Low-voltage power distribution equipment operation status monitoring system

Abstract

This invention provides a low-voltage power distribution equipment operation status monitoring system, comprising a data acquisition module, a data processing module, a parameter fusion analysis module, and a status analysis module. The data acquisition module simultaneously collects electrical and environmental parameters by deploying multimodal sensing units at key nodes. The data processing module performs timestamp calibration and validity verification on the two types of parameters, generating a spatiotemporally correlated real-time data sequence. The parameter fusion analysis module spatially binds electrical and environmental parameters of the same node based on physical location topology, inputting a dynamic coupling model and outputting coupling analysis results. The status analysis module combines an equipment health model and an aging knowledge base to dynamically assess the operating status of key components and generate a comprehensive diagnostic report. This improves monitoring real-time performance, enables dynamic coupling analysis, and enhances fault early warning accuracy.

Description

Technical Field

[0001] This invention relates to the field of power equipment monitoring technology, and in particular to a low-voltage power distribution equipment operation status monitoring system. Background Technology

[0002] The stability of low-voltage power distribution equipment depends on whether the system remains within the set electrical and mechanical parameter range. Voltage fluctuations, current distortions, and environmental changes such as dust accumulation are directly related to temperature rise and increase the rate of insulation aging. Without regular inspections and remote sensor monitoring, and neglecting load balancing and heat dissipation, accelerated wear of mechanical components or sudden overcurrent conditions may lead to short circuit risks, thereby affecting the continuity of the entire power supply network. Therefore, through condition assessment and preventive maintenance practices, it is possible to predict equipment degradation trends, reduce the probability of failure, and improve system availability.

[0003] The significant technical challenge in monitoring the operational status of low-voltage power distribution equipment lies in the difficulty of achieving dynamic and coordinated analysis of environmental factors and electrical parameters. The main reason is that existing monitoring methods rely on discrete sensors and manual inspections, resulting in fragmented data acquisition and delayed response. For example, in industrial power distribution systems, the simultaneous operation of multiple units causes current distortion. However, due to the sparse deployment of temperature sensors and their lack of association with current monitoring, the excessive temperature rise and overload coupling effect in dust accumulation areas cannot be identified in time, ultimately accelerating the oxidation and melting of cable joints and affecting the continuity of power supply.

[0004] Therefore, how to improve the real-time performance of monitoring, realize dynamic coupling analysis, and enhance the accuracy of fault early warning are technical problems that urgently need to be solved by those skilled in the art. Summary of the Invention

[0005] This invention provides a low-voltage power distribution equipment operation status monitoring system to improve monitoring real-time performance, realize dynamic coupling analysis, and enhance fault early warning accuracy.

[0006] On one hand, the present invention provides a low-voltage power distribution equipment operation status monitoring system, which includes:

[0007] The data acquisition module is used to deploy multimodal sensing units on key node equipment of low-voltage power distribution equipment. The multimodal sensing units are used to collect electrical parameters and environmental parameters of low-voltage power distribution equipment.

[0008] The data processing module is used to perform timestamp calibration and validity verification on the electrical parameters and environmental parameters of the low-voltage power distribution equipment, and to form a structured and spatiotemporally correlated real-time data sequence.

[0009] The parameter fusion analysis module is used to spatially associate and bind the electrical parameters of the same key point in the real-time data sequence with the associated environmental parameters of the same key point based on a preset physical location topology. The parameters are then input into the constructed dynamic coupling model to obtain the coupling analysis results. The coupling analysis results include at least one of the following: the contribution of environmental parameter changes to the temperature rise of key node equipment, the induction intensity of electrical parameter anomalies to the environmental temperature rise, and abnormal coupling information.

[0010] The status analysis module is used to dynamically evaluate the operating status of key components in critical node equipment based on a preset equipment health model and aging knowledge base, combined with the coupling analysis results, and output a comprehensive diagnostic report.

[0011] According to the present invention, a low-voltage power distribution equipment operation status monitoring system includes a parameter fusion analysis module comprising:

[0012] The influence quantization unit is used to perform control variable simulation calculations on the dynamic coupling model. By replacing specific input variables with preset reference values ​​and observing the changes in output variables, it calculates the contribution of environmental parameter changes to the temperature rise of key node equipment, and / or the inducing intensity of abnormal electrical parameters on the environmental temperature rise.

[0013] The collaborative trend analysis unit is used to construct a multivariate feature vector containing electrical parameters, environmental parameters, influence contribution, and induced intensity based on the output of the influence quantification unit, and to analyze the collaborative change trend of the multivariate feature vector using a multivariate statistical process control method to identify abnormal coupling information.

[0014] According to the present invention, a low-voltage power distribution equipment operation status monitoring system is provided, wherein the influence quantification unit includes:

[0015] The influence contribution quantification subunit is used for:

[0016] Substitute the current electrical parameter values ​​into the dynamic coupling model, and replace the environmental parameter values ​​of the dynamic coupling model with standard reference values ​​to obtain the first predicted temperature rise rate;

[0017] Calculate the first difference between the current actual temperature rise rate and the first predicted temperature rise rate;

[0018] Based on the first difference, the contribution of the change in the environmental parameters to the temperature rise is determined.

[0019] According to the low-voltage power distribution equipment operation status monitoring system provided by the present invention, the influence contribution quantification subunit, when determining the influence contribution of the environmental parameter change on the temperature rise based on the first difference, is specifically used for:

[0020] Construct a sensitivity factor matrix for equipment differentiation; the sensitivity factor matrix is ​​established based on the sensitivity coefficients of different key node equipment to environmental parameters, and the sensitivity coefficients are dynamically adjusted in combination with the equipment's operating years;

[0021] The coupling effect between environmental parameters is quantified. A coupling coefficient matrix of environmental parameter combinations is constructed based on historical fault data. The individual contribution components of each environmental parameter and the total environmental contribution after coupling amplification are calculated in combination with the sensitivity factor matrix.

[0022] A cumulative effect model in the time dimension is established, and the instantaneous contribution and cumulative contribution are distinguished and nonlinearly superimposed to obtain the total contribution.

[0023] According to the low-voltage power distribution equipment operation status monitoring system provided by the present invention, the influence contribution quantification subunit is further used for:

[0024] Based on historical fault data, the correlation between environmental parameter combinations and temperature rise anomalies is mined, and a binary coupling coefficient is established. When all binary coupled environmental parameter combinations exceed their respective preset thresholds, the binary coupling coefficient is greater than 1, and when only one of the binary coupled environmental parameter combinations exceeds its respective preset threshold, the binary coupling coefficient is equal to 1.

