Power distribution cabinet thermal fault early warning method, device and equipment

Abstract

The application relates to the technical field of power equipment fault detection, in particular to a power distribution cabinet thermal fault early warning method, device and equipment, which comprises the following steps: acquiring environment temperature data and time sequence parameters of a connection point of a power distribution cabinet; calculating temperature change rate, current change rate and current average value of the time sequence parameters in a preset time period, and constructing a temperature-current response model to obtain a current response coefficient; constructing a time delay cross-correlation function based on temperature change and current square to obtain a delay time with the largest correlation coefficient; calculating a response lag coefficient based on the delay time, the current change rate and the current average value; when the response lag coefficient is not in a threshold range, verifying the change direction of the temperature change rate and the current change rate; when the verification result is temperature rise and the current does not rise synchronously, determining a thermal fault precursor mode, and generating a hierarchical early warning information, which has the advantages of early identification of the thermal fault precursor of the power distribution cabinet and improvement of early warning timeliness.

Description

Technical Field

[0001] This application relates to the field of power equipment fault detection technology, and in particular to a method, device and equipment for early warning of thermal faults in distribution cabinets. Background Technology

[0002] As a critical node in the power distribution system, the operational reliability of the distribution cabinet directly affects the overall power supply safety and equipment lifespan. In actual operation, due to poor electrical connections, oxidation and loosening of wiring terminals, and abnormally increased contact resistance at busbar joints, localized overheating faults are easily triggered inside the distribution cabinet. The typical characteristics of these faults are low initial heat generation and slow temperature rise, making them highly concealed and difficult to detect by conventional overcurrent protection devices. As heat continues to accumulate, the contact resistance increases positively due to thermal expansion and accelerated oxidation, leading to a further increase in local temperature. Ultimately, this can cause insulation material aging and failure, phase-to-phase short circuits, or even electrical fires, seriously threatening the safe and stable operation of the power system.

[0003] Currently, the mainstream technical solution for online monitoring of overheating faults inside distribution cabinets is to install temperature sensors or use non-contact infrared temperature measurement modules at key connection points or busbar joints, set an absolute temperature threshold or a relative temperature rise threshold, and trigger an alarm when the measured temperature exceeds the preset threshold to prompt maintenance personnel to intervene.

[0004] However, the above-mentioned solutions have significant drawbacks in practical applications: overheating caused by poor contact inside the distribution cabinet is a slow and cumulative process. It often takes several hours or even days for the temperature to rise to the threshold from the initial slight abnormality in contact resistance. During this period, the temperature remains in a latent state of abnormality but has not yet reached the threshold. The existing threshold alarm mechanism only compares instantaneous values ​​and cannot identify the early slow temperature rise trend. It cannot issue a warning in the early stage of the fault. Maintenance personnel find it difficult to know the potential risks in time. Often, by the time the threshold is triggered, the fault has already developed to a more serious extent, which can easily cause maintenance delays or even power outages or safety accidents. Summary of the Invention

[0005] This application provides a method, apparatus, and equipment for early warning of thermal faults in power distribution cabinets, which can identify early signs of thermal faults in power distribution cabinets and improve the timeliness of early warning.

[0006] On one hand, embodiments of this application provide a method for early warning of thermally induced faults in power distribution cabinets, including: Acquire ambient temperature data and timing parameters of connection points for the power distribution cabinet, wherein the timing parameters include temperature data and current data; Calculate the rate of change of temperature, rate of change of current, and average current of time-series parameters within a preset time period; Based on the temperature change rate, current data, ambient temperature data, and current change rate, a temperature response model to current is constructed to obtain the current response coefficient. Based on the temperature change and current square within the preset time period, a time delay cross-correlation function is constructed to obtain the delay time with the largest correlation coefficient. The response hysteresis coefficient is calculated based on the delay time, the rate of change of current, and the average current value. The response hysteresis coefficient is used to characterize the degree of thermal response hysteresis. The response hysteresis coefficient is compared with the corresponding threshold range. If the response hysteresis coefficient is not within the threshold range, the direction of change of temperature change rate and current change rate is verified to obtain the verification result. When the verification result shows that the temperature rises but the current does not rise synchronously, it is determined to be a thermal fault precursor mode, and graded early warning information is generated based on the current response coefficient and response hysteresis coefficient.

[0007] Furthermore, the construction of the temperature-current response model based on the temperature change rate, current data, ambient temperature data, and current change rate includes: Based on the formula: Construct a temperature response model to current; in, I represents the rate of temperature change, and I represents the current data. Tp is the rate of change of current, and Tp is the temperature data at the connection point. amb Here, α represents the ambient temperature data, β represents the current response coefficient, β represents the Joule thermal steady-state coefficient, γ represents the heat dissipation condition coefficient, and ε represents the residual.

[0008] Furthermore, the calculation of the response hysteresis coefficient based on the delay time, the rate of change of current, and the average current includes: Based on the formula: Calculate the response lag factor; Where L is the response lag coefficient, t max I is the delay time, RMS(dI / dt) is the effective value of the rate of change of current, and I avg This represents the average current.

[0009] Furthermore, determining the threshold range includes: The current load rate is calculated based on the current data and the rated current of the distribution cabinet; Obtain the response lag coefficient sequence within a preset historical time period; The threshold range is determined using an adaptive quantile algorithm based on the current load rate, ambient temperature data, and response hysteresis coefficient sequence. The adaptive quantile algorithm includes: selecting historical response lag coefficients that match the current load rate and ambient temperature from the response lag coefficient sequence, and using the preset quantile of the selected historical response lag coefficients as the current threshold range.

[0010] Furthermore, the generation of graded early warning information based on the current response coefficient and the response hysteresis coefficient includes: If the response hysteresis coefficient exceeds the threshold range but the degree of exceeding the threshold is less than the first preset value, and the increase in the current response coefficient is less than the second preset value, a first-level warning message is generated. If the response hysteresis coefficient exceeds the threshold range and the degree of exceeding the threshold reaches a first preset value, or if the rise of the current response coefficient reaches a second preset value, a secondary warning message is generated. If the response hysteresis coefficient exceeds the threshold range and the degree of exceeding the threshold reaches the third preset value, and the temperature change rate exceeds the preset rate threshold, a level three warning message is generated. Among them, Level 3 early warning information has a higher priority than Level 2 early warning information. Level 2 early warning information has a higher priority than Level 1 early warning information.

