Online energy monitoring system and method

Abstract

The invention relates to the technical field of energy monitoring, in particular to an on-line energy monitoring system and method, a multi-source data acquisition module realizes omnibearing and multi-level energy network monitoring by integrating various sensors, and the comprehensiveness and accuracy of data are ensured; the adaptive acquisition control module establishes a risk assessment model by using historical data, dynamically adjusts the acquisition frequency and parameter range of the sensor, and optimizes the data acquisition efficiency. The data preprocessing module improves the data quality through filtering, denoising, alignment and standardization processing, and provides a reliable basis for subsequent analysis; the energy analysis module supports system optimization scheduling and energy-saving decision, rapidly detects abnormal points, and reduces manual intervention cost. And the intelligent response module formulates a response strategy according to an analysis result, so that self-regulation and optimization of the system are realized, and the energy utilization efficiency and the equipment operation reliability are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of energy monitoring, and in particular to an online energy monitoring system and method. BACKGROUND

[0002] In the field of energy monitoring, traditional systems rely on fixed-frequency data acquisition and static threshold judgment, making it difficult to cope with complex and variable energy network environments. The existing technology has the following limitations: Data acquisition is rigid: sensors usually work at a fixed frequency and cannot be dynamically adjusted according to real-time risks, resulting in insufficient data granularity in high-risk scenarios, while producing redundant data in low-risk situations, wasting storage and computing resources.

[0003] Risk perception lag: traditional risk assessment methods that rely on manually set thresholds lack the ability to dynamically model based on historical data, making it difficult to capture parameter trends, resulting in delayed warnings. This lag can lead to equipment failure or sudden energy efficiency, affecting system stability and efficiency.

[0004] Data processing is extensive: abnormal value filtering mostly relies on fixed threshold methods, which are sensitive to non-Gaussian distributed noise and prone to misjudgment. In addition, commonly used signal denoising techniques such as mean filtering can result in feature loss, affecting the accuracy of subsequent analysis.

[0005] Anomaly detection relies on prior knowledge: supervised anomaly detection requires a large amount of labeled data, while in industrial scenarios, abnormal samples are scarce, and algorithms such as SVM have high computational complexity, making it difficult to meet real-time requirements.

[0006] Shallow device health monitoring: traditional vibration analysis only focuses on time-domain statistics (such as RMS values), ignoring the mapping relationship between frequency-domain features and fault patterns, resulting in a high rate of early fault detection, increasing maintenance costs and downtime risks. SUMMARY

[0007] The present application provides an online energy monitoring system and method, which uses multiple sensors to capture data in real time and adopts a dynamic adjustment strategy to optimize acquisition efficiency, combines BP neural network, isolated forest algorithm, and vibration spectrum analysis technology to evaluate energy efficiency, identify abnormalities, and predict faults, and finally automatically develops response strategies based on analysis results to improve energy utilization efficiency and device operation reliability.

[0008] To achieve the purpose of the present application, the technical solution adopted is: an online energy monitoring system, comprising a multi-source data acquisition module, an adaptive acquisition control module, a data preprocessing module, an energy analysis module, and an intelligent response module; The multi-source data acquisition module includes an electric energy sensor group, an electrical characteristic sensor, and a device state sensor, the electric energy sensor group is used for monitoring basic energy data, the electrical characteristic sensor is used for monitoring power grid quality state, and the device state sensor is used for monitoring device operation health degree; The adaptive acquisition control module establishes a risk assessment model of monitoring parameters by using historical data based on data provided by the multi-source data acquisition module, and dynamically adjusts the acquisition frequency and parameter range of the electric energy sensor group, the electrical characteristic sensor, and the device state sensor according to the change trend of the monitoring parameters; The data preprocessing module receives original data from the data acquisition module, and performs filtering, denoising, and standardization processing; The energy analysis module receives data preprocessed by the data preprocessing module, adopts a BP neural network to evaluate energy efficiency, an isolated forest algorithm to identify abnormal patterns, and a vibration spectrum analysis to predict device faults, and the energy analysis module transmits analysis results to the intelligent response module, and the intelligent response module formulates a corresponding response strategy according to the analysis results; The adaptive acquisition control module includes establishment of a risk assessment model of monitoring parameters, and specifically includes: 1) Parameter risk level division;

[0009] Wherein: Q k (p) is a parameter risk level division result; F -1 (p) is an inverse function of an experience distribution function, indicating a value corresponding to a probability p of a cumulative distribution function; and x is a current parameter value; 2) Dynamic calculation of risk weight; ; wherein: H i =-∑p k log2p k ; Wherein: w i is the risk weight of the i th parameter; H i is the information entropy of the i th parameter; and p k is the frequency of occurrence of the i th parameter in the k th risk interval; 3) The risk assessment model of the monitoring parameters is: ; Wherein: R t represents a comprehensive risk value at a current moment, r i (t) is a risk level of the i th parameter at the current moment; λ is a trend sensitivity coefficient; and dR / dt is a change rate of the risk value.

