Frame circuit breaker fault diagnosis and risk prediction method and system

Abstract

The invention provides a frame circuit breaker fault diagnosis and risk prediction method, which comprises the following steps of: acquiring a vibration signal on a low-voltage power distribution cabinet and a three-phase current signal and a three-phase voltage signal flowing through a main incoming line loop connected with the low-voltage power distribution cabinet in real time on the low-voltage power distribution cabinet connected with a frame circuit breaker; temperature signals on moving and static contacts arranged on the frame circuit breaker and generated arc signals are obtained in real time; on the basis of the timestamps, the three-phase current signals, the three-phase voltage signals, the vibration signals, the temperature signals and the arc signals which are obtained in real time are aligned and then filtered, and feature extraction is further carried out; and according to the extracted characteristics corresponding to each signal, identifying the fault types when the frame circuit breaker has faults, including short circuit faults, overload faults, grounding faults, contact faults and arc faults. According to the invention, the working state of the frame circuit breaker can be monitored in real time, thereby accurately identifying the fault type and predicting the risk.

Description

Technical Field

[0001] The present invention relates to the technical field of circuit breakers, and in particular to a method and system for fault diagnosis and risk prediction of a frame circuit breaker. Background Art

[0002] Air circuit breakers (ACBs) are protective devices in low-voltage power distribution systems, primarily used for overload, short-circuit, and ground fault protection. With the rapid development of power electronics, air circuit breakers can accurately distinguish and quickly handle different types of faults, such as overload, short-circuit, ground fault, overvoltage, and undervoltage. However, as core protective devices in low-voltage power systems, failure of air circuit breakers can have serious consequences, impacting safety, economics, and the environment. Therefore, ensuring their reliability and regular maintenance is crucial.

[0003] However, facing the increasingly complex power distribution environment and higher reliability requirements, traditional frame circuit breakers are unable to monitor their own operating status in real time, resulting in an inability to accurately identify fault types and accurately predict risks. Therefore, to address the above issues, it is necessary to provide a method for diagnosing frame circuit breaker faults and predicting risks by monitoring the frame circuit breaker's operating status in real time. Summary of the Invention

[0004] The technical problem to be solved by the embodiments of the present invention is to provide a frame circuit breaker fault diagnosis and risk prediction method and system, which can monitor the working status of the frame circuit breaker in real time, thereby accurately identifying the fault type and risk prediction.

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a frame circuit breaker fault diagnosis and risk prediction method, which includes the following steps:

[0006] S1. On a low-voltage distribution cabinet connected to a frame circuit breaker, obtain in real time a vibration signal on the low-voltage distribution cabinet and a three-phase current signal and a three-phase voltage signal flowing through a main incoming line circuit connected thereto, as well as a temperature signal and an arc signal generated on the moving and static contacts of the frame circuit breaker;

[0007] S2. Based on the timestamp, the three-phase current signal, three-phase voltage signal, vibration signal, temperature signal, and arc signal acquired in real time are aligned and filtered, and further feature extraction is performed;

[0008] S3. Identify the fault type of the frame circuit breaker when a fault occurs based on the extracted features corresponding to each signal; wherein the fault type includes short circuit fault, overload fault, ground fault, contact fault and arc fault.

[0009] In step S2, the features extracted from the three-phase current signal include the amplitude, instantaneous peak value, RMS value and harmonic content of each phase current; the features extracted from the three-phase voltage signal include the voltage drop rate of each phase; the features extracted from the vibration signal include spectral energy; the features extracted from the temperature signal include temperature change gradient; and the features extracted from the arc signal include arc pulse intensity.

[0010] Wherein, the step S3 specifically includes:

[0011] If it is determined that the amplitude of a phase current is greater than a preset current amplitude, the instantaneous peak is greater than a preset current peak, the RMS value is outside a preset effective value range, or the harmonic content is greater than a preset ratio, then the frame circuit breaker is identified as having a fault, and the instantaneous peak value of the three-phase current signal, the drop rate of the three-phase voltage signal, the temperature change gradient of the temperature signal, and the spectrum energy of the vibration signal are extracted and imported into the trained fault network neural model to identify the fault type of the frame circuit breaker as one of a short circuit fault, an overload fault, a ground fault, and a contact fault.

