Temperature rise early warning method and system of circuit breaker

Abstract

The invention discloses a temperature rise early warning method and system for a circuit breaker, and the method comprises the steps: collecting a plurality of temperature data of a terminal of the circuit breaker in a working state of the circuit breaker, constructing a temperature rise change curve according to the plurality of temperature data, introducing the temperature rise change curve so as to record the change of the temperature data through the temperature rise change curve, and meanwhile, carrying out the early warning of the temperature rise of the circuit breaker. And training a temperature rise change prediction model of the circuit breaker terminal based on the plurality of temperature data in the temperature rise change curve so as to output a temperature rise prediction result based on the temperature rise change prediction model and the current temperature data, thereby defining an abnormal state or a normal state of the circuit breaker according to comparison between the temperature rise prediction result and a preset interval. The method is advantaged in that an abnormal state or a normal state of the circuit breaker can be conveniently controlled, the state of the circuit breaker is managed and controlled, an early warning signal is emitted according to the abnormal condition, temperature rise prediction and temperature rise early warning of the circuit breaker are facilitated, and the state of the circuit breaker is controlled in multiple dimensions.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature rise warning of circuit breakers, and in particular to a temperature rise warning method and system for circuit breakers. Background Art

[0002] With the progress of the national economy and the development of new power systems, the complexity of power systems has increased day by day, the electricity consumed by people in production and life has also been increasing, the load that the power system needs to bear has greatly increased, and the requirements for the safety and reliability of power grid operation have become increasingly higher.

[0003] As an important control and protection device, low-voltage circuit breakers can not only connect and disconnect normal or overload current in AC and DC low-voltage power grids, but also be responsible for timely cutting off the line when a short-circuit fault occurs. The safe and stable operation of low-voltage circuit breakers plays an important role in maintaining the reliable operation of the power grid.

[0004] In actual applications, most substations or transmission stations use infrared imagers to monitor the temperature of power equipment, and manually determine whether the equipment has a temperature rise failure, resulting in the inability to control the status of the circuit breaker in multiple dimensions and the inability to respond to abnormal situations in a timely manner. Summary of the invention

[0005] The purpose of the present invention is to overcome the shortcomings of the prior art. The present invention provides a temperature rise warning method and system for a circuit breaker. In the working state of the circuit breaker, multiple temperature data of the circuit breaker terminal are collected, and a temperature rise change curve is constructed according to the multiple temperature data, and the temperature rise change curve is introduced to record the change of temperature data through the temperature rise change curve. At the same time, a temperature rise change prediction model of the circuit breaker terminal is trained based on the multiple temperature data in the temperature rise change curve, so as to output the temperature rise prediction result based on the temperature rise change prediction model and the current temperature data, so as to define the abnormal state or normal state of the circuit breaker according to the comparison between the temperature rise prediction result and the preset interval, so as to control the abnormal state or normal state of the circuit breaker, and control the state of the circuit breaker, so as to send a warning signal according to the abnormal situation, so as to be compatible with the temperature rise prediction and temperature rise warning of the circuit breaker, so as to control the state of the circuit breaker in multiple dimensions and respond to the abnormal situation in time.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a temperature rise warning method for a circuit breaker, which is applied to a temperature rise warning scenario of a circuit breaker; the temperature rise warning method for a circuit breaker comprises: Real-time monitoring of the working status of the circuit breaker; In the working state of the circuit breaker, multiple temperature data of the circuit breaker terminals are collected, and a temperature rise change curve is constructed according to the multiple temperature data; Training a temperature rise change prediction model for circuit breaker terminals based on multiple temperature data in the temperature rise change curve; Output the temperature rise prediction result based on the temperature rise change prediction model and the current temperature data; define the abnormal state or normal state of the circuit breaker according to the comparison between the temperature rise prediction result and the preset range; When the circuit breaker is in an abnormal state, the abnormal situation of the circuit breaker is collected and an early warning signal is issued according to the abnormal situation.

[0007] Optionally, the real-time monitoring of the working status of the circuit breaker includes: Collect the location of the circuit breaker and locate the circuit breaker according to the location of the circuit breaker; Collect multiple parameters of the circuit breaker, and define the working state of the circuit breaker according to the multiple parameters of the circuit breaker. At the same time, perform real-time monitoring on the working state of the circuit breaker.

[0008] Optionally, in the working state of the circuit breaker, collecting a plurality of temperature data of the circuit breaker terminals, and constructing a temperature rise change curve according to the plurality of temperature data, including: In the working state of the circuit breaker, build a temperature rise test platform for steady-state operation of the circuit breaker; Collect multiple temperature data of circuit breaker terminals based on the temperature rise test platform; Define multiple temperature nodes according to multiple temperature data, and record corresponding change curves for two adjacent temperature nodes; A temperature rise variation curve is constructed based on multiple temperature nodes and corresponding variation curves.

