Electrical equipment operation data monitoring management system and method

Abstract

The invention discloses an electrical equipment operation data monitoring management system and method, and relates to the technical field of electrical equipment management. According to the electrical equipment operation data monitoring management method, operation state time sequence data of electrical equipment is obtained based on a set time period, and an operation time sequence change index and an operation time sequence characteristic index of the electrical equipment are analyzed; and performing evaluation analysis on the operation time sequence change index and the operation time sequence characteristic index of the electrical equipment to obtain an operation health evaluation index of the electrical equipment, and taking a preset management measure. The change rate is calculated based on the difference between the operation value and the parameter value, the operation time sequence change index of the electrical equipment is obtained, when the equipment is in the early stage of degradation, the parameters of the equipment possibly do not exceed the alarm threshold value, but the change trend is abnormal, and the hidden risk can be recognized in advance by incorporating the trend information into an evaluation system.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical equipment management, and in particular to an electrical equipment operation data monitoring and management system and method. Background Art

[0002] In the field of power systems and industrial automation, electrical equipment is the core operating unit, and the safety and stability of its operating status are directly related to the reliable operation of the entire system. With the expansion of equipment scale and the diversification of application scenarios, traditional regular inspections or post-fault maintenance modes can no longer meet the high reliability and high continuity operation requirements. In order to achieve real-time understanding of the status of electrical equipment and pre-identification of potential fault hazards, more and more systems are beginning to introduce data-driven monitoring and management methods.

[0003] At present, electrical equipment monitoring methods based on operating parameter data for status judgment have been widely used. Related technologies usually monitor and issue early warnings on the operating status of equipment by collecting basic electrical parameters such as current, voltage, and temperature, combined with rule thresholds, statistical analysis, or trend recognition models. In addition, some systems further integrate multi-source information such as environmental data, vibration information, and power characteristics in an effort to improve the comprehensiveness and accuracy of monitoring.

[0004] Prior art, such as the invention patent application with publication number CN115047813B, discloses an electrical equipment operating data monitoring and management system and method, comprising the following steps: grouping electrical equipment, collecting operating data from each group of electrical equipment, calculating measured values ​​for each group of electrical equipment, establishing thresholds for operating data, and monitoring and managing each group of electrical equipment based on the measured values ​​and the thresholds for operating data. Compared to the prior art that uses PLCs or single-chip microcomputers to control multiple motors in a single location or at the same site, this system enables unified monitoring and management of multiple motors at multiple sites, eliminating the need for staff to conduct round-trip inspections at multiple sites. This not only improves monitoring and management efficiency, but also enables timely detection of motor anomalies at each site and prompt maintenance of any abnormal motors.

[0005] Existing technology, such as the invention patent application with publication number CN119862384A, discloses an electrical equipment operation data monitoring and management system and method. The system includes a data monitoring unit, a scheme design unit, a fault maintenance unit and an optimization processing unit. By collecting the operation data of the electrical equipment, monitoring and analyzing the power resource configuration efficiency and the power equipment operation status, the failure risk degree of the power equipment is predicted and evaluated, and an electrical equipment maintenance plan is generated to perform advance maintenance on the failure risk of the electrical equipment, thereby curbing the failure risk in advance; then, by optimizing the maintenance of the power equipment and comparing and analyzing the maintenance efficiency of the power equipment, the electrical equipment maintenance plan is optimized and upgraded, and by determining the failure risk factors of the power equipment and performing targeted optimization maintenance, the work efficiency of the power equipment maintenance is improved, the stability of the power resource configuration is guaranteed, and the effective configuration of power resources and equipment maintenance is achieved.

[0006] Based on the above solution, it is found that the limitations of existing technologies include at least the following problems. Existing technologies, in electrical equipment operating data monitoring methods, only use single-point data or static statistics for status judgment and lack the ability to structurally model the temporal trends of operating parameters. In actual applications, equipment operating status often manifests as slowly rising temperature changes, low-amplitude but frequent current fluctuations, or increased high-frequency disturbances in the voltage signal before obvious abnormalities occur. These trend changes are usually not accompanied by significant instantaneous over-limit behavior, making them difficult to identify by traditional monitoring models based on average, maximum, or threshold comparisons. Furthermore, although existing technologies collect multiple parameters, they are generally processed as independent monitoring channels, lacking a structural analysis mechanism for the interrelationships and synchronous changes between parameters. As a result, when multiple parameters are individually within the normal range, but their combined changes reflect potential risk trends, the system is unable to respond effectively. Due to the lack of trend modeling and cross-parameter structural identification capabilities for equipment operating data in the temporal dimension, existing technologies cannot achieve continuous understanding and forward-looking judgment of operating status, limiting the ability to timely perceive potential risks and manage them in a hierarchical manner, and is not conducive to supporting data-driven high-reliability predictive maintenance strategies. Summary of the Invention

[0007] In response to the shortcomings of the existing technology, the present invention provides an electrical equipment operation data monitoring and management system and method, which solves the problem in the existing technology that there is a lack of structured modeling and joint evaluation of the time-varying trends of the operating status of electrical equipment, which makes it difficult to accurately identify potential abnormal evolution processes.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for monitoring and managing electrical equipment operation data, comprising the following steps: based on a set time period, obtaining the operation status time series data of the electrical equipment; performing a comprehensive analysis on the operation status time series data of the electrical equipment to obtain the operation timing change set of the electrical equipment, and analyzing the operation timing change index of the electrical equipment; inputting the operation status time series data of the electrical equipment into a pre-trained feature extraction model for feature analysis to obtain the operation timing feature set of the electrical equipment, and analyzing the operation timing feature index of the electrical equipment; evaluating and analyzing the operation timing change index and the operation timing feature index of the electrical equipment to obtain the operation health assessment index of the electrical equipment; and taking preset management measures based on the operation health assessment index of the electrical equipment.

