Multi-source heterogeneous data fusion communication system and method

Abstract

The invention discloses a multi-source heterogeneous data fusion communication system and method, relates to the technical field of big data processing, and effectively solves the limitation of a traditional single data source monitoring mode by integrating various heterogeneous data sources and collecting and preprocessing data in real time when the system runs. Through the data fusion and feature extraction module, the system can comprehensively capture the multi-dimensional state features of the equipment and obtain a feature data set Fset (t), thereby providing accurate data support for subsequent anomaly detection and prediction. Under the combined action of the anomaly detection model and the prediction model, the system can discover potential faults in time and give out early warning in advance, and meanwhile, a self-adaptive regulation and control strategy is generated to prevent further deterioration of the anomaly. In addition, through a feedback and self-adaptive optimization module, the accuracy of fault prediction and the effectiveness of a regulation and control strategy are improved, the maintenance cost is reduced, and the efficiency and the safety are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of big data processing, and in particular to a communication system and method for multi-source heterogeneous data fusion. Background Art

[0002] In the wide application of modern communication technology, communication systems, as the core of information transmission, cover a variety of forms from wireless communication to wired networks. With the diversification of data types and the development of sensor technology, multi-source heterogeneous data fusion has gradually become one of the key technologies in communication systems. This technology achieves more efficient communication quality and more accurate data analysis by integrating and processing multi-source data from different sensors, network nodes, user devices, etc.

[0003] The monitoring of equipment status usually relies on a single type of data, such as data from temperature sensors or vibration sensors. However, this single data source monitoring method has significant shortcomings and is difficult to fully reflect the comprehensive status of the equipment. Since equipment failure is usually the result of a combination of multiple factors, a single data source may not be able to capture these complex correlations. In addition, existing monitoring systems often have difficulty in achieving real-time anomaly detection and cannot provide timely warnings before failures occur, resulting in uncontrollable downtime or equipment damage. These shortcomings greatly limit operational efficiency and equipment reliability. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a communication system and method for multi-source heterogeneous data fusion, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a communication system for multi-source heterogeneous data fusion, including a data acquisition and preprocessing module, a data fusion and feature extraction module, an anomaly detection model module, a prediction model construction module, an early warning and decision module and a feedback and adaptive optimization module;

[0006] The data collection and preprocessing module collects data from multiple heterogeneous data sources in real time to form a collection data group Draw, and preprocesses the collection data group Draw to obtain a preprocessed data set Dpre;

[0007] The data fusion and feature extraction module performs data fusion on the preprocessed data set Dpre, obtains the temperature vibration comprehensive feature Ftv(t), the power consumption interference comprehensive feature Fpe(t) and the micro-vibration noise feature Fmvn(t) at time t, and then performs feature extraction to form a fused feature data set Fset(t), which is marked and stored;

[0008] The anomaly detection model module constructs an anomaly detection model through the fused feature data set Fset(t), and obtains an anomaly score set Ascore(t) of the current communication system through training and analysis of the anomaly detection model;

[0009] The prediction model building module builds a prediction model through the abnormal score set Ascore(t) and the stored historical data set, and obtains the abnormal situation factor Pfuture(t+n) through prediction by the prediction model;

[0010] The early warning and decision-making module matches the acquired abnormal situation factor Pfuture(t+n) with the preset abnormal assessment threshold YZ to obtain the abnormal matching result M(t+n), and generates an adaptive control strategy scheme according to the abnormal matching result;

[0011] The feedback and adaptive optimization module matches the anomaly matching result M(t+n) with the actual feedback result R(t+n), obtains the error term and obtains the model adjustment index Tzs for adjusting the anomaly detection model and the prediction model.

[0012] Preferably, the data acquisition and preprocessing module includes a data acquisition unit and a data preprocessing unit;

[0013] The data acquisition unit collects data in real time from multiple heterogeneous data sources, where the multiple heterogeneous data sources include temperature data collected by a temperature sensor, vibration data collected by a vibration sensor, electromagnetic interference data collected by an electromagnetic interference sensor, power consumption data collected by a device operation power consumption sensor, micro-vibration frequency data collected by an acceleration sensor, and noise data collected by a noise sensor to form a collection data group Draw, which specifically includes temperature T(t), vibration frequency V(t), electromagnetic interference intensity E(t), power consumption P(t), micro-vibration frequency MV(t), and noise spectrum NS(t);

[0014] The data preprocessing unit preprocesses the collected data group Draw, including data standardization preprocessing, denoising preprocessing and missing value preprocessing, to form a preprocessed data set Dpre;

[0015] Among them, data standardization preprocessing includes using Zscore standardization preprocessing to process parameters of different dimensions on the same scale; denoising preprocessing includes using the sliding average filtering method for denoising preprocessing to adjust the impact of high-frequency noise; missing value preprocessing includes using linear interpolation to process missing values, which retains the data trend while adjusting the analysis error caused by missing values.

[0016] Preferably, the data fusion and feature extraction module includes a data fusion unit and a feature extraction unit;

[0017] The data fusion unit performs data fusion on the preprocessed data set Dpre with time t as a variable to obtain the temperature vibration comprehensive feature Ftv(t), the power consumption interference comprehensive feature Fpe(t) and the micro-vibration noise feature Fmvn(t);

[0018] The feature extraction unit extracts the acquired temperature vibration comprehensive feature Ftv(t), power consumption interference comprehensive feature Fpe(t) and micro-vibration noise feature Fmvn(t) to form a fused feature data set Fset(t), and stores it after marking, wherein the mark includes time t and data source identifier Fid;

[0019] Among them, the feature data set Fset(t) is specifically Fset(t)={Ftv(t), Fpe(t), Fmvn(t), t, Fid}.