[0011] Furthermore, the verification of the direction of change of the temperature change rate and the current change rate includes: Obtain the symbolic sequences of temperature change rate and current change rate at multiple sampling moments within the preset time period; If the proportion of consecutive positive signs in the temperature change rate symbol sequence exceeds the first symbol threshold, and the proportion of consecutive non-positive signs in the current change rate symbol sequence exceeds the second symbol threshold, the verification result is that the temperature rises but the current does not rise synchronously. If the proportion of identical symbols in the temperature change rate symbol sequence and the current change rate symbol sequence exceeds the third symbol threshold, the verification result is that the temperature and current change synchronously.

[0012] Furthermore, after determining that it is a precursor mode to a thermally induced failure, the following steps are also included: The current response coefficient and the response hysteresis coefficient are mapped to a feature point in a two-dimensional feature plane; Calculate the Mahalanobis distance between the feature point and multiple preset fault mode center points, wherein the fault mode center points include the contact loosening mode center, the conductor oxidation mode center, and the heat dissipation blockage mode center; The fault type is determined based on the fault mode center point with the minimum Mahalanobis distance, and the fault type is added to the graded early warning information.

[0013] Furthermore, after calculating the response hysteresis coefficient based on the delay time, current change rate, and average current, the method further includes: Calculate the average response hysteresis coefficient of all connection points; Calculate the relative deviation of the response hysteresis coefficient of each connection point from the average value; If the relative deviation of any connection point exceeds a preset deviation threshold, the corresponding connection point is identified as an abnormal connection point, and the location information of the abnormal connection point is extracted. Add the location information to the graded early warning information.

[0014] On the other hand, embodiments of this application provide an early warning device for thermally induced faults in power distribution cabinets, the device comprising: The acquisition module is used to acquire ambient temperature data of the power distribution cabinet and timing parameters of at least one connection point, wherein the timing parameters include temperature data and current data. The first calculation module is used to calculate the temperature change rate, current change rate, and average current of the time sequence parameters within a preset time period. The first construction module is used to construct a temperature response model to current based on the temperature change rate, current data, ambient temperature data, and current change rate, and to obtain the current response coefficient. The second construction module is used to construct a time delay cross-correlation function based on the temperature change and current square within the preset time period, and obtain the delay time with the largest correlation coefficient. The second calculation module is used to calculate the response hysteresis coefficient based on the delay time, current change rate and average current, and the response hysteresis coefficient is used to characterize the degree of thermal response hysteresis. The comparison module is used to compare the response hysteresis coefficient with the corresponding threshold range. If the response hysteresis coefficient is not within the threshold range, the direction of change of the temperature change rate and the current change rate is verified to obtain the verification result. The determination generation module is used to determine a thermal fault precursor mode when the verification result shows that the temperature rises but the current does not rise synchronously, and to generate graded early warning information based on the current response coefficient and the response hysteresis coefficient.

[0015] In another aspect, embodiments of this application provide an electronic device, the device comprising: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements any one of the following methods for early warning of thermal faults in a power distribution cabinet.

[0016] This application discloses a method, apparatus, and device for early warning of thermally induced faults in a power distribution cabinet. By acquiring the timing parameters and ambient temperature data of the cabinet's connection points and calculating key characteristic quantities such as temperature change rate and current change rate, it can characterize and dynamically track the slow temperature rise trend caused by poor contact. This avoids the inherent defects of existing technologies that rely solely on instantaneous temperature threshold comparisons and cannot identify early latent faults. By constructing a temperature-current response model and calculating the current response coefficient, it can effectively distinguish between temperature changes caused by normal load fluctuations and heat accumulation characteristics caused by abnormal contact, thereby improving the early warning of faults to a certain extent. The accuracy of fault precursor identification is improved by calculating the response hysteresis coefficient based on the time delay cross-correlation function and combining it with the direction verification of temperature change rate and current change rate. When the temperature rises abnormally but the current does not rise synchronously, the thermal fault precursor mode can be determined. Thus, a graded early warning message can be issued before the temperature reaches the alarm threshold, realizing early alarm in the fault initiation stage. This allows operation and maintenance personnel to understand the deterioration trend of the internal connection status of the distribution cabinet in advance, arrange inspection or maintenance in a timely manner, and avoid unplanned power outages or safety accidents caused by the fault developing into a serious stage such as short circuit or fire. This improves the reliability of the power distribution system and reduces operation and maintenance costs. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating an early warning method for thermally induced faults in a power distribution cabinet, as shown in the embodiments of this application. Figure 2 This is a structural block diagram illustrating an early warning device for thermally induced faults in a power distribution cabinet, as shown in the embodiments of this application. Figure 3 This is a structural block diagram illustrating an electronic device in the embodiments of this application. Detailed Implementation

[0018] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0019] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0020] Existing overheating fault monitoring solutions for distribution cabinets primarily rely on setting absolute or relative temperature rise thresholds for alarms. However, overheating faults within the distribution cabinet caused by poor contact, oxidation and loosening of wiring terminals, or abnormally increased contact resistance at busbar connections are a slow, cumulative process. Initially, the heat generated is small, the temperature rise is slow, and it is highly concealed, making it difficult for conventional overcurrent protection devices to detect. Existing threshold alarm mechanisms only compare instantaneous values ​​and cannot identify early, slow temperature rise trends, resulting in difficulty in warning of faults in their nascent stages. Maintenance personnel often only become aware of the potential risks when the fault has progressed to a more severe stage, easily causing maintenance delays and even power outages or safety accidents.

[0021] To address the problems of existing technologies, embodiments of this application provide a method, apparatus, and device for early warning of thermally induced faults in power distribution cabinets. The following section first describes the method for early warning of thermally induced faults in power distribution cabinets provided by embodiments of this application.

[0022] Figure 1 This illustration shows a flowchart of an early warning method for thermally induced faults in a power distribution cabinet according to an embodiment of this application. Figure 1 As shown in the embodiment of this application, a method for early warning of thermally induced faults in a power distribution cabinet includes the following steps: S101. Obtain the ambient temperature data and timing parameters of the connection points of the power distribution cabinet. The timing parameters include temperature data and current data.

[0023] In this embodiment, an ambient temperature sensor, such as a thermistor or thermocouple, is installed outside the distribution cabinet to obtain ambient temperature data. Contact temperature sensors and current sensors are installed at key electrical connection points inside the distribution cabinet to obtain temperature and current data at the connection points in real time. The electrical connection points include, but are not limited to, busbar joints, circuit breaker terminals, cable crimps with switchgear or terminal blocks, fuse terminals, disconnecting switches, contactor terminals, and wire connection points on secondary circuit terminal blocks. In this embodiment, the temperature sensor can be a PT100 temperature sensor, a resistance temperature detector (RTD), or a thermocouple, and the current sensor can be a Hall effect sensor. Current data can also be obtained from smart meters or power monitoring systems, and there are no specific limitations on this.