[0009] Furthermore, the operating status timing data includes operating current values, operating voltage values, operating temperature values, power factor values, surface charge density values, operating vibration spectra and electromagnetic interference intensity values ​​within a set area at several time points, and the operating timing change set includes operating current timing change values, operating voltage timing change values, operating temperature timing change values, power factor timing change values, surface charge density timing change values, operating vibration spectrum timing change values ​​and electromagnetic interference intensity timing change values ​​within a set area.

[0010] Furthermore, the specific steps of analyzing the operation sequence variation index of the electrical equipment are as follows: obtaining operation state parameter data of the electrical equipment, wherein the operation state parameter data includes an operation current parameter value, an operation voltage parameter value, an operation temperature parameter value, a power factor parameter value, a surface charge density parameter value, a main frequency peak amplitude parameter value, and an electromagnetic interference intensity parameter value within a set area; The operating status time series data of the electrical equipment is read, and a comprehensive analysis is performed on the operating status parameter data of the electrical equipment to obtain the operating status time series change data of the electrical equipment, wherein the operating status time series change data includes the operating current change value, operating voltage change value, operating temperature change value, power factor change value, surface charge density change value, operating vibration spectrum change value and electromagnetic interference intensity change value within a set area at several time points; the operating status time series change data of the electrical equipment is comprehensively analyzed to obtain the operating time series change set of the electrical equipment, and the operating time series change index of the electrical equipment is analyzed.

[0011] Furthermore, the specific formula for calculating the operating sequence variation index of electrical equipment is as follows: ;in, is the operating sequence variation index of electrical equipment, is the time series change value of the operating temperature of the electrical equipment, is the temperature fluctuation response coefficient stored in the database, It is the time series variation value of the electromagnetic interference intensity within the set area of ​​the electrical equipment. is the electromagnetic disturbance sensitivity coefficient stored in the database, is the time series variation value of the operating vibration spectrum of the electrical equipment, is the time series variation of the surface charge density of the electrical equipment, is the time series change value of the power factor of the electrical equipment, is the time series change value of the operating current of the electrical equipment, It is the timing change value of the operating voltage of the electrical equipment.

[0012] Furthermore, the feature extraction model is specifically a deep timing feature extraction network, including a multi-channel input layer, a convolution extraction layer, a gated feature filtering layer, an embedding mapping layer, and an output layer. The runtime timing feature set includes load fluctuation factor, voltage zero-crossing frequency, heating trend slope, power factor disturbance amplitude, electrostatic density peak ratio, main frequency change rate, and interference bandwidth factor within a set area.

[0013] Furthermore, the specific steps of analyzing the operating sequence feature set of the electrical equipment are as follows: in the multi-channel input layer of the deep temporal feature extraction network, the operating status time series data of the electrical equipment is received and preprocessed to generate a standardized multi-channel input tensor; in the convolution extraction layer of the deep temporal feature extraction network, one-dimensional convolution processing is performed on the preprocessed multi-channel input tensor respectively to extract the trend pattern and local change pattern of each parameter in the time dimension, and obtain the local structure feature mapping sequence of each operating parameter; in the gated feature filtering layer of the deep temporal feature extraction network, the local structure feature mapping sequence of each operating parameter is significantly evaluated based on the attention mechanism or the gating function. Screening is performed to obtain a set of effective time series feature segments for each operating parameter; in the embedding mapping layer of the deep time series feature extraction network, the set of effective time series feature segments for each operating parameter is respectively input into the feature compression unit, and the feature representative value is extracted through the structural mapping function to obtain the load fluctuation factor of the operating current of the electrical equipment, the zero-crossing frequency of the operating voltage, the slope of the heating trend of the operating temperature, the disturbance amplitude of the power factor, the electrostatic peak ratio of the surface charge density, the main frequency change rate of the operating vibration spectrum, and the interference bandwidth factor of the electromagnetic interference intensity, thereby forming the operating time series feature set of the electrical equipment; in the output layer of the deep time series feature extraction network, the operating time series feature set of the electrical equipment is uniformly encoded and output.

[0014] Furthermore, the specific formula for calculating the operating sequence characteristic index of electrical equipment is as follows: ;in, is the operating sequence characteristic index of the electrical equipment, is the temperature increase trend slope of electrical equipment, is the temperature rise trend response coefficient stored in the database, is the interference bandwidth factor within the set area of ​​the electrical equipment, is the rate of change of the main frequency of the electrical equipment, is a natural constant, is the load fluctuation factor of the electrical equipment, is the voltage zero-crossing frequency of the electrical equipment, is the power factor disturbance amplitude of the electrical equipment, is the peak value ratio of electrostatic density of electrical equipment, is the power electrostatic difference adjustment coefficient stored in the database.

[0015] Furthermore, the specific steps for obtaining the operation health assessment index of the electrical equipment are as follows: obtaining the low-risk threshold value and the high-risk threshold value of the operation timing change of the electrical equipment; inputting the operation timing change index, the low-risk threshold value, the high-risk threshold value and the operation timing characteristic index of the electrical equipment into the health analysis model for evaluation and analysis to obtain the operation health assessment index of the electrical equipment.

[0016] Furthermore, based on the operational health assessment index of the electrical equipment, the specific steps for taking preset management measures are as follows: the operational health assessment index of the electrical equipment is judged and analyzed with several preset health assessment intervals, and each health assessment interval corresponds to a health risk level; based on the health risk level corresponding to the preset health assessment interval where the operational health assessment index of the electrical equipment is, preset management measures are taken for the electrical equipment.

[0017] An electrical equipment operation data monitoring and management system includes: a time series data acquisition unit, which acquires the operation status time series data of the electrical equipment based on a set time period; a time series change analysis unit, which performs a comprehensive analysis on the operation status time series data of the electrical equipment to obtain the operation time series change set of the electrical equipment, and analyzes the operation time series change index of the electrical equipment; a time series feature analysis unit, which inputs the operation status time series data of the electrical equipment into a pre-trained feature extraction model for feature analysis to obtain the operation time series feature set of the electrical equipment, and analyzes the operation time series feature index of the electrical equipment; a health assessment analysis unit, which evaluates and analyzes the operation time series change index and the operation time series feature index of the electrical equipment to obtain the operation health assessment index of the electrical equipment; and a management unit, which takes preset management measures based on the operation health assessment index of the electrical equipment.

