basic method of calculating the mutual information value is as follows:

[0099]

[0100] Wherein, I(X;Y) is the mutual information value between X and Y, p(x,y) and p(x,y) are the joint probability density functions of X and Y respectively, and p(x) and p(y) are the marginal probability density functions of X and Y respectively.

[0101] The greater the mutual information value, the greater the contribution of the feature to the target variable, and the stronger the prediction ability. By selecting the feature with the highest mutual information value, the most relevant feature to the target variable can be extracted, thereby improving the performance of the machine learning model.

[0102] The operating variable set after wavelet transform is denoted as S3'=(x1,...,x n The mutual information MI is used for feature screening. The mutual information measures the mutual dependence between two variables, and can be used to identify the most relevant features to the output variable. The steps of using mutual information for multivariate feature selection are as follows:

[0103] The input variable is S3', and the output variable is the cooling efficiency and energy consumption, denoted as Y=(y1,y2). The mutual information value MI(S3',Y) between them is calculated, and the calculation formula is as follows:

[0104]

[0105] Wherein, P(x,y) is the joint probability of S3' taking x and the output variable Y taking value y, and P(x) and P(y) are the marginal probabilities of x and y respectively.

[0106] According to the size of the mutual information value, the input variables are sorted, the larger the mutual information value, the stronger the dependence of the input variable on the output variable, and a threshold is set to select the top-ranked input variables to construct the input variable feature set S=(x1, x3,..., x n-3 ) into a prediction model to predict the cooling efficiency and future energy consumption.

[0107] Optionally, the step 103 inputs the input variable feature set into a prediction model and cooperates with real-time monitoring data to jointly predict the cooling efficiency and future energy consumption data, to obtain a performance degradation curve of the reactor cooler, including:

[0108] The variable feature set is input into a prediction model to obtain a predicted output variable, including a predicted cooling efficiency and a predicted energy consumption;

[0109] The overall mean of the predicted cooling efficiency and the predicted energy consumption is calculated;

[0110] The between-group sum of squares is calculated according to the number of observations and the mean at each time point, and the between-group mean square is calculated according to the between-group sum of squares;

[0111] The within-group sum of squares is calculated according to the mean at each time point and the predicted output variable, and the within-group mean square is calculated according to the within-group sum of squares;

[0112] According to the between-group mean square and the within-group mean square, the corresponding significance level is queried in a test critical value table, and the performance degradation curve is constructed according to the significance level, the predicted cooling efficiency and the predicted energy consumption.

[0113] In this embodiment, the prediction model is a SageFormer model, including:

[0114] ① Input layer: receiving the input variable feature set S=(x1, x3,..., x n-3 ) and real-time monitoring data, dividing them into multiple small blocks, not only improving the calculation efficiency and memory usage efficiency of the model, but also enhancing the ability to capture local patterns, and maintaining the learning of long-distance dependence through parallel processing and self-attention mechanism, thereby providing flexibility and adaptability for the SageFormer model in long-term multivariate time series prediction tasks.

[0115] ② Graph structure learning layer: equivalent to a special "hidden layer", which represents the complex relationship between sequences through the learned graph structure. This layer uses a graph neural network (GNN) to capture the dependence between sequences.

[0116] ③ Sequence-aware global Token layer: As a bridge between the input layer and the graph structure layer, global Token is used to capture the global statistical properties of each sequence and enhance the interaction between sequences through the graph structure layer.

[0117] ④ Iterative message passing layer: This is the core part of the model, through the iterative process of graph aggregation and temporal encoding, continuously updating the representation of sequences to integrate information from other sequences and capture temporal dependencies.

[0118] ⑤ Transformer encoder block (TEB): As part of the hidden layer, it uses self-attention mechanisms to handle temporal dependencies within sequences and further integrates information from graph aggregation layers.

[0119] ⑥ Output layer: The use of prediction heads has the advantage of a simplified linear decoder, reducing the complexity and computational cost of the model, and improving the efficiency and accuracy of prediction.

