An intelligent monitoring method and system for the running state of an electrical device

Abstract

The application discloses an intelligent monitoring method and system for the running state of electrical equipment, and relates to the technical field of electrical equipment running monitoring. The method collects dynamic electrical data, and after preprocessing and data analysis, forms an electrical characteristic data group. A multi-stage analysis is carried out with the device power mutation trigger point t0 as the core anchor point. When the real-time power output jumps, a mutation event is identified and the instantaneous current sequence in the previous time window AT is extracted. A disturbance nonlinear evolution index DYN is constructed to evaluate the device disturbance. When the device running trend is abnormal, the energy coupling deviation index PHY is calculated according to the electrical characteristic data group. The coupling evolution evaluation is carried out by constructing the coupling imbalance superposition index CFS. According to the multi-level threshold value extracted from the historical coupling stable interval, the device state is judged to realize the continuous monitoring and dynamic intervention of the structural risk of the electrical equipment. The method establishes the basis for the engineering applicability in the high dynamic power scene.

Description

Technical Field

[0001] This invention relates to the field of electrical equipment operation monitoring technology, specifically to an intelligent monitoring method and system for the operating status of electrical equipment. Background Technology

[0002] With the continuous operation of electrical equipment in industrial production, energy transmission and distribution, and power electronic drives, its internal electrical behavior exhibits high dynamism, with instantaneous voltage, current, active power, and phase constantly changing over time. Traditional monitoring methods often rely on manual interpretation of steady-state quantities or low-frequency samples, making it difficult to capture the transient operating patterns of equipment under disturbance conditions. With the development of online sensing, edge computing, and signal analysis technologies, intelligent monitoring of operational status is gradually forming a system capable of structured analysis of continuous time-series electrical quantities, enabling real-time presentation and tracking of equipment dynamic behavior. In this system, equipment is not merely viewed as an input / output port of electrical energy, but as an electrical structure with internal energy transmission paths, coupling relationships, and dynamic response mechanisms. The operational status of the electrical structure can be analyzed through disturbance characteristics, energy coupling relationships, and changing trends in time-series data, thereby establishing a diagnostic framework for structural risks.

[0003] In existing monitoring systems, the analysis of electrical structures relies heavily on single-variable indicators such as current amplitude, voltage sag, and active power deviation. While these indicators have some reference value under steady-state conditions, they often fail to accurately reflect the true evolution of the structure under conditions such as sudden disturbances, load switching, and changes in internal energy consumption paths. Traditional models often assume that the disturbance process has linear or weakly nonlinear characteristics, neglecting the disturbance evolution properties of the sequence preceding the abrupt change, making it difficult to identify abnormal trends in advance. Furthermore, existing methods for verifying energy conservation relationships typically remain at the level of instantaneous power comparison or energy flow estimation, lacking quantitative indicators that can characterize the degree of coupling shift, structural misalignment, and changes in coupling trends within the electrical structure. These shortcomings make it difficult for monitoring systems to promptly determine whether disturbances have caused energy structure deviations, and also prevent them from providing clear conclusions as to whether disturbances are evolving into structural faults. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides an intelligent monitoring method and system for the operating status of electrical equipment, solving the problems mentioned in the background section.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an intelligent monitoring method for the operating status of electrical equipment, comprising the following steps:

[0006] S1. Based on the parameter acquisition devices deployed on the operating lines of electrical equipment, dynamic electrical data of electrical equipment is collected in real time, and after preprocessing and data analysis, it is combined into an electrical characteristic data group.

[0007] S2, By calculating the rate of power change The power change rate within a continuous sampling period is judged point by point, and the trigger point t0 of the sudden change event is recorded when a sudden change occurs in the power output.

[0008] S3. Taking the trigger point t0 of the sudden event as a reference, extract all instantaneous currents I with a time length of ΔT to perform disturbance evolution analysis on the operating state of electrical equipment, and generate equipment disturbance assessment based on the analysis results;

[0009] S4. When the equipment disturbance assessment indicates that the equipment operation trend is abnormal, perform a consistency verification analysis on the operating energy of the electrical equipment based on the electrical characteristic data group.

[0010] S5. Fit the disturbance evolution analysis results and the consistency verification analysis results to perform coupled evolution analysis on the abnormal disturbance trend and structural fault in the operation of electrical equipment, and generate a disturbance evolution assessment based on the analysis results.

[0011] Preferably, S1 includes S11;

[0012] S11. After calling and initializing the parameter acquisition device deployed on the electrical equipment operating line, the dynamic electrical data of the electrical equipment is collected in real time.

[0013] The parameter acquisition device includes a three-phase voltage transformer and a three-phase current transformer;

[0014] The three-phase voltage transformer is used to connect to the AC voltage line of the input or output terminal of the electrical equipment to collect the instantaneous voltage U of the electrical equipment in real time.

[0015] The three-phase current transformer is used to be connected in series in the main circuit of the electrical equipment to collect the instantaneous current I of the electrical equipment in real time.

[0016] Preferably, S1 further includes S12;

[0017] S12. Transmit the dynamic electrical data to the edge node for preprocessing, the preprocessing including timestamp alignment and filling missing values;

[0018] The timestamp alignment uses linear interpolation resampling technology to interpolate and predict missing time points in dynamic electrical data, and the missing value filling uses missing value interpolation technology to complete dynamic electrical data with sampling interruption and communication packet loss.

[0019] The preprocessed dynamic electrical data set is then subjected to data analysis, which includes power factor calculation and active power calculation.

[0020] The power factor calculation is based on the time structure of the voltage and current waveforms formed by the continuous sequence of instantaneous voltage U and instantaneous current I changing over time. The voltage and current waveforms are formed by the analog signal sampling module built into the MCU in the electrical equipment controller and A / D conversion is performed. The phase of the sampled voltage and current waveforms is compared, and the main frequency phase difference φ is extracted using digital phase-locked loop technology. The power factor cosφ is calculated based on the main frequency phase difference φ.

