Generator set anomaly detection method based on edge computing

Abstract

The application discloses a kind of generator set anomaly detection methods based on edge computing, S1. Generation standardization generator set multi-channel operating condition data;S2. Lightweight long short-term memory network prediction model is deployed in the inside of industrial edge computing node;S3. Multimodal residual atlas is constructed;S4. Local residual sequence is discriminated to generator set anomaly and exports generator set anomaly candidate event;S5. Generator set anomaly candidate event is generated generator set anomaly causal explanation graph using explanatory analysis algorithm, and generator set anomaly causal explanation graph reveals the contribution relationship of each operating condition characteristic to generator set anomaly confidence.This application significantly improves the traceability and operability of fault location, and assists operation and maintenance personnel to formulate maintenance strategy accurately.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of generator set, and particularly relates to a generator set abnormality detection method based on edge computing. BACKGROUND

[0002] With the wide application of new generation information technology in the energy industry, the intelligent operation and maintenance level of the generator set is continuously improved, and the key tasks of equipment state monitoring, fault early warning and abnormality diagnosis gradually transit from manual inspection to automation and intelligence. Traditional unit abnormality detection usually relies on centralized SCADA system or remote monitoring platform, and abnormality identification and fault positioning are performed on the back-end server through the collection of operation data of the control system and sensor network. However, the centralized processing architecture has the following typical problems: firstly, the raw data needs to be transmitted to the remote server for processing, which is easy to cause bandwidth bottleneck, especially in the multi-channel high-frequency data scene, the data transmission delay is high, and it is difficult to meet the requirements of high real-time and response speed; secondly, the unified analysis and processing on the remote server lacks the adaptation ability to the specific operation environment of the edge scene, and it is difficult to respond sensitively to local abnormal changes; thirdly, the fault features of some key components are early subtle statistical disturbances or frequency domain signal changes, which lack sufficient time resolution and spatial granularity, causing misjudgment or missed detection.

[0003] In terms of models, most existing methods use static feature extraction and fixed window statistical analysis to model and judge the unit operation state, which fails to fully utilize the dynamic evolution characteristics of long time series data, and cannot deeply capture the working condition trend change and short-time disturbance signal pattern. At the same time, most existing models are deployed on the cloud or central server, which occupies high computing resources and is not suitable for deployment on edge nodes, making it difficult to meet the deployment needs of on-site online processing. In addition, some abnormality detection methods rely on preset fixed thresholds, which are difficult to achieve adaptive judgment in a variable working condition background, resulting in high false positive rate and false negative rate.

[0004] In addition, although some researches try to introduce deep learning models to improve prediction and identification accuracy, they often face problems such as high model calculation complexity, unclear sensitivity to input channel information, and inability to dynamically adjust the prediction range when deployed in actual industrial sites. At the same time, the abnormality detection results lack causal explanation mechanism, which makes it difficult to effectively assist dispatch personnel in rapid positioning and fault troubleshooting, and is not conducive to the landing of actual operation and maintenance.

[0005] Therefore, the existing generator set abnormality detection technology has different degrees of deficiencies in real-time, deployment flexibility, detection accuracy and explainability, and a new method that integrates edge computing, efficient sequence modeling and causal explanation analysis is urgently needed to improve the comprehensiveness, accuracy and practicality of on-site abnormality detection. SUMMARY

[0006] An object of the present application is to provide an edge computing-based generator set anomaly detection method.

[0007] According to an embodiment of the present application, an edge computing-based generator set anomaly detection method comprises the following steps:

[0008] S1. An industrial edge computing node is deployed on site to collect and preprocess multi-channel working condition data of the generator set, and to generate standardized multi-channel working condition data of the generator set;

[0009] S2. A light-weight long short-term memory network prediction model is deployed in the industrial edge computing node, which receives the standardized multi-channel working condition data of the generator set and outputs a rolling predicted generator set state estimation sequence and a corresponding prediction confidence interval;

[0010] S3. The difference between the standardized multi-channel working condition data of the generator set and the rolling predicted generator set state estimation sequence is calculated to obtain a local residual sequence, and a sliding time window is used to calculate statistical features and spectral energy to construct a multi-modal residual atlas;

[0011] S4. Based on the residual atlas and historical benchmark data, a device health index is calculated to form a global threshold baseline of the device health index, an adaptive local statistical threshold is generated according to the current statistical distribution of the residual atlas, and a dual-threshold discrimination mechanism is constructed by fusing the global threshold baseline of the device health index and the adaptive local statistical threshold to discriminate the local residual sequence for generator set anomaly and output generator set anomaly candidate events;

[0012] S5. An explanatory analysis algorithm is used to generate a generator set anomaly causal explanation graph for the generator set anomaly candidate events, which reveals the contribution relationship of each working condition feature to the confidence of the generator set anomaly.

[0013] Optionally, the S1 comprises the following steps:

[0014] S11. Through the industrial edge computing node deployed on site, real-time working condition raw data of the generator set control system, sensor network and SCADA system are collected to obtain each piece of multi-channel working condition raw data of the generator set, which together form a multi-channel working condition raw data set of the generator set;

[0015] S12. The multi-channel working condition raw data set of the generator set is processed for time sequence alignment to obtain a time sequence aligned multi-channel working condition data matrix;

[0016] S13. For the multi-channel operating condition data matrix after time-series alignment, the long-term trend component is extracted by using a moving average model for the data sequence of each channel, and the trend residual value of the operating condition data after trend removal is obtained by subtracting the moving average trend component of the corresponding channel at the time step from each measurement value.

[0017] S14. The residual values ​​of the operating condition data after trend removal are normalized by Z-score normalization method to obtain normalized operating condition data.

[0018] S15. Combine all normalized operating condition data into a standardized operating condition data matrix.