[0025] Calculate the second difference between the actual value and the standard value of each environmental parameter, and calculate the product of the second difference and the sensitivity coefficient of the corresponding key node equipment as the individual contribution component of each environmental parameter;

[0026] The individual contribution components of all environmental parameters are summed to obtain the first sum value;

[0027] For each parameter pair with a coupling relationship, the individual contribution components of the two environmental parameters in each parameter pair are multiplied together, and then multiplied by the binary coupling coefficient between the two environmental parameters in each parameter pair. The calculation results of all parameter pairs with a coupling relationship are summed to obtain a second sum. The first sum and the second sum are added together to obtain the total environmental contribution.

[0028] According to the low-voltage power distribution equipment operation status monitoring system provided by the present invention, the influence contribution quantification subunit is further used for:

[0029] The instantaneous contribution is obtained by multiplying the total environmental contribution by the time decay coefficient; wherein, the time decay coefficient is related to the rate of change of environmental parameters. The faster the rate of change of environmental parameters, the larger the value of the time decay coefficient, and the maximum value is a first preset value.

[0030] The total contribution is obtained by integrating the product of the total environmental contribution and the time accumulation coefficient over time; wherein the time accumulation coefficient satisfies the following condition: for every additional preset duration of continuous exceedance of environmental parameters, the first preset proportion is increased, and the upper limit is a second preset value.

[0031] According to the low-voltage power distribution equipment operation status monitoring system provided by the present invention, the influence contribution quantification subunit is further used for:

[0032] By simulating different environmental conditions in the experimental chamber, the temperature rise curves of various key node devices were tested, and the sensitivity coefficients for different environmental parameters were extracted.

[0033] An aging correction coefficient is calculated based on the equipment's operating years, and the sensitivity coefficient is dynamically corrected to construct the sensitivity factor matrix; wherein, for every preset increase in the operating years, the sensitivity coefficient increases by a second preset ratio.

[0034] According to the present invention, a low-voltage power distribution equipment operation status monitoring system is provided, wherein the influence quantification unit includes:

[0035] The induced intensity quantization subunit is used to substitute the current environmental parameter values ​​into the dynamic coupling model and replace the current harmonic content with zero or standard limit values ​​to obtain the second predicted temperature rise rate.

[0036] Calculate the second difference between the current actual temperature rise rate and the second predicted temperature rise rate;

[0037] Based on the second difference, the induced intensity of the current harmonic component on the temperature rise is determined.

[0038] According to the present invention, a low-voltage power distribution equipment operation status monitoring system, including a collaborative trend analysis unit, is specifically used for:

[0039] The normal statistical distribution space of the multivariate feature vectors under the health state of the equipment is constructed based on principal component analysis;

[0040] Real-time calculation of T in the normal statistical distribution space of the feature vector of the multivariate to be identified 2 The statistic and / or SPE statistic; wherein, the T 2 The statistic measures the degree of change of a new sample within the normal hyperplane relative to the model center, and is used to capture the co-variation among dominant variables; the SPE statistic measures the magnitude of the residual generated after the new sample is projected onto the normal hyperplane, i.e. the distance from the normal model, and is used to capture anomalies in non-dominant variables or new patterns.

[0041] When the T 2 When the statistics and / or the SPE statistics exceed the preset control limit, it is determined that the abnormal coupling phenomenon exists.

[0042] A low-voltage power distribution equipment operation status monitoring system according to the present invention further includes:

[0043] The early warning module is used to generate early warning information based on the comprehensive diagnostic report and provide it to operation and management personnel or monitoring platforms.

[0044] The low-voltage power distribution equipment operation status monitoring system provided by this invention realizes synchronous acquisition of electrical and environmental parameters through multi-modal sensing units, quantifies the interaction between environmental and electrical parameters by combining dynamic coupling models, and corrects health assessment results based on equipment aging knowledge base. This solves the problems of data fragmentation, response lag and inability to identify dynamic coupling risks in traditional monitoring methods. In this way, it can improve the real-time performance of monitoring, realize dynamic coupling analysis, and improve the accuracy of fault early warning. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0046] Figure 1 This is a schematic diagram of the low-voltage power distribution equipment operation status monitoring system provided in an embodiment of the present invention. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0048] In existing technologies, monitoring the operating status of low-voltage power distribution equipment mainly relies on discrete sensors and manual inspections, resulting in fragmented data acquisition. For example, in industrial power distribution systems, current distortion caused by the operation of multiple units often fails to identify the coupling effect of excessive temperature rise and overload in dust accumulation areas due to sparse deployment of temperature sensors that are not linked to current monitoring. In traditional methods, electrical parameters and environmental parameters belong to independent monitoring systems, lacking spatiotemporal correlation and making it difficult to capture dynamic changes in local hot spots of equipment. When cable joints experience abnormal temperature rises due to current harmonics superimposed on dust coverage, discrete monitoring data cannot reveal the synergistic effects between parameters, leading to delayed maintenance response and accelerated equipment aging.

[0049] To address the aforementioned issues, research revealed that the dynamic mismatch between environmental factors and electrical parameters is the core cause of abnormal temperature rise in equipment. Analysis of historical fault cases showed that single-parameter threshold alarm mechanisms cannot identify multi-factor coupling effects. For example, although dust concentration increases may not exceed preset limits, they significantly exacerbate the temperature rise rate under specific current harmonic conditions. Based on this, a proposal was made to deploy multimodal sensing units on key node equipment, forcibly correlate electrical and environmental parameter acquisition, and construct a dynamic coupling model to quantify the interactive effects. Experimental verification showed that timestamp synchronization accuracy and data validity verification are prerequisites for ensuring the reliability of the analysis. Therefore, a hierarchical processing mechanism was designed to transform the raw data into a spatiotemporally correlated sequence.

[0050] Therefore, the present invention proposes the following technical solution:

[0051] Figure 1 This is a schematic diagram of the low-voltage power distribution equipment operation status monitoring system provided in an embodiment of the present invention. Figure 1 As shown, the low-voltage power distribution equipment operation status monitoring system of this embodiment may include a data acquisition module 11, a data processing module 12, a parameter fusion analysis module 13, and a status analysis module 14.