[0120] The significance of the difference between the cooling efficiency and future energy consumption predicted by the model is evaluated using the analysis of variance method, with the following steps:

[0121] Calculate the overall mean of cooling efficiency and future energy consumption:

[0122]

[0123] Where N is the total number of output variables, and k represents the kth output variable.

[0124] Calculate the between-group sum of squares SSB:

[0125]

[0126] Where m is the number of time points, u j is the number of observations at the jth time point, is the mean at the jth time point.

[0127] Calculate the within-group sum of squares SSW:

[0128]

[0129] Where Y ij k is the kth output variable, the ith observation at the jth time point.

[0130] Calculate the between-group and within-group mean squares (MSB and MSW):

[0131]

[0132] Calculate the F statistic:

[0133]

[0134] determine the significance level, determine the p-value by looking up the F-distribution table or using statistical software; when the p-value is less than the significance level, it is considered that the mean of the cooling efficiency or energy consumption at least at one time point is significantly different from other time points, and the performance degradation curve is constructed by combining the efficiency-energy consumption ratio:

[0135]

[0136] Optionally, the step 104 calculates the first temperature difference and the second temperature difference according to the data in the process variable data set, including:

[0137] Subtract the operating temperature in the first sub-data set from the ambient temperature to obtain the first temperature difference;

[0138] According to the current and the reactance cooler resistance value in the second sub-data set, the resistance loss is obtained, and the resistance loss is divided by the reactor thermal resistance to obtain the second temperature difference.

[0139] In this embodiment, the constructed S1=(V1, V2) and the constructed S2=(I, Φ) are subjected to wavelet transform to obtain data sets S1'=(V1', V2') and S2'=(I', Φ'), and the temperature difference of the reactance cooler is calculated respectively.

[0140] The input first temperature difference is calculated by the data set S1' according to the following formula:

[0141] Tr1=V1'-V2' (12)

[0142] The second temperature difference is calculated by the data set S2', first calculate the resistance loss: P=(I') 2 R, where R is the resistance of the reactance cooler; the loss Q in the reactor is mainly in the form of heat dissipation, so the heat generated can be calculated by the resistance loss, which is directly related to the resistance loss P, that is, Q=P; the thermal resistance Φ is a parameter describing the difficulty of heat transfer from the heat source to the surrounding environment, and the second temperature difference formula is as follows:

[0143]

[0144] Since the calculation process of the second temperature difference is complex, the Sageformer model is used to predict the future reactance cooler temperature difference value 2; the first temperature difference is predicted by using the support vector regression (Support Vector Regression, SVR) model, and the SVR model process is as follows:

[0145] ① The input layer is used to receive the input variable set 1, which includes a plurality of first temperature differences;

[0146] ②The feature mapping layer maps the input variable set 1 to a high-dimensional space through a mapping function;

[0147] ③SVR uses a kernel function to calculate the similarity between two points in the original feature space or high-dimensional space, which is expressed as follows:

[0148]

[0149] where (β i -β i * ) represents the Lagrange multiplier of the dual space transformation, O(Tr1,Tr1 i ) represents the kernel function used to solve the quadratic equation, and b represents the bias.

[0150] ④The output layer outputs the future reactor cooler temperature difference value.

[0151] Optionally, the step 105 integrates the predicted reactor cooler temperature difference to obtain a final reactor cooler temperature difference prediction value, and calculates a service life curve of the reactor cooler in combination with the cooling efficiency of the performance degradation curve, including:

[0152] The predicted reactor cooler temperature difference value generated by the support vector regression model and the predicted reactor cooler temperature difference value generated by the prediction model are integrated to generate a final reactor cooler temperature difference prediction value;

[0153] According to the final reactor cooler temperature difference value, the predicted energy consumption and the predicted cooling efficiency, the service life curve of the reactor cooler is calculated through the Monte-Carlo life law, and the formula is:

[0154]

[0155] where T is the service life, A is a constant related to the insulation material grade, α is a preset constant, Tr is the final reactor cooler temperature difference value, y1 is the predicted cooling efficiency, and y2 is the predicted energy consumption.

