Pollution control equipment state prediction method based on long time series attention network

Abstract

The embodiments of the present disclosure provide a method for predicting the status of pollution control equipment based on a long-time series attention network; the method relates to the field of pollution control equipment status prediction. The method includes preprocessing various types of data on the pollution control equipment to be predicted to obtain the time series to be predicted; inputting the time series to be predicted into the long-time series attention network, which uses its own local causal attention module to obtain the local attention information of the time series to be predicted, and uses its own long-term compressed memory module to obtain the historical information of the pollution control equipment to be predicted, and outputs a predicted time series based on the local attention information and historical information; and predicts the status of the pollution control equipment to be predicted based on the predicted time series. In this way, the prediction accuracy and flexibility of the long-time series are greatly improved, and it can cope with time series of different lengths, solving the problem of sparse status data of pollution control equipment.

Description

Technical Field

[0001] The present disclosure relates to the field of pollution control equipment status prediction, and in particular to a pollution control equipment status prediction method based on a long time series attention network. Background Art

[0002] In recent years, with the continuous advancement of industrial automation, various complex equipment has been widely used in scenarios such as pollution control and manufacturing. These devices, operating under long-term, high-load conditions, are inevitably subject to interference and impact from various environmental factors, leading to performance fluctuations and potential failures. Furthermore, the operational data of industrial equipment typically exhibits highly time-series characteristics and is influenced by factors such as equipment type, operating environment, and maintenance status. The data patterns are often complex, making it difficult for traditional equipment monitoring and early warning systems to fully capture these dynamic trends. Therefore, achieving accurate anomaly detection and fault warning based on historical data has become a key challenge in equipment maintenance and intelligent decision-making systems. In daily life, pollution control equipment such as sewage treatment facilities and air purification systems plays a key role in improving living environments. However, failures or anomalies in pollution control equipment can lead to problems such as air or water pollution, directly impacting residents' quality of life and health. Therefore, there is an urgent need for an intelligent monitoring and decision-making system to monitor the status of pollution control equipment.

[0003] At present, there are mainly the following methods for predicting the status of pollution control equipment: the least squares support vector machine prediction method based on Kalman filtering, the pollution control equipment status prediction method based on LSTM, and the long time series status equipment prediction model based on recurrent neural network. Due to the complexity of actual application scenarios and huge amounts of data, these methods have some problems. For example, the least squares support vector machine prediction method based on Kalman filtering has high computational complexity, and the pollution control equipment status prediction method based on LSTM and the long time series status equipment prediction model based on recurrent neural network have low accuracy in long time series prediction, high computing resource requirements, and sparse training data, making it difficult to ensure the accuracy and efficiency of prediction under large-scale data. Summary of the Invention

[0004] The present disclosure provides a method and apparatus for predicting the state of pollution control equipment based on a long time series attention network, equipment, and storage medium.

[0005] According to a first aspect of the present disclosure, a method for predicting the status of pollution control equipment based on a long-time series attention network is provided. The method comprises:

[0006] Preprocess various data of pollution control equipment to be predicted to obtain the time series to be predicted;

[0007] Inputting the time series to be predicted into a long time series attention network, so that the long time series attention network uses its own local causal attention module to obtain local attention information of the time series to be predicted, and uses its own long-term compressed memory module to obtain historical information of the pollution control equipment to be predicted, and outputs a predicted time series based on the local attention information and historical information;

[0008] The state of the pollution control equipment to be predicted is predicted according to the prediction time series.

[0009] In some implementations of the first aspect, the preprocessing includes:

[0010] Normalize various data of the pollution control equipment to be predicted and obtain the normalized time series;

[0011] According to the preset sequence length, the normalized time series is divided into multiple time segments, and the multiple time segments are used as the time series to be predicted.

[0012] In some implementations of the first aspect, the using its own local causal attention module to obtain local attention information of the time series to be predicted includes:

[0013] In the local causal attention module, the projection matrix is ​​used to calculate the attention query value, key-value pair and value matrix of the time series to be predicted;

[0014] According to the attention query value, key-value pair and value matrix of the time series to be predicted, the local attention context representation of the time series to be predicted is calculated using the function.