[0021] The active power calculation is based on the instantaneous voltage U, instantaneous current I, and power factor cosφ to calculate the active power Py of the electrical equipment, Py=U×I×cosφ;

[0022] Instantaneous voltage U, instantaneous current I, power factor cosφ, and active power Py together form the electrical characteristic data set.

[0023] Preferably, S2 includes S21 and S22;

[0024] S21. Calculate the rate of change of active power Py using the moving difference method to form an active power sequence that varies with time. Where Py(t) represents the active power at time t, and dt represents the sign of the time variable;

[0025] S22. Set a disturbance judgment threshold TP based on the allowable power fluctuation under standard conditions, and the power change rate. By comparing the results, the rate of power change within the continuous sampling period is judged point by point. When this time, it indicates that the current power output is normal; continue normal monitoring. When the current power output suddenly changes, it indicates that the current power fluctuation is identified as a power mutation event, and the current time point t0 is recorded as the trigger point of the mutation event.

[0026] Preferably, S3 includes S31;

[0027] S31. Taking the trigger point t0 of the sudden event as a reference, extract all instantaneous currents I over a time period of ΔT, perform disturbance evolution analysis on the operating state of electrical equipment within the time window ΔT, and calculate the disturbance nonlinear evolution index DYN to reflect the continuous nonlinear disturbance intensity of the current sequence before the sudden event on the time scale, as follows:

[0028] ;

[0029] Among them, I avg dt represents the average current, ΔT represents the backtracking time window length, t0 represents the trigger point of the sudden event, I(t) represents the instantaneous current at time t, and dt represents the sign of the time variable.

[0030] Preferably, S3 further includes S32;

[0031] S32. Extract the perturbation nonlinear evolution index DYN sequence of the normal segment before mutation within half a year, calculate the median value through a sorting algorithm, and multiply it with the deviation tolerance constant k to construct the perturbation nonlinear evolution threshold Td. Compare the perturbation nonlinear evolution threshold Td with the obtained perturbation nonlinear evolution index DYN, and generate equipment perturbation assessment based on the comparison results. The deviation tolerance constant k takes the value of [1.5, 2.5].

[0032] The equipment disturbance assessment is as follows;

[0033] When the disturbance nonlinear evolution index DYN < the disturbance nonlinear evolution threshold Td, it indicates that the equipment operation trend is stable. At this time, the current time period is marked as a stable operation period, and the standard sampling frequency is maintained.

[0034] When the disturbance nonlinear evolution index DYN is greater than or equal to the disturbance nonlinear evolution threshold Td, it indicates that the equipment operation trend is abnormal. At this time, the current time period is marked as the disturbance critical segment, and the consistency verification analysis is activated.

[0035] Preferably, S4 includes S41;

[0036] S41. When equipment disturbance is assessed as an abnormal equipment operating trend, a consistency check analysis is performed on the operating energy of the electrical equipment based on the electrical characteristic data set, and the energy coupling deviation index PHY is calculated to reflect the degree to which the operating energy of the equipment satisfies the law of energy conservation. The impact of disturbance on the equipment operating law is analyzed, as follows:

[0037] ;

[0038] Where N represents the number of sampling time points within the time window ΔT, Py i U i and I i U represents the active power, instantaneous voltage, and instantaneous current at the i-th sampling point, respectively. bz，i I bz，i and φ bz，i Represents the theoretical instantaneous voltage, instantaneous current, and phase difference at the i-th sampling point under standard conditions, where cos represents the cosine function, and cosφ bz，i Let be the theoretical power factor of the i-th sampling point under standard conditions.

[0039] Preferably, S5 includes S51;

[0040] S51. The disturbance nonlinear evolution index DYN is fitted with the energy coupling deviation index PHY to perform coupled evolution analysis on the abnormal disturbance trend and structural faults in the operation of electrical equipment, and the coupling imbalance superposition index CFS is calculated to represent the degree of structural vulnerability of the equipment and reflect the overall structural vulnerability of the equipment, as follows:

[0041] ;

[0042] Where ln represents the logarithmic function, The symbol for tensor multiplication in mathematics is DYN. PHY represents the coupling strength between the perturbation nonlinear evolution index and the coupling energy coupling deviation index, and ∇PHY represents the trend of the energy coupling deviation index.

[0043] Preferably, S5 further includes S52;

[0044] S52. Extract the coupling imbalance superposition index (CFS) sequence of all coupled stable states within six months, and calculate the 75th percentile value using the percentile method as the coupling stability threshold Cw. Extract the maximum value as the structural degradation risk threshold Cl, and then compare it with the obtained coupling imbalance superposition index CFS. Based on the comparison results, generate a coupling evolution assessment. The disturbance evolution assessment is as follows.

[0045] When the coupling imbalance superposition index CFS < coupling stability threshold Cw, it indicates that the electrical structure of the equipment is stable and there is no energy structure mismatch behavior. At this time, the current state is marked as acceptable disturbance and normal monitoring is maintained.

[0046] When the coupling stability threshold Cw ≤ coupling imbalance superposition index CFS ≤ structural degradation risk threshold Cl, it indicates that there is a deviation in the equipment disturbance evolution and there is energy structure mismatch behavior, but the overall operating state of the equipment is in the controllable coupling stability range. At this time, coupling deviation information is generated and the monitoring frequency is increased by 50%. If there is a deviation for three consecutive cycles, structural degradation information is generated immediately.

[0047] When the coupling imbalance superposition index CFS > the structural degradation risk threshold Cl, it indicates that there is a risk of degradation in the equipment disturbance evolution, structural mismatch behavior exists, and the coordination between mismatches is gradually increasing. At this time, coupling degradation information is generated, the cooling power is increased by 25%, the node load is limited to 70% of the rated power, the queued tasks are migrated to the adjacent stable node, and the relevant maintenance personnel are notified to conduct equipment inspection.

[0048] An intelligent monitoring system for the operating status of electrical equipment includes a data acquisition module, an event recognition module, a disturbance evolution module, a consistency verification module, and a coupling imbalance analysis module.

[0049] The data acquisition module is used to collect dynamic electrical data of electrical equipment in real time based on parameter acquisition devices deployed on the operating lines of electrical equipment, and to form electrical feature data groups after preprocessing and data analysis.

