Method and device for predicting service life of chemical filter

Abstract

The invention relates to the technical field of life prediction, and discloses a method and device for predicting the service life of a chemical filter, and the method comprises the steps: collecting the historical multi-dimensional use state data of the chemical filter, and carrying out the standardization preprocessing, and obtaining a time sequence feature data set; carrying out load feature clustering analysis to obtain a filter load mode feature vector; constructing a double-layer performance attenuation prediction model, and outputting a target performance attenuation prediction sequence through physical attenuation coefficient calculation and deep learning network training; performing filter state probability transition calculation to obtain a state transition prediction sequence; performing multi-target joint optimization on the state transition prediction sequence, and calculating to obtain an optimal operation control parameter; and real-time multi-dimensional use state data is collected based on the optimal operation control parameters, parameter optimization is performed on the double-layer performance attenuation prediction model, a service life prediction model is obtained, and the method improves the accuracy and reliability of chemical filter service life prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of life prediction, and in particular to a method and device for predicting the service life of a chemical filter. Background Art

[0002] Traditional chemical filter life prediction methods mainly rely on expert experience and simple mathematical and statistical models. It is difficult to accurately capture the performance degradation law of filters under complex working conditions, resulting in insufficient prediction accuracy and inability to provide reliable support for equipment maintenance decisions.

[0003] In recent years, with the development of industrial sensing technology and data acquisition systems, the operating status data of chemical filters have shown multi-dimensional and large-scale characteristics. However, these data often have complex time series correlation, variable load patterns, severe noise interference and other problems. The traditional single modeling method is difficult to effectively use multi-source heterogeneous data for accurate prediction, especially when the operating conditions change drastically, the generalization ability of the prediction model decreases significantly. In addition, the performance attenuation process of chemical filters is affected by both physical mechanisms and environmental factors. Existing prediction methods either rely too much on mechanism models and ignore actual operating data, or completely adopt data-driven methods without physical constraints, resulting in a large deviation between the prediction results and actual engineering needs. Summary of the invention

[0004] The invention provides a method and device for predicting the service life of a chemical filter, which are used to improve the accuracy and reliability of the prediction of the service life of the chemical filter.

[0005] In a first aspect, the present invention provides a method for predicting the service life of a chemical filter, the method for predicting the service life of a chemical filter comprising: Collect historical multi-dimensional usage status data of chemical filters and perform standardized preprocessing to obtain a time series feature data set; Performing load feature clustering analysis on the time series feature data set to obtain a filter load pattern feature vector; A double-layer performance attenuation prediction model is constructed based on the filter load pattern feature vector, and a target performance attenuation prediction sequence is output through physical attenuation coefficient calculation and deep learning network training; Performing filter state probability transfer calculation on the target performance attenuation prediction sequence to obtain a state transfer prediction sequence; Performing multi-objective joint optimization on the state transition prediction sequence and calculating the optimal operation control parameters; Based on the optimal operation control parameters, real-time multi-dimensional usage status data is collected, and the parameters of the double-layer performance degradation prediction model are tuned to obtain a service life prediction model.

[0006] In a second aspect, the present invention provides a device for predicting the service life of a chemical filter, the device for predicting the service life of a chemical filter comprising: The acquisition module is used to collect the historical multi-dimensional usage status data of the chemical filter and perform standardized preprocessing to obtain a time series feature data set; A clustering module, used for performing load feature clustering analysis on the time series feature data set to obtain a filter load pattern feature vector; A construction module is used to construct a double-layer performance attenuation prediction model based on the filter load pattern feature vector, and output a target performance attenuation prediction sequence through physical attenuation coefficient calculation and deep learning network training; A calculation module, used for performing filter state probability transfer calculation on the target performance attenuation prediction sequence to obtain a state transfer prediction sequence; An optimization module, used for performing multi-objective joint optimization on the state transition prediction sequence and calculating the optimal operation control parameters; A parameter tuning module is used to collect real-time multi-dimensional usage status data based on the optimal operation control parameters, and to perform parameter tuning on the double-layer performance attenuation prediction model to obtain a service life prediction model.

[0007] The third aspect of the present invention provides a device for predicting the service life of a chemical filter, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the device for predicting the service life of a chemical filter executes the above-mentioned method for predicting the service life of a chemical filter.

[0008] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned method for predicting the service life of a chemical filter.

[0009] In the technical solution provided by the present invention, a double-layer performance degradation prediction model is constructed to combine physical mechanism constraints with deep learning, thereby improving the model accuracy while ensuring the interpretability of the prediction; a load feature clustering analysis method with a dual time window is adopted to realize the accurate identification of load patterns of filters at different time scales, thereby enhancing the model's adaptability to changes in working conditions; a state probability transfer calculation method based on a dual hidden Markov prediction model is used to accurately capture the dynamic characteristics of filter performance degradation; a multi-objective joint optimization strategy including life maximization, cost minimization and efficiency maximization is designed to realize intelligent regulation of filter operating parameters; through a dynamic parameter tuning mechanism, the prediction model has the ability to adaptively update, thereby ensuring the stability of the model's prediction performance during long-term operation; the present invention improves the accuracy and reliability of filter life prediction through multi-level feature analysis and prediction strategies.

[0010] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0011] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic diagram of an embodiment of a method for predicting the service life of a chemical filter in an embodiment of the present invention; Figure 2 A schematic diagram of an embodiment of a device for predicting the service life of a chemical filter in an embodiment of the present invention; Figure 3 It is a schematic diagram of an embodiment of a device for predicting the service life of a chemical filter in an embodiment of the present invention. DETAILED DESCRIPTION

[0013] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0014] The terms "including" and "having" and any variations thereof mentioned in the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device end including a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or device ends.

[0015] To facilitate understanding of this embodiment, a method for predicting the service life of a chemical filter disclosed in an embodiment of the present invention is first described in detail. Figure 1 As shown, the method comprises the following steps: 101. Collect historical multi-dimensional usage status data of chemical filters and perform standardized preprocessing to obtain a time series feature data set; It is understandable that the execution subject of the present invention may be a prediction device for the service life of a chemical filter, or may be a terminal or a server, which is not specifically limited here. The embodiment of the present invention is described by taking a server as the execution subject as an example.

[0016] Specifically, the historical multi-dimensional usage status data of the chemical filter is collected, including the monitoring of multiple key parameters, such as inlet pressure, outlet pressure, flow rate, filter medium concentration, filter temperature, filter efficiency, and filter saturation. These data together constitute the comprehensive usage status of the filter. The historical multi-dimensional usage status data is cleaned to remove outliers and noise, fill in missing values, ensure the integrity and accuracy of the data, and obtain a preprocessed data set. The preprocessed data set is standardized and mapped. Different state parameters have different dimensions and numerical ranges. These parameters are uniformly converted into a standard interval to eliminate the impact caused by different dimensions, so that each parameter is comparable in subsequent model construction. The standardization methods include Z-score standardization and Min-Max normalization, which effectively convert the data into a uniform distribution, making the subsequent analysis and modeling process more stable and effective. The standardized data set is divided into time windows, and the data is divided into multiple time periods to capture the dynamic characteristics that change over time. When dividing the time window, an overlapping time window is set, that is, there is a certain overlap in each time period to ensure that the continuity and change trend of the data are captured. In this way, multiple time series data segments are obtained, representing the usage status of the filter in different time periods. The time series data segments are labeled to convert them into time series feature data sets. This process relies on expert knowledge or previous experience to mark the characteristic status of each time period, such as the normal working state, performance degradation state or near saturation state of the filter.