[0012] Wherein, the step S3 further includes:

[0013] If it is determined that the arc pulse intensity of the arc signal is greater than the preset intensity threshold, the frame circuit breaker is identified as having a fault, and the instantaneous peak value of the three-phase current signal and the drop rate of the three-phase voltage signal are combined and imported into the preset weighted voting model to calculate the corresponding weighted score. When it is determined that the calculated weighted score is greater than the preset threshold, the fault type of the frame circuit breaker is identified as an arc fault.

[0014] Wherein, the method further comprises:

[0015] When a fault occurs in the frame circuit breaker, the status of the energy storage motor, the opening magnetic flux, the closing magnetic flux and the energy storage spring provided on the frame circuit breaker is monitored, and the monitored status of the energy storage motor, the opening magnetic flux, the closing magnetic flux and the energy storage spring is scored according to the severity, frequency and detection degree, and the risk level of the energy storage motor, the opening magnetic flux, the closing magnetic flux and the energy storage spring is further predicted based on the scoring results.

[0016] An embodiment of the present invention further provides a frame circuit breaker fault diagnosis and risk prediction system, comprising:

[0017] A data acquisition unit is used to obtain, in real time, a vibration signal on a low-voltage distribution cabinet connected to a frame circuit breaker and a three-phase current signal and a three-phase voltage signal flowing through a main incoming line circuit connected to the low-voltage distribution cabinet, as well as a temperature signal and an arc signal generated on the moving and static contacts of the frame circuit breaker;

[0018] A feature extraction unit is used to align the three-phase current signal, three-phase voltage signal, vibration signal, temperature signal and arc signal acquired in real time based on the timestamp, perform filtering processing, and further perform feature extraction;

[0019] The fault diagnosis unit is used to identify the fault type of the frame circuit breaker when a fault occurs based on the features extracted corresponding to each signal; wherein the fault type includes short circuit fault, overload fault, ground fault, contact fault and arc fault.

[0020] Among them, the features extracted corresponding to the three-phase current signal include the amplitude, instantaneous peak value, RMS value and harmonic content of each phase current; the features extracted corresponding to the three-phase voltage signal include the voltage drop rate of each phase; the features extracted corresponding to the vibration signal include spectral energy; the features extracted corresponding to the temperature signal include temperature change gradient; the features extracted corresponding to the arc signal include arc pulse intensity.

[0021] Wherein, the fault diagnosis unit includes:

[0022] The first diagnostic module is configured to identify a fault in the frame circuit breaker if it is determined that the amplitude of a phase current is greater than a preset current amplitude, the instantaneous peak value is greater than a preset current peak value, the RMS value is outside a preset effective value range, or the harmonic content is greater than a preset ratio. The module also extracts the instantaneous peak value of the three-phase current signal, the sag rate of the three-phase voltage signal, the temperature change gradient of the temperature signal, and the spectrum energy of the vibration signal, and imports these into a trained fault network neural model to identify the fault type of the frame circuit breaker as one of a short circuit fault, an overload fault, a ground fault, and a contact fault.

[0023] Wherein, the fault diagnosis unit further includes:

[0024] The second diagnostic module is used to identify that the frame circuit breaker has a fault if it is determined that the arc pulse intensity of the arc signal is greater than a preset intensity threshold, and to import the instantaneous peak value of the three-phase current signal and the drop rate of the three-phase voltage signal into a preset weighted voting model to calculate the corresponding weighted score. When it is determined that the calculated weighted score is greater than the preset threshold, it is identified that the fault type of the frame circuit breaker is an arc fault.

[0025] Among them, also include:

[0026] a risk prediction unit, configured to monitor the status of an energy storage motor, an opening magnetic flux, a closing magnetic flux, and an energy storage spring provided on the frame circuit breaker when a fault occurs in the frame circuit breaker, and score the monitored status of the energy storage motor, the opening magnetic flux, the closing magnetic flux, and the energy storage spring according to severity, frequency, and detection, and further predict the risk level of the energy storage motor, the opening magnetic flux, the closing magnetic flux, and the energy storage spring based on the scoring results.