[0010] As an optimization scheme of the present application, the electric energy sensor group includes an electric energy sensor and a power meter, which captures the power consumption and power information in real time; the electrical characteristic sensor includes a voltage sensor, a current sensor, and a power factor sensor, which monitors the stability and health condition of the power grid; the device state sensor includes a temperature sensor and a vibration sensor, which evaluates the working state of the device by monitoring the working temperature and vibration frequency of the key device.

[0011] As an optimization scheme of the present application, the core target of dynamically adjusting the acquisition frequency is to optimize the data acquisition efficiency according to Rt and the change trend dR / dt, which specifically includes: A) generating a comprehensive risk value at the current moment based on a risk assessment model; B) capturing the change trend of the risk by using a sliding window mechanism and a time decay factor; C) dynamically adjusting the acquisition frequency according to the comprehensive risk value and the change trend; The dynamic boundary calculation adjusts the upper and lower limit ranges of the parameters according to the risk value, further optimizing the acquisition efficiency; As an optimization scheme of the present application, the acquisition frequency adjustment strategy is formulated according to the comprehensive risk value Rt and the change trend dR / dt: 1) high-risk region: R t >R high or dR / dt > dR threshold : Increase the acquisition frequency to monitor the high-risk parameters in real time; adjustment formula: f new =f base ×k high； f new is the new acquisition frequency, f base is the basic acquisition frequency, k high is the high-risk adjustment coefficient, R high is the high-risk threshold, dR threshold is the threshold of the risk change rate; 2) medium-risk region: R low ≤R t ≤R high and dR / dt ≤ dR threshold , maintain the basic acquisition frequency, f new =f base ; 3) low-risk region: R t <R low and dR / dt ≤ dR threshold , reduce the acquisition frequency to save resources, adjustment formula: f new =f base ×k low , k low is the low-risk adjustment coefficient, R lowThe low risk threshold.

[0012] As an optimization scheme of the present application, the data preprocessing module processes include: Data alignment, time synchronization and resampling solve the time deviation problem of multi-source data; Outlier processing, using improved Hampel filter to remove outliers, and filling missing values through ARIMA model; Signal denoising, using wavelet threshold denoising technology to remove high frequency noise and retain the main characteristics of the signal; Feature standardization converts data to a unified scale through dynamic Z-score standardization.

[0013] As an optimization scheme of the present application, the energy analysis module receives the data preprocessed by the data preprocessing module, and the specific steps of evaluating energy efficiency using BP neural network are as follows: 1) Prepare the training data set; the data preprocessed by the data preprocessing module constitutes the training data set; 2) Input layer: n-dimensional characteristic electric energy, power factor and temperature; Hidden layer: using hyperbolic tangent activation function; Output layer: Sigmoid function outputs energy efficiency score; Train the BP neural network model: adjust the weight through back propagation algorithm to minimize the error.

[0014] As an optimization scheme of the present application, the energy analysis module transmits the analysis result to the intelligent response module, and the intelligent response module formulates the corresponding response strategy according to the analysis result, which specifically includes: S71, receiving and analyzing the analysis result; Input: energy efficiency score, abnormal score and device health status from the energy analysis module; Energy efficiency score: output by BP neural network, ranging from (0, 1]; Abnormal score: calculated by Isolation Forest algorithm, reflecting whether the data point is abnormal; Device health status: based on vibration spectrum analysis, to assess whether the device has a risk of failure; S72, formulate response strategy; according to the analyzed result, the intelligent response module needs to formulate specific response strategy; including energy efficiency score response strategy, abnormal score response strategy and device health status response strategy.

[0015] As an optimization scheme of the present application, formulate response strategy; according to the analyzed result, the intelligent response module needs to formulate specific response strategy; Energy efficiency score response strategy; condition: when energy efficiency score S efficiency<0.5, indicating low energy efficiency; strategies include reducing the operating time or load of high-energy-consuming equipment, increasing the workload of low-energy-consuming equipment, adjusting the equipment operation schedule, and taking advantage of the peak-valley electricity price difference to reduce costs; Abnormal score response strategy; condition: when the abnormal score S anomaly ≥0.6, indicating a clear abnormality; when 0.5≤S anomaly <0.6, indicating a suspected abnormality; when a clear abnormality occurs, an alarm is triggered: immediately notify the relevant personnel for manual verification, and take appropriate measures according to the type of abnormality; when a suspected abnormality occurs, a log is recorded: record the abnormal condition in the system log for subsequent analysis; 3) Equipment health state response strategy; when the equipment health state shows a potential risk of failure, perform advance maintenance, arrange preventive maintenance of the equipment according to the vibration spectrum analysis result, and avoid sudden failure.