[0009] Optionally, the training of the temperature rise change prediction model of the circuit breaker terminal based on the multiple temperature data in the temperature rise change curve includes: Fixed frame temperature rise curve; Define marking points based on the temperature rise curve, and present corresponding temperature data based on the marking points; Collect multiple temperature data and use the multiple temperature data as training data; The learning model is collected and trained according to the learning model and the training data to output a temperature rise change prediction model for the circuit breaker terminal. At this time, the long short-term memory network model is selected to perform time series prediction of the temperature rise change.

[0010] Optionally, the training of the temperature rise change prediction model of the circuit breaker terminal based on the multiple temperature data in the temperature rise change curve further includes: The calculation formula for selecting the long short-term memory network model is as follows:

[0011] in, x represents the input vector, hrepresents the output vector, ⊙ represents the dot product operator, and the matrix W represents the parameters to be trained, σ (∙) represents the sigmoid nonlinear function, and tan h (∙) represents the hyperbolic tangent function.

[0012] Optionally, the training of the temperature rise change prediction model of the circuit breaker terminal based on the multiple temperature data in the temperature rise change curve further includes: The root mean square error is used to evaluate the prediction accuracy of the temperature rise change prediction model. The root mean square error is calculated as follows:

[0013] Among them, RMSE is the root mean square error, To predict the temperature, is the actual measured temperature.

[0014] Optionally, outputting a temperature rise prediction result based on the temperature rise change prediction model and the current temperature data; and defining an abnormal state or a normal state of the circuit breaker according to a comparison between the temperature rise prediction result and a preset interval include: Fixed-frame temperature rise change prediction model; Correlate the temperature rise change prediction model with the current temperature data; The temperature rise prediction results are output based on the temperature rise change prediction model and the current temperature data.

[0015] Optionally, the outputting of the temperature rise prediction result based on the temperature rise change prediction model and the current temperature data; and defining the abnormal state or normal state of the circuit breaker according to the comparison between the temperature rise prediction result and a preset interval, further includes: Collecting preset intervals corresponding to circuit breaker terminals; Correlate temperature rise prediction results with preset intervals; Compare the temperature rise prediction result with the preset interval and output the comparison result; The abnormal state or normal state of the circuit breaker is defined based on the comparison result.

[0016] Optionally, when the circuit breaker is in an abnormal state, collecting the abnormal condition of the circuit breaker and issuing an early warning signal according to the abnormal condition includes: When the circuit breaker is in an abnormal state, collect the temperature rise data of the circuit breaker in the abnormal state; Define the abnormal condition of the circuit breaker according to the temperature rise data of the circuit breaker in the abnormal state; Define exception types based on the exception situation; The corresponding warning signal is matched according to the abnormal type and issued.

[0017] Optionally, a temperature rise warning system for a circuit breaker is provided, wherein the temperature rise warning system for a circuit breaker is applied to the temperature rise warning method for a circuit breaker, and the temperature rise warning system for a circuit breaker comprises: Monitoring module, used to monitor the working status of the circuit breaker in real time; The temperature rise variation curve module is used to collect multiple temperature data of the circuit breaker terminals when the circuit breaker is in working state, and to construct a temperature rise variation curve according to the multiple temperature data; A temperature rise change prediction model module is used to train a temperature rise change prediction model of a circuit breaker terminal based on multiple temperature data in a temperature rise change curve; A comparison module is used to output a temperature rise prediction result based on the temperature rise change prediction model and the current temperature data; and to define an abnormal state or a normal state of the circuit breaker according to the comparison between the temperature rise prediction result and a preset interval; The early warning module is used to collect the abnormal conditions of the circuit breaker when the circuit breaker is in an abnormal state, and issue an early warning signal according to the abnormal conditions.