[0019] Optionally, S2 includes the following steps:

[0020] S21. Organize the data from each time step in the standardized operating condition data matrix into a time step input vector according to channel order. Each time step input vector contains the standardized measurements of all channels. For each time step input vector, calculate the channel attention weight coefficient vector using weight parameters and bias parameters. Multiply the channel attention weight coefficient vector element-wise with the time step input vector to obtain the channel-aware weighted input vector.

[0021] S22. Weight the channel-aware input vector Input lightweight Long Short-Term Memory (LSTM) network prediction model lite In the middle, the hidden state h is output at each time step. k And with the most recent W h The hidden state sequence within each time step constitutes the hidden state window H. k ={h k -W h +1,…,h k};

[0022] S23. Based on the hidden state window H k The residual perturbation changes in the hidden state are used to construct the state perturbation intensity index S. k The state disturbance intensity index is used to measure the overall magnitude of hidden state changes within the current window. It is based on the state disturbance intensity index S within the current window. k Given a specified maximum prediction step size and control coefficient, the rolling prediction step size H is adaptively adjusted using an exponential decay method. p (k), the prediction step size is automatically shortened when the state disturbance intensity index is greater than the threshold, and automatically extended when the state disturbance intensity index is less than the threshold;

[0023] S24. Based on the state disturbance intensity index S k Simultaneously, construct pruning importance constraint indicators;

[0024] S25. At the current time step k, use the dynamically pruned lightweight Long Short-Term Memory (LSTM) network prediction model. lite Using rolling prediction step size H p (k) Output the future generator set state prediction sequence And combined with the recent W h Step state disturbance intensity index S k Calculate the confidence index γ k =1-tanh(ηS) k And generate prediction confidence intervals:

[0025]

[0026] Where σ is the standard deviation of historical residuals, and γ k It reflects the dynamic adjustment capability of prediction reliability as it changes with disturbances;

[0027] S26. Predict the sequence and the corresponding prediction confidence interval {I k+h Store it in the edge node cache area.

[0028] Optionally, the pruning importance constraint index is calculated as the sensitivity of each weight parameter of the lightweight long short-term memory network prediction model to the state perturbation intensity index. The sensitivity is defined as the product of the partial derivative of the weight parameter with respect to the state perturbation intensity index and the weight parameter itself. All weight parameters with sensitivity greater than the pruning threshold are retained, and other weight parameters are set to zero.

[0029] Optionally, S3 includes the following steps:

[0030] S31. Based on the standardized generator set multi-channel operating condition data matrix and the rolling predictive generator set state prediction sequence, calculate the prediction error at each time step to obtain the local residual sequence. Where x k+h This represents the actual measurement vector at time step k+h. This is the corresponding predicted value vector;

[0031] S32. For the local residual sequence e k+h Construct a single-channel residual sequence according to channel number j. In the sliding window length W r Within, calculate the residual moving average for each channel. and residual sliding variance

[0032] S33. Apply a short-time Fourier transform to the residual sequence of each channel, and calculate the spectral energy density value E of the channel at each frequency component and time window position. (j)(f, t);

[0033] S34. Jointly encode the residual sliding mean, residual sliding variance and spectral energy density value of all channels within the current sliding window, to construct the residual atlas R k ;

[0034] S35. Calculate the relative change rate of each channel's current measurement value with respect to the mean value of the channel's most recent stable window within the same sliding time window:

[0035]

[0036] wherein, is the mean value of the channel j's most recent stable window, v" k,j represents the normalized measurement value of the multi-channel operating condition data of the generator set at the current time step k and channel number j, and ∈ is a constant;

[0037] Assemble the relative change rates of all channels into the operating condition relative change atlas D k ;

[0038] S36. Calculate the Pearson correlation coefficient ρ i,j between each pair of residual time series of all channels within the same sliding time window, and assemble the Pearson correlation coefficients between all channels into the structural consistency atlas C k ;

[0039] S37. Fuse the residual atlas R k , the operating condition relative change atlas D k , and the structural consistency atlas C k to form a multi-modal residual atlas

[0040] Optionally, the S4 comprises the following steps:

[0041] S41. Based on the multi-modal residual atlas, sum the absolute values of the residual sliding means, sum the residual sliding variances, and sum the spectral energy density values at all frequencies and time windows of all channels, according to the weighted aggregation coefficient vector w = [w1, w2, w3] T to obtain the multi-modal residual comprehensive indicator A k of the current time step;

[0042] S42. Under the action of a set exponential smoothing coefficient α, recursively calculate the generator set equipment health index EHI k-1 based on the historical multi-modal residual comprehensive indicator sequence {A k-2 , …}. k = αA k+ (1 - a)EHI k-1 , wherein EHI0takes the mean value of {A -N} in the historical reference period, EHI k The larger the value, the lower the overall generator set equipment health level.

[0043] S43. Utilize the historical sliding window W g The maximum-minimum normalization of the generator set equipment health index in the window is performed to obtain the normalized health score The normalized health score is multiplied by a preset amplification coefficient and added to a safety margin constant to map and generate the global health threshold baseline G k ;

[0044] S44. In the current sliding window, the local statistical mean and local statistical standard deviation of the multi-modal residual comprehensive index are calculated, the local statistical standard deviation is multiplied by the quantile constant corresponding to the significance level under the standard normal distribution and added to the local statistical mean to generate the adaptive local statistical threshold L k ;

[0045] S45. The global health threshold baseline and the adaptive local statistical threshold are fused to construct a double-threshold discrimination mechanism, and the determination result Flag k ;

[0046] S46. The determination result Flag k of S45 is packaged and output with the corresponding multi-modal residual comprehensive index A k , the global threshold G k , and the local threshold L k

[0047] Optionally, the double-threshold discrimination mechanism is specifically: if the multi-modal residual comprehensive index of a certain time step exceeds both the global health threshold baseline and the adaptive local statistical threshold, it is determined that there is a generator set anomaly at the corresponding time step, otherwise it is considered to be normal.