[0017] 102. Perform load feature clustering analysis on the time series feature data set to obtain a filter load pattern feature vector; Specifically, the cumulative filtering amount of the first time window and the second time window is calculated for the time series feature data set, and the two time windows are set to 24 hours and 48 hours respectively. Through these time windows, the first load time series index and the second load time series index are obtained to reflect the load status of the filter in different time periods. The first load time series index and the second load time series index are calculated by segmentation threshold. The first load time series index is divided into a first low load segment, a first medium load segment and a first high load segment, and the second load time series index is divided into a second low load segment, a second medium load segment and a second high load segment. The segmentation process more clearly identifies the performance of the filter under different load conditions, and obtains the first load segmentation result and the second load segmentation result. Based on the segmentation results, the first load segmentation result and the second load segmentation result are respectively extracted by feature value, including calculating the first pressure change rate, the first temperature distribution feature, the first efficiency decay rate and the second pressure change rate, the second temperature distribution feature and the second efficiency decay rate. Through calculation, the first feature parameter set and the second feature parameter set are obtained. A double-layer feature association matrix is ​​constructed based on the first feature parameter set and the second feature parameter set to capture the association relationship between different features and obtain a multi-scale feature association result. The principal component analysis is performed on the multi-scale feature association results to extract the feature combination of the first principal component and the second principal component to form a multi-dimensional dimension reduction feature set. The multi-dimensional dimension reduction feature set is subjected to double clustering calculation to obtain the first cluster center and the second cluster center respectively. Through these two cluster centers, the first distance matrix and the second distance matrix are established to perform pattern discrimination. The process of pattern discrimination effectively classifies the load pattern and obtains multi-level load pattern labels to reflect the load characteristics of the filter under different working conditions. The multi-level load pattern labels are combined with the multi-dimensional dimension reduction feature set, and the filter load pattern feature vector is finally obtained through the cascade transformation of the first feature map and the second feature map.

[0018] 103. A double-layer performance attenuation prediction model is constructed based on the filter load pattern feature vector, and the target performance attenuation prediction sequence is output through physical attenuation coefficient calculation and deep learning network training; Specifically, the filter load mode feature vector is divided into a first feature sub-vector and a second feature sub-vector. The first feature sub-vector includes the pressure change rate and the efficiency decay rate, which directly reflect the load of the filter during operation; the second feature sub-vector contains the temperature distribution characteristics and the saturation change rate, which affect the working performance of the filter. According to the first feature sub-vector, a physical attenuation layer is constructed. This layer consists of an attenuation parameter calculation unit and a physical constraint unit. In the attenuation parameter calculation unit, a polynomial fitting structure is adopted, and a third-order polynomial is used for parameter fitting. Through this method, the attenuation behavior of the filter under different load conditions is effectively described. At the same time, an adaptive weight module is set to dynamically adjust the weight of the attenuation parameter according to the feedback under different working conditions to ensure that the model can adapt flexibly. The physical constraint unit uses a boundary constraint structure to ensure that the prediction results are consistent with physical reality. The maximum pressure drop constraint and the minimum efficiency constraint are introduced in the physical constraint unit to ensure that the filter does not exceed its actual working range when predicting performance decay. After the construction of the physical attenuation layer is completed, the attenuation parameter calculation unit is trained. During the training process, the first feature sub-vector is input into the physical attenuation layer. By calculating the attenuation coefficient, the first performance attenuation prediction sequence is obtained, which contains the performance attenuation trend of the filter in the future. The deep learning layer is constructed based on the second feature sub-vector and the first performance attenuation prediction sequence. This layer mainly consists of two modules: the time series feature extractor and the performance predictor. The time series feature extractor adopts the bidirectional long short-term memory network (Bi-LSTM) structure to capture the time series dependency in the time series data. The time series feature extractor contains three layers of bidirectional LSTM units, each with 128 hidden nodes, and a Dropout layer is set between the layers to reduce the risk of overfitting. The performance predictor adopts the residual attention network structure, which can effectively extract deep features. This module consists of five residual blocks, each of which contains two fully connected layers and a channel attention module. The weight of key features is enhanced through the attention mechanism to improve the prediction ability of the model. The first performance attenuation prediction sequence and the second feature sub-vector are input into the deep learning layer for training. The model generates the second performance attenuation prediction sequence by learning the complex relationship between the two. This sequence supplements the expected performance change information of the filter under different working conditions. In order to improve the accuracy and reliability of the prediction, a fusion optimization layer is constructed. This layer contains an adaptive weight module and a timing calibration module, which dynamically weights and fuses the first performance decay prediction sequence and the second performance decay prediction sequence to form the final performance prediction result. The adaptive weight module is updated online according to the historical performance decay data of the chemical filter to ensure that the model remains adaptable under new data. The timing calibration module is used to align the fusion results in time to ensure that the prediction results at different time points can be reasonably connected.Finally, the output results of the fusion optimization layer are reconstructed into a target performance attenuation prediction sequence through time series reconstruction, reflecting the future performance trend of the filter.

[0019] 104. Calculate the filter state probability transfer for the target performance attenuation prediction sequence to obtain a state transfer prediction sequence; Specifically, the target performance decay prediction sequence is segmented according to the time window, divided into the first time window and the second time window, and the first segmented sequence samples and the second segmented sequence samples are obtained, which respectively reflect the change characteristics of the filter performance under different time scales. The first segmented sequence samples and the second segmented sequence samples are subjected to dual feature extraction, and the state characteristics in different time periods are analyzed to better understand the working state of the filter and the potential performance decay mechanism. Through feature extraction, the first state feature sequence and the second state feature sequence are obtained respectively. Based on these two state feature sequences, a double-layer state discrimination model is constructed. The first layer performs local feature analysis to capture the state changes within a specific time window, and the second layer performs global feature analysis to identify long-term trends and patterns in the entire use cycle. Through the double-layer analysis, the first state probability vector and the second state probability vector of the chemical filter are calculated to reflect the possibility distribution of the filter under different states. The state probability vector is input into the dual hidden Markov prediction model. The model consists of two parts: the first prediction sub-model and the second prediction sub-model. The first prediction sub-model processes the first state probability vector to calculate the corresponding transition probability, while the second prediction sub-model processes the second state probability vector to calculate its transition probability. Obtain the state transition probabilities of two time scales and analyze the dynamic relationship between different states. Perform weighted fusion and multi-scale rolling prediction on the first transition probability matrix and the second transition probability matrix. Combine information from different time scales to achieve more accurate state transition prediction. The weighted fusion method assigns different weights to each time scale according to its reliability and effectiveness to ensure the accuracy and rationality of the final result. Multi-scale rolling prediction means that when making predictions, the continuity and dynamic changes of the time series are taken into account so that the model can continue to adapt to new data. Double smoothing is performed on the generated multi-scale state prediction sequence to reduce the interference of noise on the prediction results, making the final state transition prediction sequence smoother and more stable. The accuracy and reliability of state transition prediction can be effectively improved through appropriate smoothing algorithms, such as sliding average or exponential smoothing.