[0016] In order to achieve the purpose of the application, the technical scheme adopted is: a monitoring method of an online energy monitoring system, comprising: multi-source data acquisition, adaptive acquisition control, data preprocessing, energy analysis and intelligent response; The multi-source data acquisition includes an electric energy sensor group, an electrical characteristic sensor and a device state sensor, the electric energy sensor group is used for monitoring basic energy data, the electrical characteristic sensor is used for monitoring the quality state of the power grid, and the device state sensor is used for monitoring the operation health degree of the equipment; The adaptive acquisition control establishes a risk assessment model of the monitoring parameters based on the data provided by the multi-source data acquisition module, and dynamically adjusts the acquisition frequency and parameter range of the electric energy sensor group, the electrical characteristic sensor and the device state sensor according to the change trend of the monitoring parameters; The data preprocessing receives the original data from the data acquisition module, and performs filtering, denoising and standardization processing; The energy analysis receives the preprocessed data from the data preprocessing module, adopts a BP neural network to evaluate energy efficiency, an isolated forest algorithm to identify abnormal patterns, and a vibration spectrum analysis to predict equipment failure, and the energy analysis transmits the analysis result to the intelligent response module, and the intelligent response module formulates a corresponding response strategy according to the analysis result.

[0017] The application has positive effects: 1) The invention improves data collection efficiency and accuracy; multi-source data collection integrates multiple types of sensors (such as power sensor groups, electrical characteristic sensors, and device state sensors), achieving multi-level and all-around data collection of energy networks. This comprehensive data collection method not only provides rich basic information, but also lays a solid foundation for subsequent in-depth analysis. Adaptive collection control: based on the risk assessment model established by historical data analysis, the risk value and trend can be dynamically adjusted according to the current risk value and trend, and the collection frequency and parameter range of the sensor can be dynamically adjusted. Ensure that critical data can be obtained in real time in high-risk situations, and resources can be effectively saved in low-risk conditions.

[0018] 2) The invention enhances the intelligent level of the system: sliding window mechanism and trend-sensitive mechanism: these mechanisms are used to capture the changing trend of risk and warn of potential problems in advance. They not only improve the response speed of the system, but also enhance the prediction ability, so that the system can take preventive measures before failure occurs. BP neural network evaluation of energy efficiency: through nonlinear modeling of multi-dimensional features, BP neural network can accurately evaluate the energy efficiency level of the system or device and provide optimization scheduling suggestions. This helps to identify inefficient operation modes and improve overall energy utilization efficiency. Isolation forest algorithm identifies abnormal patterns: without labeled data, it can complete anomaly detection, reduce the cost of manual intervention, and quickly identify abnormal points to avoid major losses.

[0019] 3) The invention optimizes data quality and reduces operating costs: data preprocessing: including time synchronization, outlier processing, signal denoising, and feature standardization, etc. steps, which significantly improve the data quality. High-quality data provides reliable protection for subsequent analysis and reduces false positives caused by data quality problems.

[0020] Dynamic boundary calculation: dynamically adjust the upper and lower limit range of parameters according to the risk value, further optimize the data collection efficiency, avoid the collection of redundant or invalid data, and thus reduce the operating costs.

[0021] 4) The invention improves the reliability of device operation and prolongs the service life. FFT is applied to convert vibration signals into frequency domain signals, accurately diagnose whether the device has specific types of faults (such as imbalance, misalignment, etc.). This makes maintenance work more targeted, can arrange preventive maintenance in advance, reduces the probability of sudden failure, and prolongs the service life of the device. According to the analysis results, automatic response strategies are formulated, covering energy efficiency score response strategies, abnormal score response strategies, and device health state response strategies, etc. aspects, ultimately realizing self-regulation and optimization of the system. BRIEF DESCRIPTION OF DRAWINGS

[0022] The invention will be further described in detail below in conjunction with the drawings and specific embodiments.

[0023] Figure 1 is a block diagram of the principles of the present application. DETAILED DESCRIPTION

[0024] The terms "first", "second", "third", "fourth" and the like in the description and in the claims of the present application, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of the terms so termed is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of orderly or chronological mundane operation, without necessitating a sequential or chronological order in the articles of manufacture or processes making use of or including such embodiments. It is also to be understood that the use of terms such as "including", "comprising" or "having" and variations thereof herein, is intended to encompass the inclusion of whole or integral steps or elements but not exclusion of any other steps or elements or incident thereto or thereof. It is to be understood that such terms are merely used in their non-limiting sense and, as such, should be interpreted in the context of the present application.

[0025] For the purpose of facilitating understanding, the specific flow of the embodiments of the present application is described below, please refer to Figure 1 The online energy monitoring system in the embodiments of the present application comprises a multi-source data acquisition module, an adaptive acquisition control module, a data preprocessing module, an energy analysis module and an intelligent response module. The multi-source data acquisition module comprises an electric energy sensor group, an electrical characteristic sensor and a device state sensor. The electric energy sensor group is used for monitoring basic energy data, the electrical characteristic sensor is used for monitoring the quality state of the power grid, and the device state sensor is used for monitoring the running health degree of the device. The electric energy sensor group comprises an electric energy sensor and a power meter, which can capture real-time power consumption, power and other information, helping to understand the power consumption situation and trend. The electrical characteristic sensor comprises a voltage sensor, a current sensor and a power factor sensor, which can monitor the stability and health condition of the power grid, such as detecting voltage fluctuation, current imbalance and power factor change, which is crucial for ensuring the safe operation of the power grid. The device state sensor can monitor the working temperature and vibration frequency of the key equipment (transformer, circuit breaker) to evaluate the working state of the equipment and find potential faults in advance. For example, overheating or abnormal vibration may be an early sign of mechanical component wear. The multi-source data acquisition module realizes all-around and multi-level monitoring of the energy network by integrating various types of sensors, providing solid data support for the online energy monitoring system.