[0024] S102. Calculate the temperature change rate, current change rate, and average current of the time sequence parameters within the preset time period. In this embodiment, the temperature change rate can be obtained by differential calculation of the temperature data of continuously collected connection points. For example, the temperature difference between two adjacent sampling times can be divided by the time interval, or the temperature sequence can be smoothed by moving average, Kalman filtering, etc., before differentiation calculation. There is no specific limitation on this. The current change rate can be calculated by dividing the difference between the current value at the current sampling time and the current value at the previous sampling time by the sampling time interval. It can also be calculated by digital filtering and differentiation of the current signal. There is no specific limitation on this. The average current value is calculated by averaging all current sampling values ​​within a preset time period.

[0025] It should be noted that the preset time period can be determined by a reference thermal time constant or sampling period, and can also be dynamically adjusted. For example, for the reference thermal time constant, select 1 / 3 to 1 / 2 of the thermal time constant of the distribution cabinet, such as 5 to 10 minutes. The reference thermal time constant can be estimated by consulting a manual, theoretical calculation, or on-site measurement. For the sampling period, it should include at least 10 to 20 sampling points to ensure stable calculation of the rate of change. For dynamic adjustment, when the current fluctuates greatly, shorten the time period, such as 2 minutes, and when the current is stable, extend it to 15 minutes.

[0026] S103. Based on the temperature change rate, current data, ambient temperature data, and current change rate, construct a temperature response model to current to obtain the current response coefficient.

[0027] Specifically, based on the formula: Construct a temperature-current response model; where, I represents the rate of temperature change, and I represents the current data. Tp is the rate of change of current, and Tp is the temperature data at the connection point. ambHere, α represents the ambient temperature data, β represents the current response coefficient, β represents the Joule thermal steady-state coefficient, γ represents the heat dissipation condition coefficient, and ε represents the residual.

[0028] Among them, the temperature change rate is used to represent how quickly the temperature at the connection point changes over time; I represents the current flowing through the connection point, which is the direct cause of the connection point's heating; the current change rate is used to reflect the trend and speed of the instantaneous change in current; I∙dI / dt is used to capture the instantaneous effect of current changes on the temperature response; I 2 This is used to quantify the continuous heat generated by the current passing through the resistor at the connection point under steady-state or quasi-steady-state operating conditions; the temperature data of the connection point is the actual operating temperature of the key connection point inside the distribution cabinet; the ambient temperature data is the ambient temperature around the distribution cabinet, which has a significant impact on the heat dissipation conditions of the connection point.

[0029] In this embodiment, the current response coefficient is used to quantify the contribution of the current dynamic term I∙dI / dt to the rate of temperature change, reflecting the sensitivity of the connection point to transient changes in current; the Joule thermal steady-state coefficient is used to quantify the Joule thermal term I. 2 The contribution of the temperature change rate to reflect the heating characteristics of the connection point under steady-state current; the heat dissipation condition coefficient is used to quantify the temperature difference T between the connection point and the environment. p -T amb The contribution of the temperature change rate to reflect the heat dissipation capacity of the connection point; the residual represents the random error, measurement noise, or unmodeled complex factors in the temperature-current response model.

[0030] in, The equation is a linear regression equation. The current response coefficient, Joule thermal steady-state coefficient, and heat dissipation condition coefficient are calculated using least squares.

[0031] In this embodiment, a temperature-current response model is constructed by using the Joule heating effect, current dynamic change term, and environmental heat dissipation conditions. This comprehensively captures various factors affecting the temperature change of the connection point. The temperature-current response model can quantify the dynamic characteristics of the thermal response, solving the shortcomings of traditional models in integrating current dynamic changes, heat dissipation conditions, and ambient temperature. To a certain extent, it improves the accuracy of the temperature-current response, thereby reflecting the actual thermal behavior of the connection point. This allows for timely identification even if the temperature rise is slow in the early stage of a fault, thus providing a timely and reliable basis for early warning of thermal faults in the distribution cabinet.

[0032] S104. Construct a time delay cross-correlation function based on temperature change and current square within a preset time period to obtain the delay time with the largest correlation coefficient.

[0033] Within a preset time period, for example, within 10 minutes, temperature sequence T(k) and current sequence I(k) are collected at a sampling interval of Δt = 1 second, for a total of N points.

[0034] Construct a temperature change sequence: ΔT(i) = T(i) - T(i-1), i = 1, 2, 3, ..., N; Construct the excitation sequence: Q(k) = [I(k)] 2 k=1,2,3,...,N; Time-delay cross-correlation function: R(τ) ; Wherein, τ is the delay step, and the value of τ is in the range of [-M, M]. M is set according to the actual thermal inertia, and in this embodiment, it is one-third of the number of sampling points.

[0035] In this embodiment, all delay steps are traversed to determine τ∗, which maximizes R(τ), where τ∗ is the delay step and the delay time = τ∗∙T. s T s This represents the sampling time interval.

[0036] S105. Calculate the response hysteresis coefficient based on the delay time, current change rate, and average current value. The response hysteresis coefficient is used to characterize the degree of thermal response hysteresis.

[0037] Specifically, based on the formula: Calculate the response lag factor; where L is the response lag factor, t max I is the delay time, RMS(dI / dt) is the effective value of the rate of change of current, and I avg This represents the average current.

[0038] In this embodiment, the response hysteresis coefficient is used to characterize the degree of thermal response hysteresis at the connection point of the distribution cabinet, reflecting the response speed and sensitivity of the connection point to current changes in temperature. When an anomaly occurs at the connection point, the thermal inertia changes, thereby exacerbating the degree of thermal response hysteresis and increasing the response hysteresis coefficient accordingly. In this embodiment, the instantaneous current change rate is obtained by differential calculation of the collected current data. The effective value of the current change rate is obtained by calculating the root mean square value of these instantaneous change rates within a preset time period. For example, the current change rate within each window is calculated using the sliding window method, and the sum of the squares and the square root average is taken. The average current is the average current flowing through the connection point within the preset time period, used to reflect the average load level of the connection point. For example, it is determined by calculating the average value of all current samples within the preset time period.

[0039] After calculating the response hysteresis coefficient based on the delay time, current change rate, and average current, the method further includes: calculating the average response hysteresis coefficient of all connection points; calculating the relative deviation of the response hysteresis coefficient of each connection point from the average value; if the relative deviation of any connection point exceeds a preset deviation threshold, designating the corresponding connection point as an abnormal connection point and extracting the location information of the abnormal connection point; and adding the location information to the hierarchical early warning information.