[0020] 105. Perform multi-objective joint optimization on the state transfer prediction sequence and calculate the optimal operation control parameters; Specifically, the state transition prediction sequence is constructed by constructing the first objective function and the second objective function, wherein the first objective function includes the life maximization term and the efficiency maximization term, reflecting the direct concern for the filter performance; while the second objective function includes the operation cost minimization term and the replacement cost minimization term, reflecting the pursuit of economic benefits. By setting, it is ensured that both performance and cost are taken into account during the optimization process to form a dual-objective optimization function. The first constraint condition set and the second constraint condition set are set according to the dual-objective optimization function. The first constraint condition set mainly limits the pressure variation range and efficiency variation range of the filter to ensure that the physical limitations and work safety standards of the equipment are not violated during the optimization process. The second constraint condition set limits the life range and cost range of the filter to ensure that the optimization result is economically feasible. For the dual-objective optimization function and its constraints, the first weight coefficient allocation and the second weight coefficient allocation are performed. The hierarchical analysis method is used to calculate the weights of the objective function and the constraints to form a multi-level weight matrix. Based on the multi-level weight matrix, the first Pareto optimal solution set and the second Pareto optimal solution set are constructed, and the two solution sets correspond to the short-term optimization target and the long-term optimization target respectively. In this way, the optimization requirements under different time scales are taken into account at the same time, providing more options for the final decision. The double-layer Pareto solution set is screened for non-inferior solutions. The solution set is sorted by the first objective criterion and the second objective criterion to screen out the candidate solution sequence. After this screening process, the most potential solution is selected to form a more refined solution set. Based on the candidate solution sequence, the operating parameter mapping relationship is constructed, and the optimal solution is mapped to the dynamic adjustment parameters of the filter pressure, filtration temperature and filtration flow, and a set of specific parameter adjustment sequences are obtained. The parameter adjustment sequence is optimized for time series coordination. Parameter smoothing is performed based on the dual constraints of the first time scale and the second time scale to ensure that in actual applications, the adjustment process will not fluctuate violently, maintain the smooth operation of the equipment, and obtain a coordinated control sequence. The coordinated control sequence is converted into a combined instruction set of the filter's pressure control instructions, temperature control instructions, and flow control instructions to obtain the optimal operation control parameters.

[0021] 106. Based on the optimal operation control parameters, real-time multi-dimensional usage status data is collected, and the parameters of the double-layer performance degradation prediction model are optimized to obtain a service life prediction model.

[0022] Specifically, based on the optimal operation control parameters, the chemical filter is monitored in real time to collect real-time multi-dimensional usage status data, including inlet pressure, outlet pressure, flow rate, filter medium concentration, filter temperature, filter efficiency, filter saturation and other information. Through continuous monitoring of key parameters, the operating status of the filter is understood. The real-time multi-dimensional usage status data is input into the double-layer performance decay prediction model. The physical decay layer is inferred to evaluate the physical performance of the filter in combination with real-time data; at the same time, the deep learning layer performs online inference, and generates a real-time performance decay prediction sequence by analyzing the real-time input data to reflect the performance change trend of the filter under the current operating conditions. The real-time performance decay prediction sequence is compared and analyzed with the actual performance data to calculate the prediction error. These errors are classified and counted according to pressure error, efficiency error and life error to construct an error feature matrix. The matrix reflects the accuracy of the model prediction and reveals the deviations and deficiencies in the prediction process. The cause analysis of the error feature matrix is ​​performed. The key influencing parameters in the physical decay layer and the deep learning layer are determined. By identifying these influencing parameters, a clear parameter optimization direction is obtained to ensure that subsequent model updates can effectively improve the accuracy of the prediction. According to the determined parameter optimization direction, the physical parameters and network parameters in the double-layer performance attenuation prediction model are updated. The adjustment of physical parameters usually involves aspects such as attenuation coefficient, efficiency and pressure change, while the update of network parameters includes adjusting the weights, learning rate and network structure in the deep learning model. The update process optimizes the performance of the model so that it can better adapt to real-time data and improve the overall prediction ability. Through the above steps, a service life prediction model is obtained. The model can reflect the performance attenuation of the filter in real time, and dynamically adjust according to the latest operating data to ensure that it always maintains a high prediction accuracy in practical applications.

[0023] In the embodiments of the present invention, a double-layer performance degradation prediction model is constructed to combine physical mechanism constraints with deep learning, thereby improving the model accuracy while ensuring the interpretability of the prediction; a load feature clustering analysis method with a dual time window is adopted to achieve accurate identification of load patterns of filters at different time scales, thereby enhancing the model's adaptability to changes in operating conditions; a state probability transfer calculation method based on a dual hidden Markov prediction model accurately captures the dynamic characteristics of filter performance degradation; a multi-objective joint optimization strategy including life maximization, cost minimization and efficiency maximization is designed to achieve intelligent regulation of filter operating parameters; through a dynamic parameter tuning mechanism, the prediction model has the ability to adaptively update, thereby ensuring the stability of the model's prediction performance during long-term operation; the present invention improves the accuracy and reliability of filter life prediction through multi-level feature analysis and prediction strategies.

[0024] In a specific embodiment, the process of executing step 101 may specifically include the following steps: Collect data on the inlet pressure, outlet pressure, flow rate, filter medium concentration, filter temperature, filter efficiency and filter saturation of the chemical filter to obtain historical multi-dimensional usage status data; Perform data cleaning on historical multi-dimensional usage status data to obtain a preprocessed data set; Perform standardized mapping on the preprocessed data set, convert the state parameters of different dimensions into a standard range, and obtain a standardized data set; Divide the standardized data set into time windows, set overlapping time windows to segment the standardized data set, and obtain time series data segments; The time series data segments are labeled to obtain the time series feature data set.

[0025] Specifically, data collection was performed on chemical filters, focusing on several key parameters, including inlet pressure ( )、Outlet pressure( ),flow( )、Filter media concentration( )、Filtration temperature( )、Filtration efficiency( ) and filter saturation ( ). Through effective data collection, historical multi-dimensional data of these parameters under different usage conditions are obtained. The data collection process is achieved by installing sensors and data acquisition systems. Sensors monitor the inlet and outlet pressures of the filter in real time, flow meters measure flow rates, chemical analysis instruments detect the concentration of the filter medium, and temperature sensors are used to monitor the filtration temperature. These sensors send the collected data to the data processing system to form a raw data set containing multiple dimensions, including the status information of the filter under various operating conditions. Data cleaning is performed on the historical multi-dimensional usage status data to remove noise and erroneous data, for example, outliers caused by sensor failure or environmental factors are eliminated. This can be achieved by setting reasonable thresholds or using statistical methods (such as standard deviation, mean, etc.). For example, for the outlet pressure data of the filter, its mean and standard deviation are calculated, and the data is set to be valid within the range of ±3 standard deviations of the mean. Data outside this range is regarded as outliers and is eliminated. After data cleaning, the preprocessed data set is obtained. The preprocessed data set is standardized and mapped. The state parameters of different dimensions are uniformly converted to the standard range for effective comparison and analysis. The standardization adopts the Z-score standardization formula: ; in, is the standardized value, is the original data value, is the mean of the data, is the standard deviation. By standardization, the values ​​of each parameter are adjusted to the same scale so that they are in the same standard range, eliminating the impact of dimension on analysis. After completing standardization, divide the data set into time windows. Segment the standardized data according to the time series. Set overlapping time windows to capture the time correlation of the data. Set a window size of The time window is expressed by the following formula: ; in, Indicates the time range of the segment. is the starting point of the time series, is the window size. Data labeling is performed on the segmented time series data to extract the time series feature data set. Data labeling is based on actual application requirements. For example, the performance indicators of the filter, such as filtration efficiency and saturation, are set as labels. The filtration efficiency is calculated using the following formula: ; in, is the filtration efficiency, is the inlet concentration, is the outlet concentration. Through this step, the characteristic data in each time period are obtained.