[0015] In some implementations of the first aspect, the acquiring of historical information of the pollution control equipment to be predicted by using its own long-term compressed memory module includes:

[0016] According to the attention query value of the time series to be predicted, the historical information of the pollution control equipment to be predicted is retrieved from the long-term compressed memory module.

[0017] In some implementations of the first aspect, outputting a predicted time series based on the local attention information and historical information includes:

[0018] Concatenating the local attention information with the historical information to generate a comprehensive context representation;

[0019] Performing linear projection on the comprehensive context representation using a linear projection layer;

[0020] The linearly projected data is passed through the layer normalization module, the fully connected layer, and the residual connection layer in sequence to obtain the predicted time series.

[0021] In some implementations of the first aspect, the method further includes:

[0022] The autoregressive generation method is used to interpolate the forecast time series to generate a complete forecast time series.

[0023] In some implementations of the first aspect, the method further includes:

[0024] The abnormal sequence is determined based on the complete forecast time series and the actual observation sequence corresponding to the complete forecast time series.

[0025] According to a second aspect of the present disclosure, a pollution control equipment state prediction device based on a long time series attention network is provided. The device comprises:

[0026] The module for obtaining the time series to be predicted is used to preprocess various data of the pollution control equipment to be predicted and obtain the time series to be predicted;

[0027] A predicted time series output module is configured to input the time series to be predicted into a long time series attention network, so that the long time series attention network uses its own local causal attention module to obtain local attention information of the time series to be predicted, and uses its own long-term compressed memory module to obtain historical information of the pollution control equipment to be predicted, and outputs a predicted time series based on the local attention information and historical information;

[0028] The pollution equipment state prediction module is used to predict the state of the pollution control equipment to be predicted based on the prediction time series.

[0029] According to a third aspect of the present disclosure, an electronic device is provided. The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method described above.

[0030] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method described above.

[0031] In this disclosure, various data about the pollution control equipment to be predicted are preprocessed to obtain a time series to be predicted. This time series is then fed into a long-term attention network, which uses its local causal attention module to obtain local attention information about the time series to be predicted, and its long-term compressed memory module to obtain historical information about the pollution control equipment to be predicted. Based on this local attention information and historical information, the network outputs a predicted time series. Based on this predicted time series, the status of the pollution control equipment to be predicted is predicted. This approach significantly improves the accuracy and flexibility of long-term predictions, adapts to time series of varying lengths, and addresses the sparsity of pollution control equipment status data.

[0032] It should be understood that the contents described in the Summary of the Invention section are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are provided for a better understanding of the present disclosure and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which:

[0034] Figure 1 A flowchart of a method for predicting the state of pollution control equipment based on a long time series attention network is shown in an embodiment of the present disclosure;

[0035] Figure 2 A long time series attention network framework diagram provided by an embodiment of the present disclosure is shown;

[0036] Figure 3 A schematic diagram of a long time series attention module provided by an embodiment of the present disclosure is shown;

[0037] Figure 4 A structural diagram of a pollution control equipment state prediction device based on a long time series attention network provided by an embodiment of the present disclosure is shown;

[0038] Figure 5 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0039] To make the purpose, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of the present disclosure.

[0040] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0041] In response to the problems arising from the background technology, the embodiments of the present disclosure provide a method for predicting the status of pollution control equipment based on a long time series attention network. Specifically, various types of data of the pollution control equipment to be predicted are preprocessed to obtain the time series to be predicted; the time series to be predicted is input into the long time series attention network, so that the long time series attention network uses its own local causal attention module to obtain the local attention information of the time series to be predicted, and uses its own long-term compression memory module to obtain the historical information of the pollution control equipment to be predicted, and outputs the predicted time series based on the local attention information and historical information; based on the predicted time series, the status of the pollution control equipment to be predicted is predicted. In this way, the prediction accuracy and flexibility of the long time series are greatly improved, time series of different lengths can be handled, and the sparsity problem of the status data of the pollution control equipment is solved.

[0042] The following describes in detail the pollution control equipment status prediction method and device based on the long time series attention network provided by the embodiments of the present disclosure through specific embodiments in conjunction with the accompanying drawings.

[0043] Figure 1 A flowchart of a method for predicting the state of pollution control equipment based on a long-time series attention network according to an embodiment of the present disclosure is shown. The method 100 includes the following steps:

[0044] S110, preprocessing various data of the pollution control equipment to be predicted to obtain a time series to be predicted.