[0048] Optionally, the S5 includes the following steps:

[0049] S51. When receiving an abnormal candidate event and the abnormality discrimination flag is abnormal, the standardized generator set multi-channel operating condition input vector x k = [v″ k,1 , v″ k,2 , …, v″ k,C ] T of the current time step is extracted, and the multi-modal residual map corresponding to the current time step is recorded.

[0050] S52. A lightweight long short-term memory network prediction model LSTM lite ​An explanation objective function of the forward model The normalized multi-channel working condition input vector of the current time step is input into the forward model, and the integrated gradient attribution analysis algorithm is used to calculate the prediction contribution degree of each working condition feature in the normalized multi-channel working condition input vector of the generator set;

[0051] S53. The prediction contribution degrees of all working condition features are combined into a feature contribution degree vector, and are fused with the structural consistency features in the multi-modal residual atlas of the current time step to obtain a generator set abnormal causal explanation graph with feature contribution degrees and structural consistency features;

[0052] S54. All nodes in the generator set abnormal causal explanation graph are ranked according to the feature contribution degrees, and the top N channels in the feature contribution degree ranking are selected as abnormal causal path nodes, and an abnormal causal path set is constructed in accordance with the order from high to low of the feature contribution degrees;

[0053] S55. The generator set abnormal causal explanation graph and the abnormal causal path set are structured and visualized to generate a generator set abnormal causal explanation atlas, which is used to assist dispatchers in fault confirmation and maintenance strategy decision-making.

[0054] Optionally, the integrated gradient attribution analysis algorithm accumulates the partial derivative of the output of the forward model to each working condition feature on the path from the baseline input interpolation to the actual input of the normalized multi-channel working condition input vector of the generator set, multiplies the difference between the working condition feature and the baseline input, and obtains the corresponding prediction contribution degree.

[0055] The beneficial effects of the present application are:

[0056] (1) The present application deploys a lightweight long short-term memory network prediction model on an industrial edge computing node, introduces an adaptive rolling prediction mechanism based on state disturbance and a pruning importance constraint mechanism, dynamically adjusts the prediction step while ensuring the real-time of the model, can more accurately capture the early signals of state mutation or fluctuation of the device, can adaptively shorten or lengthen the prediction range according to the hidden state disturbance intensity index, thereby improving the sensitivity when the working condition changes dramatically and reducing the false alarm rate when running smoothly, in addition, the network structure is constrained by the pruning importance index, only the weight parameters sensitive to the state disturbance are retained, the redundant calculation of the model is reduced, and the efficiency of the edge deployment is improved.

[0057] (2) The application first constructs a multi-modal residual atlas that fuses residual statistics, spectral features and structural consistency, and comprehensively depicts the microscopic fluctuation characteristics and channel structure coordination of the generator set operating state, which is particularly effective in discriminating critical states or early weak faults. The health index based on the atlas can not only reflect single-point abnormalities, but also depict the structural instability trend at the system level. Combined with the adaptive statistical threshold, a double-threshold discrimination mechanism is formed, which effectively improves the detection accuracy.

[0058] (3) The application introduces an abnormal causal explanation graph generation algorithm based on an integrated gradient attribution mechanism, which analyzes the explainability of the contribution of the input multi-channel working condition features to the forward prediction model, constructs a structured abnormal explanation atlas with causal relationships, and automatically generates an abnormal causal path set by analyzing the fusion results of feature contribution and structural consistency atlas, significantly improving the traceability and operability of fault location, and assisting maintenance personnel in accurately formulating maintenance strategies. BRIEF DESCRIPTION OF DRAWINGS

[0059] The accompanying drawings are included to provide a further understanding of the application, and constitute a part of the specification, together with the embodiments of the application, to explain the application, and do not constitute a limitation on the application. In the drawings:

[0060] Figure 1 A flowchart of an abnormality detection method for a generator set based on edge computing is provided. DETAILED DESCRIPTION

[0061] The application will now be described in further detail with reference to the drawings. These drawings are simplified schematic diagrams that only schematically illustrate the basic structure of the application, and therefore only show the components related to the application.

[0062] REFERENCE Figure 1 An abnormality detection method for a generator set based on edge computing includes the following steps:

[0063] S1. An industrial edge computing node is deployed on site to collect and locally cache multi-channel working condition data of the generator set, and performs time alignment, missing interpolation, trend removal and normalization preprocessing on the multi-channel working condition data of the generator set using the industrial edge computing node to generate standardized multi-channel working condition data of the generator set;

[0064] S2. A lightweight long short-term memory network prediction model is deployed in the industrial edge computing node, which receives the standardized multi-channel working condition data of the generator set and outputs a rolling prediction generator set state estimation sequence and a corresponding prediction confidence interval;

[0065] S3. Calculate the difference between the standardized multi-channel operating condition data of the generator set and the rolling predicted generator set state estimation sequence to obtain a local residual sequence, apply a sliding time window to the local residual sequence to calculate statistical features and spectral energy, and construct a multi-modal residual atlas;

[0066] S4. Calculate the equipment health index based on the residual atlas and historical benchmark data to form a global threshold baseline of the equipment health index, generate an adaptive local statistical threshold according to the current statistical distribution of the residual atlas, fuse the global threshold baseline of the equipment health index and the adaptive local statistical threshold to construct a double-threshold discrimination mechanism, and perform generator set anomaly discrimination on the local residual sequence and output generator set anomaly candidate events;

[0067] S5. Use an explanatory analysis algorithm to generate a generator set anomaly causal explanation graph for the generator set anomaly candidate event, and the generator set anomaly causal explanation graph reveals the contribution relationship of each operating condition feature to the confidence of the generator set anomaly.

