An operation and maintenance data prediction method and system based on adaptive adjustment of location information

Abstract

The application discloses an operation and maintenance data prediction method and system based on adaptive adjustment of position information, and the method comprises the following steps: obtaining historical operation and maintenance data, and constructing a time series data set of operation and maintenance data; position coding embedding is performed on all time series data in the time series data set, all time series data embedded with position coding are decomposed into seasonal terms and trend terms; the trend terms are adjusted according to the periodic information in the seasonal terms, and adaptive terms are constructed for each time series data by using the seasonal terms and the adjusted trend terms; the seasonal terms, the adjusted trend terms and the adaptive terms of each time series data are fused respectively to obtain fused time series feature representations; and the fused time series feature representations are input into a Transformer network to obtain a prediction result of operation and maintenance data.

Description

Technical Field

[0001] The present invention relates to the field of operation and maintenance data prediction, and in particular to an operation and maintenance data prediction method and system based on adaptive adjustment of location information. Background Art

[0002] Amidst the wave of digital transformation, enterprises are placing higher demands on the efficient operation and maintenance of production equipment, facilities, and systems. To ensure the continuity and stability of production processes, timely detection and prevention of potential failures are crucial. With the advancement of sensor technology and the Internet of Things (IoT), various devices in factories can collect large amounts of real-time operational data, such as temperature, pressure, vibration, power consumption, and other parameters. This data forms a complex time-series dataset. Effectively utilizing this data for analysis and prediction can help enterprises predict equipment failures, optimize maintenance plans, improve production efficiency, and reduce operating costs.

[0003] Currently, deep learning technologies, particularly positional embedding, have been widely applied to time series forecasting tasks. Positional embedding captures the location information in a time series, enhancing the model's understanding of characteristics at different time points, thereby improving forecasting accuracy. By embedding location information into operational data, this approach enables the model to better understand how data changes over time, making accurate forecasting possible.

[0004] Although location embedding technology has shown potential in operation and maintenance data prediction, existing methods still face challenges in dealing with complex time dependencies. In particular, when faced with operation and maintenance data with non-stationary or multi-scale temporal patterns, traditional location encoding methods often find it difficult to effectively capture the deep characteristics of the data, making existing time series decomposition methods insufficient in terms of precision and dynamic adjustment of the relationship between seasonal terms, trend terms, and location information. These problems limit the model's prediction performance under complex operation and maintenance conditions, especially in scenarios that require high-precision and real-time predictions. Therefore, the development of more refined and flexible time series analysis and prediction methods is an urgent problem to be solved in the current field of operation and maintenance data prediction. Summary of the Invention

[0005] The present invention proposes an operation and maintenance data prediction method and system based on adaptive adjustment of location information, which solves the problem that existing operation and maintenance data prediction methods cannot dynamically adjust the relationship between seasonal items, trend items and location information of operation and maintenance time series data.

[0006] To solve the above technical problems, the present invention provides an operation and maintenance data prediction method based on adaptive adjustment of location information, comprising the following steps:

[0007] Step S1: Obtain historical operation and maintenance data and construct a time series data set of operation and maintenance data;

[0008] Step S2: Perform position encoding embedding on all time series data in the time series data set, and decompose all embedded position encoded time series data into seasonal items and trend items;

[0009] Step S3: adjusting the trend item according to the periodic information in the season item, and constructing an adaptive item for each time series data using the season item and the adjusted trend item;

[0010] Step S4: fusing the seasonal item, the adjusted trend item, and the adaptive item of each time series data respectively to obtain a fused time series feature representation;

[0011] Step S5: Input the fused time series feature representation into the Transformer network to obtain the prediction results of the operation and maintenance data.

[0012] Preferably, in step S2, the expression for position encoding and embedding all the time series data in the time series data set is:

[0013] X PE =X+PE(X);

[0014]

[0015] In the above formula, X PE is the time series data after embedding position encoding; X is the time series data; PE(X) represents the position embedding of X; pos is the position index; i is the dimension index; d is the embedding dimension.