[0018] The present invention has the following beneficial effects: (1) The electrical equipment operation data monitoring and management method obtains continuous data of multiple key operating parameters by setting a time period, and calculates the change rate based on the difference between the operating value and the parameter value, thereby obtaining the operating sequence change index of the electrical equipment. When the equipment is in the early stage of degradation, its parameters may not yet exceed the alarm threshold, but the change trend has become abnormal, such as the temperature continues to rise slowly, the voltage fluctuation intensifies, etc. By incorporating these trend information into the evaluation system, hidden risks can be identified in advance and delayed warnings can be avoided. In addition, this method can also adapt to complex operating scenarios such as slow parameter drift and alternating fluctuations. Compared with existing methods, it has stronger early recognition capabilities and operating status perception capabilities, which helps to form a pre-maintenance response mechanism and improve the stability and safety of the system.

[0019] (2) The electrical equipment operation data monitoring and management method generates a health assessment index based on a fusion model of the operation sequence variation index and the operation sequence characteristic index, and sets multiple risk interval levels. Each level corresponds to different management measures. For example, when the health index is higher than the set upper limit, the system maintains its original state operation. If the health index is in the light to moderate risk range, the sampling frequency adjustment, operation and maintenance warning, load optimization and other strategies can be linked. When the health index falls into the high risk or serious range, load limiting operation, shutdown protection and other operations can be automatically executed. This hierarchical strategy improves the pertinence of management response, enabling the operation and maintenance system to intervene in time and avoid over-response. At the same time, the evaluation indicators are consistent with the actual working conditions, ensuring that the trigger conditions are reasonable, and truly realizing the precise linkage between operation risks and management decisions.

[0020] (3) The electrical equipment operation data monitoring and management method uses a deep time series feature extraction network to perform structured modeling on multiple operation parameter channels, and finally outputs a set of single-channel indicators that reflect the characteristics of the equipment operation behavior, including load fluctuation factor, voltage zero-crossing frequency, temperature rise trend slope, etc. These characteristic parameters not only come from the operation mechanism of the equipment itself, but each feature can also correspond to a specific physical phenomenon. For example, the main frequency change rate can reflect mechanical abnormalities, and the interference bandwidth factor can reflect the impact of the external environment, etc., which makes it easier for engineering personnel to make problem judgments and subsequent maintenance decisions based on the actual operating environment. In addition, this structured feature extraction method also enhances the scalability and versatility of the model, can flexibly adapt to the characteristic differences of different types of electrical equipment, and improves the engineering implementation capabilities of the entire monitoring and management method.

[0021] (4) The electrical equipment operation data monitoring and management system integrates the key functional units required in the electrical equipment operation monitoring process into a unified system based on a modular architecture, including time series data acquisition, change analysis, feature analysis, health assessment and management units. The system architecture is not only logically clear and has a clear division of tasks, but also has close data linkage between the units. When the operating status fluctuates, it can quickly complete data analysis and health assessment, and automatically match the corresponding management strategy according to the assessment results, and finally realize remote control, load limiting or early warning operations. Compared with traditional distributed monitoring solutions, the system reduces manual intervention and multi-platform collaboration costs, improves processing efficiency and response speed, and is particularly suitable for key power equipment scenarios that require high operation continuity, providing technical support for ensuring the stability and security of the power system.

[0022] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of a method for monitoring and managing operating data of electrical equipment according to the present invention.

[0024] Figure 2 This is a flowchart of the specific steps for analyzing the operation sequence variation index of electrical equipment in a method for monitoring and managing electrical equipment operation data of the present invention.

[0025] Figure 3 This is a time series broken line graph of the operating current of electrical equipment in a method for monitoring and managing the operating data of electrical equipment according to the present invention.

[0026] Figure 4 This is a time series broken line graph of the operating voltage of electrical equipment in a method for monitoring and managing operating data of electrical equipment according to the present invention.

[0027] Figure 5 This is a time series broken line graph of the operating temperature of electrical equipment in a method for monitoring and managing the operating data of electrical equipment according to the present invention.

[0028] Figure 6 This is a time series broken line graph of the power factor of electrical equipment in a method for monitoring and managing electrical equipment operation data of the present invention.

[0029] Figure 7 This is a time series broken line graph of the surface charge density of electrical equipment in a method for monitoring and managing electrical equipment operation data of the present invention.

[0030] Figure 8 This is a time series broken line graph of the peak amplitude of the main frequency of electrical equipment in a method for monitoring and managing the operation data of electrical equipment according to the present invention.

[0031] Figure 9This is a time series broken line graph of the electromagnetic interference intensity within a set area of ​​an electrical equipment in a method for monitoring and managing electrical equipment operation data of the present invention.

[0032] Figure 10 This is a block diagram of an electrical equipment operation data monitoring and management system of the present invention. DETAILED DESCRIPTION

[0033] See also Figure 1 , an embodiment of the present invention provides a technical solution: a method for monitoring and managing electrical equipment operation data, comprising the following steps: based on a set time period (for example, five minutes), obtaining the operation status time series data of the electrical equipment; performing a comprehensive analysis on the operation status time series data of the electrical equipment to obtain the operation timing change set of the electrical equipment, and analyzing the operation timing change index of the electrical equipment; inputting the operation status time series data of the electrical equipment into a pre-trained feature extraction model for feature analysis to obtain the operation timing feature set of the electrical equipment, and analyzing the operation timing feature index of the electrical equipment; evaluating and analyzing the operation timing change index and the operation timing feature index of the electrical equipment to obtain the operation health assessment index of the electrical equipment; and taking preset management measures based on the operation health assessment index of the electrical equipment.

