A method and system for synchronous measurement of mechanical parameters of a multi-break circuit breaker fault monitoring

Abstract

The application discloses a kind of multi-break circuit breaker fault monitoring mechanical parameter synchronous measurement method and system, belong to high-voltage circuit breaker operation and maintenance technical field, solve how to realize the high-precision synchronous acquisition of mechanical parameter of multi-break circuit breaker fault monitoring;6 slave machine counters start counting from 0, master clock and slave clock are clock synchronization based on LSTM network;When the host receives GPS second pulse arrival and GPS module works normally, calculate the deviation, and directly add the difference to the count value of clock counter;When 6 slave clock counters each time a set sampling period time, trigger sampling module to synchronously collect the current and displacement signal of multi-break circuit breaker, and send the collected signal to host computer, generate synchronous acquisition curve in host computer;The application realizes the high-precision synchronous acquisition of mechanical parameter of multi-break circuit breaker fault monitoring, quickly gives more accurate synchronous measurement result, improves the efficiency and stability of entire power system.

Description

Technical Field

[0001] This invention belongs to the field of high-voltage circuit breaker operation and maintenance technology, and relates to a method and system for synchronous measurement of mechanical parameters for fault monitoring of multi-break circuit breakers. Background Technology

[0002] Currently, the operation and maintenance of multi-break circuit breakers can only be completed through power outages. Considering that the mechanical characteristics of multi-break circuit breakers change slowly, power outage maintenance is inefficient and can easily lead to unnecessary economic losses. Therefore, timely and accurate fault monitoring of multi-break circuit breakers is of great significance for reducing personnel investment in operation and maintenance, achieving precise operation and maintenance of circuit breakers, and reducing the risk of power outages. When a fault occurs in a multi-break high-voltage circuit breaker, the operating current curves of the opening and closing coils and the energy storage motor will change. When a fault occurs in the transmission mechanism, the operating displacement curve of the break will also change. In addition, if the operating time difference between the three phases of a multi-break high-voltage circuit breaker is too large, it will also affect the timeliness of the high-voltage circuit breaker's opening and closing. Therefore, it is necessary to synchronously measure the output current and displacement signals of each mechanism of the multi-break high-voltage circuit breaker. Since the locations of the various multi-break high-voltage circuit breakers are dispersed, how to achieve accurate synchronous measurement of the electrical quantities and displacement quantities of each high-voltage circuit breaker's operating mechanism is an urgent problem to be solved.

[0003] In the prior art, the patent document "Wireless Sensor Network System for Online Status Monitoring of High Voltage Circuit Breakers" with publication number CN207937565U and publication date of October 2, 2018, uses a wireless synchronous acquisition and detection method to measure the parameters of multi-break circuit breakers. However, due to the drift and deviation of the crystal oscillator, the wireless synchronous acquisition and detection method cannot achieve high-precision synchronization when using multiple multi-channel acquisition devices, and cannot quickly and accurately provide more accurate synchronous measurement results, thus making it difficult to improve the efficiency and stability of the entire power system. Summary of the Invention

[0004] The technical problem to be solved by this invention is how to achieve high-precision synchronous acquisition of mechanical parameters for fault monitoring of multi-break circuit breakers.