[0016] Preferably, in step S2, the expression for decomposing the time series data after embedding position encoding into seasonal terms and trend terms is:

[0017] D t =AvgPool(Padding(X PE ));

[0018] D s =X PE -D t ;

[0019] In the above formula, D t 、D s They are the trend item and seasonal item of the time series data set respectively; AvgPool means moving average; Padding means filling the sequence.

[0020] Preferably, in step S3, the expression for adjusting the trend item according to the periodic information in the season item is:

[0021] D p =Dt -PE(D t );

[0022] Where D p is the adjusted trend item.

[0023] Preferably, the expression for constructing the adaptive term for each time series data using the seasonal term and the adjusted trend term in step S3 is:

[0024] H=D s +D p ⊙softmax(D s );

[0025] Where H is the adaptive term; ⊙ represents the element-wise multiplication; and softmax is the activation function.

[0026] Preferably, the expression for fusing the seasonal term, the adjusted trend term and the adaptive term in step S4 is:

[0027] E=(D s W s +b s )+(D p W p +b p )+(HW h +b h );

[0028] Where, E is the fused time series feature representation; D s 、D p , H are the seasonal term, the adjusted trend term and the adaptive term of the time series data set respectively; W s 、W p 、W h D s 、D p , the weight matrix of H; b s 、b p 、b h D s 、D p , the bias term of H.

[0029] Preferably, in step S5, the fused time series feature representation is used as the input sequence of the Transformer network, the encoder of the Transformer network is used to perform deep feature extraction on the input sequence, and the feature representation output by the encoder is input into the fully connected layer of the Transformer network to be mapped into the prediction result of the operation and maintenance data.

[0030] Preferably, the encoder calculates the correlation between the query vector, key vector, and value vector of the input sequence through a multi-head attention mechanism, models the global dependency relationship of each time position in the input sequence, performs residual connection and layer normalization on the output of the multi-head attention mechanism, inputs the output into a feedforward neural network for nonlinear transformation, and again performs residual connection and layer normalization to obtain the final encoder output;

[0031] The expression of the multi-head attention mechanism is:

[0032] MultiHead(Q,K,V)=Concat(head1,...,head h )W O ;

[0033]

[0034] The expressions of the residual connection and layer normalization processing are:

[0035] E'=LayerNorm(E+MultiHead(E,E,E));

[0036] The expression for the nonlinear transformation of the input feedforward neural network is:

[0037] FFN(E')=max(0,(E'W1+b1)W2+b2);

[0038] The output of the encoder is expressed as:

[0039] Z = LayerNorm(E'+FFN(E'));

[0040] In the above formula, MultiHead is the multi-head attention mechanism; Q, K, and V are the query vector, key vector, and value vector of the multi-head attention mechanism respectively; Concat is the connection function; head i is the i-th head of the multi-head attention mechanism; W O is a learnable parameter; Attention is the attention weight; Head i The projection matrix of the query vector, key vector and value vector; softmax is the activation function; d is the embedding dimension; E' is the time series feature representation after residual connection and layer normalization; E is the fused time series feature representation; Z is the output of the encoder; LayerNorm is the layer normalization function; FFN is the output of the feedforward neural network; W1 and W2 are the weight matrices of E'; b1 and b2 are the bias terms of E'.

[0041] Preferably, the expression for the prediction result of the operation and maintenance data in step S5 is:

[0042] Y=ZW y +b y ;

[0043] Where Y is the prediction result of operation and maintenance data; is the weight matrix of Y, and f is the length of the prediction result; is the bias term of Y.