[0156] The final reactor cooler temperature difference prediction value is obtained by Blending the predicted data, and Blending integrated learning mainly includes a meta-learning layer and a generalized model layer (GM layer).

[0157] The core role of the meta-learning layer is to take the prediction results of multiple base models as input features, and make a final decision by learning the relationship between these predictions and actual outputs. This method not only improves the generalization ability and prediction accuracy of the model, but also reduces the risk of overfitting and the possibility of information leakage.

[0158] The GM layer uses the prediction results of the meta-learning layer as input features to construct the final prediction results. This layer optimizes and adjusts the prediction weights of each base model to improve the overall prediction accuracy and generalization ability. The design of the GM layer allows it to capture the relationship between different models and reduce uncertainty and potential bias through ensemble methods, providing more robust performance in complex prediction tasks.

[0159] The final reactor cooler temperature difference value Tr is obtained by integrating the prediction results of future reactor group cooler temperature difference value 1 and future reactor group cooler temperature difference value 2 based on Blending ensemble learning.

[0160] The final reactor cooler temperature difference value combines the predicted cooling efficiency in the performance degradation curve prediction module to calculate the service life of the insulating part material of the reactor cooler, i.e., the reactor cooler service life T curve, through the Monte Carlo life law, as follows:

[0161]

[0162] where A is a constant related to the grade of the insulating material, a is a constant generally equal to 0.88, and Tr is the final reactor cooler temperature difference value, is the efficiency-energy consumption ratio.

[0163] Optionally, the performance evaluation level includes:

[0164] First degradation level: good performance, long remaining service life, no immediate maintenance required;

[0165] Second degradation level: stable performance, medium remaining service life, recommended for regular inspection;

[0166] Third degradation level: performance degradation, short remaining service life, recommended for planned maintenance;

[0167] Fourth degradation level: significant performance degradation, very short remaining service life, immediate maintenance required;

[0168] The maintenance time and maintenance strategy include:

[0169] First degradation level: monitor performance, no maintenance required;

[0170] Second degradation level: schedule inspection within the next operating cycle, including visual inspection and basic functional testing;

[0171] Third degradation level: develop a detailed maintenance plan, including cleaning, component replacement, and performance testing;

[0172] Fourth degradation level: immediately perform emergency maintenance measures to avoid potential failures and downtime.

[0173] The application proposes an electric reactor cooler performance evaluation and predictive maintenance system, aiming to optimize the operation monitoring and maintenance strategy of the electric reactor cooler. The system consists of three key modules: performance degradation prediction, remaining useful life estimation and evaluation warning. In the performance degradation prediction module, the system collects real-time operation parameters of the cooler through sensors, such as temperature, flow rate, energy consumption, etc., and pre-processes and extracts features from the data through wavelet transform and mutual information algorithm. Using the Sageformer model, combined with real-time data, the cooling efficiency and energy consumption are predicted, and then the performance degradation curve is generated. In the remaining useful life estimation module, the system calculates the operating temperature difference of the cooler, and uses the SVR and Sageformer models for prediction, and obtains the final temperature difference value through the Blending integration method. Combined with the cooling efficiency, the expected service life of the electric reactor cooler is calculated according to the Monte-Shegel life law. Finally, the evaluation warning module divides the performance of the cooler into four levels according to the performance degradation curve and the service life T curve, and puts forward targeted maintenance suggestions accordingly, so as to realize preventive maintenance and improve the operation reliability and maintenance efficiency of the electric reactor cooler.

[0174] In order to realize the above-mentioned embodiments, the application further proposes an electric reactor cooler performance evaluation and predictive maintenance device. Figure 2 A structural schematic diagram of an electric reactor cooler performance evaluation and predictive maintenance device provided by an embodiment of the application is shown in Figure 2 As shown in the figure, the device comprises:

[0175] A collection module is configured to collect historical data of the electric reactor cooler in real time by using sensors, wherein the historical data comprises a process variable data set and an operation variable data set.