[0068] In this embodiment, S1 includes the following steps:

[0069] S11. Collect real-time operating condition raw data of the generator set control system, sensor network and SCADA system through an industrial edge computing node deployed on site of the generator set to obtain each piece of multi-channel operating condition raw data of the generator set, wherein the multi-channel operating condition raw data of the generator set includes a collection timestamp, a sensor measurement value and a channel type identifier, all the multi-channel operating condition raw data of the generator set collectively form a multi-channel operating condition raw data set of the generator set, the collection timestamp is used to mark a specific time of data collection, the sensor measurement value is used to represent a specific operating state of the generator set, and the channel type identifier is used to distinguish different data source types;

[0070] S12. Perform time series alignment processing on the multi-channel operating condition raw data set of the generator set, synchronize and interpolate missing data of all channels using a unified time reference sequence, so that each channel has a corresponding measurement value at each unified time point, and all channel data finally form a multi-channel operating condition data matrix with a specified total number of time steps and a specified total number of channels, each measurement value in the multi-channel operating condition data matrix corresponds to a unique time step and a channel;

[0071] S13. For the time series aligned multi-channel operating condition data matrix, a sliding average model is used to extract a long-term trend component for each channel data sequence, and a trend-removed operating condition data residual value is obtained by subtracting the sliding average trend component of the corresponding channel at the time step from each measurement value, and the trend-removed operating condition data residual value is used to eliminate the long-term change trend in the data;

[0072] S14. The trend-removed operating condition data residual values are normalized by using the Z-score normalization method. For each channel, the residual mean and residual standard deviation of the channel in the sliding window are calculated. Each trend-removed operating condition data residual value is subtracted by the residual mean of the channel and divided by the residual standard deviation of the channel to obtain the normalized operating condition data;

[0073] S15. All the normalized operating condition data are combined to form a standardized operating condition data matrix, and the standardized operating condition data matrix is cached in the local cache area of the industrial edge computing node.

[0074] In the embodiment, S2 includes the following steps:

[0075] S21. The data of each time step in the standardized operating condition data matrix is combined into a time step input vector in the order of the channels. Each time step input vector contains the standardized measurement values of all channels. For each time step input vector, a channel attention weight coefficient vector is calculated using the weight parameter and the bias parameter. The channel attention weight coefficient vector is used to measure the dominant influence degree of each channel measurement value on the evolution of the generator set state. The channel attention weight coefficient vector is multiplied by the time step input vector element by element to obtain a channel perception weighted input vector.

[0076] S22. The channel perception weighted input vector is input into the lightweight long short-term memory network prediction model LSTM lite At each time step, the output hidden state h k is obtained, and the hidden state sequence in the last W h time steps is used to form a hidden state window H k ={h k-Wh+1 ,…,h k}, which is used to describe the current short-time dynamic evolution.

[0077] S23. A state disturbance intensity indicator is constructed based on the residual disturbance change of the hidden state in the hidden state window H k . The state disturbance intensity indicator is used to measure the overall amplitude of the change of the hidden state in the current window:

[0078]

[0079] wherein, is the average hidden state vector in the window, and S k represents the state disturbance intensity indicator in the current window.

[0080] According to the state disturbance intensity indicator S kand the specified maximum prediction step size and control coefficient, the rolling prediction step size H is adaptively adjusted in an exponential decay manner p (k), the prediction step size is automatically shortened when the state disturbance intensity index is greater than a threshold, and is automatically lengthened when the state disturbance intensity index is less than the threshold:

[0081]

[0082] wherein β is a control coefficient, H max is the maximum prediction step size;

[0083] S24. Based on the state disturbance intensity index S k Meanwhile, a pruning importance constraint index is constructed;

[0084] S25. At the current time step k, the light-weight long short-term memory network prediction model LSTM lite with the rolling prediction step size H p (k) outputs a future generator set state prediction sequence and combines the recent W h step state disturbance intensity index S k to calculate a confidence intensity index γ k = 1-tanh(ηS k ), and generates a prediction confidence interval, the confidence intensity index is used to dynamically adjust the width of the prediction confidence interval, the greater the confidence intensity index, the smaller the width of the prediction confidence interval, indicating the higher the prediction credibility:

[0085]

[0086] wherein σ is the historical residual standard deviation, γ k reflects the dynamic adjustment ability of the prediction credibility with the disturbance;

[0087] S26. The prediction sequence and the corresponding prediction confidence interval {I k+h} are stored in the edge node cache area.

[0088] In the embodiment, the pruning importance constraint index is the sensitivity of each weight parameter of the light-weight long short-term memory network prediction model to the state disturbance intensity index, the sensitivity is defined as the product of the partial derivative of the weight parameter to the state disturbance intensity index and the weight parameter itself, all weight parameters with a sensitivity greater than a pruning threshold are retained, and other weight parameters are set to zero, realizing structural sparse optimization for the current state disturbance sensitive features.

[0089] The lightweight long short-term memory network prediction model in the embodiment not only performs standardization processing on the data of each channel, but also dynamically allocates the contribution degrees of the channels through an attention weight mechanism, and can automatically identify signals that are more sensitive to abnormalities in different working condition stages.

[0090] In combination with the actual state disturbance intensity, the importance of the network weight parameters is dynamically evaluated to perform structured pruning on the connections with low contribution degrees, so as to reduce the model size and the calculation overhead under the premise of ensuring the prediction accuracy. The future prediction window is dynamically contracted or expanded according to the change of the model hidden state, intelligent scheduling of high-frequency prediction in fast-changing working conditions and low-frequency prediction in stable working conditions is realized, and the response capability to sudden abnormalities and early trend changes is effectively improved. The prediction confidence interval is dynamically adjusted by using multi-level information, so that the adaptability and alarm reliability of the abnormal threshold are obviously better than those of a conventional threshold scheme based on only single-layer variance or an empirical coefficient.