[0052] The data acquisition module 11 is used to deploy multimodal sensing units at key nodes of low-voltage power distribution equipment. The multimodal sensing units are used to collect electrical parameters and environmental parameters of the low-voltage power distribution equipment. For example, multimodal sensing units integrating electrical and environmental sensors are deployed at key nodes such as circuit breakers, contactors, and busbars to collect timestamped data at a preset frequency.

[0053] The data processing module 12 is used to perform timestamp calibration and validity verification on the electrical parameters and environmental parameters of the low-voltage power distribution equipment, and to form a structured and spatiotemporally correlated real-time data sequence.

[0054] The parameter fusion analysis module 13 is used to spatially associate and bind the electrical parameters of the same key point in the real-time data sequence with the associated environmental parameters of the same key point based on a preset physical location topology, input the constructed dynamic coupling model, and obtain the coupling analysis results; wherein, the coupling analysis results include the contribution of environmental parameter changes to the temperature rise of key node equipment, the induction intensity of electrical parameter anomalies to environmental temperature rise, and abnormal coupling information;

[0055] The status analysis module 14 is used to dynamically evaluate the operating status of key components in key node equipment based on a preset equipment health model and aging knowledge base, combined with the coupling analysis results, and output a comprehensive diagnostic report.

[0056] In a specific implementation process, a multimodal sensing unit refers to a composite acquisition device that includes current sensors, voltage sensors, temperature sensors, and humidity sensors. It can be integrated or distributed according to actual needs. Timestamp calibration refers to the unified alignment of timestamps on multi-source heterogeneous data. Specifically, this can be achieved using network time protocols or hardware clock synchronization circuits to eliminate timing deviations in data acquisition. Validity verification refers to verifying the rationality of data through threshold filtering and logical rules. Specifically, this can be achieved using the sliding window mean comparison method to identify abnormal sampling points. A dynamic coupling model is a mathematical model used to simulate the interaction between environmental and electrical parameters. Specifically, it can be implemented using a set of coupled differential equations based on heat transfer equations and circuit characteristic equations, used to quantify the combined impact of different parameters on equipment temperature rise. An equipment health model is a benchmark model reflecting the normal operating parameter range of the equipment. Specifically, it can be established by combining historical operating data statistical analysis with parameters from the equipment technical manual.

[0057] Specifically, the multimodal sensing unit is deployed at key heat-generating points such as circuit breakers and busbars, simultaneously collecting data on three-phase current, contact resistance, surface temperature, and ambient humidity. The data processing module 12 aligns the time stamps of each sensor using a hardware clock synchronization circuit, employs a sliding window algorithm to eliminate transient interference data, and generates a structured data stream with a unified timestamp. The parameter fusion analysis module 13, based on the equipment's physical location topology, spatially binds the current data collected from the same circuit breaker with the corresponding temperature and humidity data, inputs it into a dynamic coupling model built based on the heat conduction equation, and calculates the weight of the impact of environmental humidity changes on the circuit breaker's temperature rise. The status analysis module 14 calls the standard temperature rise curve of this type of circuit breaker under rated load, combines the current load rate with the insulation material life decay coefficient in the aging knowledge base, assesses the degree of contact oxidation, and generates a diagnostic report including a prediction of remaining life.

[0058] This solution utilizes multimodal sensing units to achieve parameter correlation and acquisition, and combines a dynamic coupling model to quantify the interaction between environmental and electrical parameters, thereby identifying hidden temperature rise anomalies caused by the synergy between electrical and environmental parameters. Furthermore, spatial correlation binding based on device topology avoids manual configuration of data mapping relationships, improving analysis efficiency.

[0059] Through the above technical solutions, this application solves the problem of collaborative analysis failure caused by data fragmentation from discrete sensors. The deployment of multimodal sensing units ensures the spatiotemporal consistency of data acquisition, the dynamic coupling model quantifies the interactive influence of environmental and electrical parameters, and the equipment health model combined with an aging knowledge base can accurately assess equipment condition deterioration caused by multiple factors. Therefore, the system can identify coupling risks missed by traditional threshold alarm mechanisms in advance, such as issuing an early warning of abnormal temperature rise under conditions where the current is not exceeded but harmonics are superimposed on dust, thus improving the accuracy of fault prediction and the timeliness of maintenance response.

[0060] In some embodiments, this application further proposes a parameter fusion analysis module 13 including an influence quantification unit and a collaborative trend analysis unit. The influence quantification unit is used to perform controlled variable simulation calculations on a dynamic coupling model. By replacing specific input variables with preset reference values ​​and observing changes in output variables, it calculates the contribution of environmental parameter changes to the temperature rise of key node equipment, and / or the inducing intensity of abnormal electrical parameters on the environmental temperature rise. The collaborative trend analysis unit is used to construct a multivariate feature vector containing electrical parameters, environmental parameters, influence contribution, and inducing intensity based on the output results of the influence quantification unit, and uses multivariate statistical process control methods to analyze the collaborative change trend of the multivariate feature vector to identify abnormal coupling information.

[0061] Among them, controlled variable simulation calculation refers to quantifying the influence of a variable on the result by fixing other variables and replacing the target variable with a preset reference value, and observing the change in the output variable. This can be achieved through numerical simulation or experimental testing. This calculation method can separate the independent effects of a single variable on a complex system, solving the problem that traditional methods cannot distinguish the coupled effects of multiple factors.

[0062] Among them, the multivariate feature vector refers to the integration of monitoring data from different dimensions and impact quantification results into a unified data structure, which can be constructed through vector concatenation or feature engineering methods. This vector provides standardized input for subsequent collaborative analysis, overcoming the technical obstacle of the difficulty in correlated analysis of discrete data.

[0063] Among them, multivariate statistical process control methods refer to anomaly detection of multidimensional data based on multivariate statistical models. Specifically, principal component analysis combined with T... 2 The method implements statistical measures and SPE statistics. It can capture anomalies in nonlinear associations between variables and improve the ability to identify implicit coupling faults.

[0064] Specifically, when performing controlled variable simulations on a dynamically coupled model, for example, by replacing environmental parameters with standard reference values ​​and running the model, the difference between the actual temperature rise rate and the simulation results can be compared to quantify the independent impact of environmental parameter changes on temperature rise. Simultaneously, by replacing the current harmonic content with zero values ​​and running the model, the induced intensity of electrical parameter anomalies on temperature rise can be calculated. The collaborative trend analysis unit further integrates the quantification results of electrical parameters, environmental parameters, and their impacts into a multivariate feature vector, constructs a statistical distribution space under normal conditions through principal component analysis, and calculates T in real time. 2 The statistical measure measures the degree of co-shift of the dominant variables, and the SPE statistic is combined with the residual anomaly to detect anomalies, thereby identifying anomalies caused by the coupling effect of multiple factors.