[0020] Preferably, the temperature vibration comprehensive feature Ftv(t) is obtained by the following calculation formula:

[0021]

[0022] Where Ftv(t) represents the comprehensive characteristics of temperature vibration at time t, specifically the dynamic relationship between temperature T(t) at time t and vibration frequency V(t); T(t) represents temperature, specifically the temperature T at time t; V(t) represents vibration frequency, reflecting the thermal state of power grid equipment, specifically the vibration frequency at time t. represents the derivative of the vibration frequency V(t) with respect to time t, and d represents the derivative;

[0023] The power consumption interference comprehensive feature Fpe(t) is obtained by the following calculation formula:

[0024]

[0025] Wherein, Fpe(t) represents the comprehensive characteristics of power consumption interference at time t, specifically represents the dynamic relationship between the electromagnetic interference intensity E(t) and the power consumption P(t) at time t, E(t) represents the electromagnetic interference intensity of the equipment at time t, specifically represents the degree of electromagnetic interference in the equipment operation area, P(t) represents the equipment operation power consumption at time t, specifically represents the energy consumption during operation; ln represents the natural logarithm function, specifically used to adjust the range of the dynamic relationship between the electromagnetic interference intensity E(t) and the power consumption P(t);

[0026] The micro-vibration noise feature Fmvn(t) is obtained by the following calculation formula:

[0027]

[0028] Wherein, Fmvn(t) represents the micro-vibration noise characteristics at time t, specifically the dynamic relationship between the micro-vibration frequency MV(t) and the noise spectrum NS(t) at time t. MV(t) represents the micro-vibration frequency at time t, specifically the number of micro-vibrations that occur when the equipment is running at time t, reflecting the stability of the equipment's operating state. NS(t) represents the noise spectrum at time t, specifically the environmental noise state of the equipment in the operating area at time t. It represents the first-order derivative of the micro-vibration frequency MV(t) with respect to time t, specifically the rate of change of the micro-vibration frequency MV(t) with time, and is used to capture instantaneous fluctuations.

[0029] Preferably, the anomaly detection model module uses the fused feature data set Fset(t) as model input data to input the constructed anomaly detection model, wherein the construction of the anomaly detection model includes using isolation forest, principal component analysis and support vector machine algorithms to construct the model, and through the training and analysis of the anomaly detection model, the operation status of the communication system is reflected to obtain the anomaly score set Ascore(t) of the current communication system;

[0030] The anomaly score set Ascore(t) is obtained by the following calculation formula:

[0031]

[0032] Where Fset,i(t) represents the i-th feature in the feature data set Fset(t) at time t, μF,i represents the i-th feature mean, σF,i represents the i-th feature standard deviation, N represents the number of features, λ represents the adjustment coefficient, which is specifically used to balance the dynamic relationship between features and distance metrics, and Ddist(t) represents the distance metric of the feature in the anomaly detection model, which specifically indicates the degree of difference between the current feature and the qualified state feature of the model.

[0033] Preferably, the prediction model building module includes a data preparation unit and a data inference unit;

[0034] The data preparation unit synchronously extracts the stored historical data set through the anomaly score set Ascore(t) to form a historical anomaly score set Hscore(t), and performs feature selection and time series processing based on the anomaly score set Ascore(t) and the historical anomaly score set Hscore(t), including time series smoothing and difference processing, obtains the smoothed anomaly score value S(t) and the anomaly score difference value D(t) at time t, reflects the change trend of the anomaly score, and synchronously covers and replaces the anomaly score set Ascore(t) with the smoothed anomaly score value S(t) to form a smoothed anomaly score set Ascore(t);

[0035] The data inference unit constructs a prediction model by using a time series model, inputs the smoothed anomaly score set Ascore(t), the anomaly score difference value D(t) and the historical anomaly score set Hscore(t) as input data of the prediction model, performs prediction training through the prediction model, and obtains the abnormal situation factor Pfuture(t+n);

[0036] The abnormal situation factor Pfuture(t+n) is obtained by the following calculation formula:

[0037] Pfuture(t+n)=β0+β1·Ascore(t)+β2·D(t)+β3·Hscore(t);

[0038] Where β0 represents the bias term of the prediction model function, specifically represents the constant baseline, β1, β2 and β3 represent the preset weight values ​​of the smoothed anomaly score set Ascore(t), the anomaly score difference value D(t) and the historical anomaly score set Hscore(t), respectively.

[0039] Preferably, the abnormal score value S(t) is obtained by the following calculation formula:

[0040] S(t)=α·Ascore(t)+(1-α)·Hscore(t-1);

[0041] Wherein, α represents the smoothing coefficient, which is specifically used to adjust the preset weight value allocation of the anomaly score set Ascore(t) and the historical anomaly score set Hscore(t);

[0042] The abnormal score difference value D(t) is obtained by the following calculation formula:

[0043]

[0044] Preferably, the early warning and decision module matches the acquired abnormal situation factor Pfuture(t+n) with the preset abnormal assessment threshold YZ, The matching formula obtains the abnormal matching result M(t+n), and generates an adaptive control strategy scheme based on the abnormal matching result;

[0045] When the abnormal matching result M(t+n) is 1, the abnormal situation is predicted, and the abnormal matching result is generated to generate an adaptive control strategy plan, including adjusting system parameters, switching backup systems, reducing power consumption, and notifying operators to take action;

[0046] When the abnormal matching result M(t+n) is 0, the prediction is obtained without abnormality, and no abnormal matching result is generated to generate an adaptive control strategy solution.