[0005] The present invention solves the above-mentioned technical problems through the following technical solutions: A method for synchronously measuring mechanical parameters for fault monitoring of multi-break circuit breakers includes the following steps: Step 1: When the system starts up, the 60MHz clock signal inside the measurement host and the 6 measurement slaves causes the 64-bit counter to start counting from 0; Step 2: Perform high-precision clock synchronization between the master clock and the slave clock using an LSTM network; the specific steps are as follows: Step 2.1: After the measurement host timer is triggered, the measurement host starts to synchronize with the six measurement slaves according to the order of the six measurement slave address list; Step 2.2: The measurement master sends a synchronization request message to the measurement slave, assuming the synchronization round is nth, and records the sending timestamp at this time. When the measurement slave receives a synchronization request message, it records the timestamp of the received message. Send a synchronization response message to the measurement host and record the timestamp of the synchronization response message. Then send containing , The timestamp is synchronized with the attached message; Step 2.3: The measurement host receives the synchronization response message and records the receiving timestamp. Upon receiving the synchronization attachment message, extract the corresponding information for this round of synchronization. , The timestamp is used to calculate the relative time deviation of the nth round of synchronization and the transmission delay of the nth round of synchronization. Step 2.4: The master clock sends a synchronization message to the slave clock at regular intervals. After sending data messages multiple times, the time deviations for each round are as follows: , , ..., ...; After M rounds, the cumulative deviation is obtained; Step 2.5: When the accumulated deviation reaches a preset threshold, the phase deviation of the measurement slave's clock is compensated, and the LSTM network is used to predict the crystal oscillator frequency deviation between the measurement master and the measurement slave, compensating for this frequency deviation to achieve synchronization between the measurement slave frequency and the measurement master frequency, thereby achieving synchronization of the master and slave frequencies and phases; the specific method is as follows: Step 2.5.1: Collect historical aging rate data and historical temperature data of the crystal oscillator's operating environment; Step 2.5.2: Extract input features from the collected data and perform normalization processing; Step 2.5.3: Construct the LSTM network; Step 2.5.4: Obtain the crystal oscillator aging rate and operating environment temperature values ​​online, preprocess them, input them into the LSTM network, and then inverse normalize the output to obtain the frequency deviation prediction value and compensate for the deviation. Step 3: When the measurement host receives the GPS second pulse and the GPS module is working normally, the deviation between the host and the slave is calculated. The hours, minutes and seconds of the UTC time are converted into the time format of a 64-bit clock counter. Then the difference between the two is calculated. Finally, the difference is added directly to the count value of the clock counter. Step 4: When the clock counters of the 6 measurement slaves count one set sampling period, the 6 measurement slaves generate sampling pulse signals, triggering the sampling module to synchronously acquire the current and displacement signals of the multi-break circuit breaker, and wirelessly transmit the acquired signals to the host computer. After processing, the host computer generates the acquisition curve.

[0006] Furthermore, the formula for calculating the relative time deviation of the nth round of synchronization mentioned in step 2.3 is as follows: The formula for calculating the synchronization transmission delay in the nth round is as follows: .

[0007] Furthermore, the method for extracting input features from the collected data and performing normalization processing as described in step 2.5.2 is as follows: The input is a matrix composed of three input features, namely: , Where AR represents the aging rate of the crystal oscillator, and TEM represents the operating temperature of the crystal oscillator. This represents the instantaneous frequency deviation of the crystal oscillator during operation; each input feature vector is a column vector containing T data points, with each element corresponding to the value from the first sampling time point to the Tth sampling time point. The input and output are normalized to the interval [0, 1].

[0008] Furthermore, the formulas for normalizing the input and output to the interval [0, 1] are as follows: , in, and These are the state values ​​before and after normalization, respectively. and To determine the minimum and maximum values ​​of the crystal oscillator frequency deviation, the acquired timing data is mapped to [...]. , ] interval.

[0009] Furthermore, the method for constructing the LSTM network described in step 2.5.3 is as follows: Divide the training dataset and the measurement dataset according to a certain ratio; The LSTM network is trained using the training dataset, and the parameter update iteration formula is as follows: , , , , , , in, , and These represent the output states of the forget gate, input gate, and output gate at time t, respectively. This represents the state of the memory unit at time t. Let be the input feature vector at time t. This represents the output feature vector at time t-1. , , , This represents the weight matrix for each type of gate. , , , Represents the bias matrix for various gate types. This represents the sigmoid activation function; The Adam optimizer is applied, and the network parameters are adjusted based on the MAE evaluation metric. The optimization is continued until a high-precision LSTM network is obtained, and the accuracy of the model is verified using a test dataset.

[0010] Furthermore, the calculation formula for the MAE evaluation index is as follows: , Where i is the data number and N is the total number of data points. The predicted frequency deviation is represented by y, which is the actual data.

[0011] Furthermore, the formula for inverse normalization of the output described in step 2.5.4 is as follows: , in, This represents the predicted frequency deviation after inverse normalization. This represents the actual output value of the LSTM network. This indicates the maximum value of the crystal oscillator frequency deviation. This represents the minimum value of the crystal oscillator frequency deviation.

[0012] Furthermore, the conditions for the GPS module to function normally as described in step three are: , in, The current received UTC time is set to the last received UTC time. The last received UTC time was set to .

[0013] A system employing the aforementioned method for synchronous measurement of mechanical parameters in multi-break circuit breaker fault monitoring includes: one measurement host, six measurement slaves, a host computer, and a GPS module. The measurement host sends a synchronization clock to the measurement slaves, predicts and compensates for crystal oscillator frequency deviations to synchronize the host frequency with the slave frequencies, receives real data from each slave, and ultimately transmits the data to the host computer. The six measurement slaves are connected to the phase operating mechanism of each phase of the circuit breaker, synchronously acquiring current and displacement signals from the multi-break circuit breaker, including circuit breaker travel displacement signals, opening and closing solenoid valve current signals, and energy storage motor operating current signals, and then processing and sending them to the measurement host. The GPS module provides time synchronization and calibration for the measurement host. The host computer receives signals from the measurement slaves, processes them, and generates acquisition curves.