[0050] The event recognition module is used to calculate the power change rate. The power change rate within a continuous sampling period is judged point by point, and the trigger point t0 of the sudden change event is recorded when a sudden change occurs in the power output.

[0051] The disturbance evolution module is used to extract all instantaneous currents I with a time length of ΔT forward from the trigger point t0 of the sudden event to perform disturbance evolution analysis on the operating state of electrical equipment, and generate equipment disturbance assessment based on the analysis results;

[0052] The consistency verification module is used to perform consistency verification analysis on the operating energy of electrical equipment based on the electrical characteristic data group when the equipment disturbance assessment indicates that the equipment operation trend is abnormal.

[0053] The coupling imbalance analysis module is used to fit the disturbance evolution analysis results and the consistency verification analysis results, perform coupled evolution analysis on the abnormal disturbance trends and structural faults in the operation of electrical equipment, and generate a disturbance evolution assessment based on the analysis results.

[0054] This invention provides a method and system for intelligent monitoring of the operating status of electrical equipment. It has the following beneficial effects:

[0055] (1) This method uses dynamic electrical data acquisition with time resolution as the underlying input. It forms a complete perception of the continuous operation process of electrical equipment through three-phase voltage transformers and three-phase current transformers. It is supplemented by edge nodes to align the data with timestamps and fill in missing values, so that the acquired dynamic electrical data is consistent in terms of time structure and sequence continuity. The electrical feature data set constructed based on the processed instantaneous voltage U, instantaneous current I, power factor cosφ, and active power Py is equivalent to establishing a dynamic state space with real-time, continuous and process traceability for equipment operation, so that all subsequent disturbance detection, energy verification and coupling analysis have a reliable quantitative input source. On this data basis, the small trend changes that were originally masked by noise during equipment operation, the implicit time relationship between sequences, and the synchronicity between different electrical quantities can be accurately presented, forming a monitoring chassis that reflects the real operating behavior of electrical equipment.

[0056] (2) This method analyzes the time series of active power Py using the sliding difference method, identifies sudden changes during operation, and uses the trigger point t0 of the sudden event as the time anchor point. The ΔT window before the sudden event is regarded as the disturbance evolution interval. The continuous change information of the instantaneous current I sequence is extracted and the disturbance nonlinear evolution index DYN is calculated. This converts the time structure of the current before the disturbance, such as the micro-change mode, response speed, and sequence sudden change tendency, into a measurable nonlinear index. The index is then compared with the disturbance nonlinear evolution threshold Td to generate a device disturbance assessment. When the device disturbance assessment indicates that the device's operating trend is abnormal, a consistency check analysis based on the law of energy conservation is further initiated. By comparing the deviations between the instantaneous voltage U, instantaneous current I, and active power Py at the actual moment and the standard theoretical state, the energy coupling deviation index PHY is constructed, making the coupling deviation between the energy balance relationship, phase coordination relationship, and power output law within the electrical equipment clearly apparent. This process is equivalent to simultaneously incorporating two independent mechanisms, disturbance response and energy structure, into the analysis system, so that the operating state of the device can not only be detected but also interpreted as either a change in disturbance trend or a change in energy structure.

[0057] (3) This method fits the perturbation nonlinear evolution index DYN with the energy coupling deviation index PHY, and introduces tensor coupling and logarithmic transformation to construct the coupling imbalance superposition index CFS, so that the linkage between the perturbation trend and the energy structure change is integrated into the same scale in mathematical form. This index not only reveals the changing trend of the internal electromagnetic balance during the perturbation process, but also presents the manifestation of potential structural weaknesses in the perturbation amplification process. The coupling imbalance superposition index CFS sequence of all coupled stable states within half a year is extracted to construct the coupling stability threshold Cw and the structural degradation risk threshold Cl, forming a clear operation boundary between the three intervals of coupling stability, deviation, and degradation, and further triggering the corresponding monitoring strategy adjustment, cooling adjustment, load limitation, task migration and maintenance response, so that the equipment forms a closed-loop structure with predictive, judgment and adaptive adjustment capabilities during operation. Finally, it realizes the overall transition from single-point anomaly detection to perturbation behavior understanding, energy structure verification and structural risk evolution identification, so that compensation decisions and control actions have corresponding physical and trend basis, which helps to maintain the stability and controllability of equipment operation in the long term. Attached Figure Description

[0058] Figure 1 This is a schematic diagram illustrating the steps of an intelligent monitoring method for the operating status of electrical equipment according to the present invention;

[0059] Figure 2 This is a schematic diagram of the process of an intelligent monitoring system for the operating status of electrical equipment according to the present invention;

[0060] Figure 3This is a logic block diagram illustrating the implementation steps of an intelligent monitoring method for the operating status of electrical equipment according to the present invention. Detailed Implementation

[0061] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0062] Example 1, please refer to Figure 1 This invention provides an intelligent monitoring method for the operating status of electrical equipment. To achieve the above objectives, this invention employs the following technical solution, comprising the following steps:

[0063] S1. Based on the parameter acquisition devices deployed on the operating lines of electrical equipment, dynamic electrical data of electrical equipment is collected in real time, and after preprocessing and data analysis, it is combined into an electrical characteristic data group.

[0064] S2, By calculating the rate of power change The power change rate within a continuous sampling period is judged point by point, and the trigger point t0 of the sudden change event is recorded when a sudden change occurs in the power output.

[0065] S3. Taking the trigger point t0 of the sudden event as a reference, extract all instantaneous currents I with a time length of ΔT to perform disturbance evolution analysis on the operating state of electrical equipment, and generate equipment disturbance assessment based on the analysis results;

[0066] S4. When the equipment disturbance assessment indicates that the equipment operation trend is abnormal, perform a consistency verification analysis on the operating energy of the electrical equipment based on the electrical characteristic data group.

[0067] S5. Fit the disturbance evolution analysis results and the consistency verification analysis results to perform coupled evolution analysis on the abnormal disturbance trend and structural fault in the operation of electrical equipment, and generate a disturbance evolution assessment based on the analysis results.

