A distribution box safety early warning method and system

Abstract

The application provides a power distribution box safety early warning method and system, the method comprises the following steps: acquiring the state parameters of the power distribution box in real time, the state parameters include resistance signals, leakage current signals and physical state images; the state parameters are converted into state variables by a special feature extractor; the state variables are input into a body reasoning engine; the body reasoning engine performs multi-parameter fusion reasoning based on a preset multi-dimensional ontology model and a judgment rule system; the multi-parameter fusion reasoning process comprises the following steps: mapping each state variable into a fuzzy variable by fuzzy logic; fusing the fuzzy variables according to a preset fuzzy rule; and outputting a risk level; according to the risk level, a graded early warning signal and a scenario-based disposal suggestion are output; the graded early warning signal is associated with a corresponding response mechanism; and the scenario-based disposal suggestion generates operation steps based on abnormal parameter types, thereby effectively overcoming the limitations of monitoring relying on a single parameter.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of early warning, and particularly relates to a power distribution box safety early warning method and system. BACKGROUND

[0002] The power distribution box is a key safety node in the power system, and its failure may cause serious accidents such as fire and electric shock, directly threatening the safety of personnel and the stable operation of the power system. The traditional power distribution box monitoring method is usually single, for example, only monitoring temperature or only monitoring total leakage current, which is difficult to comprehensively and accurately evaluate the safety state. Temperature monitoring usually uses a thermistor or infrared, but the response to poor contact and other hidden dangers may not be sensitive enough; leakage current monitoring often focuses on the total effective value, but the capacitive component contained therein is not a direct representation of fire hazards, and the resistive fundamental component (especially the power frequency component) can better reflect the dangerous state of insulation deterioration and electric arc; the abnormality of the physical state (such as the door body being open, foreign matter intrusion, equipment displacement, and rust) is also an important risk factor, but often relies on manual inspection.

[0003] The prior art lacks the ability to effectively fuse multiple heterogeneous information due to single monitoring method, insufficient information fusion, and inaccurate risk assessment, and it is difficult to comprehensively guarantee the safety monitoring demand of the power distribution box. SUMMARY

[0004] In order to solve the above technical problems, the application provides a power distribution box safety early warning method and system to solve the technical problems in the prior art.

[0005] In one aspect, the application provides the following technical solution, a power distribution box safety early warning method, the method comprising:

[0006] Real-time acquisition of state parameters of the power distribution box, the state parameters comprising resistance signals, leakage current signals, and physical state images;

[0007] Converting the state parameters into state variables by a special feature extractor, the converted state variables comprising converting the resistance signals into temperature signals of the power distribution box connection point temperature, filtering and processing the leakage current signals to extract the resistive fundamental component, and inputting the physical state images into a preset identification model to output the physical state information of the power distribution box;

[0008] Inputting the state variables into an ontology reasoning engine, the ontology reasoning engine performing multi-parameter fusion reasoning based on a preset multi-dimensional ontology model and a judgment rule system, wherein the multi-parameter fusion reasoning process comprises mapping each state variable into a fuzzy variable by fuzzy logic, fusing the fuzzy variables according to a preset fuzzy rule, and outputting a risk level;

[0009] According to the risk level, a hierarchical early warning signal and a scenario-based treatment suggestion are output, the hierarchical early warning signal is associated with a corresponding response mechanism, and the scenario-based treatment suggestion generates operation steps based on an abnormal parameter type, and data of the multi-parameter fusion reasoning process are synchronously recorded to support traceability analysis.

[0010] Compared with the prior art, the application has the beneficial effects that: by real-time acquisition of the resistance signal (reflecting the contact point temperature), the leakage current signal (extracting the resistive fundamental component to directly reflect the insulation fault and fire risk), and the physical state image (reflecting the external hidden danger) of the distribution box, synchronous monitoring of key state parameters is realized. This comprehensive monitoring method effectively overcomes the limitations of relying on a single parameter for monitoring.

[0011] The acquired state parameters are processed by a special feature extractor: the resistance value is accurately obtained, the resistive fundamental component in the leakage current is effectively extracted (while suppressing the capacitive component and harmonic interference), and a high-performance identification model is used to automatically identify abnormal conditions of the physical state of the distribution box. This step replaces the traditional inefficient manual inspection, realizes high-precision conversion of key state parameters and automation of abnormal identification.

[0012] The knowledge expression method based on a multi-dimensional ontology model and a judgment rule system can flexibly and intelligently express complex domain knowledge (especially the association between various state combinations and actual risks). This method is more reliable than simple threshold judgment and can realize more comprehensive and actual risk condition-compliant level evaluation. Based on the evaluation result, the system outputs clear risk levels and corresponding targeted treatment suggestions, making the early warning information more instructive and facilitating rapid response by operation and maintenance personnel.

[0013] Further, the step of real-time acquisition of the state parameters of the distribution box comprises:

[0014] A platinum resistance temperature sensor is installed at the inlet and outlet terminals of the distribution box, and the resistance value of the platinum resistance temperature sensor is obtained by resistance sampling circuit measurement and resistance formula calculation as the resistance signal;

[0015] A through-hole residual current transformer is sleeved on the grounding wire of the distribution box to collect the leakage current signal on the grounding wire;

[0016] An industrial camera is used to face the distribution box door and the internal equipment area to collect the physical state image of the distribution box.