[0047] Preferably, the feedback and adaptive optimization module matches the anomaly matching result M(t+n) with the actual feedback result R(t+n), wherein the actual feedback result R(t+n) includes obtaining the error term and the model adjustment index Tzs for adjusting the anomaly detection model and the prediction model through operator feedback, and using the model adjustment index Tzs as a regulating factor to indirectly adjust the anomaly detection performance and prediction performance of the model by affecting the parameter update during the training process of the anomaly detection model and the prediction model;

[0048] The model adjustment index Tzs is obtained by the following calculation formula:

[0049] Tzs(t+n)=Tzs(t)-η·(M(t+n)-R(t+n));

[0050] Where Tzs(t) represents the model adjustment index at time t, specifically including the anomaly detection model and the prediction model, and η represents the learning rate, specifically indicating the control adjustment step size.

[0051] A communication method for multi-source heterogeneous data fusion, comprising the following steps:

[0052] Step 1: The data collection and preprocessing module collects data from multiple heterogeneous data sources in real time to form a collection data group Draw, and preprocesses the collection data group Draw to obtain a preprocessed data set Dpre;

[0053] Step 2: The data fusion and feature extraction module performs data fusion on the preprocessed data set Dpre, obtains the temperature vibration comprehensive feature Ftv(t), power consumption interference comprehensive feature Fpe(t) and micro-vibration noise feature Fmvn(t) at time t, and then performs feature extraction to form a fused feature data set Fset(t), which is marked and stored;

[0054] Step 3: The anomaly detection model module constructs an anomaly detection model through the fused feature data set Fset(t), and obtains the anomaly score set Ascore(t) of the current communication system through training and analysis of the anomaly detection model;

[0055] Step 4: The prediction model building module builds a prediction model through the anomaly score set Ascore(t) and the stored historical data set, and obtains the abnormal situation factor Pfuture(t+n) through prediction by the prediction model;

[0056] Step 5: The early warning and decision-making module matches the acquired abnormal situation factor Pfuture(t+n) with the preset abnormal assessment threshold YZ to obtain the abnormal matching result M(t+n), and generates an adaptive control strategy scheme based on the abnormal matching result;

[0057] Step 6: The feedback and adaptive optimization module matches the anomaly matching result M(t+n) with the actual feedback result R(t+n), obtains the error term and the model adjustment index Tzs used to adjust the anomaly detection model and prediction model.

[0058] The present invention provides a communication system and method for multi-source heterogeneous data fusion, which has the following beneficial effects:

[0059] (1) When the system is running, it integrates multiple heterogeneous data sources, collects and preprocesses data in real time, and effectively solves the limitations of the traditional single data source monitoring method. Through the data fusion and feature extraction module, the system can fully capture the multi-dimensional state characteristics of the equipment and obtain the feature data set Fset(t), thereby providing accurate data support for subsequent anomaly detection and prediction. Under the joint action of the anomaly detection model and the prediction model, the system can timely detect potential faults and issue early warnings, while generating adaptive control strategies to prevent further deterioration of the anomaly. In addition, through the feedback and adaptive optimization module, the system can continuously adjust and optimize itself according to actual feedback, improve the accuracy of fault prediction and the effectiveness of the control strategy. Ultimately, this system effectively makes up for the shortcomings of traditional systems in fault warning and real-time response, reduces maintenance costs, and significantly improves overall efficiency and safety.

[0060] (2) By using smoothing and differential analysis, the anomaly score data is deeply optimized to ensure that the model has higher robustness and accuracy when processing data. In addition, the system can adaptively adjust the parameters of the prediction model according to the dynamic relationship between the real-time anomaly score set Ascore(t) and the historical anomaly score set Hscore(t), making the system's prediction of future abnormal situations more accurate, thereby effectively avoiding the risks of excessive alarms and missed reports. This mechanism significantly improves the system's ability to respond to potential problems in complex environments, reduces unnecessary maintenance operations and resource consumption, and further optimizes the system's operating efficiency.

[0061] (3) Based on the abnormal situation factor Pfuture(t+n), potential abnormal situations can be judged and predicted, and targeted control strategies can be quickly generated, including adjusting system parameters, switching backup systems, reducing power consumption, and notifying operators. After implementation, the strategies can be verified through actual feedback results R(t+n). Through manual inspection by operators and automated feedback loops, the system can accurately identify the accuracy of the predictions and update model parameters in real time based on error calculations. This closed-loop feedback mechanism ensures that the system always maintains efficient abnormality detection and response capabilities while constantly adapting to environmental changes. Finally, through the continuous optimization of the model adjustment index Tzs, the system makes the abnormality detection model and the prediction model have stronger adaptive capabilities, greatly improves the response effect to complex faults, reduces false alarms and missed alarms, and thus ensures the long-term stable operation of the system and effective control of maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A block diagram of a communication system for multi-source heterogeneous data fusion according to the present invention;

[0063] Figure 2 The figure is a schematic diagram of the steps of a communication method for multi-source heterogeneous data fusion according to the present invention. DETAILED DESCRIPTION