[0068] In this embodiment, S1 constructs a complete dynamic electrical data acquisition system to form a continuous, synchronous, and traceable data foundation, solving the problem that traditional methods rely on single-point measurements and are difficult to capture operational details. Based on this, S2 utilizes the power change rate... Automatic identification of sudden behaviors is achieved by recording the trigger point t0 when a sudden change in power output occurs, thus automatically locating the sudden behavior during operation. S3 establishes an analytical entry point for continuous disturbance events using the time anchor point t0, extracting all instantaneous currents I over a time length ΔT, and performing disturbance evolution analysis on the operating state of electrical equipment within the time window ΔT. This quantifies the current change pattern of the equipment in the time period before the sudden change occurs as disturbance evolution characteristics, and generates an equipment disturbance assessment based on the analysis results, completing a structured expression of the operating trend. This method forms a coherent operational monitoring foundation from data acquisition, preprocessing, trend detection, and disturbance identification. S4, when the equipment disturbance assessment indicates an abnormal operating trend, performs a consistency check analysis on the operating energy of the electrical equipment based on the electrical characteristic data set, matching the actual energy relationship during operation with the theoretical standard state, revealing deviations within the energy conservation relationship, and solving the problem that existing monitoring methods cannot distinguish the difference between surface disturbances and energy structure changes. Furthermore, S5 fits the disturbance evolution analysis results with the consistency verification analysis results, performing coupled evolution analysis on abnormal disturbance trends and structural faults in electrical equipment operation. Based on the analysis results, it generates a disturbance evolution assessment, integrating previously isolated trend and energy information into a unified judgment system, making the source of anomalies interpretable. Compared to existing methods, this approach moves from single-measurement triggering to multi-indicator joint judgment, completing the structured analysis of complex disturbances. Building upon disturbance evolution analysis and energy consistency verification, this method constructs a coupled analysis system for abnormal trends and structural shifts, enabling not only real-time monitoring of equipment operating status but also interpretation of the type of shift, and the ability to distinguish between short-term disturbances, trend changes, and structural faults. The final generated disturbance evolution assessment is used to guide monitoring frequency adjustments, operation control strategy updates, and maintenance scheduling, enabling equipment to have adaptive response capabilities, reducing uncertainties during operation, and improving the controllability of the operation process.

[0069] Example 2, please refer to Figure 3 Specifically: S1 includes S11;

[0070] S11. After calling and initializing the parameter acquisition device deployed on the electrical equipment operating line, the dynamic electrical data of the electrical equipment is collected in real time.

[0071] The parameter acquisition device includes a three-phase voltage transformer and a three-phase current transformer;

[0072] The three-phase voltage transformer is used to connect to the AC voltage line of the input or output terminal of the electrical equipment to collect the instantaneous voltage U of the electrical equipment in real time.

[0073] The three-phase current transformer is used to be connected in series in the main circuit of the electrical equipment to collect the instantaneous current I of the electrical equipment in real time.

[0074] S1 further includes S12;

[0075] S12. Transmit the dynamic electrical data to the edge node for preprocessing, the preprocessing including timestamp alignment and filling missing values;

[0076] The timestamp alignment uses linear interpolation resampling technology to interpolate and predict missing time points in dynamic electrical data, and the missing value filling uses missing value interpolation technology to complete dynamic electrical data with sampling interruption and communication packet loss.

[0077] The preprocessed dynamic electrical data set is then subjected to data analysis, which includes power factor calculation and active power calculation.

[0078] The power factor calculation is based on the time structure of the voltage and current waveforms formed by the continuous sequence of instantaneous voltage U and instantaneous current I changing over time. The voltage and current waveforms are formed by the analog signal sampling module built into the MCU in the electrical equipment controller and A / D conversion is performed. The phase of the sampled voltage and current waveforms is compared, and the main frequency phase difference φ is extracted using digital phase-locked loop technology. The power factor cosφ is calculated based on the main frequency phase difference φ.

[0079] The active power calculation is based on the instantaneous voltage U, instantaneous current I, and power factor cosφ to calculate the active power Py of the electrical equipment, Py=U×I×cosφ;

[0080] Instantaneous voltage U, instantaneous current I, power factor cosφ, and active power Py together form the electrical characteristic data set.

[0081] In this embodiment, by calling and initializing the three-phase voltage transformers and three-phase current transformers deployed on the operating lines of electrical equipment, the equipment can acquire instantaneous voltage U and instantaneous current I in real time, forming a continuous measurement of the dynamic electrical data of the electrical equipment. The acquired dynamic electrical data is transmitted to the edge node, and the time sequence structure is uniformly calibrated by timestamp alignment and filling missing values, so that the dynamic electrical data remains stable in terms of continuity, authenticity, and resolvability. The preprocessed voltage and current sequences are used to construct voltage and current waveforms, and the phase difference φ is extracted by the analog signal sampling module built into the MCU in the electrical equipment controller. Then, the power factor cosφ is obtained by combining digital phase-locked loop technology. Subsequently, the active power Py is calculated based on the instantaneous voltage U, instantaneous current I, and power factor cosφ. The final electrical feature data set provides a unified and quantitative data foundation for subsequent disturbance analysis, energy verification, and coupling determination. Through the above steps, this implementation method realizes the extraction of structured information on the operating status of electrical equipment, enabling the monitoring object to shift from observing a single electrical quantity to a comprehensive expression with waveform structure, phase relationship and energy attributes. This lays a reliable data foundation for identifying abnormal trends, judging operating behavior and building coupled evolution models, and enables the overall monitoring process to remain stable, sensitive and interpretable in a continuous operating environment.

[0082] Example 3, please refer to Figure 3 Specifically: S2 includes S21 and S22;

[0083] S21. Calculate the rate of change of active power Py using the moving difference method to form an active power sequence that varies with time. Where Py(t) represents the active power at time t, and dt represents the sign of the time variable;

[0084] S22. Set a disturbance judgment threshold TP based on the allowable power fluctuation under standard conditions, and the power change rate. By comparing the results, the rate of power change within the continuous sampling period is judged point by point. When this time, it indicates that the current power output is normal; continue normal monitoring. When the current power output suddenly changes, it indicates that the current power fluctuation is identified as a power mutation event, and the current time point t0 is recorded as the trigger point of the mutation event.