[0017] Further, the step of converting the resistance signal into a temperature signal comprises:

[0018] The resistance sampling circuit calculates an operation voltage corresponding to the resistance signal, and inputs the operation voltage into a proportional amplifier to adjust the value of the operation voltage to a range voltage within a range of 0-5V.

[0019] The temperature signal is obtained by using a piecewise function formula based on an actual resistance calculated from the range voltage.

[0020] Further, the resistance sampling circuit comprises:

[0021] An external voltage source;

[0022] A first resistance, a second resistance, a platinum resistance temperature sensor, and a third resistance are connected in series between the external voltage source and the ground;

[0023] A fourth resistance is connected in parallel between the second resistance and the platinum resistance temperature sensor;

[0024] A first potential point is connected in parallel between the first resistance and the second resistance;

[0025] A second potential point is connected to one end of the fourth resistance away from the platinum resistance temperature sensor;

[0026] A third potential point is connected in parallel between the platinum resistance temperature sensor and the third resistance;

[0027] A voltage measurement unit is configured to measure a first potential difference between the first potential point and the second potential point, and a second potential difference between the first potential point and the third potential point.

[0028] Further, the resistance formula comprises:

[0029]

[0030] wherein, R is a resistance value of the platinum resistance temperature sensor, R1 and R3 are fixed resistances of the first resistance and the third resistance, respectively, V is the external voltage source, ΔV1 is the first potential difference at the current temperature, ΔV2 is the second potential difference;

[0031] The piecewise function formula comprises:

[0032] wherein, R is an actual resistance, T is a target temperature of the environment, and a1 and a2 are piecewise polynomial fitting coefficients, respectively. respectively represent nonlinear compensation term coefficients, respectively represent process correction coefficients.

[0033] Further, the step of filtering the leakage current signal to extract the resistive fundamental component includes:

[0034] The collected leakage current signal is converted by a variable ratio to obtain a measurable electrical signal;

[0035] The measurable electrical signal is filtered to remove high-frequency noise to obtain a full leakage current signal;

[0036] The full leakage current signal is low-pass filtered to extract its fundamental component;

[0037] The fundamental component is converted by waveform conversion, and the voltage sine wave and current sine wave of the fundamental component are converted into voltage rectangular wave and current rectangular wave, respectively;

[0038] The time difference between the rising edge of the voltage rectangular wave and the rising edge of the current rectangular wave is measured;

[0039] The time difference is converted into an angle and converted into a phase angle difference, and based on the phase angle difference and the trigonometric function relationship, the peak value and effective value of the resistive fundamental current of the fundamental component are calculated as the resistive fundamental component.

[0040] Further, the multi-dimensional ontology model includes:

[0041] Parameter feature class: define the over-temperature threshold of the temperature signal, the temperature rise rate parameter and its risk weight; define the safety threshold of the resistive fundamental component, the over-standard duration parameter and its risk weight; define the abnormal subclass corresponding to the distribution box state information and its risk weight, the abnormal subclass includes abnormal opening of the box door, cable exposure and component loosening;

[0042] Risk association class: define the association rules between different state parameters; one of the association rules is: when the distribution box state information is identified as a cable exposure abnormal subclass, the risk weight corresponding to the temperature signal is increased by a preset proportion.

[0043] Secondly, the present application provides the following technical scheme, a distribution box safety warning system, the system includes:

[0044] The acquisition module is used for acquiring the state parameters of the distribution box in real time, and the state parameters include resistance signal, leakage current signal and physical state image;

[0045] The conversion module is configured to convert the state parameters into state variables by using a dedicated feature extractor, and the converted state variables include converting the resistance signal into a temperature signal of a distribution box connection point temperature, filtering the leakage current signal to extract a resistive fundamental component, and inputting the physical state image into a preset identification model to output physical state information of the distribution box.

[0046] The reasoning module is configured to input the state variables into a body reasoning engine, and the body reasoning engine performs multi-parameter fusion reasoning based on a preset multi-dimensional body model and a judgment rule system, wherein the multi-parameter fusion reasoning process includes mapping each of the state variables into a fuzzy variable by using fuzzy logic, fusing the fuzzy variables according to a preset fuzzy rule, and outputting a risk level.

[0047] The response module is configured to output a graded early warning signal and a scenario-based disposal suggestion according to the risk level, the graded early warning signal is associated with a corresponding response mechanism, the scenario-based disposal suggestion generates an operation step based on an abnormal parameter type, and data of the multi-parameter fusion reasoning process is synchronously recorded to support traceability analysis.

[0048] In a third aspect, the present application provides a computer including a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the power distribution box safety warning method as described above when executing the computer program.