[0018] In an embodiment of the present invention, through the method in the embodiment of the present invention, in the working state of the circuit breaker, multiple temperature data of the circuit breaker terminal are collected, and a temperature rise change curve is constructed according to the multiple temperature data, and the temperature rise change curve is introduced to record the change of temperature data through the temperature rise change curve. At the same time, a temperature rise change prediction model of the circuit breaker terminal is trained based on the multiple temperature data in the temperature rise change curve, so as to output the temperature rise prediction result based on the temperature rise change prediction model and the current temperature data, so as to define the abnormal state or normal state of the circuit breaker according to the comparison between the temperature rise prediction result and the preset interval, so as to control the abnormal state or normal state of the circuit breaker, and manage the state of the circuit breaker, so as to send out an early warning signal according to the abnormal situation, so as to be compatible with the temperature rise prediction and temperature rise early warning of the circuit breaker, so as to control the state of the circuit breaker in multiple dimensions and respond to the abnormal situation in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 is a flow chart of a temperature rise warning method for a circuit breaker in an embodiment of the present invention; Figure 2 is a flow chart of S11 in the temperature rise warning method for a circuit breaker in an embodiment of the present invention; Figure 3is a flow chart of S12 in the temperature rise warning method for a circuit breaker in an embodiment of the present invention; Figure 4 is a flow chart of S13 in the temperature rise warning method for a circuit breaker in an embodiment of the present invention; Figure 5 is a flow chart of S14 in the temperature rise warning method for a circuit breaker in an embodiment of the present invention; Figure 6 is a flow chart of S15 in the temperature rise warning method for a circuit breaker in an embodiment of the present invention; Figure 7 is a schematic diagram of a temperature rise prediction result in a temperature rise early warning method for a circuit breaker in an embodiment of the present invention; Figure 8 is a schematic diagram of temperature rise points in a temperature rise early warning method for a circuit breaker in an embodiment of the present invention; Fig. 9 is a schematic diagram of an LSTM unit in a temperature rise warning method for a circuit breaker in an embodiment of the present invention; Fig.10 is a schematic diagram of a temperature rise variation curve in a temperature rise early warning method for a circuit breaker in an embodiment of the present invention; Fig.11 Schematic diagram of the structure of the temperature rise warning system of the circuit breaker in the embodiment of the present invention; Fig.12 The figure is a hardware diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Method Embodiment See also Figures 1 to 12 , a temperature rise warning method for a circuit breaker, applied to a temperature rise warning scenario of a circuit breaker; the temperature rise warning method for a circuit breaker comprises: Step S11: monitor the working status of the circuit breaker in real time; Step S12: In the working state of the circuit breaker, a plurality of temperature data of the circuit breaker terminals are collected, and a temperature rise change curve is constructed according to the plurality of temperature data; Step S13: training a temperature rise change prediction model of the circuit breaker terminal based on a plurality of temperature data in the temperature rise change curve; Step S14: outputting a temperature rise prediction result based on the temperature rise change prediction model and the current temperature data; defining an abnormal state or a normal state of the circuit breaker according to a comparison between the temperature rise prediction result and a preset interval; Step S15: When the circuit breaker is in an abnormal state, the abnormal situation of the circuit breaker is collected, and an early warning signal is issued according to the abnormal situation.

[0023] In an embodiment of the present invention, through the method in the embodiment of the present invention, in the working state of the circuit breaker, multiple temperature data of the circuit breaker terminal are collected, and a temperature rise change curve is constructed according to the multiple temperature data, and the temperature rise change curve is introduced to record the change of temperature data through the temperature rise change curve. At the same time, a temperature rise change prediction model of the circuit breaker terminal is trained based on the multiple temperature data in the temperature rise change curve, so as to output the temperature rise prediction result based on the temperature rise change prediction model and the current temperature data, so as to define the abnormal state or normal state of the circuit breaker according to the comparison between the temperature rise prediction result and the preset interval, so as to control the abnormal state or normal state of the circuit breaker, and manage the state of the circuit breaker, so as to send out an early warning signal according to the abnormal situation, so as to be compatible with the temperature rise prediction and temperature rise early warning of the circuit breaker, so as to control the state of the circuit breaker in multiple dimensions and respond to the abnormal situation in time.

[0024] See also Figure 2 , in step S11, the working status of the circuit breaker is monitored in real time; In the specific implementation process of the present invention, the specific steps may be: S111: collecting the location of the circuit breaker and locating the circuit breaker according to the location of the circuit breaker; S112: Collect multiple parameters of the circuit breaker, and define the working state of the circuit breaker according to the multiple parameters of the circuit breaker, and at the same time, perform real-time monitoring on the working state of the circuit breaker.

[0025] In an embodiment of the present application, the location of the circuit breaker is collected, and the circuit breaker is positioned according to the location of the circuit breaker; multiple parameters of the circuit breaker are collected, and the working state of the circuit breaker is defined according to the multiple parameters of the circuit breaker. At the same time, the working state of the circuit breaker is monitored in real time to facilitate further control of the working state of the circuit breaker, thereby following up the working process of the circuit breaker in real time.

[0026] See also Figure 3 , in step S12, in the working state of the circuit breaker, a plurality of temperature data of the circuit breaker terminals are collected, and a temperature rise change curve is constructed according to the plurality of temperature data; In the specific implementation process of the present invention, the specific steps may be: S121: In the working state of the circuit breaker, a temperature rise test platform for steady-state operation of the circuit breaker is built; S122: collecting multiple temperature data of the circuit breaker terminals based on the temperature rise test platform; S123: defining a plurality of temperature nodes according to the plurality of temperature data, and recording corresponding change curves for two adjacent temperature nodes; S124: Constructing a temperature rise variation curve based on the multiple temperature nodes and the corresponding variation curves.