[0045] In some embodiments, various data of pollution quality equipment are collected at multiple frequencies and dimensions through high-precision sensors; wherein, various data include temperature, pressure, vibration, energy consumption, operating time, working efficiency, temperature and humidity of the environment where the pollution control equipment is located, replacement records and maintenance records of pollution control equipment parts, and pollutant concentrations.

[0046] In some embodiments, the pre-processing comprises:

[0047] Normalize various data of the pollution control equipment to be predicted and obtain the normalized time series;

[0048] According to the preset sequence length, the normalized time series is divided into multiple time segments, and the multiple time segments are used as the time series to be predicted.

[0049] In some embodiments, the data is normalized according to the following formula:

[0050] ;

[0051] in, represents the normalized data, represents the data before normalization, It represents the mean value calculated based on various data of the pollution control equipment to be predicted. It represents the standard deviation calculated based on various data of the pollution control equipment to be predicted.

[0052] In some embodiments, the normalized time series is divided into multiple time segments according to a preset sequence length, including:

[0053] The normalized time series is divided into multiple time segments, each of which consists of multiple time steps, and the number of time steps is the same as the preset sequence length;

[0054] Specifically, the preset sequence length is , the normalized time series is ,Will Divided into T continuous time segments, i.e. , where each time segment Depend on time steps, namely: , and each time segment has several minimum time series units ;

[0055] Finally, multiple time segments are used as the time series to be predicted .

[0056] S120, input the time series to be predicted into the long time series attention network, so that the long time series attention network uses its own local causal attention module to obtain the local attention information of the time series to be predicted, and uses its own long-term compressed memory module to obtain the historical information of the pollution control equipment to be predicted, and outputs the predicted time series based on the local attention information and historical information.

[0057] In some embodiments, the long time series attention network framework is as shown in the figure Figure 2 As shown in Figure 1, the long time series attention network consists of L layers of long time series attention Transformer modules stacked in sequence. Each long time series attention Transformer module consists of a long time series attention module, a layer normalization module, a fully connected layer, and a residual connection layer connected in sequence.

[0058] Furthermore, each long-time series attention Transformer module extracts features at different levels in the time series to be predicted based on the long-time attention mechanism, thereby gradually capturing the long-distance dependencies in the time series to be predicted;

[0059] The long time series attention module can capture the global dependencies of the time series to be predicted, the layer normalization module can stabilize the feature distribution of different levels in the time series to be predicted, the fully connected layer can enhance the nonlinear expression of the long time series attention network, and the residual connection layer can retain the input data of the long time series attention network to stabilize the model training process.

[0060] In some embodiments, the method of using its own local causal attention module to obtain local attention information of the time series to be predicted includes:

[0061] In the local causal attention module, the projection matrix is ​​used to calculate the attention query value, key-value pair and value matrix of the time series to be predicted;

[0062] According to the attention query value, key-value pair and value matrix of the time series to be predicted, the local attention context representation of the time series to be predicted is calculated using the function;

[0063] Specifically, according to the following formula, based on the time series to be predicted , use the projection matrix to calculate the attention query value of the time series to be predicted , key-value pairs Sum Matrix :

[0064] ;

[0065] in, 、 、 are the projection matrices respectively;

[0066] Use the upper triangular mask matrix to Shielding is performed to impose causal constraints; the upper triangular positions in the upper triangular mask matrix represent future time steps, which are set to negative infinity, and the lower triangular and diagonal positions are set to 0. The matrix express and The product of the transpose of ;

[0067] Use the function to change the weight of the future time step position to 0, so that each time step can only focus on the current and previous time steps, avoiding the leakage of future information;

[0068] The local attention context representation is calculated according to the following formula (ie local attention information):

[0069] ;

[0070] in, The dimension of the vector representing the input to the long time series attention network, Represents the total time steps of the time series to be predicted.

[0071] In some embodiments, the long time series attention network computes Z independent attention heads in parallel, each with its own projection matrix 、 、 In order to capture the multi-level dependencies of the time series to be predicted, the local attention context representations obtained by each attention head are spliced ​​along the second dimension, the spliced ​​results are linearly projected, and the linear projection results are mapped back to the long time series attention network space, thereby generating the final attention context representations obtained by different attention heads.