[0049] In a fourth aspect, the present application provides a storage medium having a computer program stored thereon, and the computer program is executable on a processor to implement the power distribution box safety warning method as described above. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0051] Figure 1 A flowchart of the power distribution box safety warning method provided by the first embodiment of the present application;

[0052] Figure 2 A resistance sampling circuit in the first embodiment of the present application;

[0053] Figure 3 A structural block diagram of the power distribution box safety warning system provided by the second embodiment of the present application;

[0054] Figure 4 Fig. 3 is a schematic diagram of a hardware structure of a computer provided for a third embodiment of the present application.

[0055] The embodiments of the present application will be further described below with reference to the drawings. DETAILED DESCRIPTION

[0056] Embodiments of the present application are described in detail below with reference to the accompanying drawings, in which like reference numerals designate identical or similar elements throughout the several views. The embodiments described below are merely exemplary for the purpose of explaining the present application and are not to be understood as limiting the present application.

[0057] In the description of the embodiments of the present application, it is to be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are merely used for the purpose of facilitating the description of the embodiments of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application.

[0058] In addition, the terms "first", "second", "third", etc. are used only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined with "first", "second", etc. can explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, the meaning of "plurality" is two or more, unless otherwise specifically limited.

[0059] Embodiment One

[0060] In the first embodiment of the present application, as shown in FIG. 1, a power distribution box safety warning method includes the following steps S01 to S04: Figure 1

[0061] S01, real-time acquisition of state parameters of the power distribution box, the state parameters including resistance signals, leakage current signals and physical state images;

[0062] Specifically, the step of real-time acquisition of state parameters of the power distribution box includes:

[0063] S11, installing a platinum resistance temperature sensor at the incoming and outgoing line terminals of the power distribution box, measuring the resistance value of the platinum resistance temperature sensor through a resistance sampling circuit and calculating the resistance value through a resistance formula, as the resistance signal;

[0064] ​S12, a through core residual current transformer is sleeved on the grounding wire of the distribution box to collect the leakage current signal on the grounding wire;

[0065] S13, an industrial camera is used to face the distribution box door and the internal equipment area to collect the physical state image of the distribution box.

[0066] As Figure 2 further shown, the resistance sampling circuit comprises:

[0067] an external voltage source (VCC);

[0068] a first resistor (R1), a second resistor (R2), a platinum resistance temperature sensor (PT100), and a third resistor (R3) are connected in series between the external voltage source and the ground;

[0069] a fourth resistor (R4) is connected in parallel between the second resistor (R2) and the platinum resistance temperature sensor (PT100);

[0070] a first potential point (a) is connected in parallel between the first resistor and the second resistor;

[0071] a second potential point (b) is connected to one end of the fourth resistor away from the platinum resistance temperature sensor;

[0072] a third potential point (c) is connected in parallel between the platinum resistance temperature sensor and the third resistor;

[0073] a voltage measurement unit configured to measure a first potential difference between the first potential point and the second potential point, and a second potential difference between the first potential point and the third potential point.

[0074] The resistance formula comprises:

[0075]

[0076] wherein, R is the resistance value of the platinum resistance temperature sensor, R1 and R3 are fixed resistances of the first resistor and the third resistor, respectively, VCC is the external voltage source, ΔU1 is the first potential difference at the current temperature, ΔU2 is the second potential difference.

[0077] In this embodiment, a PT100 platinum resistance temperature sensor is installed at the key access terminal of the distribution box. The resistance sampling circuit shown in Figure 2 is used to calculate the resistance value of the PT100 (platinum resistance temperature sensor) by using the resistance formula.

[0078] Install a 1000:1 through-hole residual current transformer on the main grounding line of the distribution box to collect leakage current signals.

[0079] Install a 2 million pixel industrial camera 1.5 meters in front of the distribution box to collect clear images of the distribution box door and internal equipment area in a timed manner (e.g., every minute) or triggered manner (e.g., door magnetic induction).

[0080] S02, convert the state parameters into state variables by a dedicated feature extractor, the converted state variables include converting the resistance signal into a temperature signal of the distribution box connection point temperature, filtering and processing the leakage current signal to extract its resistive fundamental component, and inputting the physical state image into a preset recognition model to output the physical state information of the distribution box;

[0081] Further, the step of converting the resistance signal into a temperature signal includes:

[0082] S21, based on the resistance sampling circuit, calculate the operating voltage corresponding to the resistance signal, input the operating voltage into a proportional amplifier, and adjust its value to a range voltage within the range of 0-5V;

[0083] S22, using a piecewise function formula, based on the actual resistance calculated from the range voltage, the temperature signal is obtained by back calculation.

[0084] Specifically, the step of obtaining the actual resistance based on the range voltage includes substituting the range voltage into the resistance formula to obtain the actual resistance by back calculation, specifically as follows:

[0085]

[0086] wherein, is the actual resistance, are the fixed resistances of the first and third resistances, respectively, is an external voltage source, is the range voltage corresponding to the first potential difference calculated by step S21, is the range voltage corresponding to the second potential difference calculated by step S21.

[0087] Specifically, the piecewise function formula includes:

[0088]

[0089] wherein, is the actual resistance, is the target temperature of the environment, and are the piecewise polynomial fitting coefficients, respectively, are the nonlinear compensation term coefficients, respectively, These are respectively represented as process correction coefficients.