[0026] The adaptive acquisition control module establishes a risk assessment model of the monitoring parameters based on the data provided by the multi-source data acquisition module, and dynamically adjusts the acquisition frequency and parameter acquisition range of the electric energy sensor group, the electrical characteristic sensor and the device state sensor according to the change trend of the monitoring parameters.

[0027] The adaptive acquisition control module includes the establishment of a risk assessment model for monitoring parameters and the implementation of dynamic adjustment. The establishment of the risk assessment model for monitoring parameters specifically includes: 1) Parameter risk level division (dynamic quantile division method);

[0028] wherein: Q k (p) is the parameter risk level division result; F -1 (p) is the inverse function of the empirical distribution function, indicating the value corresponding to the probability p of the cumulative distribution function; x is the current parameter value.

[0029] 2) Dynamic calculation of risk weight (weight distribution based on information entropy); ; wherein: H i =-∑p k log2p k ; w i is the risk weight of the i-th parameter; H i is the information entropy of the i-th parameter, reflecting its uncertainty; p k is the frequency of the i-th parameter in the k-th risk interval. ∑(1-H j ): the weighted sum of information entropy of all parameters.

[0030] The risk assessment model for monitoring parameters is: ; R t represents the comprehensive risk value at the current time (time point t), w i is the risk weight of the i-th parameter, r i (t) is the risk level of the i-th parameter at the current time. λ is a trend sensitivity coefficient, used to adjust the influence degree of risk change rate on the final risk value. dR / dt is the change rate of risk value, i.e., the change trend of risk over time.

[0031] The implementation of dynamic adjustment specifically includes: 1) Sliding window mechanism;

[0032] wherein: is the variance at the current time, α is the time decay factor, x t is the observation value at the current time, μ t-1 is the mean value at the previous time. ; wherein, is the weighted moving average at the current time.

[0033] 2) Dynamic boundary calculation; ; dynamic adjustment coefficient k, whose value is determined according to R t : ; [L t , H t ] upper and lower limit range of monitoring parameters (i.e. dynamic boundary).

[0034] 3) Trend-sensitive mechanism; ; T is the time span of the sliding window.

[0035] The risk assessment model of the monitoring parameter is responsible for generating the current risk value, reflecting the instantaneous state of the system.

[0036] The dynamic boundary calculation and sliding window mechanism are responsible for optimizing the data parameter collection range, ensuring that the collected data is representative. The trend-sensitive mechanism is responsible for capturing the changing trend of the risk, helping the system to early warn potential problems.

[0037] The core goal of dynamically adjusting the collection frequency is to optimize data collection efficiency according to Rt and the change trend dR / dt, ensuring real-time monitoring of key parameters, while reducing resource consumption of low-risk parameters. Specifically, it can be divided into the following steps: Generate the comprehensive risk value at the current time based on the risk assessment model.

[0038] B) Capture the changing trend of the risk using the sliding window mechanism and the time decay factor.

[0039] C) Dynamically adjust the collection frequency according to the comprehensive risk value and the change trend.

[0040] D) Optimize the collection range (dynamic boundary calculation): adjust the upper and lower limit range of the parameters according to the risk value, further optimizing the collection efficiency.

[0041] Determine the collection frequency adjustment strategy: according to the comprehensive risk value Rt and the change trend dR / dt, develop the collection frequency adjustment strategy: 1) High-risk area (R t > R high or dR / dt > dR threshold ): Increase the collection frequency to monitor high-risk parameters in real time. Adjustment formula: f new = f base × k high； f new is the new collection frequency, f base is the basic collection frequency. k high is the high-risk adjustment coefficient (usually takes the value of 2~5). R high is the high-risk threshold. dR thresholdThreshold for risk change rate.

[0042] 2) Medium-risk area (R low ≤R t ≤R high and dR / dt≤dR threshold ): Maintain the basic acquisition frequency. f new =f base。

[0043] 3) Low-risk area (R t <R low and dR / dt≤dR threshold ): Reduce the acquisition frequency to save resources. Adjustment formula: f new =f base ×k low , k low is the low-risk adjustment coefficient (usually 0.2~0.5). R low is the low-risk threshold.

[0044] The adaptive acquisition control module can dynamically adjust the acquisition frequency and parameter acquisition range according to the risk value and change trend of the monitoring parameters. The specific effects include: improving data acquisition efficiency: increasing the acquisition frequency in the high-risk area to ensure real-time monitoring of key parameters. Reduce the acquisition frequency in the low-risk area to save resources.

[0045] Enhance the response capability of the system: the sliding window mechanism and the trend-sensitive mechanism can quickly capture the risk change trend and provide early warning of potential problems.