[0014] A storage medium storing a computer program, which, when executed by a processor, performs the steps of the synchronous measurement method for mechanical parameters of multi-break circuit breaker fault monitoring as described above.

[0015] The advantages of this invention are: The technical solution of this invention uses six high-precision counters on the slave devices to count from 0. Simultaneously, the master clock and slave clocks are synchronized using a high-precision LSTM network. When the master receives a GPS second pulse and the GPS module is working normally, the deviation between the two is calculated, and the difference is directly added to the count value of the clock counters. When the six slave clock counters count a set sampling period, the sampling module is triggered to synchronously acquire signals such as current and displacement of the multi-break circuit breaker, and the acquired signals are wirelessly transmitted to the host computer. After processing, a synchronous acquisition curve is generated on the host computer. This invention achieves high-precision synchronous acquisition of mechanical parameters for fault monitoring of multi-break circuit breakers, quickly providing more accurate synchronous measurement results and improving the efficiency and stability of the entire power system. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the three-phase foundation installation of the multi-break circuit breaker of the present invention at the measurement site; Figure 2 This is a structural diagram of the multi-break circuit breaker fault monitoring mechanical parameter synchronous measurement system of the present invention; Figure 3 This is a flowchart of the method for synchronous measurement of mechanical parameters for fault monitoring of multi-break circuit breakers according to the present invention; Figure 4 This is a flowchart of the synchronization algorithm between the measurement host clock and the measurement slave clock of the present invention; Figure 5This is a schematic diagram of the algorithm for crystal oscillator frequency deviation compensation based on LSTM network according to the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] The technical solution of the present invention will be further described below with reference to the accompanying drawings and specific embodiments: Example 1 like Figure 1 The diagram shown is a ground installation schematic of the multi-break circuit breaker of the present invention for on-site measurement. Figure 1 (a) is the front view. Figure 1 (b) is a side view, showing six foundations arranged in two rows and three columns.

[0019] like Figure 2 The diagram shows the structure of the multi-break circuit breaker fault monitoring mechanical parameter synchronous measurement system of the present invention, including: one measurement host, six measurement slaves, a host computer, and a GPS module. The measurement host is used to send a synchronization clock to the measurement slaves, predict and compensate for the frequency deviation of the crystal oscillator, and realize the synchronization of the frequency of the measurement host and the frequency of the measurement slaves, thereby achieving the synchronization of the frequency and phase of the master and slaves. It is also responsible for receiving real data from each measurement slave and finally transmitting the data to the host computer. The six measurement slaves are connected to the phase operating mechanism of each phase of the circuit breaker and are used to synchronously collect current and displacement signals from the multi-break circuit breaker, including circuit breaker travel displacement signals, opening and closing solenoid valve current signals, and energy storage motor operating current signals, and send them to the measurement host after processing. The GPS module is used for time synchronization and calibration of the measurement host. The host computer is used to receive the signals sent by the measurement slaves and generate acquisition curves after processing.

[0020] The measurement host includes an ADC module, a main control unit, a wireless communication module, and a counting clock module. The ADC module is used to connect to the corresponding sensor modules for acquiring electrical and mechanical signals of the high-voltage circuit breaker, and is connected to the main control unit via digital signals. It is triggered and started by a synchronization control signal to realize the analog-to-digital conversion of the electrical and mechanical signals of the high-voltage circuit breaker, and provides the conversion results to the main control unit. The main control unit is used to control the acquisition of the ADC, and is responsible for receiving, processing, and sending data, as well as adjusting the counting clock module. The wireless communication module is used for data interaction with the measurement host. The counting clock module is used for timing and providing local time stream information.

[0021] The measurement slave unit includes: a master control unit, a wireless communication module, and a counting clock module; the master control unit The module is used to receive and process signals from the GPS module, and is responsible for receiving, processing and sending data, as well as adjusting the counting clock module; the wireless communication module is used to interact with the measurement host; the counting clock module is used for timing and providing local time stream information.

[0022] Example 2 like Figure 3 As shown, this invention provides a method for synchronously measuring mechanical parameters for fault monitoring of multi-break circuit breakers, comprising the following steps: Step 1: When the system starts up, the 60MHz clock signal inside the measurement host and the 6 measurement slaves causes the 64-bit counter to start counting from 0; Step 2: Perform high-precision clock synchronization between the master clock and the slave clock using an LSTM network. (See [link to relevant documentation]). Figure 4 The specific steps are as follows: Step 2.1: After the measurement master timer is triggered, the measurement master starts to synchronize with the six measurement slaves according to the order of the six measurement slave address list.