[0090] Optionally, a correction formula can be introduced to improve the accuracy of the actual resistance, resulting in a more precise actual resistance. The correction formula is as follows:

[0091]

[0092] in, Expressed as a more precise actual resistance, This is the actual resistance. The reference resistance at 20°C for a single conductor (typically the resistance of a PT100 lead). The temperature coefficient of the conductor. The target temperature of the environment.

[0093] Then obtain a more accurate actual resistance Substituting the values ​​into the piecewise function formula to calculate the temperature, the piecewise function formula then... The value corresponds to The value of .

[0094] Specifically, the step of filtering the leakage current signal to extract its resistive fundamental component includes:

[0095] S23, the collected leakage current signal is transformed by a ratio conversion to obtain a measurable electrical signal;

[0096] S24, the measurable electrical signal is filtered to remove high-frequency noise to obtain the full leakage current signal;

[0097] S25, perform low-pass filtering on the full leakage current signal to extract its fundamental component;

[0098] S26, Perform waveform conversion on the fundamental component, converting the voltage sine wave and current sine wave of the fundamental component into a voltage rectangular wave and a current rectangular wave, respectively;

[0099] S27, Measure the time difference between the rising edge of the voltage rectangular wave and the rising edge of the current rectangular wave;

[0100] S28, the time difference is converted into an angle and then into a phase angle difference. Based on the phase angle difference and trigonometric function relationships, the peak value and effective value of the resistive fundamental current of the fundamental component are calculated and used as the resistive fundamental component.

[0101] In this embodiment, the transformation of the ratio in S23 is to convert the microampere level leakage current by a current transformer into a milliamper level measurable signal in proportion (such as N2), to ensure the safety of the subsequent circuit processing, and to convert the original microampere level current into a 0-5 mA measurable signal by the ratio N2. The filtering in S24 is to remove high-frequency noise (such as electromagnetic interference) by using a simple RC filter, and to retain the main frequency components. The fundamental component extraction in S25: a second-order Butterworth low-pass filter (cutoff frequency 50 Hz) filters out high-order harmonics and only retains the fundamental component. Phase angle difference calculation: wherein is the phase angle difference, is the time difference, is 50. The effective value of the resistive fundamental current is calculated as , and the peak value of the resistive fundamental current is calculated as wherein, is the fundamental current amplitude, is the effective value, is the peak value of the resistive fundamental current.

[0102] S03, input the state parameters into the ontology reasoning engine, and the ontology reasoning engine performs multi-parameter fusion reasoning based on a preset multi-dimensional ontology model and a judgment rule system, wherein the multi-parameter fusion reasoning process includes mapping each state parameter to a fuzzy variable through fuzzy logic, fusing the fuzzy variables according to a preset fuzzy rule, and outputting a risk level;

[0103] Specifically, the multi-dimensional ontology model includes:

[0104] 1. Parameter characteristic class: define the over-temperature threshold of the temperature signal, the temperature rise rate parameter and its risk weight; define the safety threshold of the resistive fundamental component, the over-standard duration parameter and its risk weight; define the abnormal sub-class corresponding to the distribution box state information and its risk weight, and the abnormal sub-class includes abnormal opening of the box door, cable exposure and component loosening.

[0105] 2. Risk association class: define the association rules between different state parameters; wherein one association rule is: when the distribution box state information is identified as the cable exposure abnormal sub-class, the risk weight corresponding to the temperature signal is increased by a preset proportion.

[0106] In this embodiment, the judgment rule system is a SWRL (Semantic Web Rule Language) rule system, including hierarchical rules:

[0107] 1. Basic rule: directly determine the risk level when a single parameter exceeds the standard, such as "temperature signal (a temperature) and the temperature value (a numerical value) and the numerical value is greater than 70, then the risk level (the risk level corresponding to the temperature is high risk)".

[0108] 2. Combination rule: multi-parameter collaborative judgment, such as "leakage current (a current) and the current value (a certain value) and the value is greater than 50 and the distribution box state (a certain state) and the state of the box door is open, the risk level (the risk level corresponding to the state is high risk)".

[0109] 3. Association rule: dynamically adjust the weight of parameters, and the SWRL rule system supports updating the rule threshold based on historical data.

[0110] The fuzzy logic processing includes: mapping the temperature signal to "high" and "extremely high" and the resistive fundamental component to "slightly over standard" and "seriously over standard" fuzzy variables through fuzzy membership functions, and then performing fusion reasoning through the fuzzy rule "extremely high temperature and seriously over standard resistive fundamental, then determining high risk".

[0111] The operation flow in specific implementation is as follows:

[0112] The "original information" to be processed includes three categories: temperature signal, such as the temperature measured in the distribution box (which may have a positive or negative error of 2℃); resistive fundamental component, such as the detected leakage current (which may fluctuate due to line interference); and distribution box state, such as "box door half open" and "cable slightly exposed" (not absolute "on / off" and "exposed / normal") captured by the camera.