[0091] In the embodiment, S3 includes the following steps:

[0092] S31. Based on the standardized generator set multi-channel working condition data matrix and the rolling prediction generator set state prediction sequence, the prediction error of each time step is calculated to obtain a local residual error sequence where x k+h is an actual measurement vector at time step k+h, is a corresponding predicted value vector;

[0093] S32. The local residual error sequence e k+h is constructed according to the channel number j In a sliding window length W r , the residual sliding mean and the residual sliding variance of each channel are calculated. The residual sliding mean represents the average level of the residual of the channel in the current sliding window, and the residual sliding variance represents the fluctuation degree of the residual of the channel in the current sliding window.

[0094] S33. The short-time Fourier transform is adopted for each channel residual error sequence, and the spectral energy density value E (j) (f,t) of the channel at the frequency component and the time window position is calculated at each frequency component and each time window position. The spectral energy density value is used to measure the energy distribution of the channel at different frequencies and time windows.

[0095] S34. The residual sliding mean, the residual sliding variance and the spectral energy density value of all channels in the current sliding window are jointly coded to construct a residual atlas for comprehensively depicting the statistical features and frequency domain features of the residual signals of the channels at the current time step:

[0096]

[0097] wherein C is the total number of channels of the generator set multi-channel operating condition data;

[0098] S35. Calculate the relative change rate of each channel current measured value relative to the mean value of the current channel recent stable window within the same sliding time window:

[0099]

[0100] wherein, is the mean value of the channel j recent stable window, and ∈ is a constant;

[0101] Assemble the operating condition relative change graph of all channels:

[0102]

[0103] S36. Calculate the Pearson correlation coefficient between the residual time series of all channels two by two within the same sliding time window:

[0104]

[0105] wherein, i,j represents the Pearson correlation coefficient of the residual series of the i-th channel and the j-th channel in the current sliding window in the multi-channel operating condition of the generator set, used to measure the structural consistency of the change of different channel residuals, the value range is [-1, 1], the closer to 1 represents that the two channel residuals are highly positively correlated, the closer to -1 represents highly negatively correlated, and close to 0 represents no significant correlation, represents the local residual value of the i-th channel at time step k-h moment, i.e., the difference between the measured value and the predicted value of the i-th channel of the generator set, represents the residual mean value of the i-th channel within the current sliding window length W r , used to remove the mean value effect when calculating the correlation coefficient, W r is the sliding window length of residual analysis;

[0106] Assemble the Pearson correlation coefficient between all channels into a structural consistency graph C k =[ρ i,j ] C×C , used to describe the residual coupling structure between channels;

[0107] S37. Fuse the residual graph R k , the operating condition relative change graph D k , and the structural consistency graph C k to form a multi-modal residual graph and store the multi-modal residual graph in the edge computing node graph buffer.

[0108] In this embodiment, S4 includes the following steps:

[0109] S41. Based on the multi-modal residual atlas, sum the residual sliding mean absolute value of all channels, sum the residual sliding variance, and sum the spectral energy density value under all frequencies and time windows, according to the weighted aggregation coefficient vector w = [w1, w2, w3] T The weighted accumulation obtains the multi-modal residual comprehensive index A of the current time step k ;

[0110] S42. Under the action of the set exponential smoothing coefficient a, the generator set equipment health index EHI is recursively calculated according to the historical multi-modal residual comprehensive index sequence {A k-1 ,A k-2 ,…}:

[0111] EHI k = aA k + (1-a) EHI k-1 ;

[0112] Wherein, EHI0 takes the mean value of {A -N} in the historical reference period, and EHI k The larger the value is, the lower the overall generator set equipment health level is;

[0113] S43. The generator set equipment health index is maximum-minimum normalized in the window W g to obtain the normalized health score After multiplying the normalized health score by the preset amplification coefficient and adding the safety margin constant, the global health threshold baseline G k is generated;

[0114] S44. In the current sliding window, the local statistical mean and the local statistical standard deviation of the multi-modal residual comprehensive index are calculated, the local statistical standard deviation is multiplied by the quantile constant corresponding to the significance level under the standard normal distribution and added to the local statistical mean to generate the adaptive local statistical threshold L k The local statistical mean represents the central tendency of the residual level in the time window, and the local statistical standard deviation represents the fluctuation degree of the residual level in the time window;

[0115] S45. The global health threshold baseline and the adaptive local statistical threshold are fused to construct a double-threshold discrimination mechanism, and the determination result Flag k is obtained;

[0116] S46. The determination result Flag k of S45 is fused with the corresponding multi-modal residual comprehensive index A k , the global threshold Gk and local threshold L k packaging output abnormal candidate events and push to the edge computing node alarm queue.

[0117] In this embodiment, the double-threshold discrimination mechanism is specifically: if the multi-modal residual comprehensive index of a certain time step simultaneously exceeds the global health threshold baseline and the adaptive local statistical threshold, it is determined that the corresponding time step has a generator set abnormality, otherwise it is considered to have no abnormality. The double-threshold discrimination mechanism combines long-term trend and local fluctuation information, and improves the sensitivity and reliability of the generator set discrimination.