[0023] Step 2.2: The measurement master sends a synchronization request message to the measurement slave, assuming the synchronization round is nth, and records the sending timestamp at this time. When the measurement slave receives a synchronization request message, it records the timestamp of the received message. Send a synchronization response message to the measurement host and record the timestamp of the synchronization response message. Then send containing , The timestamp is synchronized with the attached message; Step 2.3: The measurement host receives the synchronization response message and records the receiving timestamp. Upon receiving the synchronization attachment message, extract the corresponding information for this round of synchronization. , The timestamp indicates the relative time deviation of the nth round of synchronization: (1) Synchronization transmission delay in round n: (2) Save the relevant data and increment the synchronization round by one.

[0024] Step 2.4: The master clock sends a synchronization message to the slave clock at regular intervals. After sending data messages multiple times, the time deviations for each round are as follows: , , ..., , ……

[0025] After M rounds, the cumulative deviation is obtained: (3) Step 2.5: When the accumulated deviation reaches a preset threshold, the phase deviation of the measurement slave's clock is compensated, and the LSTM network is used to predict the crystal frequency deviation between the measurement master and measurement slave, compensating for this frequency deviation to achieve synchronization between the measurement slave's frequency and the measurement master's frequency, thereby achieving synchronization of the master and slave's frequencies and phases; see [link to relevant documentation] Figure 5 The specific steps are as follows: Step 2.5.1: Collect historical aging rate data and historical temperature data of the crystal oscillator's operating environment.

[0026] Step 2.5.2: Extract input features from the collected data and perform normalization processing.

[0027] Step 2.5.2.1: The input is a matrix composed of three input features, i.e.: (4) Where AR represents the aging rate of the crystal oscillator, and TEM represents the operating temperature of the crystal oscillator. This represents the instantaneous frequency deviation of the crystal oscillator during operation; each input feature vector is a column vector containing T data points, with each element corresponding to the value from the first sampling time point to the Tth sampling time point.

[0028] Step 2.5.2.2: Normalize the input and output to the interval [0, 1]; the normalization is performed using the following formula: (5) in, and These are the state values ​​before and after normalization, respectively. and To determine the minimum and maximum values ​​of the crystal oscillator frequency deviation, the acquired timing data is mapped to [...]. , ] interval.

[0029] Step 2.5.3: Construct the LSTM network; Step 2.5.3.1: Divide the training dataset and the measurement dataset according to a certain ratio.

[0030] Step 2.5.3.2: Train the LSTM network using the training dataset. The parameter update formula is as follows: (6) (7) (8) (9) (10) (11) in, , and These represent the output states of the forget gate, input gate, and output gate at time t, respectively. This represents the state of the memory unit at time t. Let be the input feature vector at time . This represents the output feature vector at time t-1. , , , This represents the weight matrix for each type of gate. , , , Represents the bias matrix for various gate types. This indicates the sigmod activation function.

[0031] Step 2.5.3.3: Apply the Adam optimizer and adjust the network parameters based on the MAE evaluation metric, continuously optimizing until a high-precision LSTM network is obtained. Then, use a test dataset to verify the model's accuracy.

[0032] The formula for calculating MAE is as follows: [ (12) Where i is the data number and N is the total number of data points. The predicted frequency deviation is represented by y, which is the actual data.

[0033] Step 2.5.4: Obtain the crystal oscillator aging rate and operating environment temperature values ​​online, preprocess them, input them into the LSTM network, and then inverse normalize the output to obtain the frequency deviation prediction value and compensate for the deviation.

[0034] The formula for inverse normalizing the output is as follows: (13) in, This represents the predicted frequency deviation after inverse normalization. This represents the actual output value of the LSTM network. This indicates the maximum value of the crystal oscillator frequency deviation. This represents the minimum value of the crystal oscillator frequency deviation.

[0035] Step 3: When the measurement host receives the GPS second pulse and the GPS module is working normally, the deviation between the host and slave is calculated. The hours, minutes and seconds of UTC (Coordinated Universal Time) are converted into the time format of a 64-bit clock counter. Then the difference between the two is calculated. Finally, the difference is added directly to the count value of the clock counter.

[0036] The conditions for the GPS module to function normally are as follows: (14) in, The current received UTC time is set to the last received UTC time. The last received UTC time was set to .

[0037] If the GPS module malfunctions, the GPS second pulse signal and UTC time signal will be invalidated and will not be calibrated. In this case, the clock counter will count normally.