[0113] The specific operation of "multi-parameter fusion reasoning" is divided into four steps:

[0114] (1) "Input ontology reasoning engine": that is, input these parameters into an intelligent judgment system. The system has stored in advance a "knowledge base" (multi-dimensional ontology model) and "judgment standard" (SWRL rule system) of distribution box safety, such as "temperature exceeding 70℃ may have fire risk" and "leakage current too large may cause electric shock".

[0115] (2) "Based on the preset multi-dimensional ontology model and SWRL rule system": the multi-dimensional ontology model is equivalent to the "dictionary" of the system, which defines the meaning, normal range and correlation of each parameter. For example, the temperature dimension clearly defines "normal (less than or equal to 50℃)", "slightly high (50℃ to 70℃)", and "too high (greater than or equal to 70℃)"; the current dimension clearly defines "safe (less than or equal to 30mA)", "over standard (30mA to 50mA)", and "seriously over standard (greater than or equal to 50mA)"; and the state dimension clearly defines the risk weight of states such as "box door normally closed", "half open", "completely open", and cable exposure. The SWRL rule system is equivalent to the "judgment formula" of the system, including simple rules (such as "temperature too high, then determine high risk") and combination rules (such as "temperature slightly high and leakage current over standard and box door open, then determine medium risk").

[0116] (3) "Handle parameter uncertainty through fuzzy logic": In reality, parameters are often not "black or white" (for example, the temperature of 69°C is close to the 70°C threshold, and the box door "half open" is not completely abnormal). This "fuzzy state" is "parameter uncertainty". The role of fuzzy logic is to convert these "fuzzy states" into calculable "fuzzy variables", for example, temperature 69°C is classified as "close to excessive", leakage current 48mA is classified as "close to serious over-standard", and box door half open is classified as "mild abnormality".

[0117] (4) "Map parameters to fuzzy variables and fuse through fuzzy rules": The converted "fuzzy variables" are integrated according to the pre-set "fuzzy rules", for example, "close to excessive temperature and close to serious over-standard current, then the risk level is raised" "mild abnormal state (box door half open) will amplify the risk of current / temperature", and finally the integrated risk level (such as "secondary risk") is obtained.

[0118] Take a practical example: Suppose the actual state of the distribution box is temperature 69°C (close to 70°C threshold, with error), leakage current 48mA (close to 50mA threshold, with fluctuation), and camera captures "box door half open" (not absolutely abnormal). First, use fuzzy logic to process: temperature corresponds to "close to excessive", current corresponds to "close to serious over-standard", and box door corresponds to "mild abnormality"; then fuse using SWRL rules: "close to excessive and close to serious over-standard and mild abnormality, then determine as secondary risk"; finally, output the risk level as "secondary".

[0119] The advantage of such processing is to avoid misjudgment due to small errors of a single parameter (such as 69°C misjudged as "normal") or state ambiguity (such as box door half open), and to make risk judgment more in line with actual scenarios.

[0120] S04, output a graded warning signal and a scenario-based disposal suggestion according to the risk level, the graded warning signal is associated with a corresponding response mechanism, and the scenario-based disposal suggestion generates operation steps based on abnormal parameter types, and simultaneously records data of the multi-parameter fusion reasoning process to support traceability analysis.

[0121] The response mechanism of the graded warning signal includes:

[0122] First-level risk: red sound and light alarm and high-frequency flashing, linkage with distribution box local power-off module, 10 seconds to cut off non-essential load power supply, push the warning to the safety responsible person and trigger the monitoring center pop-up window;

[0123] Second-level risk: yellow sound and light alarm and medium-frequency flashing, push the warning to the maintenance team and generate a high-priority repair work order;

[0124] Third-level risk: blue warning light and low-frequency flashing, record abnormal parameters and push reminders to inspection personnel.

[0125] The scenario-based treatment suggestion comprises:

[0126] When the temperature is greater than or equal to 70℃ and the heat dissipation hole is blocked, the recommended steps are: remotely start the heat dissipation fan, clean the heat dissipation hole debris, and detect the contact resistance of the incoming and outgoing line terminals;

[0127] When the resistive fundamental wave component is between 30mA and 50mA and the cable is exposed, the recommended steps are: close the box door and lock it, wrap the exposed cable with an insulating tool, and shake the line insulation resistance;

[0128] When there are multiple abnormal parameters, the priority is to deal with the "box door open" type of abnormality.

[0129] Synchronously recording the data of the multi-parameter fusion reasoning process comprises:

[0130] The specific SWRL rules, parameter change curves, associated historical data, and treatment result feedback are used to trigger early warnings, and the feedback is used to update the threshold values of the SWRL rule system.

[0131] In specific implementation:

[0132] 1. Hierarchical early warning signals and corresponding response mechanisms refer to different risk levels triggering different alarm forms, and each alarm automatically starting preset response measures. For example: a first-level risk (high risk) corresponds to a red audible and visual alarm and automatically cuts off part of the power supply and immediately pushes information to the safety officer; a second-level risk (medium risk) corresponds to a yellow alarm and generates a maintenance work order and notifies the maintenance personnel; a third-level risk (low risk) corresponds to a blue warning light and is included in the daily inspection plan.