[0065] This solution uses controlled variable simulation calculations to dynamically decouple the interaction between the environment and electrical parameters. Combined with multivariate statistical methods, it can identify collaborative abnormal patterns. For example, when the current harmonic content is slightly exceeded in a high-temperature environment, it can provide an early warning of the oxidation risk of cable joints, avoiding the problem of missed detection caused by a single parameter not exceeding the threshold in traditional methods.

[0066] Through the above technical solution, this application can accurately quantify the dynamic coupling effect of environmental and electrical parameters, solving the problems of misjudgment and response lag caused by data fragmentation in existing monitoring systems. For example, in industrial power distribution scenarios, when dust accumulation and current distortion coexist, the system can identify abnormal temperature rises caused by heat dissipation obstruction and overload coupling in cable joints by calculating the contribution of dust to temperature rise and the inducing intensity of current distortion, combined with multivariate collaborative trend analysis. Compared with traditional single-parameter threshold detection methods, this can advance the fault warning time and reduce the false alarm rate.

[0067] In some embodiments, this application further proposes an impact contribution quantification subunit, comprising: substituting the values ​​of electrical parameters at the current moment into a dynamic coupling model, and replacing the values ​​of environmental parameters in the dynamic coupling model with standard reference values ​​to obtain a first predicted temperature rise rate; calculating a first difference between the current actual temperature rise rate and the first predicted temperature rise rate; and determining the impact contribution of environmental parameter changes on the temperature rise based on the first difference.

[0068] The standard reference value refers to a pre-set benchmark value for environmental parameters, which can be achieved using temperature, humidity, and dust concentration thresholds under the equipment's rated operating conditions, serving as a benchmark for comparison with actual measured values. The first predicted temperature rise rate refers to the theoretical temperature rise rate output by the model when the environmental parameters are replaced with the standard reference value. This can be obtained through numerical solution of the dynamically coupled model and is used to eliminate the interference of environmental fluctuations on the analysis results. The first difference refers to the deviation between the actual temperature rise and the theoretical temperature rise, which can be calculated through subtraction and is used to characterize the actual impact of abnormal environmental parameters on the equipment's temperature rise.

[0069] Specifically, during equipment operation, electrical and environmental parameters interact through a dynamically coupled model. By replacing real-time collected environmental parameters with standard reference values, the impact of environmental fluctuations on the model output can be eliminated, thus separating the independent contribution of environmental parameter anomalies to temperature rise. The first predicted temperature rise rate reflects the theoretical temperature rise state of the equipment under standard conditions, and the difference between it and the actual temperature rise rate directly quantifies the magnitude of the impact of environmental anomalies. For example, when the ambient temperature exceeds the standard value, the temperature rise rate output by the model after replacing it with the standard temperature will be lower than the actual measured value; the difference between the two is the contribution of the temperature exceedance to the equipment's temperature rise. This difference is further weighted using the sensitivity factor matrix and coupling coefficient matrix to ultimately obtain an accurate assessment result of the environmental contribution.

[0070] This scheme achieves dynamic decoupling analysis of the influence of environmental parameters by replacing the standard reference value with a dynamic coupling model. For example, in existing technologies, when both temperature and humidity exceed the standard, it is difficult to distinguish the individual contributions and synergistic effects of the two. However, this scheme can accurately calculate the independent influence components and coupling amplification effects of each parameter by using the controlled variable method.

[0071] Through the above technical solution, this application can accurately quantify the contribution of environmental parameter changes to equipment temperature rise and effectively identify potential faults caused by environmental anomalies. For example, in high temperature and high humidity environments, it can accurately calculate the individual impact of excessive humidity on cable joint temperature rise and the synergistic amplification effect of temperature-humidity coupling, providing maintenance personnel with targeted environmental control basis and avoiding misjudgments or missed detections caused by parameter coupling.

[0072] In some embodiments, this application further proposes that when the influence contribution quantification subunit determines the influence contribution of environmental parameter changes on temperature rise based on the first difference, it constructs a device-differentiated sensitivity factor matrix. The sensitivity factor matrix is ​​established based on the sensitivity coefficients of different key node devices to environmental parameters, and the sensitivity coefficients are dynamically corrected in combination with the equipment's operating years. The coupling effect between environmental parameters is quantified. A coupling coefficient matrix of environmental parameter combinations is constructed based on historical fault data. The individual contribution components of each environmental parameter and the total environmental contribution after coupling amplification are calculated in combination with the sensitivity factor matrix. A time-dimensional cumulative effect model is established to distinguish between instantaneous contribution and cumulative contribution and perform nonlinear superposition to obtain the total contribution.

[0073] The equipment-differentiated sensitivity factor matrix refers to a weighted matrix established based on the differences in the response of different equipment types to environmental parameters. Specifically, it can be achieved by simulating different environmental conditions in the laboratory and testing the equipment's temperature rise curves to extract initial sensitivity coefficients, which are then dynamically corrected based on the equipment's operating years. This addresses the problem of declining heat dissipation performance due to equipment aging. The coupling effect between environmental parameters refers to the nonlinear superposition effect generated when multiple environmental parameters act together. Specifically, it can be achieved by statistically analyzing the synergistic effect strength of different parameter combinations using historical fault data, constructing a coupling coefficient matrix to quantify the amplification effect between parameters, thus solving the problem of neglecting synergistic effects in single-parameter analysis. The time-dimensional cumulative effect model distinguishes the difference in the impact of sudden changes in environmental parameters versus long-term exceedances on equipment. Specifically, it can be achieved by calculating instantaneous contribution combined with rate-of-change weighting, and calculating the time integral of cumulative contribution, thus solving the problem that traditional static analysis cannot reflect continuous effects.