[0118] In this embodiment, S5 comprises the following steps:

[0119] S51. When receiving an abnormal candidate event and the abnormality discrimination flag is abnormal, extracting the standardized generator set multi-channel working condition input vector x of the current time step k = [v" k,1 ,v" k,2 ,…,v" k,C ] T , and recording the multi-modal residual spectrum corresponding to the current time step;

[0120] S52. Constructing a lightweight long short-term memory network prediction model LSTM lite as the explanation objective function of the forward model Input the standardized generator set multi-channel working condition input vector of the current time step into the forward model, and calculate the prediction contribution degree of each working condition feature in the standardized generator set multi-channel working condition input vector using the integrated gradient attribution analysis algorithm. The prediction contribution degree represents the attribution intensity of each working condition feature to the model output prediction error. The integrated gradient attribution analysis algorithm accumulates the partial derivative of the forward model output to each working condition feature on the path from the baseline input interpolation to the actual input of the standardized generator set multi-channel working condition input vector, multiplies the difference between the working condition feature and the baseline input, and obtains the corresponding prediction contribution degree;

[0121] S53. Grouping the prediction contribution degrees of all working condition features into a feature contribution degree vector, and fusing it with the structural consistency features in the multi-modal residual spectrum of the current time step to obtain a generator set abnormality causal explanation graph with feature contribution degrees and structural consistency features. The structural consistency features are composed of correlation coefficients between all channels. All channel numbers are corresponded to nodes of the explanation graph. Each node is assigned its feature contribution degree, and the edge between any two nodes is assigned a structural consistency correlation coefficient.

[0122] S54. Rank all nodes in the generator set anomaly causal explanation graph according to feature contribution, select the top N channels with the highest feature contribution as the anomaly causal path nodes, and construct an anomaly causal path set in descending order of feature contribution;

[0123] S55. Structure and visualize the generator set anomaly causal explanation graph and the anomaly causal path set to generate a generator set anomaly causal explanation atlas, jointly package the generator set anomaly causal explanation atlas with the abnormal candidate event, and push it to the generator set operation and maintenance system for assisting dispatchers in fault confirmation and maintenance strategy decision-making.

[0124] Example 1: A 600 MW coal-fired power plant in East China No. 1 generator set is in a load operation state, the running load is about 580 MW, at 14:08 that day, the edge computing node deployed in the main control room of the unit began to detect that the prediction errors of the “main steam pressure” and “reheater outlet temperature” two channels continued to rise, which had exceeded the upper limit of the 90% confidence interval for 8 consecutive time steps.

[0125] The system records that the residual values of the two channels reach 0.126 and 0.147, respectively, which are about 2.6 times and 3.1 times higher than the historical stable period mean, respectively. The multi-modal residual atlas analysis found that the “spectrum energy density (3.3Hz-4.5Hz)” in the corresponding time window was amplified synchronously on the above two channels, and the system automatically marked this time as a suspected disturbance enhancement point.

[0126] The system automatically shortens the prediction step from the original 12 steps to 6 steps according to the state disturbance intensity index, in order to enhance the response ability of the prediction model to small disturbances, and recalculates the health index EHI as 0.782, which is higher than the historical 95% threshold of 0.733, and triggers the double threshold mechanism for the first time, judging that there is a potential anomaly.

[0127] Within 0.6 seconds after triggering the system, an abnormal candidate event is automatically generated and the explanation module is called, and the integrated gradient algorithm is used for attribution analysis of the current input vector (a total of 118 channels). The system found that the contribution degrees of “main steam flow”, “denitration ammonia injection flow” and “air preheater differential pressure” were significantly increased, reaching 0.284, 0.193 and 0.112, respectively, which were much higher than the average level of other channels (about 0.021).

[0128] The abnormal causal explanation atlas is visualized and uploaded to the dispatching and control platform by the system to generate a report file “EVD-20241018-01”. The atlas shows that the sudden increase in denitration ammonia injection flow causes the increase in ammonia escape, which leads to the increase in thermal deviation in the boiler tail heat exchange area, and then affects the stability of the reheater and the main steam system.

[0129] Upon receiving the system report, the dispatcher immediately contacted the operations team and retrieved video footage from the on-site cameras. They confirmed that a short-term fluctuation had occurred in the ammonia injection control loop, with the ammonia injection valve opening suddenly increasing from 35% to 61% for approximately 3 minutes. Further investigation revealed that this sudden increase was due to an amplified ammonia concentration feedback error.

[0130] The on-duty engineer manually intervened in the ammonia injection PID parameters and recalibrated the target value. In the following 5 minutes, the system monitored that the residuals of each major thermal channel gradually recovered, and the health index dropped to 0.543, which was lower than the benchmark threshold. The system judged that the abnormality was resolved and formed a closed-loop event record.

[0131] This anomaly did not cause a direct unit trip or alarm, but it was a typical weak disturbance-thermal deviation chain reaction event. If not intervened in time, it would evolve into blockage of the tail heat exchanger or excessive main steam temperature.

[0132] During this period, the system processed a total of 2.136 million data samples, compared to the traditional SCADA fixed threshold mechanism:

[0133] Table 1 compares the traditional SCADA fixed threshold mechanism.

[0134] Comparison index System of the present invention Traditional SCADA discrimination mechanism Detection response time (seconds) 5.6 42.3 Abnormal report generation time (seconds) 1.8 Unable to generate Abnormal positioning accuracy (main channel) ± 2 channels ± 7 channels Abnormal intervention effective window 3.7 minutes <1 minute or no warning Abnormal explanation atlas generation Yes No

[0135] The model training is based on the power plant's historical dataset of the past 3 months (containing approximately 120 million time-series records). After adopting an adaptive pruning mechanism, the LSTMlite inference time is reduced by 61%. It can run efficiently with GPU resource usage on edge devices not exceeding 12%. Within 7 days of system deployment, a total of 12 candidate abnormal events were identified, of which 9 were confirmed by the operation and maintenance department as early warning signals of operating condition fluctuations.