[0072] In some embodiments, the method of using its own long-term compressed memory module to obtain historical information of the pollution control equipment to be predicted includes:

[0073] According to the attention query value of the time series to be predicted, the historical information of the pollution control equipment to be predicted is retrieved from the long-term compressed memory module;

[0074] Furthermore, historical information of the pollution control equipment to be predicted is retrieved The formula is as follows:

[0075] ;

[0076] in, represents the memory state of the previous time series, 、 Represents the attention query value of the time series to be predicted The nonlinear activation function value of and the normalization term of the previous time series key-value pair;

[0077] Specifically, , ,

[0078] ,in, is the exponential linear activation function, For the t A time series of key-value pairs, are adjustable hyperparameters, nonlinear activation functions and Together, they ensure numerical stability during computation and convergence during spatial training of long-time series attention networks.

[0079] In some embodiments, the memory in the long-term compressed memory module and the normalized item of the current time series key-value pair are updated to obtain the memory state of the next time series;

[0080] Specifically, update according to the following formula:

[0081] ;

[0082] ;

[0083] represents the memory state of the previous time series, Represents the memory state of the current time series, Represents the normalized item of the current time series key-value pair, is the association binding operator; where the initial memory state of the time series is the zero vector;

[0084] The memory state of the current time series and the normalized item of the key-value pair of the current time series are passed to the next time series, thereby obtaining the memory state of the next time series;

[0085] Furthermore, , Represents key-value pairs K The associative binding operator first retrieves the value of the key-value pair that already exists in the long-term compressed memory module, then subtracts the value of the retrieved key-value pair from the key-value pair of the time series newly input into the long-term attention network, and finally applies the associative binding to obtain the memory state of the current time series; if the associative binding operator already exists in the long-term compressed memory module, the associative binding method remains unchanged, and the method of obtaining the normalized item of the key-value pair is guaranteed to be the same.

[0086] In some embodiments, outputting a predicted time series based on the local attention information and historical information includes:

[0087] Concatenating the local attention information with the historical information to generate a comprehensive context representation;

[0088] Performing linear projection on the comprehensive context representation using a linear projection layer;

[0089] The linearly projected data is passed through the layer normalization module, the fully connected layer, and the residual connection layer in sequence to obtain the predicted time series.

[0090] In some embodiments, a schematic diagram of a long time series attention module is shown as follows: Figure 3 As shown, the long-term compressed memory module and the local causal attention module are connected to the linear projection layer through the splicing layer respectively;

[0091] Specifically, the memory state of the previous time series and the attention query value of the current time series Q After obtaining historical information through the long-term compressed memory module, the attention query value of the current time series Q and the memory state of the current time series The local attention information is obtained through the local causal attention module. The historical information and the local attention information are spliced ​​through the splicing layer respectively. The spliced ​​data passes through the linear projection layer to obtain the final output of the long time series attention module. The final output is expressed by the following equation:

[0092] ;

[0093] represents the time series to be predicted (i.e., the current time series) input to the long time series attention module, is the attention query value of the current time series, Represents the processing of long time series, Represents the attention mechanism.

[0094] In some embodiments, the local attention information and historical information are concatenated to generate a comprehensive context representation, including:

[0095] According to the gated scalar , adjust the proportion of local attention information and historical information to generate a comprehensive context representation ;

[0096] Specifically, , sigmoid is the activation function.

[0097] In some embodiments, for multi-head attention, the output of the local causal attention module and the long-term compressed memory module are concatenated to obtain the output O It can be expressed as: , is the weight.

[0098] In some embodiments, the normalization method of the layer normalization module is as follows:

[0099] ;

[0100] 、 Respectively represent the data before and after normalization of the layer normalization module, 、 Respectively represent the mean and variance of the data before normalization by the layer normalization module, 、 Represent the scaling parameter and translation parameter respectively.

[0101] In some embodiments, the fully connected layer includes a combination of two linear transformations and a nonlinear activation function, namely , represents the input of the fully connected layer, represents the operation of the fully connected layer, is a nonlinear activation function, and , which is an expression about the variable The nonlinear activation function, 、 are weight matrices, 、 are bias terms respectively.