[0074] Specifically, in determining the contribution of environmental parameter changes to temperature rise, the process first simulates different temperature, humidity, and dust conditions in an experimental chamber to test the temperature rise response of equipment such as cable joints and air circuit breakers, establishing initial sensitivity coefficients. For example, the temperature sensitivity coefficient for cable joints is set to 1.5, humidity to 0.8, and dust to 1.2. Then, based on the actual operating years of the equipment, the sensitivity coefficients are increased according to a first preset ratio; for example, the temperature sensitivity coefficient for cable joints that have been in operation for more than 5 years increases by 20%. Next, the coupling effect of environmental parameter combinations is analyzed based on historical fault data. For example, when the temperature exceeds 40℃ and the humidity exceeds 70%, the coupling coefficient is set to 1.4. The individual contribution components are multiplied by the coupling coefficients and then summed to obtain the total environmental contribution. Finally, the instantaneous contribution is calculated using a time decay coefficient weighting; for example, for every 5℃ / minute increase in the rate of change of environmental parameters, the time decay coefficient increases by 0.2. Simultaneously, a time integral model is used to calculate the cumulative contribution; for example, for every hour of continuous humidity exceeding the limit, the cumulative coefficient increases by 5%. Finally, the two are nonlinearly superimposed to obtain the total contribution.

[0075] This solution, by dynamically adjusting the sensitivity coefficient, introducing a coupling coefficient matrix, and a time-dimensional model, can more accurately quantify the impact of environmental parameters under complex operating conditions. Furthermore, through the aforementioned technical solutions, this application can accurately distinguish the differences in the response of different equipment types and aging states to environmental parameters, identify abnormal temperature rises caused by the synergistic effect of multiple environmental parameters, and dynamically assess the impact weights of instantaneous changes and long-term exceedances on equipment. This improves the accuracy of low-voltage power distribution equipment operating status assessment and provides a more reliable basis for preventative maintenance decisions.

[0076] In some embodiments, this application further proposes an impact contribution quantification subunit in the parameter fusion analysis module 13, which mines the correlation between environmental parameter combinations and temperature rise anomalies based on historical fault data, and establishes a binary coupling coefficient; when all binary coupled environmental parameter combinations exceed their respective preset thresholds, the binary coupling coefficient is greater than 1, and when only one binary coupled environmental parameter combination exceeds its respective preset threshold, the binary coupling coefficient is equal to 1; calculates the second difference between the actual value and the standard value of each environmental parameter, and calculates the product of the second difference and the sensitivity coefficient of the corresponding key node equipment as the individual contribution component of each environmental parameter; sums the individual contribution components of all environmental parameters to obtain a first sum value; for each parameter pair with a coupling relationship, multiplies the individual contribution components of the two environmental parameters in each parameter pair, multiplies them by the binary coupling coefficient between the two environmental parameters, and sums the calculation results of all parameter pairs with a coupling relationship to obtain a second sum value, and adds the first sum value and the second sum value to obtain the total environmental contribution.

[0077] The binary coupling coefficient quantifies the synergistic effect of two environmental parameters on temperature rise anomalies. Specifically, it can be calculated as the ratio of the frequency of temperature rise anomalies when a combination of parameters exceeds the standard to the frequency when a single parameter exceeds the standard in historical fault data. For example, when both temperature and humidity exceed the standard, this coefficient can be set to 1.4. The individual contribution component quantifies the impact of a single environmental parameter deviating from its standard value on temperature rise. This can be calculated by multiplying the parameter deviation by the equipment sensitivity coefficient. For example, a temperature deviation of 5℃ multiplied by a sensitivity coefficient of 1.2 yields a temperature contribution component of 6. The first sum is the linear superposition of the individual contribution components of all environmental parameters, reflecting the total impact without coupling. The second sum is the nonlinear superposition of the contribution components of parameter pairs with coupling relationships, reflecting the amplification effect of synergistic interactions between parameters.

[0078] Specifically, in an industrial power distribution scenario, when a temperature sensor detects a temperature of 45℃ and a humidity sensor detects a humidity of 75%RH in a certain area, the system first determines whether both parameters exceed preset thresholds. If the temperature threshold is set to 40℃ and the humidity threshold to 70%RH, the binary coupling coefficient calculation is triggered. In this case, the binary coupling coefficient for temperature and humidity is set to 1.4, indicating that their combined effect increases the temperature rise by 40%. Then, the individual contribution components for a 5℃ temperature deviation and a 5%RH humidity deviation are calculated separately; for example, the temperature contribution is 5 × 1.5 = 7.5, and the humidity contribution is 5 × 0.8 = 4.0. The first sum is 7.5 + 4.0 = 11.5. Next, the coupled contribution component of temperature and humidity is calculated, i.e., 7.5 × 4.0 × 1.4 = 42.0, and the second sum is also 42.0. The final total environmental contribution is 11.5 + 42.0 = 53.5, which will be input into subsequent models for anomaly detection.

[0079] In a specific implementation process, traditional methods only calculate the influence components of individual environmental parameters and perform simple superposition, without considering the synergistic amplification effect between parameters. For example, under the same conditions of excessive temperature and humidity, the traditional method calculates a result of 11.5, while this scheme, by introducing coupling coefficients and product calculations, increases the total contribution to 53.5, more realistically reflecting the actual temperature rise risk. Existing technologies using linear superposition statistical methods tend to underestimate the role of combined environmental factors, while this scheme, through the construction of coupling coefficients driven by historical data, can accurately capture the accelerated degradation effect of combined conditions such as high temperature and high humidity.

[0080] Through the above technical solution, this application solves the technical problem of the difficulty in quantifying and analyzing the synergistic effects between environmental parameters, and realizes the accurate calculation of the impact of complex environmental factors on equipment temperature rise. Under the condition of dust accumulation on cable joints accompanied by a sudden temperature rise, the system can automatically identify abnormal synergistic changes through the coupling coefficient. Compared with the traditional single-parameter threshold alarm method, it issues a warning signal more than 30 minutes in advance, effectively avoiding sudden equipment meltdown accidents caused by the coupling effects of environmental parameters.

[0081] In some embodiments, this application further proposes that the influence contribution quantification subunit is also used to multiply the total environmental contribution by the time decay coefficient to obtain the instantaneous contribution. The time decay coefficient is related to the rate of change of the environmental parameters. The faster the rate of change of the environmental parameters, the larger the value of the time decay coefficient, and the maximum value is a first preset value. The total contribution is obtained by integrating the product of the total environmental contribution and the time accumulation coefficient over time. The time accumulation coefficient increases by a first preset proportion for every preset duration of continuous exceedance of the environmental parameters, and the upper limit is a second preset value.