[0034] The operating status timing data includes the operating current value, operating voltage value, operating temperature value, power factor value, surface charge density value, operating vibration spectrum and electromagnetic interference intensity value within the set area at several time points. The operating timing change set includes the operating current timing change value, operating voltage timing change value, operating temperature timing change value, power factor timing change value, surface charge density timing change value, operating vibration spectrum timing change value and electromagnetic interference intensity timing change value within the set area.

[0035] The operating current value can be measured and obtained by a current transformer (CT) or a Hall current sensor installed in the main electrical circuit.

[0036] The operating voltage value can be measured and obtained through a voltage transformer (PT) or a high-precision voltage sampling module.

[0037] The operating temperature value can be obtained by measuring with a thermocouple (T type, K type).

[0038] The power factor value can be calculated in real time based on the voltage-current phase angle through the distribution management terminal or smart energy meter.

[0039] The surface charge density value can be measured and obtained using an electrostatic charge sensor (such as a surface charge coupling probe or an ESD electric field probe).

[0040] The operating vibration spectrum can be measured and obtained using a MEMS triaxial accelerometer or a piezoelectric vibration sensor (IEPE type).

[0041] The electromagnetic interference intensity value within the set area can be measured and obtained using an electromagnetic interference probe (such as a near-field probe or a broadband electromagnetic interference monitoring module).

[0042] Specifically, if Figure 2 As shown, the specific steps of analyzing the operation sequence variation index of the electrical equipment are as follows: obtaining the operation state parameter data of the electrical equipment, the operation state parameter data including the operation current parameter value, the operation voltage parameter value, the operation temperature parameter value, the power factor parameter value, the surface charge density parameter value, the main frequency peak amplitude parameter value and the electromagnetic interference intensity parameter value in the set area; reading the operation state time series data of the electrical equipment, and performing a comprehensive analysis based on the operation state parameter data of the electrical equipment to obtain the operation state time series variation data of the electrical equipment, the operation state time series variation data including the operation current variation value, the operation voltage variation value, the operation temperature variation value, the power factor variation value, the surface charge density variation value, the operation vibration spectrum variation value and the electromagnetic interference intensity variation value in the set area at several time points; performing a comprehensive analysis on the operation state time series variation data of the electrical equipment (i.e., performing an average analysis on several time points) to obtain the operation sequence variation set of the electrical equipment, and analyzing the operation sequence variation index of the electrical equipment.

[0043] Among them, the operating current change value = (operating current value - operating current parameter value) / operating current parameter value.

[0044] Operating voltage change value = |(operating voltage value - operating voltage parameter value) / operating voltage parameter value|.

[0045] Operating temperature change value = |(operating temperature value - operating temperature parameter value) / operating temperature parameter value|.

[0046] Power factor change value = |(power factor value - power factor parameter value) / power factor parameter value|.

[0047] Surface charge density change value = |(surface charge density value - surface charge density parameter value) / surface charge density parameter value|.

[0048] The operating vibration spectrum change value is obtained by first extracting the main frequency peak amplitude value from the operating vibration spectrum, and then calculating it in combination with the main frequency peak amplitude parameter value, that is, the operating vibration spectrum change value = |(main frequency peak amplitude value - main frequency peak amplitude parameter value) / main frequency peak amplitude parameter value|.

[0049] The change value of electromagnetic interference intensity = |(electromagnetic interference intensity value-electromagnetic interference intensity parameter value) / electromagnetic interference intensity parameter value|.

[0050] The specific implementation example of analyzing the operating sequence variation index of electrical equipment is as follows. The existing parameters include the operating current value (A), operating voltage value (V), operating temperature value (°C), power factor value, surface charge density value (nC / m²), main frequency peak amplitude value (Hz), and electromagnetic interference intensity value (dBμV / m) in the set area at six time points of the electrical equipment. The specific data are shown in Table 1 and Figure 3-9 As shown: Table 1 Example of time series data of the operating status of electrical equipment at six time points In addition, the operating current parameter value of the electrical equipment is approximately: 125.0A.

[0051] The operating voltage parameter value is approximately: 380.0V.

[0052] The operating temperature parameter value is approximately: 65.0℃.

[0053] The power factor parameter value is approximately: 0.95.

[0054] The surface charge density parameter is approximately: 180.0nC / m².

[0055] The peak amplitude parameter value of the main frequency is approximately: 52.5Hz.

[0056] The electromagnetic interference intensity parameter value in the set area is approximately: 45.0dBμV / m.

[0057] The above data are combined with the data in Table 1 for comprehensive analysis to obtain the time series change data of the operating status of the electrical equipment. The specific data is shown in Table 2: Table 2 Example of time series data of the operating status of electrical equipment at six time points Performing mean analysis on the data in Table 2, we obtain: The time series change value of the operating current of electrical equipment is approximately: 0.013.

[0058] The operating voltage timing change value of electrical equipment is approximately: 004.

[0059] The time series change value of the operating temperature of electrical equipment is approximately: 0.016.

[0060] The power factor time series change value of electrical equipment is approximately: 0.01.

[0061] The time series variation of the surface charge density of electrical equipment is approximately: 0.013.

[0062] The time series change value of the operating vibration spectrum of electrical equipment is approximately: 0.012.

[0063] The time series variation value of the electromagnetic interference intensity within the set area of ​​the electrical equipment is approximately: 0.02.

[0064] The specific formula for calculating the operating sequence variation index of electrical equipment is as follows: ;in, is the operating sequence variation index of electrical equipment, is the time series change value of the operating temperature of the electrical equipment, is the temperature fluctuation response coefficient stored in the database, It is the time series variation value of the electromagnetic interference intensity within the set area of ​​the electrical equipment. is the electromagnetic disturbance sensitivity coefficient stored in the database, is the time series variation value of the operating vibration spectrum of the electrical equipment, is the time series variation of the surface charge density of the electrical equipment, is the time series change value of the power factor of the electrical equipment, is the time series change value of the operating current of the electrical equipment, It is the timing change value of the operating voltage of the electrical equipment.