[0136] This invention deploys a lightweight long short-term memory network prediction model on industrial edge computing nodes and introduces an adaptive rolling prediction mechanism based on state perturbation and a pruning importance constraint mechanism. While ensuring the real-time performance of the model, it achieves dynamic adjustment of the prediction step size, enabling more accurate capture of early signals of sudden changes or fluctuations in equipment state. The prediction range can be adaptively shortened or extended according to the hidden state perturbation intensity index, thereby improving sensitivity when operating conditions change drastically and reducing the false alarm rate during stable operation. In addition, by constraining the network structure through the pruning importance index, only weight parameters sensitive to state perturbation are retained, reducing redundant model calculations and improving the deployment efficiency at the edge.

[0137] The application firstly constructs a multi-modal residual atlas fusing residual statistics, spectral features and structural consistency, and comprehensively depicts the micro-fluctuation characteristics and channel structure coordination of the generator set operation state through the multi-dimensional fusion atlas composed of the residual atlas, the relative change atlas and the inter-channel Pearson correlation, which is particularly effective in discriminating the critical state or the early stage of weak fault. The health index based on the atlas can not only reflect the single-point anomaly, but also depict the structural instability trend at the system level. Combined with the adaptive statistical threshold, a double-threshold discrimination mechanism is formed, which effectively improves the detection accuracy.

[0138] The application introduces an abnormal causal explanation graph generation algorithm based on an integrated gradient attribution mechanism, combines the explainability analysis of the contribution of the input multi-channel working condition features to the forward prediction model, constructs a structured abnormal explanation atlas with causal relationship, automatically generates an abnormal causal path set by analyzing the fusion results of the feature contribution degree and the structural consistency atlas, and significantly improves the traceability and operability of fault positioning, thereby assisting the operation and maintenance personnel in accurately formulating maintenance strategies.

[0139] The above is only a preferred specific embodiment of the application, but the protection scope of the application is not limited thereto, any person skilled in the art can make equivalent replacement or change according to the technical solution and the inventive concept of the application within the technical range disclosed by the application, which should be covered within the protection scope of the application.

Claims

1. A generator set anomaly detection method based on edge computing, characterized in that, Includes the following steps: S1. Deploy industrial edge computing nodes at the generator set site to collect multi-channel operating condition data of the generator set and preprocess it to generate standardized multi-channel operating condition data of the generator set. S2. Deploy a lightweight long short-term memory network prediction model within an industrial edge computing node. The lightweight long short-term memory network prediction model receives standardized multi-channel operating condition data of generator sets and outputs a rolling prediction generator set state estimation sequence and corresponding prediction confidence interval. S2 includes the following steps: S21. Organize the data from each time step in the standardized operating condition data matrix into a time step input vector according to channel order. Each time step input vector contains the standardized measurement values ​​of all channels. For each time step input vector, calculate the channel attention weight coefficient vector using weight parameters and bias parameters. Multiply the channel attention weight coefficient vector element-wise with the time step input vector to obtain the channel-aware weighted input vector. ; S22. Weight the channel-aware input vector Input lightweight long short-term memory network prediction model In the middle, the hidden state is output at each time step. and with the most recent The hidden state window is composed of the hidden state sequence within each time step. ; S23. Based on hidden state window The residual perturbation changes in the hidden state are used to construct the state perturbation intensity index. The state perturbation intensity index is used to measure the overall magnitude of hidden state changes within the current window. Based on the state perturbation intensity index within the current window... Given a specified maximum prediction step size and control coefficient, the rolling prediction step size is adaptively adjusted using an exponential decay method. The prediction step size is automatically shortened when the state disturbance intensity index is greater than the threshold, and automatically extended when the state disturbance intensity index is less than the threshold. S24. Based on state disturbance intensity index Simultaneously, construct pruning importance constraint indicators; S25. At the current time step Lightweight Long Short-Term Memory Network Prediction Model After Dynamic Pruning predicting step size using rolling Output future generator state prediction sequence And combined with recent Step-state disturbance intensity index Calculate the confidence index And generate prediction confidence intervals: ； in, The standard deviation of historical residuals. It reflects the dynamic adjustment capability of prediction reliability as it changes with disturbances; S26. Predict the sequence and the corresponding prediction confidence interval Store in the edge node cache area; S3. Calculate the difference between the standardized generator set multi-channel operating condition data and the rolling prediction generator set state estimation sequence to obtain the local residual sequence, and apply the sliding time window to calculate the statistical characteristics and spectral energy to construct a multimodal residual map; S4. Calculate the equipment health index based on the residual map and historical benchmark data, form a global threshold baseline for the equipment health index, generate an adaptive local statistical threshold according to the current statistical distribution of the residual map, and construct a dual threshold discrimination mechanism by fusing the global threshold baseline for the equipment health index and the adaptive local statistical threshold to perform generator set anomaly discrimination on the local residual sequence and output generator set anomaly candidate events. S5. Use an interpretive analysis algorithm to generate a causal interpretation graph of generator set anomalies for candidate events. The causal interpretation graph of generator set anomalies reveals the contribution relationship of each operating condition feature to the confidence of generator set anomalies.

2. The generator set anomaly detection method based on edge computing according to claim 1, characterized in that, S1 includes the following steps: S11. By deploying industrial edge computing nodes at the generator set site, real-time raw operating data of the generator set control system, sensor network and SCADA system are collected to obtain each generator set multi-channel raw operating data, which together form the generator set multi-channel raw operating dataset. S12. Perform time-series alignment processing on the original dataset of multi-channel operating conditions of the generator set to obtain the time-series aligned multi-channel operating condition data matrix. S13. For the multi-channel operating condition data matrix after time-series alignment, the long-term trend component is extracted by using a moving average model for the data sequence of each channel, and the trend residual value of the operating condition data after trend removal is obtained by subtracting the moving average trend component of the corresponding channel at the time step from each measurement value. S14. The residual values ​​of the operating condition data after trend removal are normalized by Z-score normalization method to obtain normalized operating condition data. S15. Combine all normalized operating condition data into a standardized operating condition data matrix.