[0027] The implementation of the embodiments of the present invention has the following beneficial effects:

[0028] 1. The present invention extracts features based on the vibration signal on the low-voltage distribution cabinet and the three-phase current and voltage signals flowing through the main incoming line circuit connected to it, as well as the temperature signal and arc signal generated on the moving and static contacts of the frame circuit breaker. Based on the corresponding extracted features, the present invention identifies the fault type when a frame circuit breaker fails. This allows for real-time monitoring of the frame circuit breaker's operating status, thereby accurately identifying the fault type.

[0029] 2. When the frame circuit breaker fails, the present invention monitors the status of the energy storage motor, opening magnetic flux, closing magnetic flux and energy storage spring provided on the frame circuit breaker to score, and realizes risk prediction of the frame circuit breaker based on the scoring results. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying any creative work, other drawings obtained based on these drawings still fall within the scope of the present invention.

[0031] Figure 1 A flow chart of a frame circuit breaker fault diagnosis and risk prediction method provided by an embodiment of the present invention;

[0032] Figure 2 A schematic structural diagram of a frame circuit breaker fault diagnosis and risk prediction system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention will be described in further detail below with reference to the accompanying drawings.

[0034] like Figure 1 As shown in the figure, a frame circuit breaker fault diagnosis and risk prediction method is provided in an embodiment of the present invention, and the method includes the following steps:

[0035] Step S1: On a low-voltage distribution cabinet connected to a frame circuit breaker, a vibration signal on the low-voltage distribution cabinet and a three-phase current signal and a three-phase voltage signal flowing through a main incoming line circuit connected thereto are obtained in real time, as well as a temperature signal and an arc signal generated on the moving and static contacts of the frame circuit breaker;

[0036] The specific process is as follows: First, install a frame circuit breaker (such as Schneider Masterpact MTZ or ABB Emax2) in a low-voltage distribution cabinet (AC 400V, 50Hz) and connect it to the main incoming line circuit of the low-voltage distribution cabinet, ensuring that the wiring complies with the IEC60947-2 standard. At the same time, configure the frame circuit breaker's rated current (such as 1600A), short-circuit breaking capacity (such as 65kA), and protection parameters (set the instantaneous trip threshold to 10 times the rated current).

[0037] Next, install high-precision current transformers (CT, Class 0.5 accuracy) and voltage sensors (PT) on the three-phase lines of the main incoming line. Also, integrate a temperature sensor (such as PT100) at the circuit breaker contacts, a vibration sensor (piezoelectric) inside the cabinet, and a UV sensor inside the circuit breaker's arc chamber.

[0038] Current: Three-phase current signal (range 0-2000A, sampling rate 10kHz). Voltage: Line voltage (0-600V) and phase voltage (0-400V), sampling rate 1kHz. Temperature: Contact temperature (-20°C to 150°C), sampling rate 1Hz. Vibration: Cabinet vibration acceleration (0-10g), sampling rate 500Hz.

[0039] Finally, through the above-mentioned sensors, the vibration signal on the low-voltage distribution cabinet and the three-phase current signal and three-phase voltage signal flowing through the main incoming line circuit connected to it are obtained in real time, as well as the temperature signal and the arc signal generated on the moving and static contacts of the frame circuit breaker.

[0040] Step S2: Based on the timestamp, the three-phase current signal, three-phase voltage signal, vibration signal, temperature signal and arc signal acquired in real time are aligned and filtered, and further feature extraction is performed;

[0041] The specific process is as follows: first, the three-phase current signal, three-phase voltage signal, vibration signal, temperature signal and arc signal are aligned through timestamp (error <1ms).

[0042] Next, a digital low-pass filter (Butterworth, cutoff frequency 1kHz) was used to remove high-frequency interference from the three-phase current, three-phase voltage, temperature, and arc signals. Furthermore, wavelet denoising (Daubechies 4) was applied to the vibration signal to extract the effective frequency band (50Hz-2kHz).