[0082] The time decay coefficient is an adjustment factor used to weight the instantaneous impact of sudden environmental parameter changes. It can be implemented using a first-derivative weighted algorithm, dynamically adjusting the weight values ​​by capturing the rate characteristics of parameter changes. This coefficient automatically increases when environmental parameters change abruptly to strengthen the weight of the instantaneous contribution. The time accumulation coefficient is an adjustment factor used to quantify the long-term impact of continuously exceeding environmental parameters. It can be implemented using an integral model, constructing a nonlinear growth function based on the duration and a preset increase ratio. This coefficient gradually increases as the parameter exceeds the standard for longer to reflect the cumulative effect. The nonlinear superposition rule is a calculation method for handling the simultaneous existence of instantaneous and cumulative contributions. It can be implemented using a weighted summation method, introducing a reduction factor to avoid double counting and ensure that the comprehensive evaluation of the two contributions conforms to actual physical laws.

[0083] Specifically, when environmental parameters fluctuate rapidly, the system amplifies the instantaneous contribution using a time decay coefficient to reflect the immediate impact of sudden changes. For persistently exceeding parameters, the system uses a time accumulation coefficient to construct an integral model to calculate the long-term cumulative effect. After calculating the two contributions separately, a nonlinear superposition rule is used for comprehensive evaluation. For example, a sudden temperature surge during summer thunderstorms triggers a high instantaneous contribution, while persistent humidity exceeding the standard during the plum rain season accumulates to form a high cumulative contribution. The superposition calculation result of the two can accurately reflect the comprehensive impact of complex environmental factors on equipment temperature rise.

[0084] This solution constructs a dual-channel analysis model with a time dimension, which can simultaneously capture the combined effects of sudden anomalies and gradual degradation, thus solving the problem that a single assessment model is insufficient in representing the mechanism of action of complex environmental factors.

[0085] Through the above technical solution, this application realizes the full life cycle quantitative assessment of the dynamic change process of environmental parameters, effectively identifies the superposition effect of short-term shocks and long-term accumulation, provides accurate contribution analysis basis for early warning of abnormal equipment temperature rise, and avoids misjudgment or omission due to ignoring the time dimension characteristics.

[0086] In some embodiments, this application further proposes an impact contribution quantification subunit that simulates the temperature rise curves of various key node devices under different environmental conditions in an experimental chamber, extracts sensitivity coefficients for different environmental parameters, calculates aging correction coefficients based on the equipment's operating years, dynamically corrects the sensitivity coefficients, and constructs a sensitivity factor matrix, wherein the sensitivity coefficients increase by a second preset ratio for each additional preset number of years of operation.

[0087] Among them, the experimental chamber simulates different environmental conditions by reproducing the actual working conditions through a closed test environment with adjustable temperature, humidity and dust concentration. Specifically, it can be achieved by integrating a dust generator into the constant temperature and humidity experimental chamber, which is used to establish a quantitative relationship between equipment temperature rise and environmental parameters.

[0088] The sensitivity coefficient refers to the response strength of the equipment's temperature rise rate to changes in environmental parameters. Specifically, it can be achieved by collecting temperature rise gradient data under different environmental combinations and fitting a regression equation, which is used to quantify the influence weight of environmental parameters on the equipment.

[0089] The aging correction factor refers to the amplification effect of material performance degradation caused by the service life of the equipment on the sensitivity coefficient. Specifically, it can be implemented using a piecewise function of service life or an exponential decay model. For example, after five years of operation, the temperature sensitivity coefficient of the cable joint increases by 20%, which is used to reflect the decrease in heat dissipation capacity caused by insulation aging.

[0090] The sensitivity factor matrix refers to the correlation table between equipment type and environmental parameters. Specifically, it can be implemented by creating a two-dimensional array to store the basic sensitivity coefficients of different equipment types on each environmental parameter, which is used to provide a differentiated weighting benchmark for subsequent contribution calculation.

[0091] Specifically, during the experimental calibration phase, multiple environmental combinations are generated by controlling the temperature, humidity, and dust concentration of the experimental chamber. Temperature rise data of the tested equipment is simultaneously collected and curves are plotted. The sensitivity coefficients corresponding to each environmental parameter are obtained using the least squares method. For equipment whose service life exceeds a preset threshold, an aging correction coefficient is calculated based on its historical operating data and added to the base sensitivity coefficient, forming a dynamically updated sensitivity factor matrix. For example, the humidity sensitivity coefficient of an air circuit breaker is adjusted from 1.3 to 1.43 after three years of operation, and the temperature sensitivity coefficient of a cable joint increases from 1.5 to 1.8 after five years of operation, thereby ensuring the accuracy of quantifying the impact of environmental parameters.

[0092] This approach establishes an initial sensitivity benchmark using experimental chamber data and dynamically adjusts the sensitivity factor matrix based on operational years, thus resolving model inaccuracies caused by individual equipment differences and performance degradation.

[0093] Through the above technical solution, this application can accurately quantify the sensitivity of different equipment to environmental parameters at different life cycles, effectively identify the abnormal temperature rise caused by insulation aging, improve the accuracy of the assessment of the impact of environmental factors on equipment status, and provide a reliable basis for early warning.

[0094] In some embodiments, this application further proposes that the influence quantification unit in the parameter fusion analysis module 13 includes an induced intensity quantification subunit, which is used to substitute the value of the environmental parameter at the current moment into the dynamic coupling model, and replace the current harmonic content with zero value or standard limit value to obtain a second predicted temperature rise rate; calculate a second difference between the current actual temperature rise rate and the second predicted temperature rise rate; and determine the induced intensity of the current harmonic component on the temperature rise based on the second difference.

[0095] Replacing the current harmonic content with zero or standard limits refers to isolating the influence of specific variables by modifying the model input parameters. This can be achieved using a preset harmonic component zeroing algorithm or an industry standard limit substitution method, used to eliminate harmonic interference and assess its independent effect. Induced intensity is a quantitative indicator of the driving force of abnormal electrical parameters on equipment temperature rise. It can be calculated using the difference ratio method or gradient analysis method, used to reflect the direct impact of harmonic distortion on temperature rise.

[0096] Specifically, when the system detects abnormal current harmonic content, the induced intensity quantification subunit substitutes real-time collected environmental parameters into the dynamic coupling model, and simultaneously forces the current harmonic components to be corrected to standard limits or zeroed out, generating a theoretical temperature rise rate. By comparing the deviation between the actual temperature rise rate and the theoretical value, the temperature rise increment caused by the harmonic component alone can be accurately separated. For example, when the total harmonic distortion rate of a distribution cabinet suddenly increases to 15%, the subunit finds through model calculation that the actual temperature rise rate is 0.8℃ / min higher than the predicted value under harmonic-free conditions, thus determining that the harmonic component induced intensity has reached the level two warning threshold.