[0064] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0065] Example 1

[0066] The present invention provides a communication system for multi-source heterogeneous data fusion, please refer to Figure 1 , including data acquisition and preprocessing module, data fusion and feature extraction module, anomaly detection model module, prediction model construction module, early warning and decision module and feedback and adaptive optimization module;

[0067] The data collection and preprocessing module collects data from multiple heterogeneous data sources in real time to form a collection data group Draw, and preprocesses the collection data group Draw to obtain a preprocessed data set Dpre;

[0068] The data fusion and feature extraction module performs data fusion on the preprocessed data set Dpre, obtains the temperature vibration comprehensive feature Ftv(t), the power consumption interference comprehensive feature Fpe(t) and the micro-vibration noise feature Fmvn(t) at time t, and then performs feature extraction to form a fused feature data set Fset(t), which is marked and stored;

[0069] The anomaly detection model module constructs an anomaly detection model through the fused feature data set Fset(t), and obtains an anomaly score set Ascore(t) of the current communication system through training and analysis of the anomaly detection model;

[0070] The prediction model building module builds a prediction model through the abnormal score set Ascore(t) and the stored historical data set, and obtains the abnormal situation factor Pfuture(t+n) through prediction by the prediction model;

[0071] The early warning and decision-making module matches the acquired abnormal situation factor Pfuture(t+n) with the preset abnormal assessment threshold YZ to obtain the abnormal matching result M(t+n), and generates an adaptive control strategy scheme according to the abnormal matching result;

[0072] The feedback and adaptive optimization module matches the anomaly matching result M(t+n) with the actual feedback result R(t+n), obtains the error term and obtains the model adjustment index Tzs for adjusting the anomaly detection model and the prediction model.

[0073] In this embodiment, by integrating multiple heterogeneous data sources, real-time data collection and preprocessing, the limitations of the traditional single data source monitoring method are effectively solved. Through the data fusion and feature extraction module, the system can fully capture the multi-dimensional state characteristics of the equipment and obtain the feature data set Fset(t), thereby providing accurate data support for subsequent anomaly detection and prediction. Under the joint action of the anomaly detection model and the prediction model, the system can timely detect potential faults and issue early warnings, and generate adaptive control strategies to prevent further deterioration of the anomaly. In addition, through the feedback and adaptive optimization module, the system can continuously adjust and optimize itself according to actual feedback, improve the accuracy of fault prediction and the effectiveness of the control strategy. In the end, this system effectively makes up for the shortcomings of traditional systems in fault warning and real-time response, reduces equipment downtime, reduces maintenance costs, and significantly improves overall efficiency and safety.

[0074] Example 2

[0075] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the data acquisition and preprocessing module includes a data acquisition unit and a data preprocessing unit;

[0076] The data acquisition unit collects data in real time from multiple heterogeneous data sources, where the multiple heterogeneous data sources include temperature data collected by a temperature sensor, vibration data collected by a vibration sensor, electromagnetic interference data collected by an electromagnetic interference sensor, power consumption data collected by a device operation power consumption sensor, micro-vibration frequency data collected by an acceleration sensor, and noise data collected by a noise sensor to form a collection data group Draw, which specifically includes temperature T(t), vibration frequency V(t), electromagnetic interference intensity E(t), power consumption P(t), micro-vibration frequency MV(t), and noise spectrum NS(t);

[0077] The data preprocessing unit preprocesses the collected data group Draw, including data standardization preprocessing, denoising preprocessing and missing value preprocessing, to form a preprocessed data set Dpre;

[0078] Among them, data standardization preprocessing includes using Zscore standardization preprocessing to process parameters of different dimensions on the same scale; denoising preprocessing includes using the sliding average filtering method for denoising preprocessing to adjust the impact of high-frequency noise; missing value preprocessing includes using linear interpolation to process missing values, which retains the data trend while adjusting the analysis error caused by missing values.

[0079] The data fusion and feature extraction module includes a data fusion unit and a feature extraction unit;

[0080] The data fusion unit performs data fusion on the preprocessed data set Dpre with time t as a variable to obtain the temperature vibration comprehensive feature Ftv(t), the power consumption interference comprehensive feature Fpe(t) and the micro-vibration noise feature Fmvn(t);

[0081] The feature extraction unit extracts the acquired temperature vibration comprehensive feature Ftv(t), power consumption interference comprehensive feature Fpe(t) and micro-vibration noise feature Fmvn(t) to form a fused feature data set Fset(t), and stores it after marking, wherein the mark includes time t and data source identifier Fid;

[0082] Among them, the feature data set Fset(t) is specifically Fset(t)={Ftv(t), Fpe(t), Fmvn(t), t, Fid}.