[0102] In some embodiments, the prediction training process of the long time series attention network is as follows:

[0103] Collect data covering multiple areas, including rainfall, human health data, electricity meter readings, smart home device usage data, river water levels, air quality index, soil temperature and humidity changes, and manage these data in layers. Then, preprocess the data after layer management to obtain training sample sets. Layered data management can maximize the inclusion of various data, ensuring a relatively balanced data volume in each field, and the data complexity increases with the number of statistical feature layers.

[0104] Several minimum time series units in the training sample set are input into the long time series attention network according to the batch size. The batch size can be adjusted according to the computing resources, data scale, etc.

[0105] According to the above time series prediction method, the long time series attention network is trained based on the training sample set;

[0106] According to the following formula, the predicted time series is obtained:

[0107] ;

[0108] in, 、 Respectively represent the encoding and decoding operations in the corresponding steps, Indicates the m The unit vector of the time series corresponding to the time points, Indicates the first m The unit vector of the time series corresponding to the time points, From the first time point after the encoding operation to the A vector composed of the unit vectors of the time series corresponding to the time points, From the first time point after the encoding operation to the A vector composed of the unit vectors of the time series corresponding to the time points, From the first time point after the encoding operation to the A vector composed of the unit vectors of the time series corresponding to the time points, L for l the number of The operations performed by the long time series attention Transformer module, represents the first m A time series, Represents the first output of the long-time series attention network m+ 1 A forecast time series;

[0109] Calculate the mean square error between the predicted time series output by the long time series attention network and the corresponding actual time series, adjust the network parameters according to the mean square error and re-input the adjusted network parameters into the long time series attention network;

[0110] Repeat the prediction training steps until the prediction loss function converges; the prediction loss function is the mean squared error between the predicted time series output by the long time series attention network and the corresponding actual time series.

[0111] In some embodiments, the interpolation training process of the long time series attention network is as follows:

[0112] A set of observation time series is set in the training sample set. Some time series units are randomly selected in the observation time series for masking, and the data in some time series units are set to 0 to simulate missing conditions.

[0113] Train the long time series attention network based on the training sample set;

[0114] Calculate the mean square error between the interpolated sequence output by the long time series attention network and the corresponding observation time series, adjust the network parameters according to this mean square error and re-input the adjusted network parameters into the long time series attention network;

[0115] The interpolation training steps are repeated until the interpolation loss function converges; the interpolation loss function is the mean squared error between the interpolated sequence output by the long time series attention network and the corresponding observation time series.

[0116] In some embodiments, the long time series attention network when both the prediction loss function and the interpolation loss function converge is a trained long time series attention network, and the trained long time series attention network is used to interpolate the predicted time series.

[0117] In some embodiments, the method 100 further includes:

[0118] The autoregressive generation method is used to interpolate the forecast time series, generate a complete forecast time series and output it;

[0119] Specifically, if the obtained predicted time series is a time series with vacancies, the long time series attention network generates the first interpolation value based on the predicted time series before the vacant time point, and then generates the second interpolation value based on the time series before the first interpolation value. In this way, all interpolation values ​​corresponding to the vacant time series can be generated, and all the generated interpolation values ​​are filled into the corresponding vacant time points to obtain a complete predicted time series.

[0120] In some embodiments, an autoregressive generation method is used to calculate an interpolation sequence based on the predicted time series before the missing time point, so as to calculate the next interpolation sequence based on the interpolation sequence, thereby obtaining a complete predicted time series.

[0121] In some embodiments, the method 100 further includes:

[0122] Determine the abnormal sequence based on the complete forecast time series and the actual observation sequence corresponding to the complete forecast time series;

[0123] Specifically, on the training sample set, several minimum time series units are randomly perturbed to simulate anomalies, and the above-mentioned time prediction method is used to generate the corresponding predicted time series for these perturbed time segments. The error series is obtained by calculating the mean square error (MSE) between the predicted time series and its corresponding actual observation series. , U is the error sequence The total time steps in represents the error data corresponding to the u-th time step in the error sequence, The first time segment generated after the disturbance A forecast time series, Represents The corresponding actual observation sequence, v represents the number of time segments of the disturbance, and the error sequence is used to find the anomaly threshold for anomaly detection;

[0124] For this error sequence Perform distribution analysis and select quantiles As anomaly threshold ,Right now ,in, Represents the error sequence of Quantile, for confidence levels exceeding anomaly thresholds time segment, that is, satisfying time step, marking it as a potential abnormal location;

[0125] After the anomaly detection training is completed, in actual application, the corresponding error sequence is obtained by calculating the mean square error between the complete predicted time series and its corresponding actual observation sequence, and the confidence level of the error sequence exceeds the anomaly threshold. The time segments are marked as abnormal sequences.