[0133] 2. The characteristics of scenario-based treatment suggestions are that the alarm not only indicates the danger, but also clearly points out the problem and specific processing steps. For example: if the alarm is due to "temperature greater than or equal to 70℃ and heat dissipation hole blocked", the recommended steps are: a. remotely start the distribution box fan for heat dissipation; b. clean the heat dissipation hole debris on site; c. check if the line contact is loose (to avoid poor contact causing overheating). For example: if the alarm is due to "leakage between 30mA and 50mA and cable exposed", the recommended steps are: a. close the distribution box door and lock it; b. wrap the exposed cable with insulating tape; c. check if the line insulation meets the standards.

[0134] 3. Recording the reasoning process to support traceability analysis refers to automatically saving the basis for determining the risk level, including: the specific reason for triggering the alarm (such as "temperature 80℃ and leakage current 60mA"), the rule referred to when judging (such as "temperature greater than or equal to 70℃ and leakage current greater than or equal to 50mA, then determine as level 1 risk"), and the processing result (such as "after processing, the temperature drops to 40℃ and the leakage current disappears"). These records can be used to trace the alarm cause after the fact, verify the processing effect, and also assist in optimizing the system judgment rules.

[0135] In summary, a power distribution box safety warning method has the following effects:

[0136] By real-time acquisition of the resistance signal (reflecting the contact point temperature), the leakage current signal (extracting the resistive fundamental component to directly reflect the insulation fault and fire risk), and the physical state image (reflecting external hidden dangers), synchronous monitoring of key state parameters is realized. This comprehensive monitoring method effectively overcomes the limitations of relying on a single parameter for monitoring.

[0137] The collected state parameters are processed by a special feature extractor: the resistance value is accurately obtained, the resistive fundamental component in the leakage current is effectively extracted (while suppressing the capacitive component and harmonic interference), and a high-performance recognition model is used to automatically identify abnormal conditions of the physical state of the power distribution box. This step replaces the traditional inefficient manual inspection, realizing high-precision conversion of key state parameters and automation of abnormal identification.

[0138] The knowledge expression method based on a multi-dimensional ontology model and a judgment rule system can flexibly and intelligently express complex domain knowledge (especially the association between various state combinations and actual risks). This method is more reliable than simple threshold judgment and can achieve a more realistic risk condition-based comprehensive level evaluation. Based on this evaluation result, the system outputs a clear risk level and corresponding targeted disposal suggestions, making the warning information more instructive and facilitating rapid response by operation and maintenance personnel.

[0139] The entire method realizes full-process automation from data acquisition, processing, identification, reasoning to warning output, significantly improving the efficiency of power distribution box state monitoring and the timeliness of risk response.

[0140] Embodiment Two

[0141] As shown in Figure 3 The second embodiment of the present application provides a power distribution box safety warning system, which comprises:

[0142] The acquisition module 10 is used to acquire the state parameters of the power distribution box in real time, and the state parameters include resistance signals, leakage current signals, and physical state images.

[0143] The conversion module 20 is used to convert the state parameters into state parameters through a dedicated feature extractor. The converted state parameters include converting the resistance signal into a temperature signal of the distribution box connection point temperature, filtering the leakage current signal to extract its resistive fundamental component, and inputting the physical state image into a preset recognition model to output the physical state information of the distribution box.

[0144] The reasoning module 30 is used to input the state parameters into the ontology reasoning engine. The ontology reasoning engine performs multi-parameter fusion reasoning based on a preset multi-dimensional ontology model and judgment rule system. The multi-parameter fusion reasoning process includes mapping each state parameter to a fuzzy variable through fuzzy logic, fusing the fuzzy variables according to preset fuzzy rules, and outputting a risk level.

[0145] The response module 40 is used to output a graded early warning signal and scenario-based handling suggestions according to the risk level. The graded early warning signal is associated with a corresponding response mechanism. The scenario-based handling suggestions generate operation steps based on the abnormal parameter type and synchronously record the data of the multi-parameter fusion reasoning process to support source tracing analysis.

[0146] The power distribution box safety early warning system provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the system embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0147] Example 3

[0148] like Figure 4 As shown, in the third embodiment of the present invention, the present invention provides the following technical solution: a computer, including a memory 202, a processor 201, and a computer program stored in the memory 202 and executable on the processor 201, wherein the processor 201 executes the computer program to implement the distribution box safety early warning method as described above.

[0149] Specifically, the processor 201 may include a central processing unit, a specific integrated circuit, or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0150] The memory 202 can include mass storage for data or instructions. As an example and not by way of limitation, the memory 202 can include a hard disk drive, a floppy disk drive, a solid-state drive, a flash memory, a compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a tape drive, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 202 can include removable or non-removable media. Where appropriate, the memory 202 can be internal or external to the data processing apparatus. In particular embodiments, the memory 202 is non-volatile memory. In particular embodiments, the memory 202 includes read-only memory (ROM), and random access memory (RAM). Where appropriate, this ROM can be mask programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), electrically alterable ROM (EAROM), or flash memory or a combination of two or more of these. Where appropriate, this RAM can be static RAM, dynamic RAM, or a combination of static and dynamic RAM. Where appropriate, the data processing apparatus 200 can include one or more memories or levels of memory.