[0085] In this embodiment, the sliding difference method is applied to the active power sequence in S21 to calculate the rate of power change. And in S22, the power change rate By comparing the data point-by-point with the disturbance judgment threshold TP set according to standard operating conditions, this step establishes a dynamic judgment mechanism capable of identifying abnormal power jumps in real time under continuous sampling rhythm. When the rate of power change exceeds the threshold, the current moment is immediately marked as the trigger point t0 of the sudden event, enabling subsequent disturbance evolution analysis to proceed with precise time anchors. This implementation transforms the traditional averaged trend judgment of power changes into an instantaneous identification mode based on time-series structure, providing clear triggering criteria when rapid disturbances occur during operation, improving the observability of transient changes, and establishing clear, accurate, and physically meaningful starting reference points for subsequent disturbance evolution analysis, consistency verification, and coupled evolution processing. Overall, this enhances the entire monitoring system's ability to capture and analyze sudden operational behaviors.

[0086] Example 4, please refer to Figure 3 Specifically: S3 includes S31;

[0087] S31. Taking the trigger point t0 of the sudden event as a reference, extract all instantaneous currents I over a time period of ΔT, perform disturbance evolution analysis on the operating state of electrical equipment within the time window ΔT, and calculate the disturbance nonlinear evolution index DYN to reflect the continuous nonlinear disturbance intensity of the current sequence before the sudden event on the time scale, as follows:

[0088] ;

[0089] Among them, I avg dt represents the average current, ΔT represents the backtracking time window length, t0 represents the trigger point of the sudden event, I(t) represents the instantaneous current at time t, and dt represents the sign of the time variable.

[0090] S3 further includes S32;

[0091] S32. Extract the perturbation nonlinear evolution index DYN sequence of the normal segment before mutation within half a year, calculate the median value through a sorting algorithm, and multiply it with the deviation tolerance constant k to construct the perturbation nonlinear evolution threshold Td. Compare the perturbation nonlinear evolution threshold Td with the obtained perturbation nonlinear evolution index DYN, and generate equipment perturbation assessment based on the comparison results. The deviation tolerance constant k takes the value of [1.5, 2.5].

[0092] The equipment disturbance assessment is as follows;

[0093] When the disturbance nonlinear evolution exponent DYN < the disturbance nonlinear evolution threshold Td, it indicates that the equipment operation trend is stable and the disturbance can be absorbed by the equipment itself. At this time, the current time period is marked as a stable operation period, and the standard sampling frequency is maintained.

[0094] When the disturbance nonlinear evolution index DYN is greater than or equal to the disturbance nonlinear evolution threshold Td, it indicates that the equipment operation trend is abnormal. At this time, the current time period is marked as the disturbance critical segment, and the consistency verification analysis is activated.

[0095] In this embodiment, S31 uses the power mutation trigger point t0 as the time reference, extracts all instantaneous currents I(t) by backtracking the time window ΔT, and calculates the perturbation nonlinear evolution index DYN based on the change law of instantaneous currents I(t) on the continuous time scale, so that the hidden perturbation characteristics of the current sequence before the mutation is formed are quantified. The time acceleration of the current sequence corresponds to the inertial response of electromagnetic quantities, the second-order effect caused by inductance and capacitance during load abrupt changes, and the higher-order changes caused by discrete control. Therefore, the second derivative represents the sensitive signal of the device's "disturbance resistance capability". The square operation comes from the mathematical energy norm, avoiding the cancellation of positive and negative values, so that all changes are accumulated in the same direction of measurement. The corresponding engineering meaning is that rapid changes in any direction will increase the current disturbance excitation energy. Equivalent to the form of "energy integral" in circuit theory, it reflects the accumulation of disturbances within the entire window. The integral represents the accumulated disturbance amount in the time dimension, and dividing by ΔT represents the average disturbance energy density. The overall square root converts the energy measure into an "amplitude measure", which is close to the root mean square (RMS) structure in form, making it easy to make comparable matching with other indices. As a normalization factor, the disturbance intensity is scaled to match the equipment's reference current, avoiding misinterpreting normal minor disturbances in high-current systems as anomalies. S32 sorts and statistically analyzes the disturbance nonlinear evolution index DYN sequence under normal operating conditions over a six-month period, obtaining its median value and combining it with the deviation tolerance constant k to construct the disturbance nonlinear evolution threshold Td. This allows the equipment to form an adaptive disturbance baseline based on its own safety level. By comparing the real-time disturbance nonlinear evolution index DYN with the disturbance nonlinear evolution threshold Td, it distinguishes between trend-stable states and disturbance critical states, enabling early identification of operational trend changes and automatically triggering consistency verification analysis when anomalies occur. This process transitions disturbance detection from "passive discovery of sudden changes" to "active identification of the evolutionary process before sudden changes," enhancing the precision of operational trend judgment and enabling the equipment to detect potential deviations in advance. This helps to discover the formation mechanism of operational fluctuations at an earlier stage, improving the accuracy of subsequent energy verification and coupled evolution analysis, while reducing operational risks caused by sudden events, making the overall monitoring process more coherent and controllable.

[0096] Example 5, please refer to Figure 3 Specifically: S4 includes S41;

[0097] S41. When equipment disturbance is assessed as an abnormal equipment operating trend, a consistency check analysis is performed on the operating energy of the electrical equipment based on the electrical characteristic data set, and the energy coupling deviation index PHY is calculated to reflect the degree to which the operating energy of the equipment satisfies the law of energy conservation. The impact of disturbance on the equipment operating law is analyzed, as follows:

[0098] ;

[0099] Where N represents the number of sampling time points within the time window ΔT, Py i U i and I i U represents the active power, instantaneous voltage, and instantaneous current at the i-th sampling point, respectively. bz，i I bz，i and φ bz，i Represents the theoretical instantaneous voltage, instantaneous current, and phase difference at the i-th sampling point under standard conditions, where cos represents the cosine function, and cosφ bz，i Let be the theoretical power factor of the i-th sampling point under standard conditions.