[0126] S130: Predicting the status of the pollution control equipment to be predicted based on the prediction time series.

[0127] In some embodiments, the time series to be predicted is input into a long time series attention network to generate a group of predicted time series, which is then spliced ​​with the time series to be predicted and input into the long time series attention network as a new time series to be predicted to generate a predicted time series for the next time step. This process continues until the generated predicted time series reaches a preset target length. If the length of the generated predicted time series exceeds the preset target length, the excess part at the end of the predicted time series is cut off to ensure that the length of the generated predicted time series is consistent with the preset target length.

[0128] According to the disclosed embodiments, various data items related to the pollution control equipment to be predicted are preprocessed to obtain a time series to be predicted. This time series is then fed into a long-term attention network, which uses its local causal attention module to obtain local attention information about the time series to be predicted, and its long-term compressed memory module to obtain historical information about the pollution control equipment to be predicted. Based on this local attention information and historical information, the network outputs a predicted time series. Based on this predicted time series, the state of the pollution control equipment to be predicted is predicted. This significantly improves the accuracy and flexibility of long-term predictions, adapting to time series of varying lengths and addressing the sparsity of pollution control equipment state data.

[0129] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0130] The above is an introduction to the method embodiment. The following is a further explanation of the solution disclosed in the present disclosure through an apparatus embodiment.

[0131] Figure 4 The following is a diagram showing the structure of a pollution control equipment state prediction device based on a long time series attention network provided by an embodiment of the present disclosure. The device 400 includes:

[0132] The module 410 for obtaining the time series to be predicted is used to pre-process various data of the pollution control equipment to be predicted and obtain the time series to be predicted.

[0133] In some embodiments, the module for obtaining the time series to be predicted 410 is specifically configured to:

[0134] The preprocessing comprises:

[0135] Normalize various data of the pollution control equipment to be predicted and obtain the normalized time series;

[0136] According to the preset sequence length, the normalized time series is divided into multiple time segments, and the multiple time segments are used as the time series to be predicted.

[0137] The predicted time series output module 420 is used to input the time series to be predicted into the long time series attention network, so that the long time series attention network uses its own local causal attention module to obtain the local attention information of the time series to be predicted, and uses its own long-term compressed memory module to obtain the historical information of the pollution control equipment to be predicted, and outputs the predicted time series based on the local attention information and historical information.

[0138] In some embodiments, the predicted time series output module 420 is specifically configured to:

[0139] The method of using its own local causal attention module to obtain local attention information of the time series to be predicted includes:

[0140] In the local causal attention module, the projection matrix is ​​used to calculate the attention query value, key-value pair and value matrix of the time series to be predicted;

[0141] According to the attention query value, key-value pair and value matrix of the time series to be predicted, the local attention context representation of the time series to be predicted is calculated using the function.

[0142] In some embodiments, the predicted time series output module 420 is further configured to:

[0143] The method of using its own long-term compressed memory module to obtain historical information of the pollution control equipment to be predicted includes:

[0144] According to the attention query value of the time series to be predicted, the historical information of the pollution control equipment to be predicted is retrieved from the long-term compressed memory module.

[0145] In some embodiments, the predicted time series output module 420 is further configured to:

[0146] Outputting a predicted time series according to the local attention information and historical information includes:

[0147] Concatenating the local attention information with the historical information to generate a comprehensive context representation;

[0148] Performing linear projection on the comprehensive context representation using a linear projection layer;

[0149] The linearly projected data is passed through the layer normalization module, the fully connected layer, and the residual connection layer in sequence to obtain the predicted time series.