[0027] In an embodiment of the present application, in the working state of the circuit breaker, a temperature rise test platform for steady-state operation of the circuit breaker is built, so as to introduce the temperature rise test platform, thereby collecting multiple temperature data of the circuit breaker terminals based on the temperature rise test platform, so as to perform temperature detection on the circuit breaker terminals, thereby collecting multiple temperature data. At this time, the temperature condition of the circuit breaker is presented based on the temperature condition of the circuit breaker terminals, so as to control the temperature rise of the circuit breaker.

[0028] At this time, multiple temperature nodes are defined according to multiple temperature data, and corresponding change curves are recorded for two adjacent temperature nodes; a temperature rise change curve is constructed based on the multiple temperature nodes and the corresponding change curves, so that the temperature rise change curve is constructed according to the multiple temperature nodes and the corresponding change curves, thereby ensuring the accuracy of the temperature rise change curve, and then ensuring the accuracy of each position in the temperature rise change curve.

[0029] See also Figure 4 , in step S13, a temperature rise change prediction model of the circuit breaker terminal is trained based on a plurality of temperature data in the temperature rise change curve; In the specific implementation process of the present invention, the specific steps may be: S131: Fixed temperature rise curve; S132: defining a marking point based on the temperature rise change curve, and presenting corresponding temperature data based on the marking point; S133: Collect multiple temperature data and use the multiple temperature data as training data; S134: collecting a learning model, and performing training according to the learning model and the training data to output a temperature rise change prediction model for the circuit breaker terminal. At this time, a long short-term memory network model is selected to perform time series prediction of the temperature rise change.

[0030] In an embodiment of the present application, the temperature rise variation curve is frozen, and the temperature rise variation curve is controlled, so that marking points are defined based on the temperature rise variation curve, and corresponding temperature data are presented based on the marking points, thereby introducing corresponding temperature data.

[0031] At this time, multiple temperature data are collected and used as training data; a learning model is collected and trained according to the learning model and the training data to output a temperature rise change prediction model for the circuit breaker terminal. At this time, a long short-term memory network model is selected to perform time series prediction of temperature rise changes.

[0032] The method of training the temperature rise change prediction model of the circuit breaker terminal based on the multiple temperature data in the temperature rise change curve also includes: The calculation formula for selecting the long short-term memory network model is as follows:

[0033] in, x represents the input vector, h represents the output vector, ⊙ represents the dot product operator, and the matrix W represents the parameters to be trained, σ (∙) represents the sigmoid nonlinear function, and tan h (∙) represents the hyperbolic tangent function.

[0034] In addition, the root mean square error is used to evaluate the prediction accuracy of the temperature rise change prediction model. The root mean square error is calculated as follows:

[0035] Among them, RMSE is the root mean square error, To predict the temperature, is the actual measured temperature.

[0036] See also Figure 5 , S14: outputting a temperature rise prediction result based on the temperature rise change prediction model and the current temperature data; defining an abnormal state or a normal state of the circuit breaker according to a comparison between the temperature rise prediction result and a preset interval; In the specific implementation process of the present invention, the specific steps may be: S141: Fixed-frame temperature rise change prediction model; S142: Associating the temperature rise change prediction model with the current temperature data; S143: Outputting a temperature rise prediction result according to the temperature rise change prediction model and current temperature data; S144: collecting the preset interval corresponding to the circuit breaker terminal; S145: Associating the temperature rise prediction result with the preset range; S146: Compare the temperature rise prediction result with the preset interval and output the comparison result; S147: Define the abnormal state or normal state of the circuit breaker based on the comparison result.

[0037] In an embodiment of the present application, the temperature rise change prediction model is frozen, and the temperature rise change prediction model is controlled to associate the temperature rise change prediction model and the current temperature data, so as to output the temperature rise prediction result according to the temperature rise change prediction model and the current temperature data, thereby freezing the temperature rise prediction result.

[0038] At this time, the preset interval corresponding to the circuit breaker terminal is collected, and the temperature rise prediction result is associated with the preset interval, so as to compare the temperature rise prediction result with the preset interval, and output the comparison result, thereby clarifying the comparison result, and then defining the abnormal state or normal state of the circuit breaker based on the comparison result, realizing the management and control of the abnormal state or normal state of the circuit breaker, and ensuring the state detection accuracy of the circuit breaker.

[0039] See also Figure 6 , S15: When the circuit breaker is in an abnormal state, collect the abnormal situation of the circuit breaker and issue a warning signal according to the abnormal situation; In the specific implementation process of the present invention, the specific steps may be: S151: when the circuit breaker is in an abnormal state, collecting temperature rise data of the circuit breaker in the abnormal state; S152: defining an abnormal condition of the circuit breaker according to temperature rise data of the circuit breaker in an abnormal state; S153: define the exception type according to the exception situation; S154: Match a corresponding warning signal according to the abnormality type and issue the warning signal.