[0046] Optimize data quality: dynamic boundary calculation ensures that the collected data is representative, avoiding the collection of redundant or invalid data.

[0047] Reduce operating costs: by dynamically adjusting the acquisition frequency and range, unnecessary resource consumption is reduced. The adaptive acquisition control module combines risk assessment models, sliding window mechanisms, and dynamic boundary calculations to intelligently adjust the acquisition frequency and range of the electric energy sensor group, electrical characteristic sensors, and device status sensors. This method not only improves the efficiency and quality of data acquisition, but also enhances the stability and reliability of the system, providing important support for the intelligent management of online energy monitoring systems.

[0048] The data preprocessing module receives raw data from the data acquisition module, performs filtering, denoising, and standardization processing; Data alignment: solve the time deviation problem of multi-source data through time synchronization (IEEE 1588 PTP protocol) and resampling.

[0049] Outlier processing: using improved Hampel filter to remove outliers, and filling missing values by ARIMA model (historical values and predicted values).

[0050] The improved Hampel filter process is as follows: Dynamic window selection: determine the window size k according to the local data characteristics.

[0051] Weighted statistical quantity calculation: calculate the weighted median M w and weighted MAD in the window.

[0052] Adaptive threshold determination: if ∣x i -M w ∣>λ•MAD w , mark as abnormal.

[0053] Multi-stage verification: secondary inspection on boundary outliers.

[0054] ARIMA filling: use historical data to predict the value of the abnormal point position and replace it.

[0055] The improved Hampel filter adaptive threshold and multi-stage detection reduce false positives, reduce the misjudgment rate, reduce the influence of edge noise, and dynamically adapt to data changes, improving the accuracy of outlier processing.

[0056] Signal denoising: use wavelet threshold denoising technology to remove high-frequency noise and retain the main characteristics of the signal.

[0057] Feature standardization: convert data to a unified scale through dynamic Z-score standardization.

[0058] The energy analysis module receives data preprocessed by the data preprocessing module, uses BP neural network to evaluate energy efficiency, isolated forest algorithm to identify abnormal patterns, and vibration spectrum analysis to predict equipment failure. The energy analysis module transmits the analysis results to the intelligent response module, and the intelligent response module formulates corresponding response strategies according to the analysis results.

[0059] 1. Receive data preprocessed by the data preprocessing module, and use BP neural network to evaluate energy efficiency as follows: 1) Prepare the training data set; the data preprocessed by the data preprocessing module constitutes the training data set.

[0060] 2) Input layer: n-dimensional features such as electric energy, power factor, temperature, etc. Hidden layer: use hyperbolic tangent activation function; Output layer: Sigmoid function outputs energy efficiency score.

[0061] 3) Train the BP neural network model: adjust the weights through backpropagation algorithm to minimize the error.

[0062] The basic calculation formula of BP neural network involves forward propagation and backpropagation process, where forward propagation is used to calculate the output and backpropagation is used to update the weights to reduce the error.

[0063] 2, the steps of the isolation forest algorithm to identify abnormal patterns are: Data preparation: collect and standardize normal operation data within a period of time.

[0064] Model building: build a model based on the isolation forest algorithm, set the number of trees and the size of the subsample.

[0065] Anomaly detection: input real-time data, and the model judges whether it is an abnormal point according to the decision path length.

[0066] Isolation forest (ISF) determines whether a sample is an outlier by calculating the path length required to isolate it.

[0067] 1) Isolation tree construction process; Random subsampling: randomly sample ψ samples (default 256) from the dataset without replacement as the training set of a single tree.

[0068] Recursive partitioning: randomly select a dimension in the feature space. Randomly select a split point between the minimum and maximum values in this dimension. According to the split value, divide the data into left and right sub-trees.

[0069] Termination condition: the current node contains only 1 sample; all sample feature values are the same; the tree height reaches the limit l = [log2ψ]. ψ is the subsample size.

[0070] 2. Abnormal detection process; Forest construction: generate t isolated trees (t = 100).

[0071] Path calculation: for each sample x, calculate its path length h i (x) in each tree.

[0072] Score calculation: calculate the average path length ; h(x) is the sample path length. Substitute the formula s(x, n) = 2 -E(h(x)) / c(n) ; where c(n) is the normalized path length and s(x, n) is the abnormal score.

[0073] Decision rule: s ≥ 0.6: clear anomaly (manual verification required); 0.5 ≤ s < 0.6 suspected anomaly (log record); s < 0.5 normal sample.

[0074] Example; Building Isolation Forest: Set ψ = 256, t = 100, then the tree height limit l = [log2 256] = 8; Detecting anomalies: A certain sample x has an average path length E(h(x)) = 3.2 in 100 trees; Calculate the normalized path length: c(10000) ≈ 2ln(10000) + 0.5772 = 20.723; Anomaly score: s = 2 -3.2 / 20.723 ≈0.89; Decision: s = 0.89 > 0.6, determine as an anomaly, trigger equipment maintenance process.

[0075] 3. Vibration spectrum analysis to predict equipment failure; Collect vibration data: Obtain vibration signals from equipment status sensors.