[0040] In this embodiment, the average response hysteresis coefficient can be obtained by calculating the average response hysteresis coefficient of all connection points, that is, summing and dividing by the total number of connection points; alternatively, different weights can be assigned to the response hysteresis coefficients of different connection points according to factors such as the importance of the connection points and historical failure rate, and a weighted average can be performed, without specific limitations.

[0041] In this embodiment, the relative deviation can be calculated by dividing the difference between the response hysteresis coefficient of each connection point and the average value by the average value to obtain the percentage deviation; or the absolute value of the difference between the response hysteresis coefficient of each connection point and the average value can be calculated and then divided by the average value. There is no specific limitation on this method.

[0042] In this embodiment, the preset deviation threshold can be determined based on historical data, expert experience, or system operation requirements. For example, the preset deviation threshold can be a fixed percentage value, such as 10% or 20%, or it can be determined by statistical analysis methods, such as the 3σ principle based on standard deviation. There are no specific limitations on this. When an abnormal connection point is identified, the corresponding location information is extracted. The location information can be the unique identifier of the connection point, its physical coordinates in the distribution cabinet, its circuit number, or a corresponding mark on the electrical drawing. The location information can be added as part of the text content of the warning message, or the abnormal connection point can be highlighted on the visualization interface. There are no specific limitations on this.

[0043] When the response hysteresis coefficients of all connection points exceed the preset deviation threshold, the deviation between the current average response hysteresis coefficient and the historical average during normal periods is calculated. If the deviation also exceeds the preset global deviation threshold, it is determined that the distribution cabinet has overall thermal response degradation.

[0044] In this embodiment, by calculating the average response hysteresis coefficient of all connection points, the thermal response hysteresis of each connection point is compared with the current overall operating status. This avoids interference from general fluctuations caused by overall load changes or environmental factors on the judgment of local anomalies. By calculating the relative deviation of the response hysteresis coefficient of each connection point from the average value, the deviation of the local connection point from the overall average level is quantified, rather than simply relying on a preset absolute threshold. This allows for earlier and more accurate detection of the nascent local anomalies. When the relative deviation of any connection point exceeds the preset deviation threshold, the connection point is identified as an abnormal connection point, and its location information is extracted and added to the hierarchical early warning information. This ensures that the early warning information not only indicates the existence of potential faults but also clarifies the specific location of the fault.

[0045] S106. Compare the response hysteresis coefficient with the corresponding threshold range. If the response hysteresis coefficient is not within the threshold range, verify the direction of change of temperature change rate and current change rate, and obtain the verification result.

[0046] The determination of the threshold range includes: calculating the current load rate based on current data and the rated current of the distribution cabinet; obtaining the response lag coefficient sequence within a preset historical time period; and determining the threshold range using an adaptive quantile algorithm based on the current load rate, ambient temperature data, and the response lag coefficient sequence. The adaptive quantile algorithm includes: selecting historical response lag coefficients that match the current load rate and ambient temperature from the response lag coefficient sequence, and using the preset quantile of the selected historical response lag coefficients as the current threshold range.

[0047] In this embodiment, the current load rate is an indicator for measuring the real-time operating intensity of the distribution cabinet. The current load rate can be determined by dividing the average current value at the current moment or within a short period of time by the rated current value of the distribution cabinet, or it can be determined by comparing the weighted average of the instantaneous current with the rated current. No specific limitation is made in this regard.

[0048] The response lag coefficient sequence is a set of historical response lag coefficients obtained through long-term monitoring and calculation under different operating conditions. The adaptive quantile algorithm is used to dynamically adjust the threshold so that it can adapt to changes in the operating environment of the distribution cabinet. For example, after filtering out a subset of historical response lag coefficients that match the current operating conditions, a preset quantile of the historical response lag coefficient subset is calculated, such as the 95th percentile or the 99th percentile as the upper limit of the threshold range. Alternatively, an interval can be calculated, such as the 5th percentile to the 95th percentile as the threshold range.

[0049] In this embodiment, the threshold range is determined by using the current load rate, ambient temperature data, and historical response lag coefficient sequence, and an adaptive quantile algorithm is used. This allows the threshold range to reflect the normal fluctuation range under the current operating conditions in real time and accurately, thereby improving the accuracy and reliability of the early warning to a certain extent. It avoids misjudgment or missed warnings caused by the threshold setting deviating from the actual operating conditions, thus issuing early warnings at the incipient stage of thermal faults and ensuring the safe and stable operation of the power system.

[0050] The verification of the direction of change of temperature and current change rates includes: acquiring a symbol sequence of temperature change rate and a symbol sequence of current change rate at multiple sampling times within a preset time period; if the proportion of consecutive positive symbols in the temperature change rate symbol sequence exceeds a first symbol threshold, and the proportion of consecutive non-positive symbols in the current change rate symbol sequence exceeds a second symbol threshold, the verification result is that the temperature rises but the current does not rise synchronously; if the proportion of identical symbols in the temperature change rate symbol sequence and the current change rate symbol sequence exceeds a third symbol threshold, the verification result is that the temperature and current change synchronously.

[0051] In this embodiment, obtaining the temperature change rate symbol sequence and current change rate symbol sequence at multiple sampling moments within a preset time period is to transform continuous temperature change rate and current change rate data into discrete trend representations, i.e., rising, falling, or stable. In this embodiment, the temperature change rate at each sampling moment is judged. If its value is greater than zero, it is recorded as positive; if it is less than zero, it is recorded as negative; if it fluctuates or equals zero within a preset short time window, such as within 1 second or 2 seconds, it is recorded as zero. The positive, negative, and zero values ​​are arranged in chronological order to form the temperature change rate symbol sequence. The current change rate symbol sequence is generated in the same way. For the generation of symbols, the difference between adjacent sampling points can also be calculated, and the symbol is determined according to the positive or negative value of the difference, thereby constructing the temperature change rate symbol sequence and the current change rate symbol sequence.