[0040] In an embodiment of the present application, when the circuit breaker is in an abnormal state, the temperature rise data of the circuit breaker in the abnormal state is collected, so as to control the temperature rise data of the circuit breaker in the abnormal state, and define the abnormal situation of the circuit breaker according to the temperature rise data of the circuit breaker in the abnormal state; At this time, the abnormal type is defined according to the abnormal situation; the corresponding warning signal is matched according to the abnormal type, and the warning signal is issued. Therefore, the temperature rise change prediction model of the circuit breaker terminal is trained based on multiple temperature data in the temperature rise change curve, so as to output the temperature rise prediction result based on the temperature rise change prediction model and the current temperature data, thereby defining the abnormal state or normal state of the circuit breaker according to the comparison between the temperature rise prediction result and the preset interval, so as to control the abnormal state or normal state of the circuit breaker, and control the state of the circuit breaker, so as to issue a warning signal according to the abnormal situation, so as to be compatible with the temperature rise prediction and temperature rise warning of the circuit breaker, so as to control the state of the circuit breaker in multiple dimensions and respond to abnormal situations in a timely manner.

[0041] The specific embodiments are as follows: Step ①, input the equipment parameters, working environment parameters and working electrical parameters of the low-voltage circuit breaker. The specific basic parameters include the frame grade, rated current, rated voltage, ultimate breaking capacity and operating breaking capacity of the low-voltage circuit breaker. According to the actual application of the low-voltage circuit breaker, other parameters (such as long-delay tripping current, short-delay tripping current, contact material, etc.) are selectively input. The environmental parameters include ambient temperature, humidity, air density, etc. The working electrical parameters include working current and working voltage.

[0042] Step ②, low-voltage circuit breaker temperature rise data collection. Take the low-voltage circuit breaker described in step ① as a prototype and operate it under the working conditions described in step ①. Since the contact part of the low-voltage circuit breaker is located inside the circuit breaker, the contact surface temperature cannot be directly measured. However, the temperature change of the input and output terminals of the low-voltage circuit breaker is basically consistent with the contact temperature change. Therefore, the temperature of the terminal can be measured to reflect the temperature state of the low-voltage circuit breaker.

[0043] Temperature sensors (such as temperature measuring thermocouples) are installed on the upper incoming terminal and the lower incoming terminal of the low-voltage circuit breaker. The temperature measurement interval is set to m and the sampling length is set to n according to the actual working conditions. The temperature change curve with a total length of m×n can be measured, and the obtained temperature change data is stored in the processor for the next step of processing.

[0044] Step ③, construct a prediction model for the temperature rise change of the low-voltage circuit breaker terminal. The temperature change data of the low-voltage circuit breaker terminal obtained in step ② is input into the artificial intelligence model for training. The models that can be used include but are not limited to the long short-term memory model (LSTM), exponential smoothing model, autoregressive model, sliding average model, hidden Markov model, etc. In order to obtain a better model effect, it is necessary to repeat the temperature measurement experiment of step ② at different load currents, obtain multiple sets of temperature rise change data as a training basis, and adjust the number of layers, number of nodes, loss function and other related parameters of the training model. The trained model will output the predicted temperature rise change. By calculating the error between the predicted temperature rise change and the actual temperature rise change, the prediction accuracy of the model can be evaluated. The mean absolute error (MAD) or root mean square error (RMSE) can be used as an evaluation indicator. The error allowable value is set according to the safety requirements of the on-site equipment. When the model error is below the allowable value, it is considered that the model prediction result has reached the required accuracy and can achieve reliable prediction of the temperature rise of the low-voltage circuit breaker terminal.

[0045] Step ④, import and apply the temperature rise prediction model. The temperature rise prediction model trained in step ③ is integrated into the signal processing unit. The signal processing unit can be a chip or device such as a single-chip microcomputer, FPGA, digital signal processor, host computer, etc. that can complete a series of data processing functions such as writing programs, storing data, running programs, and outputting data.

[0046] Connect the temperature sensor (such as thermocouple) to the equipment that needs to be monitored, and transmit the temperature data through data transmission and store it in the signal processing unit. The signal processing unit can input the received temperature data into the model for prediction, and feed back the prediction results to the outside world in a visual manner. The output method can be signal indicator light, visual user interface, etc.