[0100] In this embodiment, when the equipment disturbance assessment indicates an abnormal equipment operating trend, the real-time active power Py, instantaneous voltage, and instantaneous current within the time window ΔT are compared point-by-point with their corresponding values ​​under standard theoretical conditions by calling the electrical characteristic data group. This constructs the energy coupling deviation index PHY, allowing for the quantification of the degree of deviation in the actual operating energy relationship in terms of instantaneous phasor, amplitude changes, and power composition. This formula... The standard active power calculation formula, together constituting theoretical power, provides a reference for "what the ideal energy mode of the system should be," numerator... When electrical equipment is subjected to disturbance, the numerator deviation will increase, and the denominator will decrease. This represents the instantaneous energy level of electrical equipment under real-world conditions. A larger denominator indicates a higher energy level. The absolute value is used to represent the strength of the deviation, not the direction of the deviation. The mean operator is also used. This verification process reflects the overall energy deviation behavior within a time window ΔT, ensuring statistical stability of the results. It not only reveals whether energy transfer within the equipment still follows the established energy conservation law after a disturbance, but also demonstrates the coordinated changes in the energy structure from multiple perspectives, including phase difference, power factor shift, and voltage-current relationship. Through this mechanism, the system can identify potential energy structure mismatch trends in the early stages of anomalies, providing clear deviation evidence for subsequent coupled evolution analysis. This allows the judgment of equipment operating status to not only rely on the disturbance itself but also to have the ability to explain the energy structure level. This verification method expands equipment operation analysis from a single time-series disturbance identification to a comprehensive judgment framework that includes the consistency of energy relationships, significantly enhancing the accuracy of operating status assessment and the reliability of trend judgment. This provides a more solid basis for subsequent dynamic control, risk mitigation, and operational strategy generation.

[0101] Example 6, please refer to Figure 3 Specifically: S5 includes S51;

[0102] S51. The disturbance nonlinear evolution index DYN is fitted with the energy coupling deviation index PHY to perform coupled evolution analysis on the abnormal disturbance trend and structural faults in the operation of electrical equipment, and the coupling imbalance superposition index CFS is calculated to represent the degree of structural vulnerability of the equipment and reflect the overall structural vulnerability of the equipment, as follows:

[0103] ;

[0104] Where ln represents the logarithmic function, The symbol for tensor multiplication in mathematics is DYN. PHY represents the coupling strength between the perturbation nonlinear evolution index and the coupled energy coupling deviation index, reflecting the severity of structural misalignment of the equipment under perturbation. ∇PHY represents the trend of the energy coupling deviation index.

[0105] S5 also includes S52;

[0106] S52. Extract the coupling imbalance superposition index (CFS) sequence of all coupled stable states within six months, and calculate the 75th percentile value using the percentile method as the coupling stability threshold Cw. Extract the maximum value as the structural degradation risk threshold Cl, and then compare it with the obtained coupling imbalance superposition index CFS. Based on the comparison results, generate a coupling evolution assessment. The disturbance evolution assessment is as follows.

[0107] When the coupling imbalance superposition index CFS < coupling stability threshold Cw, it indicates that the electrical structure of the equipment is stable and there is no energy structure mismatch behavior. At this time, the current state is marked as acceptable disturbance and normal monitoring is maintained.

[0108] When the coupling stability threshold Cw ≤ coupling imbalance superposition index CFS ≤ structural degradation risk threshold Cl, it indicates that there is a deviation in the equipment disturbance evolution and there is energy structure mismatch behavior, but the overall operating state of the equipment is in the controllable coupling stability range. At this time, coupling deviation information is generated and the monitoring frequency is increased by 50%. If there is a deviation for three consecutive cycles, structural degradation information is generated immediately.

[0109] When the coupling imbalance superposition index CFS > the structural degradation risk threshold Cl, it indicates that there is a risk of degradation in the equipment disturbance evolution, structural mismatch behavior exists, and the coordination between mismatches is gradually increasing. At this time, coupling degradation information is generated, the cooling power is increased by 25%, the node load is limited to 70% of the rated power, the queued tasks are migrated to the adjacent stable node, and the relevant maintenance personnel are notified to conduct equipment inspection.

[0110] In this embodiment, S51 fits the perturbation nonlinear evolution index DYN with the energy coupling deviation index PHY, and constructs the coupling imbalance superposition index CFS through tensor coupling and logarithmic transformation, so that the perturbation trend and energy structure change are expressed on a unified scale, and the structural shift and vulnerability of the equipment under the perturbation are plotted accordingly. In this formula, DYN... PHY represents the cross-coupling tensor term, reflecting the combined driving effect of disturbance behavior on energy offset. Whether the two types of offsets reinforce each other is a core indicator of structural weakening. ∇PHY represents the exponential trend of energy coupling deviation. Whether the energy offset accelerates is a key manifestation of the gradual fault progression process. The essence of structural risk in electrical equipment is determined by: Risk = Size of offset + Whether the offset continues to increase. If only the coupling offset is available, it is impossible to distinguish between them; therefore, they must be added together (DYN). The combination of PHY and ∇PHY forms a complete characterization of the overall structural fragility. A logarithmic function ln is used to compress large-scale coupling quantities, resulting in a state index that can be used for grading. S52 extracts the coupling imbalance superposition index (CFS) sequence for all coupled stable states within six months, and sets the coupling stability threshold Cw and structural degradation risk threshold Cl using the percentile method. This allows the operating state to be automatically identified within three intervals: stable, offset, and deteriorated. Based on the identification results, different levels of monitoring strategies, cooling adjustments, load limits, and task migration measures are triggered, creating a linked response from state judgment to operational control. The purpose of this implementation is to reveal the structural changes behind the disturbance process through the joint calculation of coupling characteristics, enabling early identification and grading of equipment operating risks, preventing the disturbance from spreading undetected. Simultaneously, through threshold-driven dynamic control, the monitoring rhythm, heat dissipation capacity, and load arrangement can be automatically adjusted according to the state, forming an adaptive monitoring and protection system. This makes the operating state judgment more precise, the control logic more aligned with the equipment's behavior patterns, and promotes the overall operation process towards a more controllable, robust, and forward-looking direction.