[0065] Among them, the specific expression of the tanh function is: ,in, is a natural constant and can be taken as 2.71 in this embodiment, with a domain of (−∞, +∞) and a range of (−1, +1).

[0066] It should be explained that the temperature fluctuation response coefficient stored in the database , electromagnetic disturbance sensitivity coefficient The specific acquisition steps are as follows: for the temperature fluctuation response coefficient, by extracting the temperature time series data of the electrical equipment under different load states, calculating the correlation between the temperature mean square error and the load power change, and combining the thermal inertia response speed of multiple cycles to fit the regression function, extracting its stability coefficient as the temperature fluctuation response coefficient; for the electromagnetic disturbance sensitivity coefficient, by collecting multiple electromagnetic interference intensity change samples in the set area, analyzing its correlation coefficient with the operating status indicators (such as temperature rise rate, frequency offset, etc.), and using the multi-parameter sensitivity analysis method to quantify its disturbance amplification capability, thereby forming the response adjustment coefficient of the equipment in the area under electromagnetic disturbance.

[0067] In this implementation, a time-series change analysis mechanism based on parameter values ​​is constructed to systematically quantify the degree of operational deviation of electrical equipment within a set cycle. Compared with traditional methods that rely solely on current values ​​or abnormal thresholds for judgment, this method calculates the relative change rate of key operating parameters, such as current, voltage, temperature, and power factor, and extracts the peak amplitude change of the main frequency from the vibration spectrum. Combined with environmental factors such as electromagnetic interference, this method forms a comprehensive time-series change data set. At the same time, the introduction of temperature fluctuation response coefficient and electromagnetic disturbance sensitivity coefficient gives the evaluation process a certain response adjustment capability, which can adapt to the sensitivity differences of different equipment types and operating scenarios, avoiding misjudgment or underestimation of risks. By averaging the change values ​​of each parameter, the analysis's anti-fluctuation ability and overall stability are further improved. The resulting operation time-series change index can truly reflect the trend deviation and dynamic anomaly of the equipment throughout the entire cycle, providing a highly reliable basic indicator for subsequent health assessment and management response, significantly enhancing the system's practicality and early warning accuracy.

[0068] Specifically, the feature extraction model is a deep timing feature extraction network, including a multi-channel input layer, a convolution extraction layer, a gated feature filtering layer, an embedding mapping layer, and an output layer. The operating timing feature set includes load fluctuation factor, voltage zero-crossing frequency, heating trend slope, power factor disturbance amplitude, electrostatic density peak ratio, main frequency change rate, and interference bandwidth factor within the set area.

[0069] The specific steps for analyzing the operating timing feature set of electrical equipment are as follows: In the multi-channel input layer of the deep timing feature extraction network, the operating status timing data of the electrical equipment is received, and preprocessing operations are performed to generate a standardized multi-channel input tensor. Specifically, the operating status timing data of the electrical equipment obtained within a set time period is received. The timing data includes multiple physical parameter channels such as operating current, operating voltage, operating temperature, power factor, surface charge density, operating vibration spectrum, and electromagnetic interference intensity. In order to improve the stability and comparability of subsequent feature extraction, the data of all channels are uniformly preprocessed, including numerical normalization (such as Min-Max or Z-score normalization), outlier removal, sliding filter denoising, and window resampling processing, thereby constructing a multi-channel input tensor that is aligned in the time dimension, consistent in numerical scale, and stable in signal, providing a standardized original input basis for subsequent layers of the network.

[0070] In the convolution extraction layer of the deep temporal feature extraction network, one-dimensional convolution processing is performed on the preprocessed multi-channel input tensors respectively to extract the trend pattern and local change pattern of each parameter in the time dimension, and obtain the local structural feature mapping sequence of each operating parameter. Specifically, one-dimensional convolution operation is performed on the multi-channel standardized tensor output by the input layer, and the change trend and local disturbance characteristics of each parameter on the time axis are extracted through multiple sliding convolution kernels of different sizes. The main function of this layer is to extract the local structural features such as periodic oscillation, sudden transition, steady-state persistence, etc. of each parameter during the operating cycle. The convolution operation can not only capture the signal morphology changes in a short period of time, but also extract higher-order trend abstract information by stacking multiple layers, thereby forming a local structural feature mapping sequence of each operating parameter in the time dimension, which is used to reflect the basic feature map of its dynamic operating behavior.

[0071] In the gated feature filtering layer of the deep temporal feature extraction network, the local structural feature mapping sequence of each operating parameter is significantly screened based on the attention mechanism or gating function to obtain a set of effective temporal feature segments for each operating parameter. Specifically, the gating mechanism or attention mechanism is used to significantly screen the local structural feature mapping sequence of each operating parameter output by the convolutional extraction layer. By introducing a trainable gating factor or attention weight, the importance of the features of each time period is automatically evaluated to suppress redundant information segments and enhance mutational or trend feature segments, thereby accurately retaining high-value feature areas that truly affect the operating status of the equipment. This layer outputs a set of representative effective feature segments for each parameter on the periodic time axis for further feature abstraction and extraction.

[0072] In the embedding mapping layer of the deep temporal feature extraction network, the temporal effective feature segment set of each operating parameter is input into the feature compression unit respectively, and the feature representative value is extracted through the structural mapping function to obtain the load fluctuation factor of the operating current of the electrical equipment, the zero-crossing frequency of the operating voltage, the slope of the heating trend of the operating temperature, the disturbance amplitude of the power factor, the electrostatic peak ratio of the surface charge density, the main frequency change rate of the operating vibration spectrum, and the interference bandwidth factor of the electromagnetic interference intensity, thereby forming the operating temporal feature set of the electrical equipment. Specifically, the temporal effective feature segment set of each operating parameter obtained in the previous layer is input into the feature compression and structural mapping The module compresses the timing characteristics of each channel into a representative value that can express its full-cycle structural trend through a set of parameter-sharing nonlinear transformation functions combined with statistical aggregation (such as maximum pooling and attention aggregation). It finally outputs seven single-channel characteristic values ​​with actual physical significance, namely: the load fluctuation factor of the operating current, the zero-crossing frequency of the operating voltage, the slope of the heating trend of the operating temperature, the disturbance amplitude of the power factor, the electrostatic peak ratio of the surface charge density, the main frequency change rate of the operating vibration spectrum, and the interference bandwidth factor of the electromagnetic interference intensity in the set area, which constitute the operating timing characteristic set of the electrical equipment.