[0047] Step ⑤, determine whether the temperature rise of the equipment is abnormal. A multi-level evaluation mechanism for the temperature rise of the low-voltage circuit breaker terminals is formulated. The specific steps are as follows. Comprehensively examine multiple factors such as equipment model, equipment characteristics, equipment operating environment, equipment load conditions, etc., and set the temperature rise status of the low-voltage circuit breaker terminals to multiple different levels. Different levels are judged by the terminal temperature rise prediction value, such as normal state, abnormal state, dangerous state, sensor abnormal state, etc. If the temperature rise predicted by the signal processing unit is in the normal range, it is considered that the low-voltage circuit breaker has no abnormality, and the system continues to monitor and record temperature rise changes; when the temperature rise predicted by the signal processing unit is in the abnormal range, an early warning signal is issued according to the specific abnormal situation and fed back from the output port.

[0048] The temperature rise prediction and early warning method is applicable to various low-voltage circuit breaker usage scenarios. The model parameters need to be adjusted in time when the application scenarios are different or the monitoring objects are different. In situations where safety requirements are very high or the environment is harsh (such as high temperature environment, humid environment, etc.), the model parameters need to be corrected.

[0049] In an embodiment of the present invention, through the method in the embodiment of the present invention, in the working state of the circuit breaker, multiple temperature data of the circuit breaker terminal are collected, and a temperature rise change curve is constructed according to the multiple temperature data, and the temperature rise change curve is introduced to record the change of temperature data through the temperature rise change curve. At the same time, a temperature rise change prediction model of the circuit breaker terminal is trained based on the multiple temperature data in the temperature rise change curve, so as to output the temperature rise prediction result based on the temperature rise change prediction model and the current temperature data, so as to define the abnormal state or normal state of the circuit breaker according to the comparison between the temperature rise prediction result and the preset interval, so as to control the abnormal state or normal state of the circuit breaker, and manage the state of the circuit breaker, so as to send out an early warning signal according to the abnormal situation, so as to be compatible with the temperature rise prediction and temperature rise early warning of the circuit breaker, so as to control the state of the circuit breaker in multiple dimensions and respond to the abnormal situation in time.

[0050] In addition, the temperature data of the low-voltage circuit breaker is measured with a sampling interval of 1s to obtain the steady-state temperature change curve of the low-voltage circuit breaker terminal under different loads; a model for predicting the temperature change of the low-voltage circuit breaker terminal based on an artificial intelligence algorithm is constructed, and the model is trained and tested; a hierarchical early warning method for the temperature rise of the low-voltage circuit breaker terminal is designed, and early warning information is output while predicting the terminal temperature rise. The present invention can predict and warn the temperature rise change and health status of the low-voltage circuit breaker with high prediction accuracy, and has a guiding role in maintaining the safe and stable operation of low-voltage equipment.

[0051] First, set the temperature threshold. In this embodiment, set the lower limit of normal temperature rise ℃, normal temperature rise lower limit ℃, dangerous temperature rise threshold ℃, the predicted temperature rise in the next period is , then the early warning strategy is as follows: When the temperature rise of the circuit breaker is considered to be in the normal range, the temperature rise data will continue to be monitored and recorded, and the temperature rise in the next period will be predicted; when When the sensor or signal processing unit is abnormal, the signal processing unit sends a "maintenance" signal to remind the staff to inspect and troubleshoot the sensor and other external devices; When the system sends out a "caution" signal three times in a row, it means that the low-voltage circuit breaker is in an abnormal state for a long time, and the system sends out an "alarm" signal, indicating that the temperature rise of the circuit breaker is abnormal, but there is no safety hazard for the time being, and the staff needs to pay attention to the working safety of the low-voltage circuit breaker; when the system sends out a "caution" signal three times in a row, it means that the low-voltage circuit breaker is in an abnormal state for a long time, and the system sends out an "alarm" signal, and the equipment needs to be troubleshooted, repaired or replaced; when When the low voltage circuit breaker is considered to have a serious fault, the signal processor skips the "attention" signal and directly sends out the "alarm" signal.

[0052] In this embodiment, the training algorithm is used to predict the results. Figure 6 To avoid confusion, Indicates time. When it is predicted time, , the system sends out a "caution" signal; but at the next moment, the predicted temperature rise returns to the normal range , then the "Caution" signal is released; At this moment, the predicted temperature rise reaches , the system sends out a "caution" signal; At this moment, the predicted temperature rise has reached an abnormal value for three consecutive times, and the system issues an "alarm" signal. It should be noted that in this embodiment, no "maintenance" signal is issued or an alarm is directly issued. The method of using the prediction model used in the test sample described in this embodiment is not unique. In the test sample of the embodiment, a thermocouple is used to monitor the temperature rise of the terminal. In actual applications, other methods can also be used to obtain temperature rise data, such as infrared monitors. In the test sample of the embodiment, a digital signal processor is selected as the storage and calculation unit. In actual applications, any other tool that can achieve the required functions, such as a single-chip microcomputer, a host computer, etc., can be selected as needed. The safety threshold normal temperature rise lower limit set in the test sample of the embodiment ℃, normal temperature rise lower limit ℃, dangerous temperature rise threshold ℃, the number of abnormal values ​​allowed is 3 times. In actual applications, the safety threshold is adjusted according to the safety requirements of the application. In situations where high reliability requirements are placed on low-voltage circuit breakers, the safety threshold should be set more strictly.