[0044] The present invention also provides an operation and maintenance data prediction system based on adaptive adjustment of position information, which is implemented based on the above-mentioned operation and maintenance data prediction method based on adaptive adjustment of position information, and includes: a data acquisition module, a position code embedding module, a sequence decomposition module, a sequence fusion module, a feature encoding module and a data prediction module;

[0045] The data collection module collects historical operation and maintenance data and constructs an operation and maintenance time series data set;

[0046] The position code embedding module is used to embed position codes into all the operation and maintenance time series data in the operation and maintenance time series data set;

[0047] The sequence decomposition module decomposes the operation and maintenance time series data after embedding position coding to obtain the seasonal items and trend items of the operation and maintenance time series data;

[0048] The sequence fusion module: constructs an adaptive term using the seasonal term and the adjusted trend term, fuses the seasonal term, the adjusted trend term and the adaptive term to obtain a fused time series feature representation;

[0049] The feature encoding module uses a Transformer network encoder to perform deep feature extraction on the fused time series feature representation;

[0050] The data prediction module inputs the feature representation output by the feature encoding module into the fully connected layer of the Transformer network for prediction, and optimizes the parameters of the Transformer network using the mean square error loss function.

[0051] The benefits of the present invention include at least:

[0052] 1. Position codes are embedded in the operation and maintenance time series data. The embedding of position codes can enhance the model's ability to identify different position features in the time series, helping to capture seasonal changes and trend changes in the operation and maintenance time series data;

[0053] 2. Decomposing the time series into seasonal and trend terms can enable the model to more accurately identify and understand the cyclical changes and long-term trends in the data. Adjusting the trend term based on the cyclical information in the seasonal term can make the trend term more consistent with the actual cyclical changes, which helps to improve the accuracy of the model prediction.

[0054] 3. By constructing adaptive terms, the model can dynamically adjust the relationship between seasonal terms, trend terms and location information, so that the model can adapt to different operation and maintenance conditions and changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 Schematic diagram of a method flow in an embodiment of the present invention;

[0056] Figure 2 The figure is a flow chart of obtaining a fused operation and maintenance time series data set in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The following is a clear and complete description of the technical solutions in the embodiments of the present invention, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts are within the scope of protection of the present invention.

[0058] Operational time series data is a collection of data arranged in chronological order, and is commonly found in fields such as power analysis and weather forecasting. The core of time series forecasting is to build a temporal evolution model between historical data points to predict future numerical changes.

[0059] There is a set of operation and maintenance time series data sets containing multiple variables Where m represents the total number of time steps in the time series, and n represents the number of multivariate variables. Define a historical lookback window of length l Based on the given historical lookback window X l Predict the output Y for the next f time steps f = This prediction process can be achieved through f =δ(X l ) expression, where δ is the constructed prediction model. The prediction task involves using X l To predict Y f , where Y f =δ(X l ), δ is the prediction model.

[0060] Compared to other types of data, time series data often lacks clear semantic information, making positional features in the data crucial for time series prediction tasks. Therefore, before training a multivariate time series prediction model, it is necessary to effectively extract positional features from the time series data to enhance the model's expressive power and prediction accuracy. This feature extraction process can be represented as a mapping from raw time series data to a d-dimensional representation space:

[0061] To this end, the present invention proposes an operation and maintenance data prediction method based on adaptive adjustment of location information. This method can not only effectively capture the time and location information in the data, but also reduce noise interference through adaptive adjustment mechanism and improve the generalization ability of the model. The overall flow chart of this method is as follows Figure 1 As shown in the figure, by integrating position information and adaptive adjustment strategy, efficient and accurate representation learning of time series data is achieved.

[0062] Specifically, the method includes the following steps:

[0063] Step S1: Collect historical operation and maintenance data and construct an operation and maintenance time series data set. Divide the operation and maintenance time series data set and perform the initial operation and maintenance time series data X * Perform standardized preprocessing to obtain operation and maintenance time series data The expression for standardized preprocessing is:

[0064]

[0065] Where, X is the pre-processed operation and maintenance time series data; x * is the original operation and maintenance time series data; μ is the mean of the operation and maintenance time series data; σ is the standard deviation of the operation and maintenance time series data.

[0066] This normalization process can eliminate the dimensional differences between different features, allowing the model to better learn the intrinsic patterns of the data.

[0067] Step S2: Perform position encoding embedding on all operation and maintenance time series data in the operation and maintenance time series dataset, and decompose all embedded position encoded operation and maintenance time series data into seasonal items and trend items.