[0150] In some embodiments, the apparatus 400 is further configured to:

[0151] The autoregressive generation method is used to interpolate the forecast time series to generate a complete forecast time series.

[0152] The pollution equipment state prediction module 430 is used to predict the state of the pollution control equipment to be predicted based on the prediction time series.

[0153] In some embodiments, the apparatus 400 is further configured to:

[0154] The abnormal sequence is determined based on the complete forecast time series and the actual observation sequence corresponding to the complete forecast time series.

[0155] It is understandable that Figure 4 Each module / unit in the illustrated device 400 has the function of implementing each step in the method 100 provided in the embodiment of the present disclosure and can achieve its corresponding technical effect. For the sake of brevity, they will not be described in detail here.

[0156] Figure 5A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. Electronic device 500 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 500 may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0157] like Figure 5 As shown, electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. RAM 503 can also store various programs and data required for the operation of electronic device 500. Computing unit 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An I / O interface 505 is also connected to bus 504.

[0158] Multiple components in the electronic device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a magnetic disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0159] Computing unit 501 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Computing unit 501 performs the various methods and processes described above, such as method 100. For example, in some embodiments, method 100 can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed onto electronic device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by computing unit 501, one or more steps of method 100 described above can be performed. Alternatively, in other embodiments, computing unit 501 can be configured to perform method 100 in any other suitable manner (e.g., via firmware).

[0160] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0161] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0162] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0163] It should be noted that the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute method 100 and achieve the corresponding technical effect achieved by executing the method in the embodiment of the present disclosure. For the sake of concise description, they will not be repeated here.

[0164] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0165] The systems and techniques described herein can be implemented on a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with the systems and techniques described herein).

[0166] The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0167] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0168] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0169] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A pollution control equipment state prediction method based on long time series attention network, characterized in that: include: Preprocess various data of pollution control equipment to be predicted to obtain the time series to be predicted; The time series to be predicted is input into a long-term attention network, so that the long-term attention network calculates the attention query value, key-value pair and value matrix of the time series to be predicted in the local causal attention module using a projection matrix, and calculates the local attention context representation of the time series to be predicted using a function according to the attention query value, key-value pair and value matrix of the time series to be predicted; retrieves historical information of the pollution control equipment to be predicted from the long-term compressed memory module according to the attention query value of the time series to be predicted; splices the local attention information and the historical information to generate a comprehensive context representation, linearly projects the comprehensive context representation using a linear projection layer, and sequentially passes the linearly projected data through a layer normalization module, a fully connected layer, and a residual connection layer to obtain a predicted time series; The state of the pollution control equipment to be predicted is predicted according to the prediction time series.

2. The method according to claim 1, characterized in that The preprocessing comprises: Normalize various data of the pollution control equipment to be predicted and obtain the normalized time series; According to the preset sequence length, the normalized time series is divided into multiple time segments, and the multiple time segments are used as the time series to be predicted.

3. The method according to claim 1, characterized in that The method further comprises: The autoregressive generation method is used to interpolate the forecast time series, generate a complete forecast time series and output it.

4. The method according to claim 3, characterized in that The method further comprises: The abnormal sequence is determined based on the complete forecast time series and the actual observation sequence corresponding to the complete forecast time series.

5. A pollution control equipment state prediction device based on a long time series attention network, characterized in that: include: The module for obtaining the time series to be predicted is used to preprocess various data of the pollution control equipment to be predicted and obtain the time series to be predicted; A predicted time series output module is used to input the time series to be predicted into the long-term series attention network, so that the long-term series attention network uses the projection matrix to calculate the attention query value, key-value pair and value matrix of the time series to be predicted in the local causal attention module, and uses the function to calculate the local attention context representation of the time series to be predicted based on the attention query value, key-value pair and value matrix of the time series to be predicted; retrieve the historical information of the pollution control equipment to be predicted from the long-term compressed memory module based on the attention query value of the time series to be predicted; splice the local attention information and the historical information to generate a comprehensive context representation, use the linear projection layer to linearly project the comprehensive context representation, and pass the linearly projected data through the layer normalization module, the fully connected layer, and the residual connection layer in sequence to obtain the predicted time series; The pollution equipment state prediction module is used to predict the state of the pollution control equipment to be predicted based on the prediction time series.

6. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-4.

Images