[0053] In actual application, it is necessary to correct the model parameter values ​​and temperature rise thresholds according to the specific low-voltage circuit breaker category, specific product model, and specific application scenario to improve the adaptability of the method described in this patent. It is understandable that this method has a certain degree of portability and can be effective even when the object and usage scenario are changed. Therefore, it should be regarded as belonging to the scope of protection of this invention. System Example See also Fig.11 , Fig.11 It is a schematic diagram of the structural composition of the temperature rise warning system of the circuit breaker in the embodiment of the present invention.

[0054] like Fig.11 As shown, a temperature rise warning system for a circuit breaker, the temperature rise warning system for a circuit breaker comprises: A monitoring module 21, used for real-time monitoring of the working status of the circuit breaker; The temperature rise variation curve module 22 is used to collect a plurality of temperature data of the circuit breaker terminals when the circuit breaker is in a working state, and to construct a temperature rise variation curve according to the plurality of temperature data; A temperature rise change prediction model module 23, used for training a temperature rise change prediction model of a circuit breaker terminal based on a plurality of temperature data in a temperature rise change curve; A comparison module 24 is used to output a temperature rise prediction result based on the temperature rise change prediction model and the current temperature data; and to define an abnormal state or a normal state of the circuit breaker according to a comparison between the temperature rise prediction result and a preset interval; The early warning module 25 is used to collect the abnormal situation of the circuit breaker when the circuit breaker is in an abnormal state, and issue an early warning signal according to the abnormal situation.

[0055] Device Embodiment See also Fig.12 , refer to the following Fig.12The electronic device 40 according to this embodiment of the present invention will be described. Fig.12 The electronic device 40 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0056] like Fig.12 As shown, the electronic device 40 is in the form of a general computing device. The components of the electronic device 40 may include but are not limited to: at least one processing unit 41, at least one storage unit 42, and a bus 43 connecting different system components (including the storage unit 42 and the processing unit 41).

[0057] The storage unit stores program codes, which can be executed by the processing unit 41, so that the processing unit 41 executes the steps according to various exemplary embodiments of the present invention described in the above “Embodiment Method” section of this specification.

[0058] The storage unit 42 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit 421 and / or a cache storage unit 422 , and may further include a read-only storage unit (ROM) 423 .

[0059] The storage unit 42 may also include a program / utility 424 having a set (at least one) of program modules 425, such program modules 425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0060] Bus 43 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0061] The electronic device 40 may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 40, and / or any device that enables the electronic device 40 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 44. Furthermore, the electronic device 40 may also communicate with one or more networks (e.g., local area networks, wide area networks, and / or public networks, such as the Internet) via a network adapter 45. Fig.12 As shown, the network adapter 45 communicates with other modules of the electronic device 40 via the bus 43. It should be understood that although Fig.12Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 40, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, tape drives, and data backup planning systems.

[0062] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0063] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: a read-only memory, a random access memory, a disk or an optical disk, etc. In addition, it stores computer program instructions, and when the computer program instructions are executed by a computer, the computer executes the above method.

[0064] In addition, the temperature rise warning method and system for the circuit breaker provided by the embodiment of the present invention are introduced in detail above. Specific examples are used herein to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A temperature rise early warning method for a circuit breaker, characterized in that: Applied to the temperature rise warning scenario of circuit breakers; The temperature rise early warning method of the circuit breaker comprises: Real-time monitoring of the working status of the circuit breaker; In the working state of the circuit breaker, multiple temperature data of the circuit breaker terminals are collected, and a temperature rise change curve is constructed according to the multiple temperature data; Training a temperature rise change prediction model for circuit breaker terminals based on multiple temperature data in the temperature rise change curve; Output the temperature rise prediction result based on the temperature rise change prediction model and the current temperature data; define the abnormal state or normal state of the circuit breaker according to the comparison between the temperature rise prediction result and the preset range; When the circuit breaker is in an abnormal state, the abnormal situation of the circuit breaker is collected and an early warning signal is issued according to the abnormal situation.

2. The temperature rise warning method for circuit breaker according to claim 1, characterized in that: The real-time monitoring of the working status of the circuit breaker includes: Collect the location of the circuit breaker and locate the circuit breaker according to the location of the circuit breaker; Collect multiple parameters of the circuit breaker, and define the working state of the circuit breaker according to the multiple parameters of the circuit breaker. At the same time, perform real-time monitoring on the working state of the circuit breaker.