[0083] The temperature vibration comprehensive characteristic Ftv(t) is obtained by the following calculation formula:

[0084]

[0085] Where Ftv(t) represents the comprehensive characteristics of temperature vibration at time t, specifically the dynamic relationship between temperature T(t) at time t and vibration frequency V(t); T(t) represents temperature, specifically the temperature T at time t; V(t) represents vibration frequency, reflecting the thermal state of power grid equipment, specifically the vibration frequency at time t. represents the derivative of the vibration frequency V(t) with respect to time t, and d represents the derivative;

[0086] The power consumption interference comprehensive feature Fpe(t) is obtained by the following calculation formula:

[0087]

[0088] Wherein, Fpe(t) represents the comprehensive characteristics of power consumption interference at time t, specifically represents the dynamic relationship between the electromagnetic interference intensity E(t) and the power consumption P(t) at time t, E(t) represents the electromagnetic interference intensity of the equipment at time t, specifically represents the degree of electromagnetic interference in the equipment operation area, P(t) represents the equipment operation power consumption at time t, specifically represents the energy consumption during operation; ln represents the natural logarithm function, specifically used to adjust the range of the dynamic relationship between the electromagnetic interference intensity E(t) and the power consumption P(t);

[0089] The micro-vibration noise feature Fmvn(t) is obtained by the following calculation formula:

[0090]

[0091] Wherein, Fmvn(t) represents the micro-vibration noise characteristics at time t, specifically the dynamic relationship between the micro-vibration frequency MV(t) and the noise spectrum NS(t) at time t. MV(t) represents the micro-vibration frequency at time t, specifically the number of micro-vibrations that occur when the equipment is running at time t, reflecting the stability of the equipment's operating state. NS(t) represents the noise spectrum at time t, specifically the environmental noise state of the equipment in the operating area at time t. It represents the first-order derivative of the micro-vibration frequency MV(t) with respect to time t, specifically the rate of change of the micro-vibration frequency MV(t) with time, and is used to capture instantaneous fluctuations.

[0092] Example 3

[0093] This embodiment is explained in Example 2. Please refer to Figure 1Specifically: the anomaly detection model module uses the fused feature data set Fset(t) as model input data and inputs the constructed anomaly detection model, wherein the construction of the anomaly detection model includes using isolation forest, principal component analysis and support vector machine algorithms to construct the model, and through the training and analysis of the anomaly detection model, the operation status of the communication system is reflected to obtain the anomaly score set Ascore(t) of the current communication system;

[0094] The anomaly score set Ascore(t) is obtained by the following calculation formula:

[0095]

[0096] Where Fset,i(t) represents the i-th feature in the feature data set Fset(t) at time t, μF,i represents the i-th feature mean, σF,i represents the i-th feature standard deviation, N represents the number of features, λ represents the adjustment coefficient, which is specifically used to balance the dynamic relationship between features and distance metrics, and Ddist(t) represents the distance metric of the feature in the anomaly detection model, which specifically indicates the degree of difference between the current feature and the qualified state feature of the model.

[0097] The prediction model building module includes a data preparation unit and a data inference unit;

[0098] The data preparation unit synchronously extracts the stored historical data set through the anomaly score set Ascore(t) to form a historical anomaly score set Hscore(t), and performs feature selection and time series processing based on the anomaly score set Ascore(t) and the historical anomaly score set Hscore(t), including time series smoothing and difference processing, obtains the smoothed anomaly score value S(t) and the anomaly score difference value D(t) at time t, reflects the change trend of the anomaly score, and synchronously covers and replaces the anomaly score set Ascore(t) with the smoothed anomaly score value S(t) to form a smoothed anomaly score set Ascore(t);

[0099] The data inference unit constructs a prediction model by using a time series model, inputs the smoothed anomaly score set Ascore(t), the anomaly score difference value D(t) and the historical anomaly score set Hscore(t) as input data of the prediction model, performs prediction training through the prediction model, and obtains the abnormal situation factor Pfuture(t+n);

[0100] The abnormal situation factor Pfuture(t+n) is obtained by the following calculation formula:

[0101] Pfuture(t+n)=β0+β1·Ascore(t)+β2·D(t)+β3·Hscore(t);

[0102] Where β0 represents the bias term of the prediction model function, specifically represents the constant baseline, β1, β2 and β3 represent the preset weight values ​​of the smoothed anomaly score set Ascore(t), the anomaly score difference value D(t) and the historical anomaly score set Hscore(t), respectively.

[0103] The abnormal score value S(t) is obtained by the following calculation formula:

[0104] S(t)=α·Ascore(t)+(1-α)·Hscore(t-1);

[0105] Wherein, α represents the smoothing coefficient, which is specifically used to adjust the preset weight value allocation of the anomaly score set Ascore(t) and the historical anomaly score set Hscore(t);

[0106] The abnormal score difference value D(t) is obtained by the following calculation formula:

[0107]

[0108] In this embodiment, the abnormal score data is deeply optimized by using smoothing and differential analysis to ensure that the model has higher robustness and accuracy when processing data. In addition, the system can adaptively adjust the parameters of the prediction model according to the dynamic relationship between the real-time abnormal score set Ascore(t) and the historical abnormal score set Hscore(t), so that the system can predict future abnormal situations more accurately, thereby effectively avoiding the risks of excessive alarms and missed reports. This mechanism significantly improves the system's ability to respond to potential problems in complex environments, reduces unnecessary maintenance operations and resource consumption, and further optimizes the system's operating efficiency.

[0109] Example 4

[0110] This embodiment is explained in Example 3, please refer to Figure 1 Specifically: the warning and decision module matches the acquired abnormal situation factor Pfuture(t+n) with the preset abnormal assessment threshold YZ, and The matching formula obtains the abnormal matching result M(t+n), and generates an adaptive control strategy scheme based on the abnormal matching result;

[0111] When the abnormal matching result M(t+n) is 1, the abnormal situation is predicted, and the abnormal matching result is generated to generate an adaptive control strategy plan, including adjusting system parameters, switching backup systems, reducing power consumption, and notifying operators to take action;

[0112] When the abnormal matching result M(t+n) is 0, the prediction is obtained without abnormality, and no abnormal matching result is generated to generate an adaptive control strategy solution.