[0043] Finally, current features, voltage features, vibration features, temperature features, and arc features are extracted as follows:

[0044] The features of the three-phase current signal are extracted, including the amplitude, instantaneous peak value (e.g., 15kA), RMS value, and harmonic content (THD) of each phase current;

[0045] The features extracted from the three-phase voltage signal include the voltage drop rate of each phase (ΔU>30% rated voltage is considered abnormal);

[0046] The features of the vibration signal extracted include spectral energy (dominant frequency > 1kHz is considered abnormal);

[0047] The features of the temperature signal extracted include the temperature change gradient, i.e., the temperature cycle time change rate;

[0048] The characteristics of the arc signal extraction include arc pulse intensity (such as >200μW / cm 2 considered abnormal).

[0049] Step S3: Identify the fault type of the frame circuit breaker when a fault occurs based on the extracted features corresponding to each signal; wherein the fault type includes short circuit fault, overload fault, ground fault, contact fault and arc fault.

[0050] The specific process involves first constructing a CNN-based fault network neural model. Its input layer includes current peak value, voltage sag rate, temperature gradient, and vibration energy. The hidden layer is a three-layer fully connected network (128-64-32 nodes) with a Reluctant Unit (ReLU) activation function. The output layer uses a Softmax classification algorithm, including normal, short-circuit, overload, ground fault, and contact fault. Furthermore, a weighted voting model is constructed, which uses weights for high-frequency current, arc signal, and voltage sag to create a scoring model.

[0051] Secondly, based on historical data, the fault network neural model is trained and tested to obtain a trained fault network neural model. The specific process is implemented using conventional technical means in this field and will not be described in detail here.

[0052] Next, the judgment conditions for the failure of the frame circuit breaker are set, including but not limited to the amplitude of the phase current being greater than the preset current amplitude, the instantaneous peak value of the phase current being greater than the preset current peak value, the RMS value of the phase current being outside the preset effective value range, the harmonic content of the phase current being greater than the preset proportion, and the arc pulse intensity of the arc signal being greater than the preset intensity threshold, etc. The specific situation can be flexibly designed according to actual conditions and will not be elaborated here.

[0053] Finally, the frame circuit breaker fault is identified and the fault type is further identified as follows:

[0054] (1) If it is determined that the amplitude of a phase current is greater than a preset current amplitude, the instantaneous peak value is greater than a preset current peak value, the RMS value is outside the preset effective value range, or the harmonic content is greater than a preset ratio, then the frame circuit breaker is identified as having a fault, and the instantaneous peak value of the three-phase current signal, the drop rate of the three-phase voltage signal, the temperature change gradient of the temperature signal, and the spectrum energy of the vibration signal are extracted and imported into the trained fault network neural model to identify the fault type of the frame circuit breaker as one of a short circuit fault, an overload fault, a ground fault, and a contact fault.

[0055] (2) If it is determined that the arc pulse intensity of the arc signal is greater than the preset intensity threshold, the frame circuit breaker is identified as having a fault, and the instantaneous peak value of the three-phase current signal and the drop rate of the three-phase voltage signal are combined and imported into the preset weighted voting model to calculate the corresponding weighted score. When it is determined that the calculated weighted score is greater than the preset threshold, the fault type of the frame circuit breaker is identified as an arc fault. In one example, the weighted score of the instantaneous peak value of the three-phase current signal is 0.6, the weighted score of the arc signal is 0.3, and the weighted score of the drop rate of the three-phase voltage signal is 0.1. If the total score 1> the preset threshold 0.8, then the fault type is an arc fault. On the contrary, if the total score < the preset threshold 0.8, then the fault type is not an arc fault.

[0056] It is understandable that the above fault types are all judged through data after multi-information fusion, thereby improving the accuracy of identifying the fault type.

[0057] In an embodiment of the present invention, when a frame circuit breaker fails, the current waveforms of key components such as the opening and closing coils and the energy storage motor are detected, the harmonic components and transient characteristics of the current are obtained through Fourier transform, and characteristic parameters related to the health status of the circuit breaker are extracted, thereby realizing risk prediction of the frame circuit breaker.