[0176] A pre-processing module is configured to perform denoising processing on the historical data, and to filter data in the operation variable data set to obtain an input variable feature set according to mutual information values between each variable in the operation variable data set and a target variable.

[0177] A curve prediction module is configured to input the input variable feature set into a prediction model, and to cooperatively predict cooling efficiency and future energy consumption data in combination with real-time monitoring data, so as to obtain a performance degradation curve of the electric reactor cooler.

[0178] A temperature difference prediction module is configured to calculate a first temperature difference and a second temperature difference according to data in the process variable data set, and to input the first temperature difference and the second temperature difference into a support vector regression model and the prediction model respectively and generate corresponding predicted electric reactor cooler temperature difference values.

[0179] a life prediction module configured to integrate the predicted reactor cooler temperature difference to obtain a final reactor cooler temperature difference prediction value, and to calculate a life curve of the reactor cooler in combination with the cooling efficiency of the performance degradation curve;

[0180] a performance evaluation module configured to determine a performance evaluation level of the reactor cooler in combination with the performance degradation curve and the life curve, and to determine a maintenance time point and a maintenance strategy according to the performance evaluation level.

[0181] To achieve the above-mentioned embodiments, the present application further provides an electronic device, comprising a processor and a memory connected with the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to realize the method provided by the foregoing embodiments.

[0182] To achieve the above-mentioned embodiments, the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by a processor to realize the method provided by the foregoing embodiments.

[0183] To achieve the above-mentioned embodiments, the present application further provides a computer program product, comprising a computer program, wherein the computer program is executed by a processor to realize the method provided by the foregoing embodiments.

[0184] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the present application comply with relevant laws and regulations and do not violate public order and good customs.

[0185] It should be noted that the personal information from the user should be collected for legal and reasonable purposes, and should not be shared or sold outside these legal uses. In addition, such collection / sharing should be carried out after the user's informed consent is received, including but not limited to informing the user to read the user agreement / user notice before the user uses the function, and signing the agreement / authorization including authorization of relevant user information. In addition, any necessary steps should be taken to protect and ensure access to such personal information data, and to ensure that other people with access to personal information data comply with their privacy policy and processes.

[0186] The present application is expected to provide an embodiment in which the user can selectively prevent the use or access of personal information data. That is, the present disclosure is expected to provide hardware and / or software to prevent or prevent access to such personal information data. Once the personal information data is no longer needed, the risk is minimized by limiting data collection and deleting data. In addition, such personal information is de-identified to protect the privacy of the user, if applicable.

[0187] In the foregoing detailed description, reference is made to descriptive terms such as "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" etc. for describing various embodiments of the application. These descriptive terms are used for the purpose of the description and are not meant to limit or restrict the scope of the application. The use of these terms does not imply that the described feature is essential to the application or that it will be combined with other features as described to achieve the advantages described. The scope of the application is defined by the appended claims.

[0188] Furthermore, the terms "first", "second", "third", "fourth", "fifth" and the like in the description and in the claims, are used for distinguishing between similar elements and not necessarily presented chronologically. It is to be understood that the describing of a certain feature as "first", "second", "third", "fourth", "fifth" etc. does not mean that the same feature will not be described as such at a later stage. The terms "first", "second", "third", "fourth", "fifth" etc. are used to distinguish between different features, and do not mean an ordering of the features in time or in any other way. The terms "first", "second", "third", "fourth", "fifth" etc. are used to distinguish between different features, and do not mean an ordering of the features in time or in any other way.

[0189] Any process or method described in a flowchart or otherwise described herein can be understood as representing code modules, segments, or portions of code that include one or more executable instructions for implementing specific logic functions (or steps) of the process, and alternate implementations are possible. In this description and in the claims, the terms "code modules", "code segments", or "code portions" are used to generally refer to information that is a tangible representation of one or more

[0190] The logic and / or steps represented in flow diagrams or otherwise described herein, for example, can be considered as a sequence of executable instructions, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can be a product of the manufacturing and / or processing. The computer-readable medium can include, but is not limited to, the following: an electronic connection (an electronic device having one or more wires), a portable computer diskette (a magnetic device), a RAM (random access memory), a ROM (read-only memory), an EPROM (erasable programmable ROM) or a Flash memory, an optical fiber, and a portable CD ROM. In addition, the computer-readable medium can even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example via the optical scanner of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and stored in a computer memory.