[0052] The percentage of consecutive positive signs is the proportion of sampling points with consecutive positive signs in the temperature change rate symbol sequence out of the entire sequence length. For example, when the sequence length is 100 and the longest consecutive positive sign segment is 60, the proportion is 60%. When this proportion exceeds the first symbol threshold, it indicates that the upward trend of temperature is continuous and significant, rather than an occasional instantaneous fluctuation. The percentage of consecutive non-positive signs is the proportion of sampling points with consecutive non-positive signs in the current change rate symbol sequence out of the entire sequence length. Non-positive signs include negative signs or zero signs. When this proportion exceeds the second symbol threshold, it indicates that the current is not trending upward, i.e., it is decreasing. The temperature change rate symbol sequence can be stable, continuous, and significant. In this embodiment, the total length of all consecutive positive subsequences in the temperature change rate symbol sequence is calculated and compared with the total number of sampling points in the entire preset time period. Similarly, the total length of all consecutive non-positive subsequences in the current change rate symbol sequence is calculated and compared. When these two statistical values ​​meet their respective threshold conditions, it can be determined that the temperature is rising but the current is not rising synchronously. Alternatively, a sliding window method can be used to calculate the ratio of positive and non-positive symbols in each window and perform a weighted average of these ratios to further emphasize recent or continuous trends, thereby improving the sensitivity and accuracy of the determination.

[0053] In this embodiment, when the trends of temperature and current change remain consistent for most of the time, that is, when the symbol sequences of temperature change rate and current change rate are the same at most sampling points, they are determined to change synchronously. For example, the symbol sequences of temperature change rate and current change rate are compared point by point, the number of sampling points with the same symbols is counted, and the proportion of this number to the total number of sampling points is calculated. When this proportion exceeds a preset third symbol threshold, it can be determined that temperature and current change synchronously. The cross-correlation coefficient between the two symbol sequences can also be calculated. When the cross-correlation coefficient reaches a preset threshold, it indicates that the two have a high degree of synchronicity, and thus are determined to change synchronously.

[0054] The first symbol threshold, the second symbol threshold, and the third symbol threshold are set as needed. For example, the first symbol threshold can be in the range of 0.6 to 0.8, the second symbol threshold can be in the range of 0.6 to 0.8, and the third symbol threshold can be in the range of 0.7 to 0.9.

[0055] In this embodiment, the temperature change rate symbol sequence and the current change rate symbol sequence are obtained to capture the continuity of temperature and current change trends, thereby avoiding misjudgments caused by instantaneous fluctuations. When the proportion of consecutive positive symbols in the temperature change rate symbol sequence exceeds the first symbol threshold, it indicates that the temperature rise is continuous and significant, enhancing the reliability of temperature change trend determination. When the proportion of consecutive non-positive symbols in the current change rate symbol sequence exceeds the second symbol threshold, it ensures that the state of asynchronous current rise is continuous rather than a brief fluctuation. Through the dual-condition combination verification mechanism, the abnormal mode of temperature rise without synchronous current rise can be identified, thereby effectively distinguishing the precursors of thermal faults. By judging whether the proportion of the same symbols in the temperature change rate symbol sequence and the current change rate symbol sequence exceeds the third symbol threshold, the synchronous changes of temperature and current under normal operating conditions can be identified, thereby reducing the possibility of false alarms.

[0056] S107. When the verification result shows that the temperature rises but the current does not rise synchronously, it is determined to be a thermal fault precursor mode, and graded early warning information is generated based on the current response coefficient and the response hysteresis coefficient.

[0057] The system generates tiered early warning information based on the current response coefficient and response hysteresis coefficient, including: generating a Level 1 early warning when the response hysteresis coefficient exceeds a threshold range but the degree of exceeding the threshold is less than a first preset value, and the increase in the current response coefficient is less than a second preset value; generating a Level 2 early warning when the response hysteresis coefficient exceeds a threshold range and the degree of exceeding the threshold reaches the first preset value, or the increase in the current response coefficient reaches the second preset value; and generating a Level 3 early warning when the response hysteresis coefficient exceeds a threshold range and the degree of exceeding the threshold reaches a third preset value, and the temperature change rate exceeds a preset rate threshold. The Level 3 early warning has a higher priority than the Level 2 early warning. The Level 2 early warning has a higher priority than the Level 1 early warning.

[0058] The threshold range can be determined based on statistical methods, such as calculating the mean and standard deviation of historical data to set a confidence interval, or it can be determined based on expert experience such as equipment type, operating environment and safety standards. The degree of exceeding the threshold is a quantitative indicator of the response lag coefficient exceeding the threshold range. In this embodiment, the degree of exceeding the threshold is the absolute difference between the current value of the response lag coefficient and the upper limit of the threshold.

[0059] The first preset value is a critical value used to define the degree of exceeding the threshold, corresponding to the judgment standard of minor abnormality or initial failure. The first preset value can be determined based on the analysis of historical failure data. For example, by statistically analyzing a large amount of normal operation and initial failure data, the best threshold to distinguish between the two can be found. It can also be set according to the equipment manufacturer's recommendations or industry safety specifications.

[0060] In this embodiment, the rise amplitude is the amount or rate of change of the current response coefficient over a period of time. The rise amplitude is the difference between the current current response coefficient and a certain benchmark value, such as the historical average, the initial normal value, or the value at the previous moment. It can also be its rate of change per unit time. The second preset value is a critical value used to define the rise amplitude of the current response coefficient, corresponding to the judgment standard that the fault has developed to a certain extent. The second preset value can be adjusted according to factors such as equipment type, operating environment, and fault evolution speed to ensure that a higher level of early warning can be triggered in a timely manner when the fault deteriorates to a certain extent.

[0061] The third preset value is used to define the critical value of the response hysteresis coefficient exceeding the threshold, corresponding to the judgment criteria for serious faults or emergencies. The method for determining the third preset value can be as follows: collect data on the degree of response hysteresis coefficient exceeding the threshold of similar equipment before serious faults, such as thermal breakdown or insulation failure, select the minimum value or low quantile of this degree among all fault events, such as the 10th percentile, and use the selected minimum value or low quantile as the benchmark for the third preset value. For example, if historical data shows that the response hysteresis coefficient exceeds the upper limit of the threshold by at least 0.3 before a serious fault, then the third preset value is set to 0.3.

[0062] Level 1 warnings are the lowest level, indicating potential risks or minor anomalies that require attention but not immediate action. In this case, low-priority notifications can be sent to maintenance personnel, for example, via email or mobile application push notifications. Level 2 warnings are medium-level, indicating that a fault is developing or has reached a certain severity, requiring timely attention and investigation. In this case, SMS or telephone notifications can be sent to maintenance personnel, or a medium-priority alarm can be displayed on the control room interface. Level 3 warnings are the highest level, indicating that a fault is very serious or in an emergency state, requiring immediate intervention. In this embodiment, an emergency shutdown command can be automatically triggered, or an emergency telephone notification can be sent to maintenance personnel, accompanied by strong audible and visual alarms.