[0068] Specifically, for the input operation and maintenance time series data X, we first perform position embedding on it, then add it to the original data and perform time series decomposition of seasonality and trend terms. The expression for position encoding embedding of the operation and maintenance time series dataset is:

[0069] X PE =X+PE(X);

[0070]

[0071] In the above formula, XPE is the operation and maintenance time series data after embedding position encoding; X is the operation and maintenance time series data; PE(X) represents the position embedding of X; pos is the position index; i is the dimension index; d is the embedding dimension.

[0072] The expression for decomposing the operation and maintenance time series dataset after embedding position encoding is:

[0073] D t =AvgPool(Padding(X PE ));

[0074] D s =X PE -D t ;

[0075] In the above formula, D t 、D s They are the trend item and seasonal item of the operation and maintenance time series dataset; AvgPool indicates moving average; Padding indicates padding the sequence to keep the length of the sequence unchanged.

[0076] This decomposition method can effectively separate periodic patterns and long-term trends in time series data, laying the foundation for subsequent adaptive adjustments.

[0077] Step S3: Adjust the trend item according to the periodic information in the season item, and use the season item and the adjusted trend item to construct an adaptive item for each operation and maintenance time series data.

[0078] Specifically, the expression for adjusting the trend term is:

[0079] D p =D t -PE(D t );

[0080] Where D p is the adjusted trend term; PE(X) represents position embedding.

[0081] The expression for constructing the adaptive term using the seasonal term and the adjusted trend term is:

[0082] H=Ds+Dp⊙softmax(Ds);

[0083] Where H is the adaptive term; ⊙ represents the element-wise multiplication; and softmax is the activation function.

[0084] This step removes the noise position information in the trend term and uses the periodic information in the seasonal term to guide the adjustment of the trend term. Furthermore, the introduction of the softmax activation function enables the model to adaptively focus on important features in the seasonal term, thereby more effectively guiding the adjustment of the trend term.

[0085] Step S4: The seasonal item, the adjusted trend item, and the adaptive item of each operation and maintenance time series data are fused respectively to obtain a fused time series feature representation.

[0086] Specifically, the features are fused to obtain an enhanced embedding representation

[0087] E=(D s W s +b s )+(D p W p +b p )+(HW h +b h );

[0088] Where, E is the fused operation and maintenance time series dataset; D s 、D p , H are the seasonal term, adjusted trend term and adaptive term of the operation and maintenance time series dataset respectively; W s 、W p 、W h D s 、D p , the weight matrix of H; b s 、b p 、b h D s 、D p , the bias term of H.

[0089] Step S5: Input the fused time series feature representation into the Transformer network to obtain the prediction results of the operation and maintenance data.

[0090] Specifically, the fused time series feature representation is used as the input sequence of the Transformer network, and the Transformer network encoder performs deep feature extraction on the input sequence. The encoder uses a multi-head attention mechanism to calculate the correlation between the query vector, key vector, and value vector of the input sequence, modeling the global dependency relationship between each time position in the input sequence. The output of the multi-head attention mechanism is residually connected and layer-normalized, and then input into a feedforward neural network for nonlinear transformation. It then undergoes residual connection and layer-normalization again to obtain the final encoder output.

[0091] The expression of the multi-head attention mechanism is:

[0092] MultiHead(Q,K,V)=Concat(head1,...,head h )W O ;

[0093]

[0094] The expressions for residual connection and layer normalization are:

[0095] E'=LayerNorm(E+MultiHead(E,E,E)).

[0096] The expression for nonlinear transformation of the input feedforward neural network is:

[0097] FFN(E')=max(0,(E'W1+b1)W2+b2).

[0098] The final expression of the encoder output is:

[0099] Z = LayerNorm(E'+FFN(E')).

[0100] In the above formula, MultiHead is the multi-head attention mechanism; Q, K, and V are the query vector, key vector, and value vector of the multi-head attention mechanism respectively; Concat is the connection function; head i is the i-th head of the multi-head attention mechanism; W O is a learnable parameter; Attention is the attention weight; Head i The projection matrix of the query vector, key vector and value vector; softmax is the activation function; d is the dimension of the key vector, that is, the embedding dimension; E' is the time series feature representation after residual connection and layer normalization; E is the fused time series feature representation; Z is the output of the encoder; LayerNorm is the layer normalization function; FFN is the output of the feedforward neural network; W1 and W2 are the weight matrices of E'; b1 and b2 are the bias terms of E'.