3. The generator set anomaly detection method based on edge computing according to claim 1, characterized in that, The pruning importance constraint index is calculated by evaluating the sensitivity of each weight parameter of the lightweight long short-term memory network prediction model to the state perturbation intensity index. The sensitivity is defined as the product of the partial derivative of the weight parameter with respect to the state perturbation intensity index and the weight parameter itself. All weight parameters with sensitivity greater than the pruning threshold are retained, and other weight parameters are set to zero.

4. The generator set anomaly detection method based on edge computing according to claim 3, characterized in that, S3 includes the following steps: S31. Based on the standardized generator set multi-channel operating condition data matrix and the rolling predictive generator set state prediction sequence, calculate the prediction error at each time step to obtain the local residual sequence. ,in For time step The actual measurement vector, This is the corresponding predicted value vector; S32. For local residual sequences By channel number Constructing a single-channel residual sequence In the length of the sliding window Within, calculate the residual moving average for each channel. and residual sliding variance ; S33. Apply a short-time Fourier transform to the residual sequence of each channel, and calculate the spectral energy density value of the channel at each frequency component and time window position. ; S34. Jointly encode the residual moving mean, residual moving variance, and spectral energy density values ​​of all channels within the current sliding window to construct a residual map at the current time step that comprehensively characterizes the statistical and frequency domain features of the residual signals of each channel. ; S35. Calculate the relative rate of change of the current measurement value of each channel with respect to the mean of the most recent stable window of the current channel within the same sliding time window: ； in, For channel The mean of the most recent stable window, This represents the measured value of the standardized generator set multi-channel operating condition data at the current time step k and channel number j. It is a constant; The relative change rates of all channels are used to construct a relative change graph of the operating conditions. ; S36. Within the same sliding time window, calculate the Pearson correlation coefficient between each pair of residual time series from all channels. The Pearson correlation coefficients between all channels are used to construct a structural consistency map. ; S37. Residual plot Relative variation diagram of operating conditions Structural consistency map The data is fused to form a multimodal residual map. .

5. The generator set anomaly detection method based on edge computing according to claim 4, characterized in that, S4 includes the following steps: S41. Based on the multimodal residual map, sum the absolute values ​​of the residual moving mean, sum the residual moving variance, and sum the spectral energy density values ​​for all channels across all frequencies and time windows, and then aggregate them according to the weighted coefficient vector. The multimodal residual composite index for the current time step is obtained by weighted summation. ; S42. At the set exponential smoothing coefficient Under the influence of historical multimodal residual comprehensive index series Recursively calculate the health index of generator set equipment. ,in, Take the historical benchmark period The mean, The higher the value, the lower the overall health level of the generator set equipment; S43. Utilizing the history sliding window The health index of the generator set equipment is normalized by maximum-min within a window to obtain a normalized health score. The normalized health score is multiplied by a preset amplification factor and then added to a safety margin constant to generate a global health threshold baseline. ; S44. Within the current sliding window, calculate the local statistical mean and local statistical standard deviation for the multimodal residual composite index. Multiply the local statistical standard deviation by the quantile constant corresponding to the significance level under the standard normal distribution and add it to the local statistical mean to generate an adaptive local statistical threshold. ; S45. A dual-threshold discrimination mechanism is constructed by fusing the global health threshold baseline with the adaptive local statistical threshold, and the judgment result is obtained. ; S46. The result of S45. Corresponding multimodal residual comprehensive index Global threshold and local threshold Packaging output exception candidate events .

6. The generator set anomaly detection method based on edge computing according to claim 5, characterized in that, The dual-threshold discrimination mechanism is as follows: if the multimodal residual comprehensive index of a certain time step exceeds both the global health threshold baseline and the adaptive local statistical threshold, then it is determined that there is an abnormality in the generator set at the corresponding time step; otherwise, it is considered that there is no abnormality.

7. The generator set anomaly detection method based on edge computing according to claim 6, characterized in that, S5 includes the following steps: S51. When an abnormal candidate event is received and the abnormality discrimination flag is abnormal, extract the standardized generator set multi-channel operating condition input vector of the current time step. Simultaneously, record the multimodal residual map corresponding to the current time step; S52. Construct a prediction model using a lightweight long short-term memory network. The objective function for explaining the forward model The standardized generator set multi-channel operating condition input vector at the current time step is input into the forward model, and the prediction contribution of each operating condition feature in the standardized generator set multi-channel operating condition input vector is calculated using the integrated gradient attribution analysis algorithm. S53. The predicted contribution of all operating condition features is combined into a feature contribution vector, and then fused with the structural consistency feature in the multimodal residual map of the current time step to obtain a generator set anomaly causal explanation map with feature contribution and structural consistency features. S54. Rank all nodes in the generator set anomaly cause-effect interpretation diagram according to their feature contribution, select the top N channels in terms of feature contribution as the anomaly cause-effect path nodes, and construct the anomaly cause-effect path set in order of feature contribution from high to low. S55. Explain the cause-and-effect relationship of generator set anomalies. and abnormal causal path set Structured and visual coding is performed to generate a cause-and-effect explanation map of generator set anomalies, which is used to assist dispatchers in fault confirmation and maintenance strategy decision-making.

8. The generator set anomaly detection method based on edge computing according to claim 7, characterized in that, The integrated gradient attribution analysis algorithm accumulates the partial derivatives of the forward model output with respect to each operating condition feature along the path from the baseline input interpolation to the actual input of the standardized generator set multi-channel operating condition input vector, and multiplies it by the difference between the operating condition feature and the baseline input to obtain the corresponding prediction contribution.

Images