[0151] The memory 202 can be used to store or cache various data files used for processing and / or communication, and possible computer program instructions executed by the processor 201.

[0152] The processor 201 implements the power distribution box safety warning method described above by reading and executing the computer program instructions stored in the memory 202.

[0153] In some embodiments, the computer can also include a communication interface 203 and a bus 200. As shown, the processor 201, the memory 202, and the communication interface 203 are connected by the bus 200 and complete communication with each other. Figure 4

[0154] The communication interface 203 is used to realize the communication between the modules, devices, units and / or equipment in the embodiments of the present application. The communication interface 203 can also realize data communication with other components, such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations, etc.

[0155] ​Bus 200 includes a hardware, software, or both that couples components of computer to each other. Bus 200 includes, but is not limited to, at least one of a data bus, address bus, control bus, expansion bus, local bus, and the like. By way of example, and not limitation, bus 200 can include a graphics accelerator interface or other graphics bus, enhanced industry standard architecture bus, frontside bus, HyperTransport interconnect, industry standard architecture bus, wireless bandwidth interconnect, low pin count bus, memory bus, microchannel architecture bus, peripheral component interconnect bus, PCI Express bus, serial advanced technology attachment bus, video electronics standards association local bus, or the like, or a combination of two or more of these. Where appropriate, bus 200 can include one or more buses. Although this application describes and shows a particular bus, this application contemplates any suitable bus or interconnect.

[0156] Embodiment Four

[0157] In the fourth embodiment of the present application, in combination with the power distribution box safety warning method described above, the embodiment of the present application provides the following technical scheme, a storage medium, the storage medium has a computer program stored thereon, the computer program is executed by the processor to realize the power distribution box safety warning method described above.

[0158] Those skilled in the art can understand that the logic and / or steps described in the flowchart or otherwise described herein, for example, can be considered as a sequence of ordered data tables of executable instructions for implementing logical functions, which can be specifically implemented in any computer readable medium for use by or in conjunction with an instruction execution system, device or apparatus. For this specification, "computer readable medium" can be any device that can contain, store, communicate, propagate or transport programs for use by or in conjunction with an instruction execution system, device or apparatus.

[0159] More specific examples of computer readable medium include the following: an electrical connection having one or more wires, a portable computer diskette, a random access memory, a read only memory, an erasable programmable read only memory, an optical fiber device, and a portable compact disc read only memory. In addition, the computer readable medium can even be paper or other suitable medium upon which the program is printed, because the program can be electronically obtained, for example, by optical scanning of the paper or other medium, followed by electronic means to obtain, interpret or process the program, and then store it in a computer memory if necessary.

[0160] It should be understood that portions of the present application can be implemented with hardware, software, firmware, or a combination thereof. In the above embodiments, several steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and as in another embodiment, any of the following technologies known in the art or a combination thereof can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays, field programmable gate arrays, etc.

[0161] The technical features of the above-described embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described, but as long as the combinations of the technical features do not contradict each other, they should be considered within the scope of the present disclosure.

[0162] The above-described embodiments only express several implementation manners of the present application, and the description is specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A power distribution box safety early warning method, characterized in that, The method comprises: Real-time acquisition of state parameters of the distribution box, the state parameters comprising resistance signals, leakage current signals and physical state images; Conversion of the state parameters into state variables by a dedicated feature extractor, the converted state variables comprising conversion of the resistance signals into temperature signals of the distribution box connection point temperature, filtering processing of the leakage current signals to extract the resistive fundamental component, and input of the physical state images into a preset identification model to output physical state information of the distribution box; Input of the state variables into an ontology reasoning engine, the ontology reasoning engine performing multi-parameter fusion reasoning based on a preset multi-dimensional ontology model and a judgment rule system, wherein the multi-parameter fusion reasoning process comprises mapping each of the state variables into a fuzzy variable by fuzzy logic, fusing the fuzzy variables according to a preset fuzzy rule, and outputting a risk level; Output of a graded early warning signal and a scenario-based disposal suggestion according to the risk level, the graded early warning signal being associated with a corresponding response mechanism, the scenario-based disposal suggestion generating an operation step based on an abnormal parameter type, and synchronous recording of data of the multi-parameter fusion reasoning process to support traceability analysis; The step of filtering processing of the leakage current signals to extract the resistive fundamental component comprises: Variable ratio conversion of the collected leakage current signals to obtain measurable electrical signals; Filtering of the measurable electrical signals to remove high-frequency noise to obtain a total leakage current signal; Low-pass filtering of the total leakage current signal to extract a fundamental component; Waveform conversion of the fundamental component to convert voltage and current sine waves of the fundamental component into voltage and current rectangular waves, respectively; Measurement of a time difference between rising edges of the voltage and current rectangular waves; Conversion of the time difference into an angle and into a phase angle difference, calculation of a peak value and an effective value of a resistive fundamental current of the fundamental component based on the phase angle difference and a trigonometric function relationship, and taking the peak value and the effective value as the resistive fundamental component.