[0111] Example 7, please refer to Figure 2 An intelligent monitoring system for the operating status of electrical equipment includes a data acquisition module, an event recognition module, a disturbance evolution module, a consistency verification module, and a coupling imbalance analysis module.

[0112] The data acquisition module is used to collect dynamic electrical data of electrical equipment in real time based on parameter acquisition devices deployed on the operating lines of electrical equipment, and to form electrical feature data groups after preprocessing and data analysis.

[0113] The event recognition module is used to calculate the power change rate. The power change rate within a continuous sampling period is judged point by point, and the trigger point t0 of the sudden change event is recorded when a sudden change occurs in the power output.

[0114] The disturbance evolution module is used to extract all instantaneous currents I with a time length of ΔT forward from the trigger point t0 of the sudden event to perform disturbance evolution analysis on the operating state of electrical equipment, and generate equipment disturbance assessment based on the analysis results;

[0115] The consistency verification module is used to perform consistency verification analysis on the operating energy of electrical equipment based on the electrical characteristic data group when the equipment disturbance assessment indicates that the equipment operation trend is abnormal.

[0116] The coupling imbalance analysis module is used to fit the disturbance evolution analysis results and the consistency verification analysis results, perform coupled evolution analysis on the abnormal disturbance trends and structural faults in the operation of electrical equipment, and generate a disturbance evolution assessment based on the analysis results.

[0117] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended technical solutions and their equivalents.

Claims

1. A method for intelligent monitoring of the operating status of electrical equipment, characterized in that: Includes the following steps: S1. Based on the parameter acquisition devices deployed on the operating lines of electrical equipment, dynamic electrical data of electrical equipment is collected in real time, and after preprocessing and data analysis, it is combined into an electrical characteristic data group. S2, By calculating the rate of power change The power change rate within a continuous sampling period is judged point by point, and the trigger point t0 of the sudden change event is recorded when a sudden change occurs in the power output: S3. Taking the trigger point t0 of the sudden event as a reference, extract all instantaneous currents I over a time period ΔT to perform disturbance evolution analysis on the operating state of the electrical equipment, and calculate the disturbance nonlinear evolution index DYN. Based on the disturbance nonlinear evolution index DYN, evaluate the equipment disturbance, as follows: ； Among them, I avg dt represents the average current, ΔT represents the length of the backtracking time window, t0 represents the trigger point of the sudden event, I(t) represents the instantaneous current at time t, and dt represents the sign of the time variable. S4. When the equipment disturbance assessment indicates an abnormal equipment operating trend, a consistency check analysis is performed on the operating energy of the electrical equipment based on the electrical characteristic data group, and the energy coupling deviation index PHY is calculated, as follows: ； Where N represents the number of sampling time points within the time window ΔT, Py i U i and I i U represents the active power, instantaneous voltage, and instantaneous current at the i-th sampling point, respectively. bz，i I bz，i and φ bz，i Represents the theoretical instantaneous voltage, instantaneous current, and phase difference at the i-th sampling point under standard conditions, where cos represents the cosine function, and cosφ bz，i The theoretical power factor of the i-th sampling point under standard conditions; S5. Fit the disturbance evolution analysis results with the consistency verification analysis results, perform coupled evolution analysis on the abnormal disturbance trends and structural faults in the operation of electrical equipment, calculate the coupling imbalance superposition index CFS, and evaluate the disturbance evolution based on the coupling imbalance superposition index CFS, as follows: ； Where ln represents the logarithmic function, The symbol for tensor multiplication in mathematics is DYN. PHY represents the coupling strength between the perturbation nonlinear evolution index and the coupling energy coupling deviation index, and ∇PHY represents the trend of the energy coupling deviation index.

2. The intelligent monitoring method for the operating status of electrical equipment according to claim 1, characterized in that: S1 includes S11; S11. After calling and initializing the parameter acquisition device deployed on the electrical equipment operating line, the dynamic electrical data of the electrical equipment is collected in real time. The parameter acquisition device includes a three-phase voltage transformer and a three-phase current transformer; The three-phase voltage transformer is used to connect to the AC voltage line of the input or output terminal of the electrical equipment to collect the instantaneous voltage U of the electrical equipment in real time. The three-phase current transformer is used to be connected in series in the main circuit of the electrical equipment to collect the instantaneous current I of the electrical equipment in real time.

3. The intelligent monitoring method for the operating status of electrical equipment according to claim 2, characterized in that: S1 further includes S12; S12. Transmit the dynamic electrical data to the edge node for preprocessing, the preprocessing including timestamp alignment and filling missing values; The timestamp alignment uses linear interpolation resampling technology to interpolate and predict missing time points in dynamic electrical data, and the missing value filling uses missing value interpolation technology to complete dynamic electrical data with sampling interruption and communication packet loss. The preprocessed dynamic electrical data set is then subjected to data analysis, which includes power factor calculation and active power calculation. The power factor calculation is based on the time structure of the voltage and current waveforms formed by the continuous sequence of instantaneous voltage U and instantaneous current I changing over time. The voltage and current waveforms are formed by the analog signal sampling module built into the MCU in the electrical equipment controller and A / D conversion is performed. The phase of the sampled voltage and current waveforms is compared, and the main frequency phase difference φ is extracted using digital phase-locked loop technology. The power factor cosφ is calculated based on the main frequency phase difference φ. The active power calculation is based on the instantaneous voltage U, instantaneous current I, and power factor cosφ to calculate the active power Py of the electrical equipment, Py=U×I×cosφ; Instantaneous voltage U, instantaneous current I, power factor cosφ, and active power Py together form the electrical characteristic data set.