[0026] In a specific embodiment, the process of executing step 102 may specifically include the following steps: Calculate the cumulative filtering amount of the first time window and the second time window for the time series feature data set respectively, and obtain the first load time series index and the second load time series index. The length of the first time window is 24 hours, and the length of the second time window is 48 hours. Performing segmentation threshold calculation on the first load timing indicator and the second load timing indicator, dividing the first load timing indicator into a first low load segment, a first medium load segment, and a first high load segment, and dividing the second load timing indicator into a second low load segment, a second medium load segment, and a second high load segment, to obtain a first load segmentation result and a second load segmentation result; Extract characteristic values ​​from the first load segmentation result and the second load segmentation result respectively, calculate the first pressure change rate, the first temperature distribution characteristic, the first efficiency decay rate and the second pressure change rate, the second temperature distribution characteristic and the second efficiency decay rate, and obtain the first characteristic parameter set and the second characteristic parameter set; A two-layer feature association matrix is ​​constructed based on the first feature parameter set and the second feature parameter set, a multi-scale feature association result is obtained through the first-layer local association calculation and the second-layer global association calculation, and a principal component analysis is performed on the multi-scale feature association result to extract the feature combination of the first principal component and the second principal component to obtain a multi-dimensional reduced dimension feature set; Perform double clustering calculation on the multi-dimensional dimensionality reduction feature set to obtain the first cluster center and the second cluster center respectively, and establish the first distance matrix and the second distance matrix through the first cluster center and the second cluster center for pattern discrimination to obtain a multi-level load pattern label; The multi-level load pattern labels are combined with the multi-dimensional dimension reduction feature set, and the filter load pattern feature vector is obtained through the cascade transformation of the first feature map and the second feature map.

[0027] Specifically, the cumulative filtering amount of the first time window and the second time window is calculated to obtain the first load timing index and the second load timing index. The length of the first time window is 24 hours, and the length of the second time window is 48 hours. The filtering amount in each window is extracted from the time series feature data set, and the calculation is performed by accumulation. The cumulative filtering amount is expressed as: ; in, is the cumulative filtration volume, For in time The flow value at is the end time of the time window. The first load timing indicator and the second load timing indicator are segmented and threshold values ​​are calculated. The first load timing indicator is divided into a first low load segment, a first medium load segment, and a first high load segment, and the second load timing indicator is divided into a second low load segment, a second medium load segment, and a second high load segment. The segmentation process is implemented based on the set threshold value. For example, the threshold value of the load indicator is defined as and ,in is the upper limit of low load, is the lower limit of high load. The specific segmented formula is expressed as: ; in, Represents the value of the load timing indicator, is the minimum value of the load. Different load segments are marked to obtain the first load segmentation result and the second load segmentation result. Feature value extraction is performed on the load segmentation result. The first pressure change rate, the first temperature distribution feature, the first efficiency decay rate, and the second pressure change rate, the second temperature distribution feature, and the second efficiency decay rate are calculated. The pressure change rate is expressed by the formula: ; in, is the pressure change rate, and are the pressure values ​​at the end and beginning of the time period, respectively, and and is the corresponding time point. By calculating these eigenvalues, the first feature parameter set and the second feature parameter set are obtained. A two-layer feature association matrix is ​​constructed based on the first feature parameter set and the second feature parameter set. The multi-scale feature association result is obtained by calculating the first layer local association and the second layer global association. Assuming there is a eigenvector and , their correlation is expressed as: ; in, is the feature vector and The correlation between and are the norms of the vectors respectively. The multi-scale feature association results are reduced in dimension by principal component analysis, and the feature combination of the first principal component and the second principal component is extracted to obtain a multi-dimensional reduced dimension feature set. Double clustering calculation is performed on the multi-dimensional reduced dimension feature set. By analyzing the distribution of feature data, the first cluster center and the second cluster center are obtained respectively. These two cluster centers are used to establish the first distance matrix and the second distance matrix for pattern discrimination. The distance matrix is ​​expressed by the following formula: ; in, For sample With sample The distance between and The samples are and samples In the feature dimension In this way, a multi-level load pattern label is obtained. The multi-level load pattern label is combined with the multi-dimensional dimensionality reduction feature set, and the filter load pattern feature vector is obtained through the cascade transformation of the first feature map and the second feature map.

[0028] In a specific embodiment, the process of executing step 103 may specifically include the following steps: Dividing the filter load mode characteristic vector into a first characteristic sub-vector and a second characteristic sub-vector, wherein the first characteristic sub-vector includes a pressure change rate and an efficiency decay rate, and the second characteristic sub-vector includes a temperature distribution feature and a saturation change rate; Constructing a physical attenuation layer according to the first characteristic subvector, the physical attenuation layer includes an attenuation parameter calculation unit and a physical constraint unit, the attenuation parameter calculation unit adopts a polynomial fitting structure, and the physical constraint unit adopts a boundary constraint structure; Performing parameter training on the attenuation parameter calculation unit, the attenuation parameter calculation unit includes a third-order polynomial fitting module and an adaptive weight module, and the physical constraint unit includes a maximum pressure drop constraint and a minimum efficiency constraint; The first characteristic sub-vector is input into the physical attenuation layer, and a first performance attenuation prediction sequence is obtained by calculating the attenuation coefficient; A deep learning layer is constructed according to the second feature sub-vector and the first performance decay prediction sequence, wherein the deep learning layer includes a time series feature extractor and a performance predictor, wherein the time series feature extractor adopts a bidirectional long short-term memory network structure, and the performance predictor adopts a residual attention network structure; The temporal feature extractor contains three layers of bidirectional LSTM units, each layer of LSTM units contains 128 hidden nodes, and a Dropout layer is set between LSTM units; the performance predictor contains five residual blocks, each residual block contains two fully connected layers and a channel attention module; Inputting the first performance decay prediction sequence and the second feature sub-vector into the deep learning layer, and obtaining the second performance decay prediction sequence through network training; Constructing a fusion optimization layer, the fusion optimization layer includes an adaptive weight module and a timing calibration module, and dynamically weighting and fusing the first performance decay prediction sequence and the second performance decay prediction sequence; The weight parameters of the adaptive weight module are updated online according to the historical performance attenuation data of the chemical filter, and the fusion results are time-aligned through the timing calibration module to obtain the output results of the fusion optimization layer. The output results of the fusion optimization layer are time-reconstructed to generate the target performance attenuation prediction sequence.