[0063] The rate of temperature change is the rate at which the temperature at a connection point changes over time. In a three-level early warning system, exceeding a preset rate threshold is an indicator of a rapidly deteriorating fault. The rate of temperature change can be an instantaneous rate of temperature change, which is the difference between the current temperature and the previous temperature divided by the time interval, or it can be the average rate of temperature change over a certain period of time. The preset rate threshold is a critical value used to define the rate of temperature change. When the rate of temperature change exceeds the preset rate threshold, it indicates that the fault is rapidly deteriorating. The preset rate threshold can be set based on factors such as the thermal inertia of the equipment, the temperature tolerance of the materials, and safety standards. For example, for a specific distribution cabinet, a temperature rise exceeding a certain rate in a short period of time is considered abnormal.

[0064] In this embodiment, based on dynamic parameters such as the degree of exceeding the threshold of the response hysteresis coefficient, the rise of the current response coefficient, and the temperature change rate, early warning information with different priorities is generated. This solves the problem that a single early warning level cannot distinguish the severity and evolution speed of the fault, and to a certain extent avoids power outages or safety accidents caused by response delays, thereby improving the reliability and safety of the distribution cabinet operation.

[0065] After determining that it is a precursor mode of thermal fault, the process also includes: mapping the current response coefficient and the response hysteresis coefficient to a feature point in a two-dimensional feature plane; calculating the Mahalanobis distance between the feature point and multiple preset fault mode center points, where the fault mode center points include the contact loosening mode center, the conductor oxidation mode center, and the heat dissipation blockage mode center; determining the fault type based on the fault mode center point with the smallest Mahalanobis distance, and adding the fault type to the graded early warning information.

[0066] In this embodiment, the current response coefficient and the response hysteresis coefficient are mapped to a feature point in a two-dimensional feature plane. The current response coefficient and the response hysteresis coefficient of the distribution cabinet connection point are used as two independent feature dimensions to construct a two-dimensional coordinate system. The currently calculated current response coefficient and the response hysteresis coefficient are used as a point in this coordinate system. In this embodiment, the current response coefficient is directly used as the abscissa and the response hysteresis coefficient is used as the ordinate to form a feature point. In order to eliminate the influence of different dimensions or numerical ranges, these two coefficients can be normalized before mapping.

[0067] Calculating the Mahalanobis distance between a feature point and multiple preset fault mode center points involves using a two-dimensional feature plane where preset feature points, representing different fault modes (i.e., fault mode center points), are used. Mahalanobis distance is a distance metric that considers the covariance of data distribution and accurately reflects the statistical similarity between two points. By calculating the Mahalanobis distance between the current feature point and each preset fault mode center point, the similarity between the current state and various known fault modes can be determined. For example, the mean vector and covariance matrix of each fault mode can be obtained by training with historical fault data, and the distance between the current feature point and each fault mode center point can be calculated according to the Mahalanobis distance formula. Alternatively, machine learning models can be used to integrate the calculation of Mahalanobis distance into the feature extraction or classification process of the model.

[0068] The fault mode centers include contact loosening mode centers, conductor oxidation mode centers, and heat dissipation blockage mode centers. These centers are determined based on the typical distribution characteristics of different types of thermally induced faults on the two-dimensional characteristic plane of current response coefficient and response hysteresis coefficient. The contact loosening mode center represents a fault mode caused by poor contact at the connection point, leading to increased resistance and heat generation; its characteristics include a high current response coefficient and a low response hysteresis coefficient. The conductor oxidation mode center represents a fault mode caused by oxidation of the conductor surface, leading to increased contact resistance; its characteristics include a medium current response coefficient and a large response hysteresis coefficient. The heat dissipation blockage mode center represents... The table shows a fault mode in which heat cannot be effectively dissipated due to obstructed heat dissipation channels or reduced heat dissipation capacity inside the distribution cabinet. It is characterized by a low current response coefficient and a large response hysteresis coefficient. These center points can be determined by statistical analysis, clustering, or expert experience of a large amount of historical fault data. For example, in the laboratory or actual operating environment, three typical faults, namely loose contact, conductor oxidation, and heat dissipation blockage, can be specifically simulated. The corresponding current response coefficient and response hysteresis coefficient can be collected and calculated to form a sample set. For the sample set of each fault mode, its mean vector and covariance matrix can be calculated. The mean vector is the center point of the fault mode.

[0069] Determining the fault type based on the fault mode center point with the smallest Mahalanobis distance involves calculating the Mahalanobis distance between the current feature point and all preset fault mode center points, and then selecting the fault type corresponding to the fault mode center point with the smallest distance value as the fault type of the current distribution cabinet connection point. For example, if the current feature point has the smallest Mahalanobis distance to the center of the loose contact mode, the fault mode is determined to be a loose contact fault.

[0070] Adding fault types to the graded warning information means that when generating graded warning information, the identified fault types are included as part of the warning information. For example, the warning information can be a level two warning: Risk of loose contact detected, please check in time.

[0071] In this embodiment, the current response coefficient and the response hysteresis coefficient are mapped to a feature point in a two-dimensional feature plane. The current thermal response state is quantitatively characterized by the combination of the current response coefficient and the response hysteresis coefficient, forming a comparable spatial representation. The Mahalanobis distance between this feature point and the preset fault mode center point is calculated, and the fault type is determined based on the fault mode center point with the smallest Mahalanobis distance. This ensures that the identification result is based on the minimum statistical bias, thereby achieving fault mode classification. The determined fault type is added to the graded early warning information, so that the early warning not only includes the severity level but also the cause of the fault. This allows maintenance personnel to understand the nature of potential faults earlier and thus formulate more targeted maintenance plans.

[0072] Based on the method for early warning of thermally induced faults in power distribution cabinets provided in the above embodiments, this application also provides a specific implementation of an early warning device for thermally induced faults in power distribution cabinets. Please refer to the following embodiments.

[0073] First see Figure 3 This application provides an early warning device 200 for thermal faults in power distribution cabinets, comprising the following modules: The acquisition module 201 is used to acquire ambient temperature data of the power distribution cabinet and timing parameters of at least one connection point. The timing parameters include temperature data and current data. The first calculation module 202 is used to calculate the temperature change rate, current change rate and average current of the time sequence parameters within a preset time period. The first construction module 203 is used to construct a temperature response model to current based on the temperature change rate, current data, ambient temperature data, and current change rate, and to obtain the current response coefficient. The second construction module 204 is used to construct a time delay cross-correlation function based on temperature changes and current squares within a preset time period, and obtain the delay time with the largest correlation coefficient. The second calculation module 205 is used to calculate the response hysteresis coefficient based on the delay time, the rate of change of current and the average current. The response hysteresis coefficient is used to characterize the degree of thermal response hysteresis. Comparison module 206 is used to compare the response hysteresis coefficient with the corresponding threshold range. If the response hysteresis coefficient is not within the threshold range, the direction of change of temperature change rate and current change rate is verified to obtain the verification result. The judgment generation module 207 is used to determine the thermal fault precursor mode when the verification result is that the temperature rises but the current does not rise synchronously, and to generate graded early warning information based on the current response coefficient and the response hysteresis coefficient.