[0101] The feature representation output by the encoder is then input into the fully connected layer of the Transformer network and mapped to the prediction result of the operation and maintenance data:

[0102] Y=ZW y +b y ;

[0103] Where Y is the prediction result of operation and maintenance data; is the weight matrix of Y, and f is the length of the prediction result; is the bias term of Y.

[0104] To train the model and evaluate its performance, MSE is used as the loss function for the Transformer network:

[0105]

[0106] Where y ji and denote the true value and predicted value of the j-th variable at the i-th step, respectively. The choice of MSE loss function is based on its wide application and mathematical properties in regression problems.

[0107] The present invention also provides an operation and maintenance data prediction system based on adaptive adjustment of position information, which is implemented based on the above-mentioned operation and maintenance data prediction method based on adaptive adjustment of position information, and includes: a data acquisition module, a position coding embedding module, a sequence decomposition module, a sequence fusion module, a feature coding module and a data prediction module.

[0108] The data collection module is used to collect historical operation and maintenance data and construct an operation and maintenance time series data set.

[0109] The position coding embedding module is used to perform position coding embedding on all operation and maintenance time series data in the operation and maintenance time series dataset.

[0110] The sequence decomposition module is used to decompose the operation and maintenance time series data after embedding position encoding to obtain the seasonal items and trend items of the operation and maintenance time series data.

[0111] The sequence fusion module uses the seasonal term and the adjusted trend term to construct the adaptive term, and fuses the seasonal term, the adjusted trend term and the adaptive term to obtain the fused time series feature representation.

[0112] The feature encoding module uses the encoder of the Transformer network to perform deep feature extraction on the fused time series feature representation.

[0113] The data prediction module inputs the feature representation output by the feature encoding module into the fully connected layer of the Transformer network for prediction, and uses the mean square error loss function to optimize the parameters of the Transformer network.

[0114] The advantages of the method of the present invention are verified by experiments below:

[0115] 1. Data Description

[0116] In order to verify the effectiveness of the time series prediction of the present invention, the embodiment of the present invention adopts the ETT power operation and maintenance data set, which contains a variety of operation and maintenance indicators, such as load and oil temperature, including a data set sampled every hour (ETTh2) and a data set sampled every 15 minutes (ETTm2).

[0117] 2. Description of Benchmark Methodology

[0118] To evaluate the effectiveness of this invention, a comparative validation scheme was designed. Specifically, the method was compared with existing mainstream time series models. These models can be divided into two categories: Transformer-based models (iTransformer, Non-stationary, Autoformer), and non-Transformer models (TimesNet, DLinear, and SCINet).

[0119] 3. Experimental Setup

[0120] In order to ensure a fair comparison between the model of the present invention and the comparison model, the experiment strictly reproduced these comparison methods according to the methods described in the iTransformer paper, and conducted a fair comparison using officially provided or hosted codes. All experiments were conducted in an environment equipped with an NVIDIA Tesla P100 GPU and implemented using the PyTorch framework. Adam was selected as the optimizer, the initial learning rate was set in the range of {0.0001, 0.0005, 0.001}, the number of training rounds was 10, and the batch size was 32. The hyperparameter adjustment range of all Transformer layers in the model was {2, 3, 4}, the hidden layer dimension adjustment range was set to {128, 256, 512}, and the Dropout value was set to 0.1. In addition, the evaluation indicators used were mean square error (MSE) and mean absolute error (MAE), which are widely used in time series prediction tasks and can fully reflect the prediction accuracy of the model.

[0121] 4. Results of Algorithm Performance Comparison

[0122] To compare the performance of different models for predicting maintenance time series data, the experiments uniformly set the input length to 96 time steps. The prediction lengths of the evaluation models were 96, 192, 336, and 720 time steps, respectively. The experimental results are shown in Table 1 below, where MSE is the mean squared error and MAE is the mean absolute error.