[0097] This solution achieves decoupling analysis of abnormal electrical parameters and environmental parameters through the variable substitution mechanism of the dynamic coupling model. It can accurately identify the temperature rise contribution under the sole effect of harmonic distortion, and solve the problem of difficulty in attributing causes in multi-factor coupled scenarios.

[0098] Through the above technical solution, this application can effectively distinguish the superimposed effect of current harmonic anomalies and environmental factors on equipment temperature rise, accurately identify the inducing intensity of harmonic components in composite faults, provide data support for optimizing the action threshold of overload protection devices, and thereby reduce the risk of accelerated insulation aging caused by the failure to isolate harmonic distortion in time.

[0099] In some embodiments, this application further proposes a collaborative trend analysis unit specifically used to construct a normal statistical distribution space of multivariate feature vectors under the device health state based on principal component analysis, and to calculate in real time the T of the multivariate feature vector to be identified in the normal statistical distribution space. 2 Statistics and / or SPE statistics, when T 2 When the statistical value and / or SPE statistical value exceed the preset control limit, it is determined that there is an abnormal coupling phenomenon.

[0100] Principal component analysis (PCA) is a technique that reduces the dimensionality of multivariate eigenvectors to a lower-dimensional space through orthogonal transformation. Specifically, it can be implemented using the covariance matrix eigenvalue decomposition method. PCA is used to extract linear correlation features among multiple variables under equipment health conditions and to construct a normal statistical distribution space. 2 A statistical measure is an indicator that measures the degree of change of a new sample relative to the model center within the normal hyperplane. It can be calculated using Mahalanobis distance and is used to capture cooperative anomalous shifts among dominant variables. The SPE statistic measures the magnitude of the residuals produced after projecting a new sample onto the normal hyperplane. It can be calculated using the sum of squared residuals and is used to capture deviations from non-dominant variables or novel anomalous patterns. Preset control limits are statistical thresholds set based on the normal sample distribution. They can be determined using kernel density estimation or empirical distribution quantile methods and serve as a basis for judging multivariate cooperative anomalous shifts.

[0101] Specifically, during normal equipment operation, principal component analysis is used to reduce the dimensionality of the multivariate feature vectors containing electrical parameters, environmental parameters, influence contribution, and induced intensity, extracting principal components and constructing a normal statistical distribution space. During real-time monitoring, the multivariate feature vectors to be identified are projected onto this space, and their T2 statistic and SPE statistic are calculated. 2 The statistic reflects the degree of shift of the dominant variable in the reduced-dimensional space. When the operating state of the equipment undergoes an anomaly caused by the co-change of known variables, T... 2 The SPE statistic may exceed the preset control limits; the SPE statistic reflects the amount of variation in the residual space not explained by the principal components. When novel anomalies or anomalies in non-dominant variables occur, the SPE statistic will exceed the control limits. By jointly judging the exceedance of the two statistics, the types of anomaly coupling can be distinguished and an early warning can be triggered.

[0102] This approach establishes a multivariate statistical model through principal component analysis, combined with T...2 By coordinating trend monitoring with SPE statistics, abnormal phenomena caused by parameter coupling can be detected earlier, and both existing and new abnormalities can be detected in a timely manner.

[0103] Through the above technical solution, this application can effectively identify abnormal phenomena caused by the dynamic coupling of electrical parameters and environmental parameters, solve the problem of the lag in response of existing monitoring methods to multi-variable coordinated changes, improve the early warning capability for hidden faults, and provide data support for the preventive maintenance of low-voltage power distribution equipment.

[0104] In some embodiments, this application further proposes an early warning module for generating early warning information based on a comprehensive diagnostic report and providing it to operation and management personnel or a monitoring platform.

[0105] Generating early warning information refers to converting the anomaly level, fault type, and recommended measures in the comprehensive diagnostic report into identifiable alarm signals. Specifically, this can be achieved by configuring early warning strategies based on a rule engine, such as setting different alarm levels according to the temperature rise rate and coupling contribution threshold.

[0106] Providing warning information to operation and management personnel or monitoring platforms refers to transmitting and displaying warning information through standardized interfaces. Specifically, this can be achieved by connecting to the monitoring system via API interfaces or by pushing the warning information to mobile terminals via message queues. For example, warning information can be pushed to the smart terminals of operation and maintenance personnel in real time via the MQTT protocol.

[0107] Specifically, when the comprehensive diagnostic report output by the status analysis module 14 contains information about abnormal operating status of key components, the early warning module automatically generates early warning information according to preset alarm rules. For example, when the cumulative contribution of a cable joint exceeds a safety threshold and the induced intensity reaches a high-risk level, the early warning module generates a red alarm with maintenance recommendations. The early warning information is transmitted to the power distribution monitoring platform through a standardized interface. The platform distributes the alarm information to the mobile terminals of relevant maintenance personnel and triggers the work order system to generate maintenance tasks. The early warning module supports multi-level alarm strategies, such as a yellow alarm to alert attention to potential risks, an orange alarm to initiate an automatic inspection program, and a red alarm to directly trigger the circuit breaker to perform emergency tripping.

[0108] This solution, through multi-dimensional indicators such as coupling contribution and induction intensity in the comprehensive diagnostic report, can distinguish between instantaneous anomalies and cumulative risks, and dynamically adjust the alarm level. Furthermore, existing technologies typically display alarm information through a fixed interface, lacking automated linkage with operation and maintenance processes. This solution, however, achieves seamless integration of early warning information with work order systems and mobile terminals through standardized interfaces.

[0109] Through the above technical solution, this application can achieve accurate hierarchical early warning based on the results of dynamic coupling analysis, thus shortening the fault response time. For example, in scenarios where abnormal temperature rise occurs at cable joints due to dust accumulation and current harmonic coupling, the early warning module can identify the cumulative risks caused by the coupling effect in advance and trigger an early warning before the temperature rise rate reaches a critical value, preventing insulation breakdown accidents. Simultaneously, the automated linkage between early warning information and operation and maintenance processes can reduce delays caused by manual intervention and ensure timely execution of maintenance measures.