[0058] Therefore, the method further includes: when a frame circuit breaker fails, monitoring the status of the energy storage motor, opening magnetic flux, closing magnetic flux and energy storage spring provided on the frame circuit breaker, and scoring the monitored status of the energy storage motor, opening magnetic flux, closing magnetic flux and energy storage spring according to severity, frequency and detection, and further predicting the risk level of the energy storage motor, opening magnetic flux, closing magnetic flux and energy storage spring based on the scoring results.

[0059] In one example, first, the abnormal status of the energy storage motor, the opening magnetic flux, the closing magnetic flux, and the energy storage spring is identified, as shown in Table 1 below:

[0060] Table 1

[0061]

[0062] Next, based on the identified abnormal conditions in Table 1, a risk quantification (RPN) calculation is performed based on three dimensions: severity, frequency, and detection, resulting in a corresponding score, as shown in Table 2. Severity (S) is scored based on the consequences of failure (e.g., trip failure = 10, insulation aging = 5); frequency (O) is based on the statistical probability of failure based on historical data (e.g., oxidation frequency = 3, spring breakage = 2); and detection (D) is based on the current fingerprint detection capability (e.g., harmonic analysis can predict component failure in advance → D = 3).

[0063] Table 2

[0064]

[0065] Next, set up the risk level query table, as shown in Table 3 below:

[0066] Table 3

[0067]

[0068] Finally, according to the correspondence between Table 2 and Table 3, it is predicted that the risk levels of the energy storage motor, closing flux and energy storage spring are all medium risk, and the risk level of the opening flux is low risk.

[0069] like Figure 2 As shown in the figure, a frame circuit breaker fault diagnosis and risk prediction system is provided in an embodiment of the present invention, including:

[0070] The data acquisition unit 110 is configured to acquire, in real time, a vibration signal on a low-voltage distribution cabinet connected to a frame circuit breaker and a three-phase current signal and a three-phase voltage signal flowing through a main incoming line circuit connected thereto, as well as a temperature signal and an arc signal generated on the moving and static contacts of the frame circuit breaker;

[0071] The feature extraction unit 120 is used to align the three-phase current signal, three-phase voltage signal, vibration signal, temperature signal and arc signal acquired in real time based on the timestamp, perform filtering processing, and further perform feature extraction;

[0072] The fault diagnosis unit 130 is configured to identify the fault type of the frame circuit breaker when a fault occurs based on the extracted features corresponding to each signal; wherein the fault type includes short circuit fault, overload fault, ground fault, contact fault and arc fault.

[0073] Among them, the features extracted corresponding to the three-phase current signal include the amplitude, instantaneous peak value, RMS value and harmonic content of each phase current; the features extracted corresponding to the three-phase voltage signal include the voltage drop rate of each phase; the features extracted corresponding to the vibration signal include spectral energy; the features extracted corresponding to the temperature signal include temperature change gradient; the features extracted corresponding to the arc signal include arc pulse intensity.

[0074] The fault diagnosis unit 130 includes:

[0075] The first diagnostic module is configured to identify a fault in the frame circuit breaker if it is determined that the amplitude of a phase current is greater than a preset current amplitude, the instantaneous peak value is greater than a preset current peak value, the RMS value is outside a preset effective value range, or the harmonic content is greater than a preset ratio. The module also extracts the instantaneous peak value of the three-phase current signal, the sag rate of the three-phase voltage signal, the temperature change gradient of the temperature signal, and the spectrum energy of the vibration signal, and imports these into a trained fault network neural model to identify the fault type of the frame circuit breaker as one of a short circuit fault, an overload fault, a ground fault, and a contact fault.

[0076] The fault diagnosis unit 130 further includes:

[0077] The second diagnostic module is used to identify that the frame circuit breaker has a fault if it is determined that the arc pulse intensity of the arc signal is greater than a preset intensity threshold, and to import the instantaneous peak value of the three-phase current signal and the drop rate of the three-phase voltage signal into a preset weighted voting model to calculate the corresponding weighted score. When it is determined that the calculated weighted score is greater than the preset threshold, it is identified that the fault type of the frame circuit breaker is an arc fault.