[0029] Specifically, the filter load mode characteristic vector is divided into a first characteristic sub-vector and a second characteristic sub-vector, wherein the first characteristic sub-vector includes the pressure change rate and the efficiency decay rate, and the second characteristic sub-vector includes the temperature distribution characteristics and the saturation change rate. By dividing the characteristic vector by dimensional analysis and selection, it is ensured that each sub-vector represents a specific physical phenomenon. When constructing the physical attenuation layer, the attenuation parameter calculation unit and the physical constraint unit are designed based on the first characteristic sub-vector. The attenuation parameter calculation unit adopts a polynomial fitting structure and uses a third-order polynomial to represent the change in filter performance. The formula is: ; in, For time Performance indicators when are the coefficients of the polynomials, which are obtained by fitting historical data. At the same time, the physical constraint unit adopts a boundary constraint structure to ensure the rationality of the model under actual physical conditions, for example, setting the maximum pressure drop constraint and the minimum efficiency constraint. When training the parameters of the attenuation parameter calculation unit, a third-order polynomial fitting module and an adaptive weight module are constructed. Through the adaptive weight module, the weights of each parameter are dynamically adjusted according to the characteristics of the input data, making the model more flexible and effective. The goal of attenuation parameter training is to minimize the error between the predicted value and the true value, which is expressed as: ; in, is the predicted performance value, is the actual performance value, and is the number of data points. This process is iterated through optimization algorithms (such as gradient descent) until convergence. After the first feature sub-vector is input into the physical attenuation layer, the first performance attenuation prediction sequence is obtained by calculating the attenuation coefficient, which reflects the performance change of the filter over a period of time. A deep learning layer is constructed based on the second feature sub-vector and the first performance attenuation prediction sequence. The deep learning layer consists of a time series feature extractor and a performance predictor, in which the time series feature extractor adopts a bidirectional long short-term memory network (Bi-LSTM) structure to effectively capture the front and back dependencies in the time series data. The time series feature extractor contains three layers of bidirectional LSTM units, each layer of LSTM units contains 128 hidden nodes, and a Dropout layer is set between the LSTM units to prevent overfitting. The output of LSTM is expressed as: ; in, is the hidden state at the current moment, is the current input, is the hidden state of the previous moment. Through this structure, the network can effectively extract time series features. The performance predictor adopts a residual attention network structure, which contains five residual blocks, each of which consists of two fully connected layers and a channel attention module. This design helps to capture the deep correlation between features and enhance the model's learning ability for complex data. By inputting the first performance decay prediction sequence and the second feature sub-vector into the deep learning layer, the second performance decay prediction sequence is obtained after network training. A fusion optimization layer is constructed, in which the fusion optimization layer contains an adaptive weight module and a timing calibration module, which aims to dynamically weighted fuse the first performance decay prediction sequence and the second performance decay prediction sequence. The adaptive weight module is updated online through the historical performance decay data of the chemical filter to ensure the timeliness of the model parameters. Dynamic weighted fusion is expressed by the following formula: ; in, For the final fusion result, and are the first and second performance decay prediction sequences, respectively, and and is the dynamically adjusted weight coefficient. The timing calibration module is used to align the fusion results to ensure that the prediction results are consistent with the actual application scenarios, and finally the output results of the fusion optimization layer are obtained. After the timing reconstruction, the target performance attenuation prediction sequence is generated.

[0030] In a specific embodiment, the process of executing step 104 may specifically include the following steps: Segment the target performance attenuation prediction sequence into a first time window and a second time window to obtain a first segmented sequence sample and a second segmented sequence sample; Performing dual feature extraction on the first segmented sequence sample and the second segmented sequence sample respectively to obtain a first state feature sequence and a second state feature sequence; A double-layer state discrimination model is constructed based on the first state feature sequence and the second state feature sequence, and the first state probability vector and the second state probability vector of the chemical filter are calculated through the first layer local feature analysis and the second layer global feature analysis; Inputting the first state probability vector and the second state probability vector into the dual hidden Markov prediction model, respectively calculating the state transition probabilities of the two time scales through the first prediction sub-model and the second prediction sub-model, and obtaining the first transition probability matrix and the second transition probability matrix; The first transfer probability matrix and the second transfer probability matrix are weighted fused and multi-scale rolling predicted to obtain a multi-scale state prediction sequence, and the multi-scale state prediction sequence is double-smoothed to obtain a state transfer prediction sequence.

[0031] Specifically, the target performance attenuation prediction sequence is segmented into a first time window and a second time window. Assume that the length of the first time window is , the length of the second time window is , using a time index method to generate the first segment sequence sample and the second segment sequence sample, for example by selecting a time range to and to The sample data of the first segmented sequence is used to obtain the two segmented sequences. Dual feature extraction is performed on the first segmented sequence sample and the second segmented sequence sample respectively. The key state features are extracted from each time window. Feature extraction uses a variety of methods, such as statistical analysis, frequency domain analysis, etc. to obtain the characteristic values ​​related to the filter state. The results after feature extraction form the first state feature sequence and the second state feature sequence respectively. The extraction of state features is described by the following formula: ; in, is the extracted eigenvalue, For the state samples, and is the feature extraction function. After this step, the required state feature sequence is obtained. Based on the first state feature sequence and the second state feature sequence, a two-layer state discrimination model is constructed. In this model, the first layer focuses on the analysis of local features, while the second layer focuses on the analysis of global features. Through local feature analysis, the first state probability vector of the chemical filter is calculated, which is expressed as: ; in, is the probability vector of the first state, is the number of first state samples, and is the total number of samples. Accordingly, the second state probability vector The calculation is performed in a similar way. The two state probability vectors are input into the dual hidden Markov prediction model, and the state transition probabilities of the two time scales are calculated respectively by the first prediction sub-model and the second prediction sub-model. The state transition probability is expressed as: ; in, From the state Transfer to state The probability of Indicates at time This model can learn the transition rules between states through historical state data to obtain the first transition probability matrix and the second transition probability matrix. The first transition probability matrix and the second transition probability matrix are weighted fused and multi-scale rolling forecasted. The information of the two time scales is integrated to improve the accuracy of the forecast. Weighted fusion is expressed by the following formula: ; in, is the final fused transition probability matrix, and are the first and second transition probability matrices respectively, and and is the dynamically adjusted weight coefficient. Through the weighted fusion method, the transfer rules under different time scales are comprehensively considered to obtain a more comprehensive state prediction. The multi-scale state prediction sequence is double-smoothed to remove noise, making the prediction result more stable and reliable. Double smoothing is achieved through the moving average method or exponential smoothing method to obtain the state transfer prediction sequence, which is expressed as: ; in, is the smoothed state value, is the original state value, is the size of the smoothing window. Through this step, the reliability and accuracy of the predicted sequence are ensured.

[0032] In a specific embodiment, the process of executing step 105 may specifically include the following steps: A first objective function and a second objective function are constructed for the state transition prediction sequence, wherein the first objective function includes a life maximization term and an efficiency maximization term, and the second objective function includes an operation cost minimization term and a replacement cost minimization term, to obtain a dual-objective optimization function; According to the dual-objective optimization function, a first constraint condition set and a second constraint condition set are set, wherein the first constraint condition set defines a filter pressure variation range and an efficiency variation range, and the second constraint condition set defines a filter life range and a cost range, to obtain optimization constraints; Perform a first weight coefficient allocation and a second weight coefficient allocation on the dual-objective optimization function and the optimization constraint condition, calculate the objective function weight and the constraint condition weight based on the hierarchical analysis method, and obtain a multi-level weight matrix; Based on the multi-level weight matrix, the first Pareto optimal solution set and the second Pareto optimal solution set are constructed, corresponding to the short-term optimization goal and the long-term optimization goal respectively, and a double-layer Pareto solution set is obtained; The double-layer Pareto solution set is screened for non-inferior solutions, and the solution set is sorted by the first objective criterion and the second objective criterion to obtain a candidate solution sequence, and an operation parameter mapping relationship is constructed based on the candidate solution sequence, and the optimal solution is mapped to dynamic adjustment parameters of filtration pressure, filtration temperature and filtration flow to obtain a parameter adjustment sequence; The parameter adjustment sequence is optimized in time coordination, and parameter smoothing is performed based on the dual constraints of the first time scale and the second time scale to obtain a coordinated control sequence. The coordinated control sequence is then converted into a combined instruction set of pressure control instructions, temperature control instructions and flow control instructions of the filter to obtain the optimal operating control parameters.