[0191] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the above embodiments, various steps or methods can be implemented in software or firmware that is stored in memory and executed by a suitable instruction execution system. As such, in some embodiments, the steps or methods can be implemented in a combination of hardware and software. If implemented in hardware, as in another embodiment, any of the above techniques can be implemented with or without the use of a programmable digital signal processor (DSP) or other programmable device. In some embodiments, the steps or methods can be implemented using a combination of different hardware devices.

[0192] Those of skill in the art would understand that information and signals can be represented using any of a variety of technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that can be referenced throughout the above description can be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0193] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing module, or each of the units can be physically present separately, or two or more units can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0194] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A method of performance assessment and predictive maintenance of a reactor cooler, characterized in that, The method comprises the following steps: Real-time collection of historical data of the reactor cooler by using a sensor, wherein the historical data comprises a process variable data set and an operating variable data set; Denoising processing of the historical data, screening of data in the operating variable data set according to mutual information values between each variable in the operating variable data set and a target variable to obtain an input variable feature set; Inputting of the input variable feature set into a prediction model and cooperative prediction of cooling efficiency and future energy consumption data in combination with real-time monitoring data to obtain a performance degradation curve of the reactor cooler; Calculation of a first temperature difference and a second temperature difference from data in the process variable data set, inputting of the first temperature difference and the second temperature difference into a support vector regression model and the prediction model respectively and generation of corresponding predicted reactor cooler temperature difference values; Integration of the predicted reactor cooler temperature difference to obtain a final predicted reactor cooler temperature difference value and calculation of a service life curve of the reactor cooler in combination with cooling efficiency of the performance degradation curve; Determination of a performance evaluation grade of the reactor cooler in combination with the performance degradation curve and the service life curve and determination of a maintenance time point and a maintenance strategy according to the performance evaluation grade; The inputting of the input variable feature set into the prediction model and the cooperative prediction of the cooling efficiency and the future energy consumption data in combination with the real-time monitoring data to obtain the performance degradation curve of the reactor cooler comprises: Inputting of the variable feature set into the prediction model to obtain a predicted output variable, wherein the predicted output variable comprises a predicted cooling efficiency and a predicted energy consumption; Calculation of overall mean values of the predicted cooling efficiency and the predicted energy consumption; Calculation of between-group sum of squares from the number of observations and the mean values at each time point and the overall mean values and calculation of between-group mean squares from the between-group sum of squares; Calculation of within-group sum of squares from the mean values at each time point and the predicted output variable and calculation of within-group mean squares from the within-group sum of squares; Querying of corresponding significance levels in a test critical value table from the between-group mean squares and the within-group mean squares, construction of the performance degradation curve from the significance levels, the predicted cooling efficiency and the predicted energy consumption.

2. The method of claim 1, wherein, The process variable data set comprises operating temperature, ambient temperature, current and reactor thermal resistance, and the operating variable data set comprises flow rate, energy consumption data, operating state and maintenance records; The operating temperature and the ambient temperature belong to a first sub-data set of the process variable data set; The current and the reactor thermal resistance belong to a second sub-data set of the process variable data set.

3. The method of claim 2, wherein, The denoising processing of the historical data, the screening of data in the operating variable data set according to mutual information values between each variable in the operating variable data set and a target variable to obtain an input variable feature set comprises: Wavelet transformation of the historical data by using a wavelet base function and adjustment of scale factors and translation factors in the wavelet base function; Calculation of mutual information values between variables in the operating variable set after the wavelet transformation and a target variable; Retention of variables with the mutual information values greater than a preset threshold value to construct the input variable feature set.

4. The method of claim 3, wherein, The first temperature difference and the second temperature difference are calculated according to data in the process variable data set, including: The operating temperature in the first sub-data set is subtracted from the ambient temperature to obtain the first temperature difference; The resistance loss is obtained according to the current in the second sub-data set and the reactance cooler resistance value, and the second temperature difference is obtained by dividing the resistance loss by the reactor thermal resistance.