[0078] Among them, also include:

[0079] a risk prediction unit, configured to monitor the status of an energy storage motor, an opening magnetic flux, a closing magnetic flux, and an energy storage spring provided on the frame circuit breaker when a fault occurs in the frame circuit breaker, and score the monitored status of the energy storage motor, the opening magnetic flux, the closing magnetic flux, and the energy storage spring according to severity, frequency, and detection, and further predict the risk level of the energy storage motor, the opening magnetic flux, the closing magnetic flux, and the energy storage spring based on the scoring results.

[0080] The implementation of the embodiments of the present invention has the following beneficial effects:

[0081] 1. The present invention extracts features based on the vibration signal on the low-voltage distribution cabinet and the three-phase current and voltage signals flowing through the main incoming line circuit connected to it, as well as the temperature signal and arc signal generated on the moving and static contacts of the frame circuit breaker. Based on the corresponding extracted features, the present invention identifies the fault type when a frame circuit breaker fails. This allows for real-time monitoring of the frame circuit breaker's operating status, thereby accurately identifying the fault type.

[0082] 2. When the frame circuit breaker fails, the present invention monitors the status of the energy storage motor, opening magnetic flux, closing magnetic flux and energy storage spring provided on the frame circuit breaker to score, and realizes risk prediction of the frame circuit breaker based on the scoring results.

[0083] It is worth noting that in the above system embodiment, the various system units included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the various functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0084] Those skilled in the art will understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc.

[0085] The above disclosure is merely a preferred embodiment of the present invention and certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A frame circuit breaker fault diagnosis and risk prediction method, characterized in that: The method comprises the following steps: S1. On a low-voltage distribution cabinet connected to a frame circuit breaker, obtain in real time a vibration signal on the low-voltage distribution cabinet and a three-phase current signal and a three-phase voltage signal flowing through a main incoming line circuit connected thereto, as well as a temperature signal and an arc signal generated on the moving and static contacts of the frame circuit breaker; S2. Based on the timestamp, the three-phase current signal, three-phase voltage signal, vibration signal, temperature signal, and arc signal acquired in real time are aligned and filtered, and further feature extraction is performed; S3. Identify the fault type of the frame circuit breaker when a fault occurs based on the extracted features corresponding to each signal; wherein the fault type includes short circuit fault, overload fault, ground fault, contact fault and arc fault.

2. The frame circuit breaker fault diagnosis and risk prediction method according to claim 1, characterized in that: In step S2, the features extracted from the three-phase current signal include the amplitude, instantaneous peak value, RMS value and harmonic content of each phase current; the features extracted from the three-phase voltage signal include the voltage drop rate of each phase; the features extracted from the vibration signal include spectral energy; the features extracted from the temperature signal include temperature change gradient; and the features extracted from the arc signal include arc pulse intensity.

3. The frame circuit breaker fault diagnosis and risk prediction method according to claim 2, characterized in that: The step S3 specifically includes: If it is determined that the amplitude of a phase current is greater than a preset current amplitude, the instantaneous peak is greater than a preset current peak, the RMS value is outside a preset effective value range, or the harmonic content is greater than a preset ratio, then the frame circuit breaker is identified as having a fault, and the instantaneous peak value of the three-phase current signal, the drop rate of the three-phase voltage signal, the temperature change gradient of the temperature signal, and the spectrum energy of the vibration signal are extracted and imported into the trained fault network neural model to identify the fault type of the frame circuit breaker as one of a short circuit fault, an overload fault, a ground fault, and a contact fault.

4. The frame circuit breaker fault diagnosis and risk prediction method according to claim 3, characterized in that: The step S3 further includes: If it is determined that the arc pulse intensity of the arc signal is greater than the preset intensity threshold, the frame circuit breaker is identified as having a fault, and the instantaneous peak value of the three-phase current signal and the drop rate of the three-phase voltage signal are combined and imported into the preset weighted voting model to calculate the corresponding weighted score. When it is determined that the calculated weighted score is greater than the preset threshold, the fault type of the frame circuit breaker is identified as an arc fault.