[0033] Specifically, the first objective function and the second objective function are constructed for the state transition prediction sequence. The first objective function mainly includes the life maximization term and the efficiency maximization term, which are specifically expressed as: ; in, is the first objective function, For the expected life of the filter, is the filter efficiency, and are the corresponding weight coefficients, which are used to adjust the importance of the two objectives. The second objective function focuses on minimizing the operating cost and the replacement cost, and its expression is: ; in, is the second objective function, For operating costs, For replacement cost, and is also the weight coefficient. The combination of the two objective functions forms a dual-objective optimization function, expressed as: ; Weigh different goals and achieve comprehensive optimization. Set corresponding constraint sets. The first constraint set limits the pressure variation range and efficiency variation range of the filter, which can be expressed as: ; in, Represents the actual pressure of the filter, and are the minimum and maximum values ​​allowed, respectively, and and It represents the range of efficiency. The second set of constraints limits the life and cost range of the filter, which is expressed as: ; in, and are the minimum and maximum limits on filter life, and is the range of cost. The setting of constraint conditions ensures the feasibility of the optimization process in actual operation. The first weight coefficient and the second weight coefficient are assigned to the dual-objective optimization function and the optimization constraint conditions. The objective function weight and constraint weight are calculated based on the hierarchical analysis method. By scoring the relative importance of the objectives and constraints, a multi-level weight matrix is ​​formed, in which the objective weight and constraint weight are expressed in the following ways: ; in, Representative The first goal and The relative importance weights between constraints. Based on the multi-level weight matrix, the first Pareto optimal solution set and the second Pareto optimal solution set are constructed, corresponding to the short-term optimization goal and the long-term optimization goal respectively. Different objective functions are combined with constraints to form a set of non-dominated solutions. For example, through an optimization algorithm (such as a genetic algorithm or a particle swarm algorithm), multiple potential optimal solutions are obtained, and these solutions together form a double-layer Pareto solution set. Non-inferior solutions are screened for the double-layer Pareto solution set. The solution set is sorted by the first objective criterion (such as minimizing a certain objective function) and the second objective criterion (such as maximizing another objective function) to identify a sequence of candidate solutions. These candidate solutions will be used to construct a mapping relationship between operating parameters, mapping the optimal solution to the dynamic adjustment parameters of the filter's pressure, temperature and flow. The parameter adjustment sequence is established by the following formula: ; in, , and represent the optimized pressure, temperature and flow rate respectively, and It is a dynamic adjustment parameter constructed based on the optimization results. The parameter adjustment sequence is optimized in time coordination. Based on the dual constraints of the first time scale and the second time scale, the parameters are smoothed to ensure consistency and stability in actual operation. The smoothing process uses the sliding average method or other smoothing techniques to finally generate a coordinated control sequence. This sequence will be converted into a combined instruction set of the filter's pressure control instructions, temperature control instructions, and flow control instructions to obtain the optimal operating control parameters.

[0034] In a specific embodiment, the process of executing step 106 may specifically include the following steps: Real-time monitoring of chemical filters based on optimal operating control parameters, collecting real-time multi-dimensional usage status data including inlet pressure, outlet pressure, flow, filter medium concentration, filter temperature, filter efficiency and filter saturation; The real-time multi-dimensional usage status data is input into the two-layer performance degradation prediction model, and online reasoning operations are performed on the physical degradation layer and the deep learning layer to obtain a real-time performance degradation prediction sequence. The prediction error is calculated based on the real-time performance decay prediction sequence and the actual performance data, and classified and counted according to the pressure error, efficiency error and life error to obtain the error feature matrix; The cause of the error characteristic matrix is ​​analyzed to determine the key influencing parameters in the physical attenuation layer and the deep learning layer, and the parameter optimization direction is obtained. The physical parameters and network parameters in the double-layer performance attenuation prediction model are updated according to the parameter optimization direction to obtain the service life prediction model.

[0035] Specifically, based on the optimal operation control parameters, real-time multi-dimensional usage status data including inlet pressure, outlet pressure, flow, filter medium concentration, filter temperature, filter efficiency and filter saturation are collected. This data collection is completed through sensors installed at each key node of the filter. The sensors record these parameters in real time and send the information to the central control system through the data transmission system. The structure after data collection is represented as a multi-dimensional array, in which each dimension corresponds to a monitoring parameter, for example: ; in, For in time The collected multi-dimensional data vector, , , , , , and They represent inlet pressure, outlet pressure, flow rate, filter medium concentration, filter temperature, filter efficiency, and filter saturation, respectively. The real-time multi-dimensional usage status data is input into the two-layer performance decay prediction model, and the real-time performance decay prediction sequence is obtained through online reasoning operations of the physical decay layer and the deep learning layer. The physical decay layer processes the decay model based on physical principles, such as predicting the performance degradation by calculating the pressure and flow changes of the filter; while the deep learning layer processes nonlinear relationships and complex features through neural networks. For example, the prediction model is described by the following formula: ; in, Indicates at time The predicted value of performance degradation is is the performance decay prediction model function. This process ensures that the system obtains real-time feedback on filter performance from real-time monitoring data. The prediction error is calculated based on the real-time performance decay prediction sequence and the actual performance data. The error calculation is divided into multiple aspects, including pressure error, efficiency error and life error, and the calculation formula is as follows: ; ; ; in, , and represent pressure error, efficiency error and life error respectively, and , and is the actual measured parameter. Through the statistics of these errors, an error feature matrix is ​​constructed for subsequent cause analysis. The error feature matrix is ​​subjected to cause analysis. By analyzing the source of each error, the key influencing parameters in the physical attenuation layer and the deep learning layer are determined. For example, if the pressure error is significant and the efficiency error is small, it means that the flow rate of the filter is improperly set. Use statistical analysis methods (such as correlation analysis) to identify which parameters have the greatest impact on the error and obtain the direction of parameter optimization. For example, if it is found that the fluctuation of the filtration temperature is related to the efficiency error, the temperature control strategy should be optimized. According to the parameter optimization direction, the physical parameters and network parameters in the double-layer performance attenuation prediction model are updated to improve the accuracy and reliability of the prediction. Adjust the identified key parameters and retrain the deep learning model. For example, the model parameters are updated by the following formula: ; in, and Respectively represent the model parameters before and after the update, is the learning rate, is the gradient of the loss function. Updates help make the model better fit the current operating conditions.

[0036] Among them, the cause analysis of the error characteristic matrix is ​​performed, the key influencing parameters in the physical attenuation layer and the deep learning layer are determined, the parameter optimization direction is obtained, and the physical parameters and network parameters in the double-layer performance attenuation prediction model are updated according to the parameter optimization direction to obtain the service life prediction model, including the following steps: correlation decomposition of the error characteristic matrix is ​​performed, the pressure error vector, efficiency error vector and life error vector are extracted, and a classified error set is obtained; an error propagation graph is constructed based on the classified error set, and the error contribution of the physical attenuation layer and the deep learning layer is calculated to obtain the hierarchical error distribution; a sensitivity analysis of the hierarchical error distribution is performed, and the influence of each parameter on the prediction result is calculated to obtain a parameter sensitivity matrix; key influencing parameters are screened according to the parameter sensitivity matrix, and the parameter importance threshold is set for descending sorting to obtain a parameter optimization sequence; key parameters in the physical attenuation layer are sorted according to the parameter sensitivity matrix. Perform variation analysis, update the polynomial fitting coefficients and boundary constraint parameters based on the physical constraints, and obtain the optimized physical parameter set; perform gradient calculation on the key parameters in the deep learning layer, perform local fine-tuning on the network weights and biases, and obtain the optimized network parameter set; input the optimized physical parameter set into the physical attenuation layer, recalculate the attenuation coefficient, and obtain the updated physical prediction results; input the optimized network parameter set into the deep learning layer, update the parameters of the feature extractor and predictor, and obtain the updated deep learning prediction results; perform fusion optimization on the updated physical prediction results and the updated deep learning prediction results, update the fusion weight coefficients, and obtain the corrected prediction results; perform an overall performance evaluation on the double-layer performance attenuation prediction model based on the corrected prediction results, and when the prediction error meets the convergence conditions, obtain the service life prediction model.