[0076] Spectrum analysis: Apply Fast Fourier Transform (FFT) to convert time-domain signals to frequency-domain signals.

[0077] Fault diagnosis: Based on frequency component analysis, determine whether there is a specific type of fault (such as imbalance, etc.) in the equipment.

[0078] The energy analysis module integrates BP neural network, isolation forest algorithm and vibration spectrum analysis technology, which can comprehensively evaluate energy efficiency, identify abnormal patterns and predict equipment failure. This multi-dimensional analysis method not only improves the intelligent level of energy management, but also provides a scientific basis for stable operation of the system. The following is a specific summary of its effects and benefits: Through the nonlinear modeling of multi-dimensional features (such as electric energy, power factor, temperature, etc.) by BP neural network, the energy efficiency level of the system or equipment can be accurately evaluated. BP neural network has self-learning ability and can continuously adjust weights according to the latest data to adapt to system changes. Energy efficiency score can help identify low-efficiency equipment or operation mode, providing basis for optimization scheduling.

[0079] The Isolation Forest algorithm builds Isolation Trees based on random splits, enabling fast computation of path lengths for each sample and determination of whether it is an outlier. It provides clear decision rules to distinguish between normal, suspected outlier, and definite outlier samples. Without labeled data, it reduces the cost of manual intervention for anomaly detection. By identifying abnormal patterns such as energy consumption anomalies and power grid quality fluctuations, it can alert before problems worsen, avoiding significant losses. Real-time monitoring and rapid response help ensure the safe operation of power grids and equipment. Standardization using statistical properties of path lengths reduces the impact of noise on anomaly detection. The energy analysis module combines BP neural networks, Isolation Forest algorithm, and vibration spectrum analysis to achieve comprehensive monitoring of energy systems from energy efficiency, anomalies, to equipment health status. The energy analysis module combines BP neural networks, Isolation Forest algorithm, and vibration spectrum analysis to achieve comprehensive monitoring and intelligent management of energy systems.

[0080] The energy analysis module transmits the analysis results to the intelligent response module, which formulates appropriate response strategies based on the analysis results, specifically: Receive and analyze the analysis results. Input: Energy efficiency score, anomaly score, and equipment health status from the energy analysis module.

[0081] Energy efficiency score: output by BP neural network, ranging from (0, 1].

[0082] Anomaly score: calculated by Isolation Forest algorithm, reflecting whether the data point is an anomaly.

[0083] Equipment health status: based on vibration spectrum analysis, assessing whether the equipment has a risk of failure.

[0084] Formulate response strategies; based on the analyzed results, the intelligent response module needs to formulate specific response strategies.

[0085] Energy efficiency score response strategy; condition: when the energy efficiency score S efficiency <0.5, indicating low energy efficiency. Strategies include reducing the operating time or load of high-energy-consuming equipment, increasing the workload of low-energy-consuming equipment; adjusting the equipment operating schedule to take advantage of peak and valley electricity price differences to reduce costs. Enable energy-saving mode or take other energy-saving measures.

[0086] Anomaly score response strategy; condition: when the anomaly score S anomaly ≥0.6, indicating a clear anomaly; when 0.5 ≤ S anomalyA value <0.6 indicates a suspected anomaly. A clear anomaly triggers an alarm: Relevant personnel are immediately notified for manual verification and appropriate measures are taken based on the anomaly type, such as replacing faulty equipment or repairing power grid issues. Suspected anomalies are logged: The anomaly is recorded in the system log for subsequent analysis. Increase the frequency of monitoring for that area or device to continuously observe behavioral changes.

[0087] Equipment health response strategy: When equipment health indicates a potential failure risk (for example, if a specific frequency component exceeds the normal range), proactive maintenance is implemented. Based on the vibration spectrum analysis results, preventive maintenance is scheduled to prevent sudden failures. If critical components (such as bearings and gears) are severely worn, they are promptly replaced. Operating parameters are adjusted based on the equipment's current status to reduce the risk of further damage.

[0088] An online energy monitoring method including multi-source data acquisition, adaptive acquisition control, data preprocessing, energy analysis and intelligent response; Multi-source data acquisition uses a set of power sensors to capture basic energy data such as power consumption and power in real time. Electrical characteristic sensors monitor grid quality and detect voltage fluctuations, current imbalances, and other issues. Equipment status sensors monitor parameters such as operating temperature and vibration frequency of key equipment (such as transformers and circuit breakers) to assess equipment health.

[0089] Adaptive acquisition control establishes a risk assessment model for monitoring parameters based on historical data: Parameter risk level classification: Parameter risk level classification is performed using the dynamic quantile method; risk weight dynamic calculation: weights are assigned based on information entropy, combined with current risk values ​​and change trends. Dynamic adjustment of acquisition frequency and parameter range includes: 1) Sliding window mechanism: Calculate weighted moving average and variance, and adjust the time decay factor; 2) Dynamic boundary calculation: Dynamically adjust the upper and lower limits of monitoring parameters based on the comprehensive risk value.

[0090] 3) Trend-sensitive mechanism: Captures changing trends in risks and provides early warning of potential problems.