[0073] In the output layer of the deep timing feature extraction network, the operating timing feature set of the electrical equipment is uniformly encoded and output. Specifically, the operating timing feature set obtained in the embedding mapping layer is uniformly encoded to form a structured and standardized output vector. This output not only serves as a direct input for the subsequent operating status assessment model, health level calculation model or response control strategy model, but also has good channel differentiation and numerical comparability, and can support the calling and execution of multi-task evaluation and parallel decision-making modules. At this point, the multi-channel operating behavior of the electrical equipment within the current set cycle is successfully refined into a structured operating timing feature set with practical engineering significance, providing basic input for systematic judgment.

[0074] The specific formula for calculating the operating sequence characteristic index of electrical equipment is as follows: ;in, is the operating sequence characteristic index of the electrical equipment, is the temperature increase trend slope of electrical equipment, is the temperature rise trend response coefficient stored in the database, is the interference bandwidth factor within the set area of ​​the electrical equipment, is the rate of change of the main frequency of the electrical equipment, is a natural constant, and in this embodiment, its value is 2.71. is the load fluctuation factor of the electrical equipment, is the voltage zero-crossing frequency of the electrical equipment, is the power factor disturbance amplitude of the electrical equipment, is the peak value ratio of electrostatic density of electrical equipment, is the power electrostatic difference adjustment coefficient stored in the database.

[0075] It should be explained that the temperature rise trend response coefficient stored in the database , power electrostatic difference adjustment coefficient The specific acquisition steps are as follows: for the temperature rise trend response coefficient, first select typical cycle samples under different load conditions, extract their temperature time series data and fit the slope curve, and combine the response ratio between load level and temperature rise rate to calculate the average response coefficient of thermal sensitivity change as the temperature rise trend response coefficient; for the power electrostatic difference adjustment coefficient, based on the time series difference between the power factor and electrostatic density changes, calculate the normalized difference degree across cycles, and extract the power electrostatic difference adjustment coefficient through sensitivity regression analysis of the power-electrostatic covariance amplitude.

[0076] In this implementation scheme, by constructing a deep time series feature extraction network, the structural change characteristics in the electrical equipment operation data are systematically extracted from multiple dimensions, which greatly improves the accuracy of feature extraction and engineering adaptability. Compared with the traditional parameter analysis method that relies on manual settings or single statistical rules, the network can combine the trend, mutation and periodic changes in the time series, automatically identify the most representative effective feature segments, and extract characteristic indicators with actual physical meaning such as the temperature rise trend slope, main frequency change rate, interference bandwidth factor, etc. These indicators can not only accurately reflect the operating status of the equipment, but also have good interpretability and engineering reference value, which facilitates subsequent health status assessment and management strategy formulation. At the same time, the introduction of adjustment coefficient mechanism (such as temperature rise trend response coefficient, power electrostatic difference adjustment coefficient) realizes differentiated regulation of feature contribution weights, enhances the model's ability to recognize the equipment status under different working conditions, and improves the overall intelligence level and diagnostic accuracy of the system.

[0077] Specifically, the specific steps for obtaining the operation health assessment index of electrical equipment are as follows: obtain the low-risk threshold value and high-risk threshold value of the operation timing change of the electrical equipment; input the operation timing change index, the low-risk threshold value of the operation timing change, the high-risk threshold value of the operation timing change and the operation timing characteristic index of the electrical equipment into the health analysis model for evaluation and analysis to obtain the operation health assessment index of the electrical equipment.

[0078] The low-risk threshold for the operating sequence variation of electrical equipment refers to the limit value at which the operating sequence variation index of the electrical equipment is at the upper limit of the normal fluctuation range during operation. The specific steps for obtaining the threshold are as follows: Sample selection: Extract operating cycle samples that have been verified to be stable and fault-free within a certain period from the historical operating data of the equipment; Index extraction: Calculate the running time variation index for each stable period to form a low-risk sample index set; Statistical analysis: normal or skewed distribution modeling is performed on the index set. Common methods include Z-score processing and quantile calculation; Threshold determination: Set a confidence interval (e.g., 95%) and use the upper confidence bound or 95th percentile as the low-risk threshold for runtime sequence changes; Result storage: The results are stored uniformly in the system database as a benchmark for dividing low-risk segments in the health assessment model.

[0079] The high-risk threshold for operating sequence changes in electrical equipment refers to the critical value for determining whether the change index in the equipment's operating status has reached the structural fluctuation abnormality or instability warning range. The specific steps for obtaining it are: Abnormal sample screening: Filter out periodic samples that have recorded actual faults, alarms, offline, shutdowns, etc. from the equipment historical data; Index extraction: Calculate the running time variation index for these fault cycles to form an abnormal index sample set; Distribution modeling: Perform statistical analysis on the set and perform clustering or quantile analysis based on the anomaly type; Threshold setting: Select the lower boundary value where more than 80% of the abnormal index samples show warnings or instability as the high-risk threshold for runtime changes; Safety correction: To prevent false alarms, the safety margin factor can be set and fine-tuned based on the device type; Result storage: The value is stored in the system database and used for triggering judgment logic in high-risk intervals.

[0080] The health analysis model is as follows: ;in, is the operational health assessment index of electrical equipment, is the operating sequence characteristic index of the electrical equipment, is the operating sequence variation index of electrical equipment, Low risk threshold for changes in the operating sequence of electrical equipment, is the time series change evaluation coefficient stored in the database, is the time series feature evaluation coefficient stored in the database, High risk threshold for changes in the operating sequence of electrical equipment, is the interaction evaluation coefficient stored in the database.