[0037] The above describes the method for predicting the service life of the chemical filter in the embodiment of the present invention. The following describes the device for predicting the service life of the chemical filter in the embodiment of the present invention. Figure 2 In one embodiment of the present invention, a device for predicting the service life of a chemical filter includes: The acquisition module 201 is used to collect historical multi-dimensional usage status data of the chemical filter and perform standardized preprocessing to obtain a time series feature data set; A clustering module 202 is used to perform load feature clustering analysis on the time series feature data set to obtain a filter load pattern feature vector; A construction module 203 is used to construct a double-layer performance degradation prediction model based on the filter load pattern feature vector, and output a target performance degradation prediction sequence through physical attenuation coefficient calculation and deep learning network training; A calculation module 204 is used to perform filter state probability transfer calculation on the target performance attenuation prediction sequence to obtain a state transfer prediction sequence; The optimization module 205 is used to perform multi-objective joint optimization on the state transition prediction sequence and calculate the optimal operation control parameters; The parameter tuning module 206 is used to collect real-time multi-dimensional usage status data based on the optimal operation control parameters, and perform parameter tuning on the double-layer performance degradation prediction model to obtain a service life prediction model.

[0038] Through the collaborative cooperation of the above-mentioned components, a double-layer performance degradation prediction model is constructed, which combines physical mechanism constraints with deep learning, thereby improving the model accuracy while ensuring the interpretability of the prediction; a load feature clustering analysis method with a dual time window is adopted to realize the accurate identification of load patterns of filters at different time scales, and enhance the model's adaptability to changes in working conditions; a state probability transfer calculation method based on a dual hidden Markov prediction model accurately captures the dynamic characteristics of filter performance degradation; a multi-objective joint optimization strategy including life maximization, cost minimization and efficiency maximization is designed to realize intelligent regulation of filter operating parameters; through a dynamic parameter tuning mechanism, the prediction model has the ability to adaptively update, which ensures the stability of the model's prediction performance during long-term operation; the present invention improves the accuracy and reliability of filter life prediction through multi-level feature analysis and prediction strategies.

[0039] above Figure 2 The device for predicting the service life of the chemical filter in the embodiment of the present invention is described in detail from the perspective of modular functional entities, and the device for predicting the service life of the chemical filter in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0040] Figure 3It is a structural schematic diagram of a device for predicting the service life of a chemical filter provided by an embodiment of the present invention. The device 300 for predicting the service life of a chemical filter may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 310 (for example, one or more processors) and a memory 320, and one or more storage media 330 (for example, one or more mass storage device terminals) storing application programs 333 or data 332. Among them, the memory 320 and the storage medium 330 can be short-term storage or permanent storage. The program stored in the storage medium 330 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the device 300 for predicting the service life of the chemical filter. Furthermore, the processor 310 may be configured to communicate with the storage medium 330, and execute a series of instruction operations in the storage medium 330 on the device 300 for predicting the service life of the chemical filter to implement the steps of the above-mentioned method for predicting the service life of the chemical filter.

[0041] The chemical filter service life prediction device 300 may also include one or more power supplies 340, one or more wired or wireless network interfaces 350, one or more input and output interfaces 360, and / or one or more operating systems 331, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 3 The structure of the device for predicting the service life of a chemical filter shown does not constitute a limitation on the device for predicting the service life of a chemical filter provided by the present invention, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0042] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the method for predicting the service life of the chemical filter.

[0043] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0044] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0045] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the service life of a chemical filter, characterized in that: The method comprises: Collect historical multi-dimensional usage status data of chemical filters and perform standardized preprocessing to obtain a time series feature data set; Performing load feature clustering analysis on the time series feature data set to obtain a filter load pattern feature vector; A double-layer performance attenuation prediction model is constructed based on the filter load pattern feature vector, and a target performance attenuation prediction sequence is output through physical attenuation coefficient calculation and deep learning network training; Performing filter state probability transfer calculation on the target performance attenuation prediction sequence to obtain a state transfer prediction sequence; Performing multi-objective joint optimization on the state transition prediction sequence and calculating the optimal operation control parameters; Based on the optimal operation control parameters, real-time multi-dimensional usage status data is collected, and the parameters of the double-layer performance degradation prediction model are tuned to obtain a service life prediction model.

2. The method for predicting the service life of a chemical filter according to claim 1, characterized in that: The historical multi-dimensional usage status data of the chemical filter is collected and standardized preprocessed to obtain a time series feature data set, including: Collect data on the inlet pressure, outlet pressure, flow rate, filter medium concentration, filter temperature, filter efficiency and filter saturation of the chemical filter to obtain historical multi-dimensional usage status data; Performing data cleaning on the historical multi-dimensional usage status data to obtain a preprocessed data set; Performing standardized mapping on the preprocessed data set, uniformly converting state parameters of different dimensions into a standard range, and obtaining a standardized data set; Dividing the standardized data set into time windows, setting overlapping time windows to segment the standardized data set, and obtaining time series data segments; The time series data segments are data labeled to obtain a time series feature data set.

3. The method for predicting the service life of a chemical filter according to claim 2, characterized in that: The performing load feature clustering analysis on the time series feature data set to obtain a filter load pattern feature vector includes: Calculating the cumulative filtering amount of the first time window and the second time window for the time series feature data set respectively to obtain a first load time series index and a second load time series index, wherein the length of the first time window is 24 hours, and the length of the second time window is 48 hours; Performing segmentation threshold calculation on the first load timing indicator and the second load timing indicator, dividing the first load timing indicator into a first low load segment, a first medium load segment, and a first high load segment, and dividing the second load timing indicator into a second low load segment, a second medium load segment, and a second high load segment, to obtain a first load segmentation result and a second load segmentation result; Extracting characteristic values ​​of the first load segmentation result and the second load segmentation result respectively, calculating a first pressure change rate, a first temperature distribution characteristic, a first efficiency decay rate, and a second pressure change rate, a second temperature distribution characteristic, and a second efficiency decay rate, to obtain a first characteristic parameter set and a second characteristic parameter set; Constructing a two-layer feature association matrix based on the first feature parameter set and the second feature parameter set, obtaining a multi-scale feature association result through a first-layer local association calculation and a second-layer global association calculation, and performing principal component analysis on the multi-scale feature association result to extract a feature combination of the first principal component and the second principal component to obtain a multi-dimensional reduced dimension feature set; Performing double clustering calculation on the multi-dimensional dimensionality reduction feature set to obtain a first cluster center and a second cluster center respectively, and establishing a first distance matrix and a second distance matrix through the first cluster center and the second cluster center to perform pattern discrimination to obtain a multi-level load pattern label; The multi-level load pattern labels are combined with the multi-dimensional dimension reduction feature set, and a filter load pattern feature vector is obtained through a cascade transformation of a first feature map and a second feature map.