2. The electrical distribution box safety warning method of claim 1, wherein, The step of real-time acquisition of state parameters of the distribution box comprises: Installation of a platinum resistance temperature sensor at an incoming and outgoing line terminal of the distribution box, measurement of a resistance value of the platinum resistance temperature sensor by a resistance sampling circuit and calculation of the resistance value by a resistance formula to obtain the resistance signals; Sleeving of a through-core residual current transformer on a grounding wire of the distribution box to collect leakage current signals on the grounding wire; Opposite to a door body and an internal equipment area of the distribution box by an industrial camera to collect physical state images of the distribution box.

3. The electrical distribution box safety warning method of claim 2, wherein, The step of conversion of the resistance signals into temperature signals comprises: Calculation of an operating voltage corresponding to the resistance signals based on the resistance sampling circuit, input of the operating voltage into a positive proportional amplifier, and adjustment of a value of the operating voltage to a range voltage within a range of 0-5V; Reverse calculation of the temperature signals based on an actual resistance calculated from the range voltage by a piecewise function formula.

4. The electrical distribution box safety warning method of claim 3, wherein, The resistance sampling circuit comprises: An external voltage source; A first resistor, a second resistor, a platinum resistance temperature sensor and a third resistor connected in series between the external voltage source and the ground. a fourth resistor connected in parallel between the second resistor and the platinum resistance temperature sensor; a first potential point connected in parallel between the first resistor and the second resistor; a second potential point connected to one end of the fourth resistor away from the platinum resistance temperature sensor; a third potential point connected in parallel between the platinum resistance temperature sensor and the third resistor; a voltage measurement unit configured to measure a first potential difference between the first potential point and the second potential point, and a second potential difference between the first potential point and the third potential point.

5. The electrical distribution box safety warning method of claim 4, wherein, The resistance formula includes: wherein is a resistance value of the platinum resistance temperature sensor, are fixed resistances of the first and third resistors, respectively, is an external voltage source, is a first potential difference at a current temperature, is a second potential difference; The piecewise function formula includes: wherein is the actual resistance, is the target temperature of the environment, and are the piecewise polynomial fit coefficients, are the non-linear compensation term coefficients, denote the process correction coefficients, respectively.

6. The electrical box safety warning method of claim 1, wherein, The multi-dimensional ontology model includes: Parameter feature class: defining the over-temperature threshold of the temperature signal, the temperature rise rate parameter and its risk weight; defining the safety threshold of the resistive fundamental component, the over-standard duration parameter and its risk weight; defining the abnormal sub-class corresponding to the distribution box state information and its risk weight, the abnormal sub-class including abnormal opening of the box door, cable exposure and component loosening; Risk association class: defining the association rules between different state parameters; one of the association rules is that when the distribution box state information is identified as the cable exposure abnormal sub-class, the risk weight corresponding to the temperature signal is increased by a preset proportion.

7. A power distribution box safety warning system, comprising: The system includes: an acquisition module configured to acquire state parameters of a distribution box in real time, the state parameters including a resistance signal, a leakage current signal and a physical state image; a conversion module configured to convert the state parameters into state parameters through a special feature extractor, the converted state parameters including converting the resistance signal into a temperature signal of a distribution box connection point temperature, filtering and processing the leakage current signal to extract a resistive fundamental component thereof, and inputting the physical state image into a preset identification model to output physical state information of the distribution box; an inference module configured to input the state parameters into an ontology inference engine, the ontology inference engine performing multi-parameter fusion inference based on a preset multi-dimensional ontology model and a judgment rule system, wherein the multi-parameter fusion inference process includes mapping each of the state parameters into a fuzzy variable through fuzzy logic, fusing the fuzzy variables according to a preset fuzzy rule, and outputting a risk level; a response module configured to output a graded early warning signal and a scenario-based disposal suggestion according to the risk level, the graded early warning signal being associated with a corresponding response mechanism, the scenario-based disposal suggestion generating an operation step based on an abnormal parameter type, and synchronously recording data of the multi-parameter fusion inference process to support traceability analysis; The step of filtering and processing the leakage current signal to extract a resistive fundamental component thereof includes: performing a transformation ratio conversion on the collected leakage current signal to obtain a measurable electrical signal; filtering the measurable electrical signal to remove high-frequency noise to obtain a total leakage current signal; performing low-pass filtering on the total leakage current signal to extract a fundamental component thereof; performing waveform conversion on the fundamental component to convert the voltage sine wave and the current sine wave of the fundamental component into a voltage rectangular wave and a current rectangular wave, respectively; measuring the time difference between the rising edge of the voltage rectangular wave and the rising edge of the current rectangular wave; The time difference is converted into an angle difference, which is converted into a phase angle difference; based on the phase angle difference and a trigonometric function relationship, the peak value and the effective value of the resistive fundamental component current of the fundamental component are calculated, and the resistive fundamental component is obtained.

8. A computer comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the power distribution box safety warning method in any one of claims 1 to 6.

9. A storage medium, characterized by The storage medium has a computer program stored thereon, and the computer program is executed by the processor to realize the power distribution box safety warning method in any one of claims 1 to 6.

Images