4. The intelligent monitoring method for the operating status of electrical equipment according to claim 3, characterized in that: S2 includes S21 and S22; S21. Calculate the rate of change of active power Py using the moving difference method to form an active power sequence that varies with time. Where Py(t) represents the active power at time t, and dt represents the sign of the time variable; S22. Set a disturbance judgment threshold TP based on the allowable power fluctuation under standard conditions, and the power change rate. By comparing the results, the rate of power change within the continuous sampling period is judged point by point. When this time, it indicates that the current power output is normal; continue normal monitoring. When the current power output suddenly changes, it indicates that the current power fluctuation is identified as a power mutation event, and the current time point t0 is recorded as the trigger point of the mutation event.

5. The intelligent monitoring method for the operating status of electrical equipment according to claim 4, characterized in that: S3 includes S31; S31. Taking the trigger point t0 of the mutation event as a reference, extract all instantaneous currents I with a time length of ΔT, perform disturbance evolution analysis on the operating state of electrical equipment within the time window ΔT, and calculate the disturbance nonlinear evolution index DYN to reflect the continuous nonlinear disturbance intensity of the current sequence before the mutation point on the time scale.

6. The intelligent monitoring method for the operating status of electrical equipment according to claim 5, characterized in that: S3 further includes S32; S32. Extract the perturbation nonlinear evolution index DYN sequence of the normal segment before mutation within half a year, calculate the median value through a sorting algorithm, and multiply it with the deviation tolerance constant k to construct the perturbation nonlinear evolution threshold Td. Compare the perturbation nonlinear evolution threshold Td with the obtained perturbation nonlinear evolution index DYN, and generate equipment perturbation assessment based on the comparison results. The deviation tolerance constant k takes the value of [1.5, 2.5]. The equipment disturbance assessment is as follows; When the disturbance nonlinear evolution index DYN < the disturbance nonlinear evolution threshold Td, it indicates that the equipment operation trend is stable. At this time, the current time period is marked as a stable operation period, and the standard sampling frequency is maintained. When the disturbance nonlinear evolution index DYN is greater than or equal to the disturbance nonlinear evolution threshold Td, it indicates that the equipment operation trend is abnormal. At this time, the current time period is marked as the disturbance critical segment, and the consistency verification analysis is activated.

7. The intelligent monitoring method for the operating status of electrical equipment according to claim 6, characterized in that: S4 includes S41; S41. When the equipment disturbance assessment indicates an abnormal equipment operation trend, perform a consistency check analysis on the operating energy of the electrical equipment based on the electrical characteristic data group, and calculate the energy coupling deviation index PHY to reflect the satisfaction of the energy conservation law between the operating energies of the equipment, and analyze the impact of the disturbance on the equipment operation law.

8. The intelligent monitoring method for the operating status of electrical equipment according to claim 7, characterized in that: S5 includes S51; S51. The disturbance nonlinear evolution index DYN is fitted with the energy coupling deviation index PHY to perform coupling evolution analysis on the abnormal disturbance trend and structural faults in the operation of electrical equipment, and the coupling imbalance superposition index CFS is calculated to indicate the degree of structural fragility of the equipment and reflect the overall structural fragility of the equipment.

9. The intelligent monitoring method for the operating status of electrical equipment according to claim 8, characterized in that: S5 also includes S52; S52. Extract the coupling imbalance superposition index (CFS) sequence of all coupled stable states within six months, and calculate the 75th percentile value using the percentile method as the coupling stability threshold Cw. Extract the maximum value as the structural degradation risk threshold Cl, and then compare it with the obtained coupling imbalance superposition index CFS. Based on the comparison results, generate a coupling evolution assessment. The disturbance evolution assessment is as follows. When the coupling imbalance superposition index CFS < coupling stability threshold Cw, it indicates that the electrical structure of the equipment is stable and there is no energy structure mismatch behavior. At this time, the current state is marked as acceptable disturbance and normal monitoring is maintained. When the coupling stability threshold Cw ≤ coupling imbalance superposition index CFS ≤ structural degradation risk threshold Cl, it indicates that there is a deviation in the equipment disturbance evolution and there is energy structure mismatch behavior, but the overall operating state of the equipment is in the controllable coupling stability range. At this time, coupling deviation information is generated and the monitoring frequency is increased by 50%. If there is a deviation for three consecutive cycles, structural degradation information is generated immediately. When the coupling imbalance superposition index CFS > the structural degradation risk threshold Cl, it indicates that there is a risk of degradation in the equipment disturbance evolution, structural mismatch behavior exists, and the coordination between mismatches is gradually increasing. At this time, coupling degradation information is generated, the cooling power is increased by 25%, the node load is limited to 70% of the rated power, the queued tasks are migrated to the adjacent stable node, and the relevant maintenance personnel are notified to conduct equipment inspection.

10. An intelligent monitoring system for the operating status of electrical equipment, applied to the intelligent monitoring method for the operating status of electrical equipment as described in any one of claims 1-9, characterized in that: It includes a data acquisition module, an event identification module, a disturbance evolution module, a consistency verification module, and a coupling imbalance analysis module; The data acquisition module is used to collect dynamic electrical data of electrical equipment in real time based on parameter acquisition devices deployed on the operating lines of electrical equipment, and to form electrical feature data groups after preprocessing and data analysis. The event recognition module is used to calculate the power change rate. The power change rate within a continuous sampling period is judged point by point, and the trigger point t0 of the sudden change event is recorded when a sudden change occurs in the power output. The disturbance evolution module is used to extract all instantaneous currents I with a time length of ΔT forward from the trigger point t0 of the sudden event to perform disturbance evolution analysis on the operating state of electrical equipment, and generate equipment disturbance assessment based on the analysis results; The consistency verification module is used to perform consistency verification analysis on the operating energy of electrical equipment based on the electrical characteristic data group when the equipment disturbance assessment indicates that the equipment operation trend is abnormal. The coupling imbalance analysis module is used to fit the disturbance evolution analysis results and the consistency verification analysis results, perform coupled evolution analysis on the abnormal disturbance trends and structural faults in the operation of electrical equipment, and generate a disturbance evolution assessment based on the analysis results.

Images