[0074] As an optional implementation of this embodiment, the first construction module 203 is specifically used for: Based on the formula: Construct a temperature-current response model; where, I represents the rate of temperature change, and I represents the current data. Tp is the rate of change of current, and Tp is the temperature data at the connection point. amb Here, α represents the ambient temperature data, β represents the current response coefficient, β represents the Joule thermal steady-state coefficient, γ represents the heat dissipation condition coefficient, and ε represents the residual.

[0075] As an optional implementation of this embodiment, the second calculation module 205 is specifically used for: Based on the formula: Calculate the response lag factor; where L is the response lag factor, t maxI is the delay time, RMS(dI / dt) is the effective value of the rate of change of current, and I avg This represents the average current.

[0076] As an optional implementation of this embodiment, the early warning device 200 for thermal faults in the power distribution cabinet further includes: The load calculation module is used to calculate the current load rate based on current data and the rated current of the distribution cabinet; The sequence acquisition module is used to acquire the response lag coefficient sequence within a preset historical time period; The range determination module is used to determine the threshold range based on the current load rate, ambient temperature data, and response lag coefficient sequence using an adaptive quantile algorithm. The adaptive quantile algorithm includes: selecting historical response lag coefficients that match the current load rate and ambient temperature from the response lag coefficient sequence, and using the preset quantile of the selected historical response lag coefficients as the current threshold range.

[0077] As an optional implementation of this embodiment, the determination generation module 207 is specifically used for: A Level 1 warning is generated when the response hysteresis coefficient exceeds the threshold range but the degree of exceeding the threshold is less than the first preset value, and the increase in the current response coefficient is less than the second preset value. A Level 2 warning is generated when the response hysteresis coefficient exceeds the threshold range and the degree of exceeding the threshold reaches the first preset value, or the increase in the current response coefficient reaches the second preset value. A Level 3 warning is generated when the response hysteresis coefficient exceeds the threshold range and the degree of exceeding the threshold reaches the third preset value, and the temperature change rate exceeds the preset rate threshold. The Level 3 warning has a higher priority than the Level 2 warning. The Level 2 warning has a higher priority than the Level 1 warning.

[0078] As an optional implementation of this embodiment, the comparison module 206 is specifically used for: Obtain the temperature change rate symbol sequence and the current change rate symbol sequence at multiple sampling times within a preset time period; if the proportion of consecutive positive symbols in the temperature change rate symbol sequence exceeds the first symbol threshold, and the proportion of consecutive non-positive symbols in the current change rate symbol sequence exceeds the second symbol threshold, the verification result is that the temperature rises but the current does not rise synchronously; if the proportion of the same symbols in the temperature change rate symbol sequence and the current change rate symbol sequence exceeds the third symbol threshold, the verification result is that the temperature and current change synchronously.

[0079] As an optional implementation of this embodiment, the early warning device 200 for thermal faults in the power distribution cabinet further includes: The mapping module is used to map the current response coefficient and response hysteresis coefficient to a feature point in a two-dimensional feature plane after determining that a thermally induced fault precursor mode has been identified. The distance calculation module is used to calculate the Mahalanobis distance between the feature point and multiple preset fault mode center points, where the fault mode center points include the contact loosening mode center, the conductor oxidation mode center, and the heat dissipation blockage mode center. The type calculation module is used to determine the fault type based on the fault mode center point with the minimum Mahalanobis distance, and add the fault type to the graded early warning information.

[0080] As an optional implementation of this embodiment, the early warning device 200 for thermal faults in the power distribution cabinet further includes: The average value calculation module is used to calculate the average response hysteresis coefficient of all connection points after calculating the response hysteresis coefficient based on the delay time, current change rate and current average value. The deviation calculation module is used to calculate the relative deviation between the response hysteresis coefficient of each connection point and the average value; The information extraction module is used to identify any connection point as an abnormal connection point and extract its location information when the relative deviation of any connection point exceeds a preset deviation threshold. Add a module to add location information to the tiered early warning information.

[0081] Figure 3 A schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application is shown.

[0082] The electronic device may include a processor 301 and a memory 302 storing computer program instructions.

[0083] Specifically, the processor 301 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0084] Memory 302 may include mass storage for data or instructions. For example, and not limitingly, memory 302 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. In one instance, memory 302 may include removable or non-removable (or fixed) media, or memory 302 may be non-volatile solid-state memory. Memory 302 may be internal or external to the integrated gateway disaster recovery device.

[0085] In one instance, memory 302 may be read-only memory (ROM). In one instance, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0086] Memory 302 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method for early warning of thermally induced faults in a distribution cabinet according to the first aspect of this disclosure.

[0087] The processor 301 reads and executes computer program instructions stored in the memory 302 to achieve... Figure 1 An early warning method for thermal faults in a power distribution cabinet is shown in the embodiment.

[0088] In one example, the electronic device may also include a communication interface 303 and a bus 304. For example, Figure 3 As shown, the processor 301, memory 302, and communication interface 303 are connected through bus 304 and complete communication with each other.

[0089] The communication interface 303 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0090] Bus 304 includes hardware, software, or both, that couples components of an electronic device together. For example, and not as a limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 304 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0091] This electronic device can execute a method for early warning of thermal faults in a power distribution cabinet, as described in this application embodiment, thereby achieving a combination of... Figures 1-2 This invention describes a method and device for early warning of thermal faults in electrical distribution cabinets.

[0092] Furthermore, in conjunction with the early warning method for thermally induced faults in distribution cabinets described in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the early warning methods for thermally induced faults in distribution cabinets described in the above embodiments.

[0093] In an optional embodiment, in conjunction with the early warning method for thermally induced faults in the power distribution cabinet described in the above embodiments, this application embodiment can provide a computer program product to implement this method. The instructions in the computer program product are executed by the processor of an electronic device, enabling the electronic device to implement any of the early warning methods for thermally induced faults in the power distribution cabinet described in the above embodiments.