5. The frame circuit breaker fault diagnosis and risk prediction method according to claim 4, characterized in that: The method further comprises: When a fault occurs in the frame circuit breaker, the status of the energy storage motor, the opening magnetic flux, the closing magnetic flux and the energy storage spring provided on the frame circuit breaker is monitored, and the monitored status of the energy storage motor, the opening magnetic flux, the closing magnetic flux and the energy storage spring is scored according to the severity, frequency and detection degree, and the risk level of the energy storage motor, the opening magnetic flux, the closing magnetic flux and the energy storage spring is further predicted based on the scoring results.

6. A frame circuit breaker fault diagnosis and risk prediction system, characterized in that: include: A data acquisition unit is used to obtain, in real time, a vibration signal on a low-voltage distribution cabinet connected to a frame circuit breaker and a three-phase current signal and a three-phase voltage signal flowing through a main incoming line circuit connected to the low-voltage distribution cabinet, as well as a temperature signal and an arc signal generated on the moving and static contacts of the frame circuit breaker; A feature extraction unit is used to align the three-phase current signal, three-phase voltage signal, vibration signal, temperature signal and arc signal acquired in real time based on the timestamp, perform filtering processing, and further perform feature extraction; The fault diagnosis unit is used to identify the fault type of the frame circuit breaker when a fault occurs based on the features extracted corresponding to each signal; wherein the fault type includes short circuit fault, overload fault, ground fault, contact fault and arc fault.

7. The frame circuit breaker fault diagnosis and risk prediction system according to claim 6, characterized in that: The features extracted from the three-phase current signal include the amplitude, instantaneous peak value, RMS value and harmonic content of each phase current; the features extracted from the three-phase voltage signal include the voltage drop rate of each phase; the features extracted from the vibration signal include spectral energy; the features extracted from the temperature signal include temperature change gradient; the features extracted from the arc signal include arc pulse intensity.

8. The frame circuit breaker fault diagnosis and risk prediction system according to claim 7, characterized in that: The fault diagnosis unit includes: The first diagnostic module is configured to identify a fault in the frame circuit breaker if it is determined that the amplitude of a phase current is greater than a preset current amplitude, the instantaneous peak value is greater than a preset current peak value, the RMS value is outside a preset effective value range, or the harmonic content is greater than a preset ratio. The module also extracts the instantaneous peak value of the three-phase current signal, the sag rate of the three-phase voltage signal, the temperature change gradient of the temperature signal, and the spectrum energy of the vibration signal, and imports these into a trained fault network neural model to identify the fault type of the frame circuit breaker as one of a short circuit fault, an overload fault, a ground fault, and a contact fault.

9. The frame circuit breaker fault diagnosis and risk prediction system according to claim 8, characterized in that: The fault diagnosis unit further includes: The second diagnostic module is used to identify that the frame circuit breaker has a fault if it is determined that the arc pulse intensity of the arc signal is greater than a preset intensity threshold, and to import the instantaneous peak value of the three-phase current signal and the drop rate of the three-phase voltage signal into a preset weighted voting model to calculate the corresponding weighted score. When it is determined that the calculated weighted score is greater than the preset threshold, it is identified that the fault type of the frame circuit breaker is an arc fault.

10. The frame circuit breaker fault diagnosis and risk prediction system according to claim 9, characterized in that: Also includes: a risk prediction unit, configured to monitor the status of an energy storage motor, an opening magnetic flux, a closing magnetic flux, and an energy storage spring provided on the frame circuit breaker when a fault occurs in the frame circuit breaker, and score the monitored status of the energy storage motor, the opening magnetic flux, the closing magnetic flux, and the energy storage spring according to severity, frequency, and detection, and further predict the risk level of the energy storage motor, the opening magnetic flux, the closing magnetic flux, and the energy storage spring based on the scoring results.

Images