[0091] Data preprocessing includes data alignment: IEEE 1588 PTP protocol is used to address time skew between multi-source data sources and resampling is performed. Outlier processing: A modified Hampel filter is used to remove outliers, and missing values ​​are filled using the ARIMA model. Signal denoising: Wavelet threshold denoising is used to remove high-frequency noise while preserving the signal's key features. Feature normalization: Dynamic Z-score normalization is used to convert data to a uniform scale.

[0092] Energy analysis assesses energy efficiency through BP neural networks, identifies abnormal patterns with Isolation Forest algorithm, and predicts equipment failures through vibration spectrum analysis.

[0093] Intelligent response receives and analyzes results, formulates response strategies, including energy efficiency score response strategy, abnormal score response strategy, and equipment health status response strategy.

[0094] Multi-source data acquisition module: through the integration of various sensors, it realizes all-around and multi-level energy network monitoring, ensuring the comprehensiveness and accuracy of data.

[0095] Adaptive acquisition control module: using historical data to establish a risk assessment model, dynamically adjusting the acquisition frequency and parameter range of the sensor, optimizing data acquisition efficiency and representativeness.

[0096] Data preprocessing module: through filtering, denoising, alignment and standardization processing, it improves data quality and provides a reliable basis for subsequent analysis.

[0097] Energy analysis module: BP neural network: through nonlinear modeling to assess energy efficiency level, supporting system optimization scheduling and energy saving decision-making. Isolation Forest algorithm: based on random partition to build isolated trees, quickly detect abnormal points, and reduce artificial intervention cost. Vibration spectrum analysis: through FFT to extract the frequency components of vibration signals, accurately diagnose equipment failures.

[0098] Intelligent response module: formulates response strategies according to analysis results, realizes self-adjustment and optimization of the system, and improves energy utilization efficiency and equipment operation reliability.

[0099] In the embodiment of the application, a computer device is also provided, which can be a server. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected by a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in the embodiment. The network interface of the computer device is used to communicate with the external terminal through the network connection. The computer program is executed by the processor to implement the above method.

[0100] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, system and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

[0101] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the entire or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0102] The above description and the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features. These modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An online energy monitoring system, characterized in that, The system comprises a multi-source data acquisition module, an adaptive acquisition control module, a data preprocessing module, an energy analysis module and an intelligent response module. The multi-source data acquisition module comprises an electric energy sensor group, an electrical characteristic sensor and a device state sensor, the electric energy sensor group is used for monitoring basic energy data, the electrical characteristic sensor is used for monitoring power grid quality state, and the device state sensor is used for monitoring device operation health degree. The adaptive acquisition control module establishes a risk assessment model of monitoring parameters based on data provided by the multi-source data acquisition module, and dynamically adjusts the acquisition frequency and parameter range of the electric energy sensor group, the electrical characteristic sensor and the device state sensor according to the change trend of the monitoring parameters. The data preprocessing module receives raw data from the multi-source data acquisition module, and performs filtering, denoising and standardization processing. The energy analysis module receives the data preprocessed by the data preprocessing module, adopts a BP neural network to evaluate energy efficiency, an isolated forest algorithm to identify abnormal patterns, and a vibration spectrum analysis to predict device faults, and transmits the analysis results to the intelligent response module. The adaptive acquisition control module comprises the establishment of the risk assessment model of the monitoring parameters, specifically as follows: 1) parameter risk level division; ； where: Q k (p) is the parameter risk level classification result; F -1 (p) is the inverse function of the empirical distribution function, indicating the value of the cumulative distribution function corresponding to the probability p; x is the current parameter value; 2) risk weight dynamic calculation; ; where: H i =-∑p k log2p k ; where: w i is the risk weight of the i-th parameter; H i is the information entropy of the i-th parameter; p k is the frequency of occurrence of the i-th parameter in the k-th risk interval. 3) the risk assessment model of the monitoring parameters is as follows: ； wherein: R t represents the comprehensive risk value at the current time, r i (t) is the risk level of the ith parameter at the current time; λ is the trend sensitivity coefficient, and dR / dt is the change rate of the risk value.

2. An online energy monitoring system according to claim 1, characterized in that: The electric energy sensor group comprises an electric energy sensor and a power meter, which can capture real-time power consumption and power information; the electrical characteristic sensor comprises a voltage sensor, a current sensor and a power factor sensor, which are used for monitoring the stability and health condition of the power grid; and the device state sensor comprises a temperature sensor and a vibration sensor, which are used for monitoring the working temperature and vibration frequency of the key equipment to evaluate the working state of the equipment.

3. An online energy monitoring system according to claim 2, wherein: The core goal of dynamically adjusting the acquisition frequency is to optimize the data acquisition efficiency according to R t and the change trend dR / dt, specifically including: Based on the risk assessment model, a comprehensive risk value at the current time is generated. The sliding window mechanism and the time decay factor are used to capture the change trend of the risk. According to the comprehensive risk value and the change trend, the acquisition frequency is dynamically adjusted. The dynamic boundary calculation adjusts the upper and lower limit ranges of the parameters according to the risk value, and further optimizes the acquisition efficiency.