[0094] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0095] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0096] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0097] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0098] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for early warning of thermally induced faults in a power distribution cabinet, characterized in that, include: Acquire ambient temperature data and timing parameters of connection points for the power distribution cabinet, wherein the timing parameters include temperature data and current data; Calculate the rate of change of temperature, rate of change of current, and average current of time-series parameters within a preset time period; Based on the temperature change rate, current data, ambient temperature data, and current change rate, a temperature response model to current is constructed to obtain the current response coefficient. Based on the temperature change and current square within the preset time period, a time delay cross-correlation function is constructed to obtain the delay time with the largest correlation coefficient. The response hysteresis coefficient is calculated based on the delay time, the rate of change of current, and the average current value. The response hysteresis coefficient is used to characterize the degree of thermal response hysteresis. The response hysteresis coefficient is compared with the corresponding threshold range. If the response hysteresis coefficient is not within the threshold range, the direction of change of temperature change rate and current change rate is verified to obtain the verification result. When the verification result shows that the temperature rises but the current does not rise synchronously, it is determined to be a thermal fault precursor mode, and graded early warning information is generated based on the current response coefficient and response hysteresis coefficient.

2. The method for early warning of thermally induced faults in a power distribution cabinet according to claim 1, characterized in that, The construction of the temperature-current response model based on the temperature change rate, current data, ambient temperature data, and current change rate includes: Based on the formula: Construct a temperature response model to current; in, I represents the rate of temperature change, and I represents the current data. Tp is the rate of change of current, and Tp is the temperature data at the connection point. amb Here, α represents the ambient temperature data, β represents the current response coefficient, β represents the Joule thermal steady-state coefficient, γ represents the heat dissipation condition coefficient, and ε represents the residual.

3. The method for early warning of thermally induced faults in a power distribution cabinet according to claim 1, characterized in that, The calculation of the response hysteresis coefficient based on the delay time, current change rate, and average current includes: Based on the formula: Calculate the response lag factor; Where L is the response lag coefficient, t max I is the delay time, RMS(dI / dt) is the effective value of the rate of change of current, and I avg This represents the average current.

4. The method for early warning of thermally induced faults in a power distribution cabinet according to claim 1, characterized in that, Determining the threshold range includes: The current load rate is calculated based on the current data and the rated current of the distribution cabinet; Obtain the response lag coefficient sequence within a preset historical time period; The threshold range is determined using an adaptive quantile algorithm based on the current load rate, ambient temperature data, and response hysteresis coefficient sequence. The adaptive quantile algorithm includes: selecting historical response lag coefficients that match the current load rate and ambient temperature from the response lag coefficient sequence, and using the preset quantile of the selected historical response lag coefficients as the current threshold range.

5. The method for early warning of thermally induced faults in a power distribution cabinet according to claim 1, characterized in that, The generation of graded early warning information based on the current response coefficient and response hysteresis coefficient includes: If the response hysteresis coefficient exceeds the threshold range but the degree of exceeding the threshold is less than the first preset value, and the increase in the current response coefficient is less than the second preset value, a first-level warning message is generated. If the response hysteresis coefficient exceeds the threshold range and the degree of exceeding the threshold reaches a first preset value, or if the rise of the current response coefficient reaches a second preset value, a secondary warning message is generated. If the response hysteresis coefficient exceeds the threshold range and the degree of exceeding the threshold reaches the third preset value, and the temperature change rate exceeds the preset rate threshold, a level three warning message is generated. Among them, Level 3 early warning information has a higher priority than Level 2 early warning information. Level 2 early warning information has a higher priority than Level 1 early warning information.

6. The method for early warning of thermally induced faults in a power distribution cabinet according to claim 1, characterized in that, The verification of the direction of change of temperature rate of change and current rate of change includes: Obtain the symbolic sequences of temperature change rate and current change rate at multiple sampling moments within the preset time period; If the proportion of consecutive positive signs in the temperature change rate symbol sequence exceeds the first symbol threshold, and the proportion of consecutive non-positive signs in the current change rate symbol sequence exceeds the second symbol threshold, the verification result is that the temperature rises but the current does not rise synchronously. If the proportion of identical symbols in the temperature change rate symbol sequence and the current change rate symbol sequence exceeds the third symbol threshold, the verification result is that the temperature and current change synchronously.

7. The method for early warning of thermally induced faults in a power distribution cabinet according to claim 1, characterized in that, After determining that it is a precursor mode of thermal induced failure, the following is also included: The current response coefficient and the response hysteresis coefficient are mapped to a feature point in a two-dimensional feature plane; Calculate the Mahalanobis distance between the feature point and multiple preset fault mode center points, wherein the fault mode center points include the contact loosening mode center, the conductor oxidation mode center, and the heat dissipation blockage mode center; The fault type is determined based on the fault mode center point with the minimum Mahalanobis distance, and the fault type is added to the graded early warning information.

8. The method for early warning of thermally induced faults in a power distribution cabinet according to claim 1, characterized in that, After calculating the response hysteresis coefficient based on the delay time, current change rate, and average current, the method further includes: Calculate the average response hysteresis coefficient of all connection points; Calculate the relative deviation of the response hysteresis coefficient of each connection point from the average value; If the relative deviation of any connection point exceeds a preset deviation threshold, the corresponding connection point is identified as an abnormal connection point, and the location information of the abnormal connection point is extracted. Add the location information to the graded early warning information.

9. A warning device for thermally induced faults in a power distribution cabinet, characterized in that, The device includes: The acquisition module is used to acquire ambient temperature data of the power distribution cabinet and timing parameters of at least one connection point, wherein the timing parameters include temperature data and current data. The first calculation module is used to calculate the temperature change rate, current change rate, and average current of the time sequence parameters within a preset time period. The first construction module is used to construct a temperature response model to current based on the temperature change rate, current data, ambient temperature data, and current change rate, and to obtain the current response coefficient. The second construction module is used to construct a time delay cross-correlation function based on the temperature change and current square within the preset time period, and obtain the delay time with the largest correlation coefficient. The second calculation module is used to calculate the response hysteresis coefficient based on the delay time, current change rate and average current, and the response hysteresis coefficient is used to characterize the degree of thermal response hysteresis. The comparison module is used to compare the response hysteresis coefficient with the corresponding threshold range. If the response hysteresis coefficient is not within the threshold range, the direction of change of the temperature change rate and the current change rate is verified to obtain the verification result. The determination generation module is used to determine a thermal fault precursor mode when the verification result shows that the temperature rises but the current does not rise synchronously, and to generate graded early warning information based on the current response coefficient and the response hysteresis coefficient.

10. An electronic device, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements a method for early warning of thermal faults in a power distribution cabinet as described in any one of claims 1-8.

Images