[0113] The feedback and adaptive optimization module matches the anomaly matching result M(t+n) with the actual feedback result R(t+n), wherein the actual feedback result R(t+n) includes obtaining the error term and the model adjustment index Tzs for adjusting the anomaly detection model and the prediction model through operator feedback, and using the model adjustment index Tzs as a regulating factor to indirectly adjust the anomaly detection performance and prediction performance of the model by affecting the parameter update during the training process of the anomaly detection model and the prediction model;

[0114] The actual feedback result R(t+n) includes feedback from operators and automated feedback loops.

[0115] Operator feedback acquisition specifically includes: manual inspection and confirmation by operators. For example, operators determine the actual status of the system by inspecting equipment, checking system alarms, and checking the physical environment. Operators also fill out feedback reports based on the inspection results or directly enter them into the system as part of R(t+n), providing a more comprehensive system status.

[0116] The automated feedback loop method is as follows: when the system successfully avoids anomalies after executing the control strategy, the feedback result R(t+n) will be displayed as normal; if it fails to avoid anomalies, the feedback result will record the actual fault or abnormal state of the system;

[0117] Among them, when the actual feedback result R(t+n) is 1, it means that the abnormal situation predicted by the system has not been successfully resolved or the abnormality has indeed occurred, which means that although the system has carried out early warning and regulation, the problem still exists, or the system has indeed experienced an unexpected abnormality;

[0118] When the actual feedback result R(t+n) is 0, it means that the abnormal situation predicted by the system has been successfully resolved or the abnormality has not occurred. This means that there may be errors in the system's prediction, or the control strategy has successfully prevented potential abnormalities;

[0119] The model adjustment index Tzs is obtained by the following calculation formula:

[0120] Tzs(t+n)=Tzs(t)-η·(M(t+n)-R(t+n));

[0121] Where Tzs(t) represents the model adjustment index at time t, specifically including the anomaly detection model and the prediction model, and η represents the learning rate, specifically indicating the control adjustment step size.

[0122] In this embodiment, potential abnormal situations are judged and predicted based on the abnormal situation factor Pfuture(t+n), and targeted control strategies can be quickly generated, including adjusting system parameters, switching backup systems, reducing power consumption and notifying operators. After implementation, the strategy can be verified through actual feedback results R(t+n). Through manual inspection by operators and automated feedback loops, the system can accurately identify the accuracy of the prediction and update the model parameters in real time based on error calculation. This closed-loop feedback mechanism ensures that the system always maintains efficient abnormality detection and response capabilities in the process of constantly adapting to environmental changes. Ultimately, the system continuously optimizes the model adjustment index Tzs, so that the abnormality detection model and the prediction model have stronger adaptive capabilities, greatly improves the response effect to complex faults, and reduces false alarms and missed reports, thereby ensuring the long-term stable operation of the system and effective control of maintenance costs.

[0123] Example 5

[0124] A communication method for multi-source heterogeneous data fusion, please refer to Figure 2 , specifically: including the following steps:

[0125] Step 1: The data collection and preprocessing module collects data from multiple heterogeneous data sources in real time to form a collection data group Draw, and preprocesses the collection data group Draw to obtain a preprocessed data set Dpre;

[0126] Step 2: The data fusion and feature extraction module performs data fusion on the preprocessed data set Dpre, obtains the temperature vibration comprehensive feature Ftv(t), power consumption interference comprehensive feature Fpe(t) and micro-vibration noise feature Fmvn(t) at time t, and then performs feature extraction to form a fused feature data set Fset(t), which is marked and stored;

[0127] Step 3: The anomaly detection model module constructs an anomaly detection model through the fused feature data set Fset(t), and obtains the anomaly score set Ascore(t) of the current communication system through training and analysis of the anomaly detection model;

[0128] Step 4: The prediction model building module builds a prediction model through the anomaly score set Ascore(t) and the stored historical data set, and obtains the abnormal situation factor Pfuture(t+n) through prediction by the prediction model;

[0129] Step 5: The early warning and decision-making module matches the acquired abnormal situation factor Pfuture(t+n) with the preset abnormal assessment threshold YZ to obtain the abnormal matching result M(t+n), and generates an adaptive control strategy scheme based on the abnormal matching result;

[0130] Step 6: The feedback and adaptive optimization module matches the anomaly matching result M(t+n) with the actual feedback result R(t+n), obtains the error term and the model adjustment index Tzs used to adjust the anomaly detection model and prediction model.

[0131] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A communication system for multi-source heterogeneous data fusion, characterized by: It includes data collection and preprocessing module, data fusion and feature extraction module, anomaly detection model module, prediction model construction module, early warning and decision module and feedback and adaptive optimization module; The data collection and preprocessing module collects data from a number of heterogeneous data sources in real time to form a collection data group Draw, and preprocesses the collection data group Draw to obtain a preprocessed data set Dpre; The data fusion and feature extraction module performs data fusion on the preprocessed data set Dpre, obtains the temperature vibration comprehensive feature Ftv(t), the power consumption interference comprehensive feature Fpe(t) and the micro-vibration noise feature Fmvn(t) at time t, and then performs feature extraction to form a fused feature data set Fset(t), which is marked and stored; The anomaly detection model module constructs an anomaly detection model through the fused feature data set Fset(t), and obtains an anomaly score set Ascore(t) of the current communication system through training and analysis of the anomaly detection model; The prediction model building module builds a prediction model through the abnormal score set Ascore(t) and the stored historical data set, and obtains the abnormal situation factor Pfuture(t+n) through prediction by the prediction model; The early warning and decision-making module matches the acquired abnormal situation factor Pfuture(t+n) with the preset abnormal assessment threshold YZ to obtain the abnormal matching result M(t+n), and generates an adaptive control strategy scheme according to the abnormal matching result; The feedback and adaptive optimization module matches the anomaly matching result M(t+n) with the actual feedback result R(t+n), obtains the error term and obtains the model adjustment index Tzs for adjusting the anomaly detection model and the prediction model.