5. The method of claim 4, wherein, The final reactance cooler temperature difference prediction value is obtained by integrating the predicted reactance cooler temperature difference, and the service life curve of the reactance cooler is calculated in combination with the cooling efficiency of the performance degradation curve, including: The final reactance cooler temperature difference prediction value is obtained by integrating the predicted reactance cooler temperature difference generated by the support vector regression model and the predicted reactance cooler temperature difference generated by the prediction model; According to the final reactance cooler temperature difference value, the predicted energy consumption and the predicted cooling efficiency, the service life curve of the reactance cooler is calculated by the Monte-Carlo life law, and the formula is: wherein, T is the service life, A is a constant related to the insulation material grade, is a preset constant, Tr is the final reactor cooler temperature difference value, y 1 is the predicted cooling efficiency, y 2 is the predicted energy consumption.

6. The method of claim 5, wherein, The performance evaluation level includes: First degradation level: good performance, long remaining service life, no immediate maintenance required; Second degradation level: stable performance, medium remaining service life, recommended for regular inspection; Third degradation level: performance degradation, short remaining service life, recommended for planned maintenance; Fourth degradation level: significant performance degradation, very short remaining service life, immediate maintenance required; The maintenance time and maintenance strategy include: First degradation level: monitor performance, no maintenance required; Second degradation level: schedule inspection within the next operating cycle, including visual inspection and basic function test; Third degradation level: develop detailed maintenance plan, including cleaning, component replacement and performance test; Fourth degradation level: immediately perform emergency maintenance measures to avoid potential failure and downtime.

7. A reactor cooler performance evaluation and predictive maintenance device, characterized by It includes: A collection module for collecting historical data of the reactor cooler in real time using sensors, the historical data including a process variable data set and an operating variable data set; A preprocessing module for denoising the historical data, and screening data in the operating variable data set to obtain an input variable feature set according to mutual information values between each variable in the operating variable data set and a target variable; A curve prediction module for inputting the input variable feature set into a prediction model and cooperatively predicting cooling efficiency and future energy consumption data in combination with real-time monitoring data to obtain a performance degradation curve of the reactor cooler; A temperature difference prediction module for calculating a first temperature difference and a second temperature difference according to data in the process variable data set, and inputting the first temperature difference and the second temperature difference into a support vector regression model and the prediction model respectively to generate corresponding predicted reactor cooler temperature difference values; A life prediction module for integrating the predicted reactor cooler temperature difference to obtain a final reactor cooler temperature difference prediction value, and calculating a service life curve of the reactor cooler in combination with the cooling efficiency of the performance degradation curve. The performance evaluation module is configured to determine a performance evaluation level of the reactor cooler by combining the performance degradation curve and the service life curve, and determine a maintenance time point and a maintenance strategy according to the performance evaluation level. The curve prediction module comprises: A prediction submodule configured to input the variable feature set into a prediction model to obtain a predicted output variable, the predicted output variable comprising a predicted cooling efficiency and a predicted energy consumption; A mean value calculation submodule configured to calculate an overall mean value of the predicted cooling efficiency and the predicted energy consumption; An inter-group mean square calculation submodule configured to calculate an inter-group sum of squares according to the number of observations at each time point, the mean value, and the overall mean value, and calculate an inter-group mean square according to the inter-group sum of squares; An intra-group mean square calculation submodule configured to calculate an intra-group sum of squares according to the mean value at each time point and the predicted output variable, and calculate an intra-group mean square according to the intra-group sum of squares; A curve construction submodule configured to query a corresponding significance level in a test critical value table according to the inter-group mean square and the intra-group mean square, and construct the performance degradation curve according to the significance level, the predicted cooling efficiency, and the predicted energy consumption.

8. An electronic device, comprising: comprise: a processor, and a memory connected to the processor in communication; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by the processor to implement the method according to any one of claims 1-6.

Images