[0081] It should be explained that the time series change evaluation coefficient stored in the database , time series characteristic evaluation coefficient , interaction evaluation coefficient The specific steps of obtaining are as follows: first, through a large number of operation cycle samples, the operation sequence change index and the posterior health results in the corresponding period are extracted, and the minimum error regression fitting is used to calculate , to reflect the direct impact of time series changes on health status; then, the operating time series characteristic index within the same period is incorporated into the model, and by introducing regularized deviation analysis, the independent contribution strength of the characteristic trend in health assessment is determined to form Finally, by evaluating the synergistic effect of the product of the operating time variation index and the characteristic index on health fluctuations, the interaction sensitivity between the two was quantified and the As the interactive evaluation coefficient, it is uniformly stored in the database for the health analysis model to call.

[0082] In this implementation plan, a complete health assessment model is constructed by setting low-risk and high-risk thresholds and combining the operating sequence variation index and the operating sequence characteristic index. This significantly improves the accuracy of equipment operating status judgment and the hierarchical nature of management response. The low-risk threshold is extracted based on stable operating condition samples and reflects the upper limit of the normal fluctuation range. The high-risk threshold comes from the statistical modeling of fault samples and marks the lower limit of potential unstable behavior. The two together constitute a reasonable segmentation standard for equipment operating status. At the same time, the assessment model integrates the two dimensions of variation index and characteristic index. By introducing the time series variation evaluation coefficient, characteristic evaluation coefficient and interaction evaluation coefficient, it scientifically quantifies the weight and interaction relationship of various parameters in the health assessment, avoiding misjudgment or misleading under single parameter drive. This structure not only makes the assessment process adjustable and engineering adaptable, but also can flexibly adjust the parameter threshold according to different equipment characteristics and operating requirements, realize dynamic perception and hierarchical management of the operating status of electrical equipment, and provide solid data support for the stability of system operation and the scientific nature of operation and maintenance strategies.

[0083] Specifically, the specific steps for taking preset management measures based on the operational health assessment index of electrical equipment are as follows: the operational health assessment index of the electrical equipment is judged and analyzed with several preset health assessment intervals, and each health assessment interval corresponds to a health risk level; based on the health risk level corresponding to the operational health assessment index of the electrical equipment in the preset health assessment interval, the preset management measures are taken for the electrical equipment.

[0084] Health assessment intervals and pre-set management measures include but are not limited to the following examples: [0.85, 1.00]: Completely healthy, indicating a stable condition with no intervention required.

[0085] [0.70,0.85): Mild risk, indicating slight fluctuations and can be observed for early warning.

[0086] [0.50, 0.70): Moderate risk, indicating an abnormal trend, and intervention is recommended.

[0087] [0.30,0.50): High risk, indicating abnormal fluctuations and requiring load limiting or maintenance.

[0088] [0.00,0.30): Serious fault, indicating that there are signs of fault and the machine should be shut down immediately.

[0089] In this implementation plan, by constructing a mapping relationship between the health assessment index and the risk level, the hierarchical judgment of the operating status of electrical equipment and the automatic execution of the corresponding management strategy are realized. Compared with the traditional single alarm mechanism, this method accurately divides the health status level according to the interval of the assessment value, and matches multi-level management measures such as observation and warning, intervention adjustment, load-limited operation, and shutdown processing respectively. This structured response method can dynamically adjust the management strategy according to the degree of change of the equipment status, which not only ensures operational safety, but also avoids unnecessary excessive intervention, significantly improving the rationality, precision and system execution efficiency of operation and maintenance decisions.

[0090] See also Figure 10 , an embodiment of the present invention provides a technical solution: an electrical equipment operation data monitoring and management system, comprising: a time series data acquisition unit, which acquires the operation status time series data of the electrical equipment based on a set time period; a time series change analysis unit, which performs a comprehensive analysis on the operation status time series data of the electrical equipment, obtains the operation time series change set of the electrical equipment, and analyzes the operation time series change index of the electrical equipment; a time series feature analysis unit, which inputs the operation status time series data of the electrical equipment into a pre-trained feature extraction model for feature analysis, obtains the operation time series feature set of the electrical equipment, and analyzes the operation time series feature index of the electrical equipment; a health assessment analysis unit, which evaluates and analyzes the operation time series change index and the operation time series feature index of the electrical equipment, and obtains the operation health assessment index of the electrical equipment; a management unit, which takes preset management measures based on the operation health assessment index of the electrical equipment.

[0091] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0092] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for monitoring and managing operating data of electrical equipment, characterized in that: The following steps are involved: Based on the set time period, obtain the operating status time series data of the electrical equipment; Conduct comprehensive analysis on the operating status time series data of electrical equipment to obtain the operating time series change set of electrical equipment and analyze the operating time series change index of electrical equipment; Input the operating status time series data of the electrical equipment into the pre-trained feature extraction model for feature analysis, obtain the operating time series feature set of the electrical equipment, and analyze the operating time series feature index of the electrical equipment; Evaluate and analyze the operating sequence variation index and operating sequence characteristic index of electrical equipment to obtain the operating health assessment index of electrical equipment; Take preset management measures based on the operational health assessment index of electrical equipment.

2. The method for monitoring and managing electrical equipment operation data according to claim 1, characterized in that: The operating status timing data includes the operating current value, operating voltage value, operating temperature value, power factor value, surface charge density value, operating vibration spectrum and electromagnetic interference intensity value within a set area at several time points, and the operating timing change set includes the operating current timing change value, operating voltage timing change value, operating temperature timing change value, power factor timing change value, surface charge density timing change value, operating vibration spectrum timing change value and electromagnetic interference intensity timing change value within a set area.