4. An online energy monitoring system according to claim 3, wherein: According to the comprehensive risk value R t And the change trend dR / dt, the collection frequency adjustment strategy is made: a) High risk region is R t R high or dR / dt > dR threshold : Increase the collection frequency to monitor high-risk parameters in real time; adjust the formula: f new =f base ×k high； f new is the new collection frequency, f base is the basic collection frequency, k high is the high-risk adjustment coefficient, R high is the high-risk threshold, dR threshold is the threshold of risk change rate; b) the medium risk zone is R low ≤ R t ≤ R high and dR / dt < dR threshold , the base acquisition frequency, f new = f base ; c) Low risk area is R t <R low and dR / dt ≤ dR threshold , reduce the collection frequency to save resources, adjust the formula: f new = f base × k low , k low is the low-risk adjustment coefficient, R low is the low-risk threshold.

5. An online energy monitoring system according to claim 4, wherein: The data preprocessing module comprises the following processing: Data alignment solves the time deviation problem of multi-source data through time synchronization and resampling; Abnormal value processing uses an improved Hampel filter to eliminate abnormal values, and uses an ARIMA model to fill in missing values; Signal denoising uses wavelet threshold denoising technology to remove high-frequency noise and retain the main characteristics of the signal; Feature standardization converts the data to a unified scale through dynamic Z-score standardization.

6. An online energy monitoring system according to claim 5, wherein: The energy analysis module receives the data preprocessed by the data preprocessing module, and adopts a BP neural network to evaluate energy efficiency, specifically as follows: A) Prepare the training data set; The data preprocessed by the data preprocessing module constitutes the training data set; B) Input layer: n-dimensional characteristic electric energy, power factor and temperature; Hidden layer: uses a hyperbolic tangent activation function; Output layer: Sigmoid function outputs energy efficiency score; C) Train the BP neural network model: adjust the weight through the back propagation algorithm to minimize the error.

7. An online energy monitoring system according to claim 6, wherein: The energy analysis module transmits the analysis result to the intelligent response module, and the intelligent response module formulates a corresponding response strategy according to the analysis result, specifically including: S71, receiving and analyzing the analysis result; Input: energy efficiency score, abnormal score and device health status from the energy analysis module; Energy efficiency score: output by the BP neural network, ranging from (0, 1]; Abnormal score: calculated by the isolation forest algorithm, reflecting whether the data point is abnormal; Device health status: based on vibration spectrum analysis, to assess whether the device has a risk of failure; S72, formulating a response strategy; according to the analyzed result, the intelligent response module needs to formulate a specific response strategy; including energy efficiency score response strategy, abnormal score response strategy and device health status response strategy.

8. An online energy monitoring system according to claim 7, wherein: Formulate a response strategy; according to the analyzed result, the intelligent response module needs to formulate a specific response strategy; Energy efficiency score response strategy; Condition: When the energy efficiency score S efficiency <0.5, indicating that the energy efficiency is low; the strategy includes reducing the running time or load of high-energy-consuming equipment, increasing the workload of low-energy-consuming equipment; adjusting the equipment running schedule to take advantage of the peak-valley electricity price difference to reduce costs; Abnormal score response strategy; Conditions: When the abnormal score S anomaly ≥ 0.6, it indicates a clear abnormality; When 0.5≤S anomaly <0.6, indicates a suspected anomaly; trigger an alarm when the anomaly is clear: immediately notify the relevant personnel for manual verification, take appropriate measures according to the type of anomaly; record the log when the anomaly is suspected: record the abnormal situation in the system log for subsequent analysis; 3) Device health status response strategy; When the device health status shows potential risk of failure, carry out advance maintenance, arrange the preventive maintenance of the device according to the vibration spectrum analysis result, and avoid sudden failure.

9. A monitoring method for an online energy monitoring system as claimed in claim 8, characterized in that, Including: Multi-source data acquisition, adaptive acquisition control, data preprocessing, energy analysis and intelligent response; The multi-source data acquisition includes an electric energy sensor group, an electrical characteristic sensor and a device state sensor, the electric energy sensor group is used for monitoring basic energy data, the electrical characteristic sensor is used for monitoring power grid quality state, and the device state sensor is used for monitoring device operation health degree; The adaptive acquisition control establishes a risk assessment model of monitoring parameters by using historical data based on the data provided by the multi-source data acquisition module, and dynamically adjusts the acquisition frequency and parameter range of the electric energy sensor group, the electrical characteristic sensor and the device state sensor according to the change trend of the monitoring parameters; The data preprocessing receives original data from the data acquisition module, and performs filtering, denoising and standardization processing; The energy analysis receives the data pretreated by the data preprocessing module, adopts a BP neural network to evaluate energy efficiency, an isolation forest algorithm to identify abnormal mode and a vibration spectrum analysis to predict device failure, and transmits the analysis result to the intelligent response module, and the intelligent response module formulates a corresponding response strategy according to the analysis result.

Images