4. The method for predicting the service life of a chemical filter according to claim 3, characterized in that: The double-layer performance attenuation prediction model is constructed based on the filter load pattern feature vector, and a target performance attenuation prediction sequence is output through physical attenuation coefficient calculation and deep learning network training, including: Dividing the filter load mode characteristic vector into a first characteristic sub-vector and a second characteristic sub-vector, wherein the first characteristic sub-vector includes a pressure change rate and an efficiency decay rate, and the second characteristic sub-vector includes a temperature distribution feature and a saturation change rate; Constructing a physical attenuation layer according to the first characteristic subvector, the physical attenuation layer comprising an attenuation parameter calculation unit and a physical constraint unit, the attenuation parameter calculation unit adopts a polynomial fitting structure, and the physical constraint unit adopts a boundary constraint structure; Performing parameter training on the attenuation parameter calculation unit, wherein the attenuation parameter calculation unit includes a third-order polynomial fitting module and an adaptive weight module, and the physical constraint unit includes a maximum pressure drop constraint and a minimum efficiency constraint; Inputting the first characteristic sub-vector into the physical attenuation layer, and obtaining a first performance attenuation prediction sequence by calculating the attenuation coefficient; Constructing a deep learning layer according to the second feature sub-vector and the first performance decay prediction sequence, the deep learning layer comprising a time series feature extractor and a performance predictor, the time series feature extractor adopts a bidirectional long short-term memory network structure, and the performance predictor adopts a residual attention network structure; The temporal feature extractor comprises three layers of bidirectional LSTM units, each layer of LSTM units comprises 128 hidden nodes, and a Dropout layer is set between the LSTM units; the performance predictor comprises five residual blocks, each residual block comprises two fully connected layers and a channel attention module; Inputting the first performance decay prediction sequence and the second feature sub-vector into the deep learning layer, and obtaining a second performance decay prediction sequence through network training; Constructing a fusion optimization layer, wherein the fusion optimization layer includes an adaptive weight module and a timing calibration module, and dynamically weighting and fusing the first performance decay prediction sequence and the second performance decay prediction sequence; The weight parameters of the adaptive weight module are updated online according to the historical performance attenuation data of the chemical filter, and the fusion results are time-aligned through the timing calibration module to obtain the output result of the fusion optimization layer, and the output result of the fusion optimization layer is time-reconstructed to generate a target performance attenuation prediction sequence.

5. The method for predicting the service life of a chemical filter according to claim 4, characterized in that: The performing filter state probability transfer calculation on the target performance attenuation prediction sequence to obtain a state transfer prediction sequence includes: Performing a first time window segmentation and a second time window segmentation on the target performance attenuation prediction sequence to obtain a first segmented sequence sample and a second segmented sequence sample; Performing dual feature extraction on the first segmented sequence samples and the second segmented sequence samples respectively to obtain a first state feature sequence and a second state feature sequence; Building a double-layer state discrimination model based on the first state feature sequence and the second state feature sequence, and calculating a first state probability vector and a second state probability vector of the chemical filter through a first-layer local feature analysis and a second-layer global feature analysis; Inputting the first state probability vector and the second state probability vector into a dual hidden Markov prediction model, respectively calculating the state transition probabilities of two time scales through the first prediction sub-model and the second prediction sub-model, to obtain a first transition probability matrix and a second transition probability matrix; The first transfer probability matrix and the second transfer probability matrix are weightedly fused and multi-scale rolling predicted to obtain a multi-scale state prediction sequence, and the multi-scale state prediction sequence is double-smoothed to obtain a state transfer prediction sequence.

6. The method for predicting the service life of a chemical filter according to claim 5, characterized in that: The multi-objective joint optimization of the state transition prediction sequence and calculating the optimal operation control parameters include: Constructing a first objective function and a second objective function for the state transition prediction sequence, wherein the first objective function includes a life maximization term and an efficiency maximization term, and the second objective function includes an operation cost minimization term and a replacement cost minimization term, to obtain a dual-objective optimization function; According to the dual-objective optimization function, a first set of constraints and a second set of constraints are set, wherein the first set of constraints defines a filter pressure variation range and an efficiency variation range, and the second set of constraints defines a filter life range and a cost range, to obtain optimization constraints; Performing a first weight coefficient allocation and a second weight coefficient allocation on the dual-objective optimization function and the optimization constraint condition, calculating the objective function weight and the constraint condition weight based on the hierarchical analysis method, and obtaining a multi-level weight matrix; Based on the multi-level weight matrix, a first Pareto optimal solution set and a second Pareto optimal solution set are constructed, which correspond to the short-term optimization target and the long-term optimization target respectively, to obtain a double-layer Pareto solution set; The double-layer Pareto solution set is screened for non-inferior solutions, the solution set is sorted by the first objective criterion and the second objective criterion to obtain a candidate solution sequence, and an operation parameter mapping relationship is constructed based on the candidate solution sequence, and the optimal solution is mapped into dynamic adjustment parameters of filtration pressure, filtration temperature and filtration flow rate to obtain a parameter adjustment sequence; The parameter adjustment sequence is optimized in time coordination, and parameter smoothing is performed based on the dual constraints of the first time scale and the second time scale to obtain a coordinated control sequence, and the coordinated control sequence is converted into a combined instruction set of pressure control instructions, temperature control instructions and flow control instructions of the filter to obtain optimal operation control parameters.

7. The method for predicting the service life of a chemical filter according to claim 6, characterized in that: The real-time multi-dimensional usage status data is collected based on the optimal operation control parameters, and the parameters of the double-layer performance degradation prediction model are tuned to obtain a service life prediction model, including: Based on the optimal operation control parameters, the chemical filter is monitored in real time to collect real-time multi-dimensional usage status data including inlet pressure, outlet pressure, flow rate, filter medium concentration, filter temperature, filter efficiency and filter saturation; Input the real-time multi-dimensional usage status data into the two-layer performance degradation prediction model, perform online reasoning operations on the physical degradation layer and the deep learning layer, and obtain a real-time performance degradation prediction sequence; Calculate the prediction error according to the real-time performance decay prediction sequence and the actual performance data, and classify and count the pressure error, efficiency error and life error to obtain an error feature matrix; The cause analysis of the error characteristic matrix is ​​performed to determine the key influencing parameters in the physical attenuation layer and the deep learning layer, and the parameter optimization direction is obtained. The physical parameters and network parameters in the double-layer performance attenuation prediction model are updated according to the parameter optimization direction to obtain a service life prediction model.

8. A device for predicting the service life of a chemical filter, characterized in that: The device is used to perform the method for predicting the service life of a chemical filter according to any one of claims 1 to 7, the device comprising: The acquisition module is used to collect the historical multi-dimensional usage status data of the chemical filter and perform standardized preprocessing to obtain a time series feature data set; A clustering module, used for performing load feature clustering analysis on the time series feature data set to obtain a filter load pattern feature vector; A construction module is used to construct a double-layer performance attenuation prediction model based on the filter load pattern feature vector, and output a target performance attenuation prediction sequence through physical attenuation coefficient calculation and deep learning network training; A calculation module, used for performing filter state probability transfer calculation on the target performance attenuation prediction sequence to obtain a state transfer prediction sequence; An optimization module, used for performing multi-objective joint optimization on the state transition prediction sequence and calculating the optimal operation control parameters; The parameter tuning module is used to collect real-time multi-dimensional usage status data based on the optimal operation control parameters, and to perform parameter tuning on the double-layer performance attenuation prediction model to obtain a service life prediction model.

9. A device for predicting the service life of a chemical filter, characterized in that: The device for predicting the service life of a chemical filter comprises: a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instructions in the memory to enable the device for predicting the service life of the chemical filter to perform the method for predicting the service life of the chemical filter according to any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by a processor, a method for predicting the service life of a chemical filter as described in any one of claims 1 to 7 is implemented.

Images