[0123] Table 1 Comparison of prediction results

[0124]

[0125]

[0126] The experimental results in Table 1 demonstrate that the proposed time series prediction method achieves state-of-the-art performance across 16 experimental settings. Compared to the current best Transformer-based model, iTransformer, and the best non-Transformer-based model, TimesNet, the proposed method achieves an average mean square error (MSE) reduction of 1.40% and 5.91%, respectively. This result strongly demonstrates that decomposing time series and leveraging seasonal cycles to manipulate trend and position information can significantly improve embedding performance. Furthermore, other recent innovative models, such as DLinear (using seasonal trend decomposition and channel independence), Non-stationary (using a non-stationary attention mechanism to construct time series information), and SCINet (using recursive downsampling convolutional interactions), while modeling time series information to varying degrees, fail to surpass the performance of our proposed method in most cases. Overall, the experimental results of our proposed method on real-world operational and maintenance datasets demonstrate superior performance and excellent applicability. This further validates the robustness of our time series modeling capabilities and emphasizes the importance of accurately identifying time series position information in time series tasks.

[0127] The present invention effectively solves the problem of poor performance of standard position embedding in time series prediction tasks through an improved adaptive position embedding mechanism, and can better capture the periodicity and long-term trend information in operation and maintenance data. By removing the noise position information in the trend term, the interference of irrelevant information on the model prediction is effectively reduced, and the prediction accuracy is significantly improved. By using the periodic information in the seasonal term to guide the adjustment of the trend term, the model can adaptively focus on the important features in the time series data, enhancing the flexibility and generalization ability of the model. In addition, by linearly transforming and fusing the seasonal term, the adjusted trend term and the adaptive term, a richer and more accurate time series representation can be obtained, providing high-quality feature input for subsequent prediction tasks. In summary, the present invention effectively improves the representation ability of time series data through innovative time series decomposition and adaptive adjustment mechanisms. This method has good interpretability in theory and has also demonstrated superior performance in practice, which is of great significance for improving the accuracy of operation and maintenance predictions.

[0128] The technical features of the above embodiments may be combined in any manner. To simplify the description, not all possible combinations of the technical features in the above embodiments are described. Only preferred embodiments of the present invention are presented. While the description is relatively specific and detailed, it should not be construed as limiting the scope of the present invention. As long as there are no contradictions in the combination of these technical features, they should be considered to be within the scope of this specification.

[0129] It should be noted that those skilled in the art may make various modifications and improvements without departing from the scope of the present invention, and these modifications and improvements fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be based on the appended claims.

Claims

1. A method for predicting operation and maintenance data based on adaptive adjustment of location information, characterized in that: The following steps are involved: Step S1: Obtain historical operation and maintenance data and construct a time series data set of operation and maintenance data; Step S2: Perform position encoding embedding on all time series data in the time series dataset: The expression for position encoding embedding of all time series data in the time series dataset is: X PE =X+PE(X); In the above formula, X PE is the time series data after embedding position encoding; X is the time series data; PE(X) represents the position embedding of X; pos is the position index; i is the dimension index; d is the embedding dimension; Decompose all embedded position encoded time series data into seasonal terms and trend terms: D t =AvgPool(Padding(X PE )); D s =X PE -D t ; In the above formula, D t 、D s They are the trend item and seasonal item of the time series data set respectively; AvgPool means moving average; Padding means filling the sequence; Step S3: Adjust the trend item according to the periodic information in the season item: D p =D t -PE(D t ); Where D p is the adjusted trend item; Construct an adaptive term for each time series data using the seasonal term and the adjusted trend term: H=D s +D p ⊙softmax(D s ); Where H is the adaptive term; ⊙ represents the element-wise multiplication; softmax is the activation function; Step S4: fusing the seasonal item, the adjusted trend item, and the adaptive item of each time series data respectively to obtain a fused time series feature representation; Step S5: Input the fused time series feature representation into the Transformer network to obtain the prediction results of the operation and maintenance data.