[0110] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A low-voltage power distribution equipment operation status monitoring system, characterized in that, include: The data acquisition module is used to deploy multimodal sensing units on key node equipment of low-voltage power distribution equipment. The multimodal sensing units are used to collect electrical parameters and environmental parameters of low-voltage power distribution equipment. The data processing module is used to perform timestamp calibration and validity verification on the electrical parameters and environmental parameters of the low-voltage power distribution equipment, and to form a structured and spatiotemporally correlated real-time data sequence. The parameter fusion analysis module is used to spatially associate and bind the electrical parameters of the same key point in the real-time data sequence with the associated environmental parameters of the same key point based on a preset physical location topology. The parameters are then input into the constructed dynamic coupling model to obtain the coupling analysis results. The coupling analysis results include at least one of the following: the contribution of environmental parameter changes to the temperature rise of key node equipment, the induction intensity of electrical parameter anomalies to the environmental temperature rise, and other abnormal coupling information. The status analysis module is used to dynamically evaluate the operating status of key components in key node equipment based on a preset equipment health model and aging knowledge base, combined with the coupling analysis results, and output a comprehensive diagnostic report. The parameter fusion analysis module includes: The influence quantization unit is used to perform control variable simulation calculations on the dynamic coupling model. By replacing specific input variables with preset reference values ​​and observing the changes in output variables, it calculates the contribution of environmental parameter changes to the temperature rise of key node equipment, and / or the inducing intensity of abnormal electrical parameters on the environmental temperature rise. The collaborative trend analysis unit is used to construct a multivariate feature vector containing electrical parameters, environmental parameters, influence contribution and / or induced intensity based on the output of the influence quantification unit, and to analyze the collaborative change trend of the multivariate feature vector using a multivariate statistical process control method to identify abnormal coupling information. The influence quantization unit includes: The influence contribution quantification subunit is used for: Substitute the current electrical parameter values ​​into the dynamic coupling model, and replace the environmental parameter values ​​of the dynamic coupling model with standard reference values ​​to obtain the first predicted temperature rise rate; Calculate the first difference between the current actual temperature rise rate and the first predicted temperature rise rate; Based on the first difference, determine the contribution of the change in the environmental parameters to the temperature rise; The influence contribution quantification subunit, when determining the contribution of the environmental parameter change to the temperature rise based on the first difference, is specifically used for: Construct a sensitivity factor matrix for equipment differentiation; the sensitivity factor matrix is ​​established based on the sensitivity coefficients of different key node equipment to environmental parameters, and the sensitivity coefficients are dynamically adjusted in combination with the equipment's operating years; The coupling effect between environmental parameters is quantified. A coupling coefficient matrix of environmental parameter combinations is constructed based on historical fault data. The individual contribution components of each environmental parameter and the total environmental contribution after coupling amplification are calculated in combination with the sensitivity factor matrix. A cumulative effect model in the time dimension is established, and the instantaneous contribution and cumulative contribution are distinguished and nonlinearly superimposed to obtain the influence contribution. The process of obtaining the instantaneous contribution includes: The instantaneous contribution is obtained by multiplying the total environmental contribution by the time decay coefficient; wherein, the time decay coefficient is related to the rate of change of environmental parameters. The faster the rate of change of environmental parameters, the larger the value of the time decay coefficient, and the maximum value is a first preset value. The process of obtaining the cumulative contribution includes: The cumulative contribution is obtained by integrating the product of the total environmental contribution and the time accumulation coefficient over time; wherein the time accumulation coefficient satisfies the following: for every additional preset duration of continuous exceedance of environmental parameters, the first preset proportion is increased, and the upper limit is a second preset value.

2. The low-voltage power distribution equipment operation status monitoring system according to claim 1, characterized in that, The influence contribution quantification subunit is also used for: Based on historical fault data, the correlation between environmental parameter combinations and temperature rise anomalies is mined, and a binary coupling coefficient is established. When all binary coupled environmental parameter combinations exceed their respective preset thresholds, the binary coupling coefficient is greater than 1, and when only one of the binary coupled environmental parameter combinations exceeds its respective preset threshold, the binary coupling coefficient is equal to 1. Calculate the second difference between the actual value and the standard value of each environmental parameter, and calculate the product of the second difference and the sensitivity coefficient of the corresponding key node equipment as the individual contribution component of each environmental parameter; The individual contribution components of all environmental parameters are summed to obtain the first sum value; For each parameter pair with a coupling relationship, the individual contribution components of the two environmental parameters in each parameter pair are multiplied together, and then multiplied by the binary coupling coefficient between the two environmental parameters in each parameter pair. The calculation results of all parameter pairs with a coupling relationship are summed to obtain a second sum. The first sum and the second sum are added together to obtain the total environmental contribution.

3. The low-voltage power distribution equipment operation status monitoring system according to claim 1, characterized in that, The influence contribution quantification subunit is also used for: By simulating different environmental conditions in the experimental chamber, the temperature rise curves of various key node devices were tested, and the sensitivity coefficients for different environmental parameters were extracted. An aging correction coefficient is calculated based on the equipment's operating years, and the sensitivity coefficient is dynamically corrected to construct the sensitivity factor matrix; wherein, for every preset increase in the operating years, the sensitivity coefficient increases by a second preset ratio.

4. The low-voltage power distribution equipment operation status monitoring system according to claim 1, characterized in that, The influence quantization unit includes: The induced intensity quantization subunit is used to substitute the current environmental parameter values ​​into the dynamic coupling model and replace the current harmonic content with zero or standard limit values ​​to obtain the second predicted temperature rise rate. Calculate the second difference between the current actual temperature rise rate and the second predicted temperature rise rate; Based on the second difference, the induced intensity of the current harmonic content on the temperature rise is determined.

5. The low-voltage power distribution equipment operation status monitoring system according to claim 1, characterized in that, The collaborative trend analysis unit is specifically used for: The normal statistical distribution space of the multivariate feature vectors under the health state of the equipment is constructed based on principal component analysis; Real-time calculation of T in the normal statistical distribution space of the feature vector of the multivariate to be identified 2 The T statistic and / or SPE statistic; wherein, the T 2 The statistic measures the degree of change of a new sample within the normal hyperplane relative to the model center, and is used to capture the co-variation among dominant variables; the SPE statistic measures the magnitude of the residual generated after the new sample is projected onto the normal hyperplane, i.e. the distance from the normal model, and is used to capture anomalies in non-dominant variables or new patterns. When the T 2 If the statistical quantity and / or the SPE statistical quantity exceed the preset control limit, it is determined that there is an abnormal coupling phenomenon.

6. The low-voltage power distribution equipment operation status monitoring system according to any one of claims 1-5, characterized in that, Also includes: The early warning module is used to generate early warning information based on the comprehensive diagnostic report and provide it to operation and management personnel or monitoring platforms.

Images