3. The method for monitoring and managing electrical equipment operation data according to claim 2, characterized in that: The specific steps for analyzing the operating sequence variation index of electrical equipment are as follows: Acquiring operating status parameter data of the electrical equipment, the operating status parameter data including operating current parameter value, operating voltage parameter value, operating temperature parameter value, power factor parameter value, surface charge density parameter value, main frequency peak amplitude parameter value, and electromagnetic interference intensity parameter value within a set area; Reading the operating status time series data of the electrical equipment and performing a comprehensive analysis in combination with the operating status parameter data of the electrical equipment to obtain the operating status time series change data of the electrical equipment, wherein the operating status time series change data includes the operating current change value, operating voltage change value, operating temperature change value, power factor change value, surface charge density change value, operating vibration spectrum change value and electromagnetic interference intensity change value within a set area at several time points; Comprehensively analyze the time series change data of the operating status of the electrical equipment to obtain the operating time series change set of the electrical equipment and analyze the operating time series change index of the electrical equipment.

4. The method for monitoring and managing electrical equipment operation data according to claim 2, characterized in that: The specific formula for calculating the operating sequence variation index of electrical equipment is as follows: ； in, 、 、 、 、 、 、 They are the operating time series change index of electrical equipment, operating temperature time series change value, operating vibration spectrum time series change value, surface charge density time series change value, power factor time series change value, operating current time series change value, and operating voltage time series change value. It is the time series variation value of the electromagnetic interference intensity within the set area of ​​the electrical equipment. 、 They are the temperature fluctuation response coefficient and electromagnetic disturbance sensitivity coefficient stored in the database respectively.

5. The method for monitoring and managing electrical equipment operation data according to claim 1, characterized in that: The feature extraction model is specifically a deep timing feature extraction network, including a multi-channel input layer, a convolution extraction layer, a gated feature filtering layer, an embedding mapping layer, and an output layer. The runtime timing feature set includes load fluctuation factor, voltage zero-crossing frequency, heating trend slope, power factor disturbance amplitude, electrostatic density peak ratio, main frequency change rate, and interference bandwidth factor within a set area.

6. The method for monitoring and managing electrical equipment operation data according to claim 5, characterized in that: The specific steps for analyzing the operating sequence feature set of electrical equipment are as follows: In the multi-channel input layer of the deep time series feature extraction network, the operating status time series data of the electrical equipment is received and preprocessed to generate a standardized multi-channel input tensor; In the convolutional extraction layer of the deep temporal feature extraction network, one-dimensional convolution processing is performed on the preprocessed multi-channel input tensor to extract the trend pattern and local change pattern of each parameter in the time dimension, and obtain the local structural feature mapping sequence of each operating parameter; In the gated feature filtering layer of the deep temporal feature extraction network, the local structural feature map sequence of each operating parameter is significantly screened based on the attention mechanism or gating function to obtain a set of temporally effective feature segments for each operating parameter. In the embedding mapping layer of the deep temporal feature extraction network, the set of effective temporal feature segments of each operating parameter is input into the feature compression unit respectively. The characteristic representative value is extracted through the structural mapping function to obtain the load fluctuation factor of the operating current of the electrical equipment, the zero-crossing frequency of the operating voltage, the slope of the temperature rise trend of the operating temperature, the disturbance amplitude of the power factor, the electrostatic peak ratio of the surface charge density, the main frequency change rate of the operating vibration spectrum, and the interference bandwidth factor of the electromagnetic interference intensity, thus forming the operating temporal feature set of the electrical equipment; In the output layer of the deep timing feature extraction network, the operating timing feature set of the electrical equipment is uniformly encoded and output.

7. The method for monitoring and managing electrical equipment operation data according to claim 5, characterized in that: The specific formula for calculating the operating sequence characteristic index of electrical equipment is as follows: ； in, 、 、 、 、 、 、 They are the operating sequence characteristic index of electrical equipment, temperature rise trend slope, main frequency change rate, load fluctuation factor, voltage zero-crossing frequency, power factor disturbance amplitude, and electrostatic density peak ratio. is a natural constant, is the interference bandwidth factor within the set area of ​​the electrical equipment, 、 They are the temperature rise trend response coefficient and the power electrostatic difference adjustment coefficient stored in the database.

8. The method for monitoring and managing electrical equipment operation data according to claim 1, characterized in that: The specific steps to obtain the operational health assessment index of electrical equipment are as follows: Obtaining a low-risk threshold value and a high-risk threshold value of an operation timing change of electrical equipment; The operation timing variation index, operation timing variation low risk threshold, operation timing variation high risk threshold and operation timing characteristic index of the electrical equipment are input into the health analysis model for evaluation and analysis to obtain the operation health evaluation index of the electrical equipment.

9. The method for monitoring and managing electrical equipment operation data according to claim 1, characterized in that: Based on the operational health assessment index of electrical equipment, the specific steps for taking preset management measures are as follows: The operational health assessment index of the electrical equipment is judged and analyzed against several preset health assessment intervals, and each health assessment interval corresponds to a health risk level; Based on the health risk level corresponding to the preset health assessment range of the operating health assessment index of the electrical equipment, preset management measures are taken for the electrical equipment.

10. An electrical equipment operation data monitoring and management system, applying the electrical equipment operation data monitoring and management method according to any one of claims 1 to 9, characterized in that: include: A time series data acquisition unit, which acquires the time series data of the operating status of the electrical equipment based on a set time period; The timing change analysis unit comprehensively analyzes the timing data of the operating status of the electrical equipment, obtains the operating timing change set of the electrical equipment, and analyzes the operating timing change index of the electrical equipment; The timing feature analysis unit inputs the operating status timing data of the electrical equipment into the pre-trained feature extraction model for feature analysis, obtains the operating timing feature set of the electrical equipment, and analyzes the operating timing feature index of the electrical equipment; The health assessment and analysis unit evaluates and analyzes the operating sequence variation index and operating sequence characteristic index of the electrical equipment to obtain the operating health assessment index of the electrical equipment; The management unit takes preset management measures based on the operational health assessment index of the electrical equipment.

Images