2. The method for predicting operation and maintenance data based on adaptive adjustment of location information according to claim 1, characterized in that: The expression for fusing the seasonal term, the adjusted trend term, and the adaptive term in step S4 is: E=(D s W s +b s )+(D p W p +b p )+(HW h +b h ); Where, E is the fused time series feature representation; D s 、D p , H are the seasonal term, the adjusted trend term and the adaptive term of the time series data set respectively; W s 、W p 、W h D s 、D p , the weight matrix of H; b s 、b p 、b h D s 、D p , the bias term of H.

3. The method for predicting operation and maintenance data based on adaptive adjustment of location information according to claim 1, characterized in that: In step S5, the fused time series feature representation is used as the input sequence of the Transformer network, the encoder of the Transformer network is used to perform deep feature extraction on the input sequence, and the feature representation output by the encoder is input into the fully connected layer of the Transformer network to be mapped into the prediction result of the operation and maintenance data.

4. The method for predicting operation and maintenance data based on adaptive adjustment of location information according to claim 3, characterized in that: The encoder calculates the correlation between the query vector, key vector, and value vector of the input sequence through a multi-head attention mechanism, models the global dependency relationship of each time position in the input sequence, performs residual connection and layer normalization on the output of the multi-head attention mechanism, inputs it into a feedforward neural network for nonlinear transformation, and again performs residual connection and layer normalization to obtain the final encoder output; The expression of the multi-head attention mechanism is: MultiHead(Q,K,V)=Concat(head1,...,head h )W O ; head i =Attention(QW i Q ,KW i K ,VW i v ); The expressions of the residual connection and layer normalization processing are: E'=LayerNorm(E+MultiHead(E,E,E)); The expression for the nonlinear transformation of the input feedforward neural network is: FFN(E')=max(0,(E'W1+b1)W2+b2); The output of the encoder is expressed as: Z = LayerNorm(E'+FFN(E')); In the above formula, MultiHead is the multi-head attention mechanism; Q, K, and V are the query vector, key vector, and value vector of the multi-head attention mechanism respectively; Concat is the connection function; head i is the i-th head of the multi-head attention mechanism; W O is a learnable parameter; Attention is the attention weight; W i Q 、W i K 、W i v Head i The projection matrix of the query vector, key vector and value vector; softmax is the activation function; d is the embedding dimension; E' is the time series feature representation after residual connection and layer normalization; E is the fused time series feature representation; Z is the output of the encoder; LayerNorm is the layer normalization function; FFN is the output of the feedforward neural network; W1 and W2 are the weight matrices of E'; b1 and b2 are the bias terms of E'.

5. The method for predicting operation and maintenance data based on adaptive adjustment of location information according to claim 4, characterized in that: The expression for the prediction result of the operation and maintenance data in step S5 is: Y=ZW y +b y ; Where Y is the prediction result of operation and maintenance data; is the weight matrix of Y, and f is the length of the prediction result; is the bias term of Y.

6. An operation and maintenance data prediction system based on adaptive adjustment of location information, implemented based on the operation and maintenance data prediction method based on adaptive adjustment of location information according to any one of claims 1 to 5, characterized in that: include: Data acquisition module, position coding embedding module, sequence decomposition module, sequence fusion module, feature coding module and data prediction module; The data acquisition module collects historical operation and maintenance data and constructs an operation and maintenance time series data set; The position code embedding module is used to embed position codes into all the operation and maintenance time series data in the operation and maintenance time series data set; The sequence decomposition module decomposes the operation and maintenance time series data after embedding position coding to obtain the seasonal items and trend items of the operation and maintenance time series data; The sequence fusion module: constructs an adaptive term using the seasonal term and the adjusted trend term, fuses the seasonal term, the adjusted trend term and the adaptive term to obtain a fused time series feature representation; The feature encoding module uses a Transformer network encoder to perform deep feature extraction on the fused time series feature representation; The data prediction module inputs the feature representation output by the feature encoding module into the fully connected layer of the Transformer network for prediction, and optimizes the parameters of the Transformer network using the mean square error loss function.

Images