2. A communication system for multi-source heterogeneous data fusion according to claim 1, characterized in that: The data acquisition and preprocessing module includes a data acquisition unit and a data preprocessing unit; The data acquisition unit collects data in real time from multiple heterogeneous data sources, which include temperature data collected by a temperature sensor, vibration data collected by a vibration sensor, electromagnetic interference data collected by an electromagnetic interference sensor, power consumption data collected by a device operation power consumption sensor, micro-vibration frequency data collected by an acceleration sensor, and noise data collected by a noise sensor, to form a collection data group Draw.

3. A communication system for multi-source heterogeneous data fusion according to claim 2, characterized in that: The collected data group Draw specifically includes temperature T(t), vibration frequency V(t), electromagnetic interference intensity E(t), power consumption P(t), micro-vibration frequency MV(t) and noise spectrum NS(t).

4. A communication system for multi-source heterogeneous data fusion according to claim 2, characterized in that: The data preprocessing unit preprocesses the collected data group Draw, including data standardization preprocessing, denoising preprocessing and missing value preprocessing, to form a preprocessed data set Dpre; Among them, the data standardization preprocessing includes using Zscore standardization preprocessing to process parameters of different dimensions on the same scale; the denoising preprocessing includes using a sliding average filtering method for denoising preprocessing, and the missing value preprocessing includes using a linear interpolation method for missing value processing.

5. The communication system for multi-source heterogeneous data fusion according to claim 1, characterized in that: The data fusion and feature extraction module includes a data fusion unit and a feature extraction unit; The data fusion unit performs data fusion on the preprocessed data set Dpre with time t as a variable to obtain the temperature vibration comprehensive feature Ftv(t), the power consumption interference comprehensive feature Fpe(t) and the micro-vibration noise feature Fmvn(t); The feature extraction unit extracts the acquired temperature vibration comprehensive feature Ftv(t), power consumption interference comprehensive feature Fpe(t) and micro-vibration noise feature Fmvn(t) to form a fused feature data set Fset(t), and stores it after marking, wherein the mark includes time t and data source identifier Fid; Among them, the feature data set Fset(t) is specifically Fset(t)={Ftv(t), Fpe(t), Fmvn(t), t, Fid}.

6. A communication system for multi-source heterogeneous data fusion according to claim 1, characterized in that: The temperature vibration comprehensive characteristic Ftv(t) is obtained by the following calculation formula: Where Ftv(t) represents the comprehensive characteristics of temperature vibration at time t, specifically the dynamic relationship between temperature T(t) at time t and vibration frequency V(t); T(t) represents temperature, specifically the temperature T at time t; V(t) represents vibration frequency, reflecting the thermal state of power grid equipment, specifically the vibration frequency at time t. represents the derivative of the vibration frequency V(t) with respect to time t, and d represents the derivative; The power consumption interference comprehensive feature Fpe(t) is obtained by the following calculation formula: Wherein, Fpe(t) represents the comprehensive characteristics of power consumption interference at time t, specifically represents the dynamic relationship between the electromagnetic interference intensity E(t) and the power consumption P(t) at time t, E(t) represents the electromagnetic interference intensity of the equipment at time t, specifically represents the degree of electromagnetic interference in the equipment operation area, P(t) represents the equipment operation power consumption at time t, specifically represents the energy consumption during operation; ln represents the natural logarithm function, specifically used to adjust the range of the dynamic relationship between the electromagnetic interference intensity E(t) and the power consumption P(t); The micro-vibration noise feature Fmvn(t) is obtained by the following calculation formula: Wherein, Fmvn(t) represents the micro-vibration noise characteristics at time t, specifically the dynamic relationship between the micro-vibration frequency MV(t) and the noise spectrum NS(t) at time t. MV(t) represents the micro-vibration frequency at time t, specifically the number of micro-vibrations that occur when the equipment is running at time t, reflecting the stability of the equipment's operating state. NS(t) represents the noise spectrum at time t, specifically the environmental noise state of the equipment in the operating area at time t. It represents the first-order derivative of the micro-vibration frequency MV(t) with respect to time t, specifically the rate of change of the micro-vibration frequency MV(t) with time, and is used to capture instantaneous fluctuations.

7. The communication system for multi-source heterogeneous data fusion according to claim 1, characterized in that: The anomaly detection model module uses the fused feature data set Fset(t) as model input data and inputs the constructed anomaly detection model, wherein the construction of the anomaly detection model includes using isolation forest, principal component analysis and support vector machine algorithms to construct the model, and through the training and analysis of the anomaly detection model, the operation status of the communication system is reflected to obtain the anomaly score set Ascore(t) of the current communication system; The anomaly score set Ascore(t) is obtained by the following calculation formula: Where Fset,i(t) represents the i-th feature in the feature data set Fset(t) at time t, μF,i represents the i-th feature mean, σF,i represents the i-th feature standard deviation, N represents the number of features, λ represents the adjustment coefficient, which is specifically used to balance the dynamic relationship between features and distance metrics, and Ddist(t) represents the distance metric of the feature in the anomaly detection model, which specifically indicates the degree of difference between the current feature and the qualified state feature of the model.