3. The temperature rise warning method for circuit breaker according to claim 2, characterized in that: In the working state of the circuit breaker, a plurality of temperature data of the circuit breaker terminals are collected, and a temperature rise change curve is constructed according to the plurality of temperature data, including: In the working state of the circuit breaker, a temperature rise test platform for steady-state operation of the circuit breaker is built; Collect multiple temperature data of circuit breaker terminals based on the temperature rise test platform; Define multiple temperature nodes according to multiple temperature data, and record corresponding change curves for two adjacent temperature nodes; A temperature rise variation curve is constructed based on multiple temperature nodes and corresponding variation curves.

4. The temperature rise warning method for circuit breaker according to claim 1, characterized in that: The method of training a temperature rise change prediction model of a circuit breaker terminal based on a plurality of temperature data in a temperature rise change curve comprises: Fixed frame temperature rise curve; Define marking points based on the temperature rise curve, and present corresponding temperature data based on the marking points; Collect multiple temperature data and use the multiple temperature data as training data; The learning model is collected and trained according to the learning model and the training data to output a temperature rise change prediction model for the circuit breaker terminal. At this time, the long short-term memory network model is selected to perform time series prediction of the temperature rise change.

5. The temperature rise warning method for circuit breaker according to claim 4, characterized in that: The method of training the temperature rise change prediction model of the circuit breaker terminal based on the multiple temperature data in the temperature rise change curve also includes: The calculation formula for selecting the long short-term memory network model is as follows: in, x represents the input vector, h represents the output vector, ⊙ represents the dot product operator, and the matrix W represents the parameters to be trained, σ (∙) represents the sigmoid nonlinear function, and tan h (∙) represents the hyperbolic tangent function.

6. The temperature rise warning method for circuit breaker according to claim 5, characterized in that: The method of training the temperature rise change prediction model of the circuit breaker terminal based on the multiple temperature data in the temperature rise change curve also includes: The root mean square error is used to evaluate the prediction accuracy of the temperature rise change prediction model. The root mean square error is calculated as follows: Among them, RMSE is the root mean square error, To predict the temperature, is the actual measured temperature.

7. The temperature rise early warning method for a circuit breaker according to claim 1, characterized in that: The method of outputting a temperature rise prediction result based on the temperature rise change prediction model and the current temperature data; and defining an abnormal state or a normal state of the circuit breaker according to a comparison between the temperature rise prediction result and a preset interval includes: Fixed-frame temperature rise change prediction model; Correlate the temperature rise change prediction model with the current temperature data; The temperature rise prediction results are output based on the temperature rise change prediction model and the current temperature data.

8. The temperature rise warning method for circuit breaker according to claim 7, characterized in that: The method outputs a temperature rise prediction result based on the temperature rise change prediction model and the current temperature data; and defines an abnormal state or a normal state of the circuit breaker according to a comparison between the temperature rise prediction result and a preset interval, further comprising: Collecting preset intervals corresponding to circuit breaker terminals; Correlate temperature rise prediction results with preset intervals; Compare the temperature rise prediction result with the preset interval and output the comparison result; The abnormal state or normal state of the circuit breaker is defined based on the comparison result.

9. The temperature rise warning method for circuit breaker according to claim 8, characterized in that: When the circuit breaker is in an abnormal state, collecting the abnormal situation of the circuit breaker and issuing an early warning signal according to the abnormal situation includes: When the circuit breaker is in an abnormal state, collect the temperature rise data of the circuit breaker in the abnormal state; Define the abnormal condition of the circuit breaker according to the temperature rise data of the circuit breaker in the abnormal state; Define exception types based on the exception situation; The corresponding warning signal is matched according to the abnormal type and issued.

10. A temperature rise warning system for a circuit breaker, characterized in that: The temperature rise warning system of the circuit breaker is applied to the temperature rise warning method of the circuit breaker according to any one of claims 1 to 9, and the temperature rise warning system of the circuit breaker comprises: Monitoring module, used to monitor the working status of the circuit breaker in real time; The temperature rise variation curve module is used to collect multiple temperature data of the circuit breaker terminals when the circuit breaker is in working state, and to construct a temperature rise variation curve according to the multiple temperature data; A temperature rise change prediction model module is used to train a temperature rise change prediction model of a circuit breaker terminal based on multiple temperature data in a temperature rise change curve; A comparison module is used to output a temperature rise prediction result based on the temperature rise change prediction model and the current temperature data; and to define an abnormal state or a normal state of the circuit breaker according to the comparison between the temperature rise prediction result and a preset interval; The early warning module is used to collect the abnormal conditions of the circuit breaker when the circuit breaker is in an abnormal state, and issue an early warning signal according to the abnormal conditions.

Images