8. The communication system for multi-source heterogeneous data fusion according to claim 1, characterized in that: The prediction model building module includes a data preparation unit and a data inference unit; The data preparation unit synchronously extracts the stored historical data set through the anomaly score set Ascore(t) to form a historical anomaly score set Hscore(t), and performs feature selection and time series processing based on the anomaly score set Ascore(t) and the historical anomaly score set Hscore(t), including time series smoothing and difference processing, obtains the smoothed anomaly score value S(t) and the anomaly score difference value D(t) at time t, reflects the change trend of the anomaly score, and synchronously covers and replaces the anomaly score set Ascore(t) with the smoothed anomaly score value S(t) to form a smoothed anomaly score set Ascore(t); The data inference unit constructs a prediction model by using a time series model, inputs the smoothed anomaly score set Ascore(t), the anomaly score difference value D(t) and the historical anomaly score set Hscore(t) as input data of the prediction model, performs prediction training through the prediction model, and obtains the abnormal situation factor Pfuture(t+n).

9. A communication system for multi-source heterogeneous data fusion according to claim 8, characterized in that: The abnormal situation factor Pfuture(t+n) is obtained by the following calculation formula: Pfuture(t+n)=β0+β1·Ascore(t)+β2·D(t)+β3·Hscore(t); Where β0 represents the bias term of the prediction model function, specifically represents the constant baseline, β1, β2 and β3 represent the preset weight values ​​of the smoothed anomaly score set Ascore(t), the anomaly score difference value D(t) and the historical anomaly score set Hscore(t), respectively.

10. A communication system for multi-source heterogeneous data fusion according to claim 8, characterized in that: The abnormal score value S(t) is obtained by the following calculation formula: S(t)=α·Ascore(t)+(1-α)·Hscore(t-1); Wherein, α represents the smoothing coefficient, which is specifically used to adjust the preset weight value allocation of the anomaly score set Ascore(t) and the historical anomaly score set Hscore(t); The abnormal score difference value D(t) is obtained by the following calculation formula:

11. A communication system for multi-source heterogeneous data fusion according to claim 1, characterized in that: The early warning and decision module matches the acquired abnormal situation factor Pfuture(t+n) with the preset abnormal assessment threshold YZ, and The matching formula obtains the abnormal matching result M(t+n), and generates an adaptive control strategy scheme based on the abnormal matching result; When the abnormal matching result M(t+n) is 1, the abnormal situation is predicted, and the abnormal matching result is generated to generate an adaptive control strategy plan, including adjusting system parameters, switching backup systems, reducing power consumption, and notifying operators to take action; When the abnormal matching result M(t+n) is 0, the prediction is obtained without abnormality, and no abnormal matching result is generated to generate an adaptive control strategy solution.

12. A communication system for multi-source heterogeneous data fusion according to claim 1, characterized in that: The feedback and adaptive optimization module matches the anomaly matching result M(t+n) with the actual feedback result R(t+n), wherein the actual feedback result R(t+n) includes obtaining the error term and the model adjustment index Tzs for adjusting the anomaly detection model and the prediction model through operator feedback, and using the model adjustment index Tzs as a regulating factor to indirectly adjust the anomaly detection performance and prediction performance of the model by affecting the parameter update during the training process of the anomaly detection model and the prediction model; The model adjustment index Tzs is obtained by the following calculation formula: Tzs(t+n)=Tzs(t)-η·(M(t+n)-R(t+n)); Where Tzs(t) represents the model adjustment index at time t, specifically including the anomaly detection model and the prediction model, and η represents the learning rate, specifically indicating the control adjustment step size.

13. A communication method for multi-source heterogeneous data fusion, comprising a communication system for multi-source heterogeneous data fusion as claimed in any one of claims 1 to 12, characterized in that: The following steps are involved: Step 1: The data collection and preprocessing module collects data from multiple heterogeneous data sources in real time to form a collection data group Draw, and preprocesses the collection data group Draw to obtain a preprocessed data set Dpre; Step 2: The data fusion and feature extraction module performs data fusion on the preprocessed data set Dpre, obtains the temperature vibration comprehensive feature Ftv(t), power consumption interference comprehensive feature Fpe(t) and micro-vibration noise feature Fmvn(t) at time t, and then performs feature extraction to form a fused feature data set Fset(t), which is marked and stored; Step 3: The anomaly detection model module constructs an anomaly detection model through the fused feature data set Fset(t), and obtains the anomaly score set Ascore(t) of the current communication system through training and analysis of the anomaly detection model; Step 4: The prediction model building module builds a prediction model through the anomaly score set Ascore(t) and the stored historical data set, and obtains the abnormal situation factor Pfuture(t+n) through prediction by the prediction model; Step 5: The early warning and decision-making module matches the acquired abnormal situation factor Pfuture(t+n) with the preset abnormal assessment threshold YZ to obtain the abnormal matching result M(t+n), and generates an adaptive control strategy scheme based on the abnormal matching result; Step 6: The feedback and adaptive optimization module matches the anomaly matching result M(t+n) with the actual feedback result R(t+n), obtains the error term and the model adjustment index Tzs used to adjust the anomaly detection model and prediction model.

Images