[0038] Step 4: When the clock counters of the 6 measurement slaves count one set sampling period, the 6 measurement slaves generate sampling pulse signals, triggering the sampling module to synchronously acquire the current and displacement signals of the multi-break circuit breaker, and wirelessly transmit the acquired signals to the host computer. After processing, the host computer generates the acquisition curve.

[0039] Example 3 This embodiment provides a storage medium storing a computer program. When the computer program is run by a processor, it executes the steps of the synchronous measurement method for mechanical parameters of multi-break circuit breaker fault monitoring described in Embodiment 2.

[0040] This invention uses GPS to precisely synchronize and calibrate the host clock, and then uses an LSTM network to achieve high-precision synchronization between the host clock and the slave clock. Finally, it synchronously acquires the synchronization curves of displacement and current signals, realizing high-precision synchronous acquisition of mechanical parameters for multi-break circuit breaker fault monitoring. It quickly provides more accurate synchronous measurement results, and the wireless and high-precision acquisition facilitates more accurate calculation of the three-phase synchronicity, improving the efficiency and stability of the entire power system.

[0041] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for synchronously measuring mechanical parameters for fault monitoring of multi-break circuit breakers, characterized in that, Includes the following steps: Step 1: When the system starts up, the 60MHz clock signal inside the measurement host and the 6 measurement slaves causes the 64-bit counter to start counting from 0; Step 2: Perform high-precision clock synchronization between the master clock and the slave clock using an LSTM network; the specific steps are as follows: Step 2.1: After the measurement host timer is triggered, the measurement host starts to synchronize with the six measurement slaves according to the order of the six measurement slave address list; Step 2.2: The measurement master sends a synchronization request message to the measurement slave, assuming the synchronization round is nth, and records the sending timestamp at this time. When the measurement slave receives a synchronization request message, it records the timestamp of the received message. Send a synchronization response message to the measurement host and record the timestamp of the synchronization response message. Then send containing , The timestamp is synchronized with the attached message; Step 2.3: The measurement host receives the synchronization response message and records the receiving timestamp. Upon receiving the synchronization attachment message, extract the corresponding information for this round of synchronization. , The timestamp is used to calculate the relative time deviation of the nth round of synchronization and the transmission delay of the nth round of synchronization. Step 2.4: The master clock sends a synchronization message to the slave clock at regular intervals. After sending data messages multiple times, the time deviations for each round are as follows: , , ..., ...; After M rounds, the cumulative deviation is obtained; Step 2.5: When the accumulated deviation reaches a preset threshold, the phase deviation of the measurement slave's clock is compensated, and the LSTM network is used to predict the crystal oscillator frequency deviation between the measurement master and the measurement slave, compensating for this frequency deviation to achieve synchronization between the measurement slave frequency and the measurement master frequency, thereby achieving synchronization of the master and slave frequencies and phases; the specific method is as follows: Step 2.5.1: Collect historical aging rate data and historical temperature data of the crystal oscillator's operating environment; Step 2.5.2: Extract input features from the collected data and perform normalization processing; Step 2.5.3: Construct the LSTM network; Step 2.5.4: Obtain the crystal oscillator aging rate and operating environment temperature values ​​online, preprocess them, input them into the LSTM network, and then inverse normalize the output to obtain the frequency deviation prediction value and compensate for the deviation. Step 3: When the measurement host receives the GPS second pulse and the GPS module is working normally, the deviation between the host and the slave is calculated. The hours, minutes and seconds of the UTC time are converted into the time format of a 64-bit clock counter. Then the difference between the two is calculated. Finally, the difference is added directly to the count value of the clock counter. Step 4: When the clock counters of the 6 measurement slaves count one set sampling period, the 6 measurement slaves generate sampling pulse signals, triggering the sampling module to synchronously acquire the current and displacement signals of the multi-break circuit breaker, and wirelessly transmit the acquired signals to the host computer. After processing, the host computer generates the acquisition curve.

2. The method for synchronous measurement of mechanical parameters for fault monitoring of multi-break circuit breakers according to claim 1, characterized in that, The formula for calculating the relative time deviation of the nth round of synchronization mentioned in step 2.3 is as follows: The formula for calculating the synchronization transmission delay in the nth round is as follows: 。 3. The method for synchronous measurement of mechanical parameters for fault monitoring of multi-break circuit breakers according to claim 1, characterized in that, The method for extracting input features from the collected data and performing normalization processing as described in step 2.5.2 is as follows: The input is a matrix composed of three input features, namely: , Where AR represents the aging rate of the crystal oscillator, and TEM represents the operating temperature of the crystal oscillator. This represents the instantaneous frequency deviation of the crystal oscillator during operation; each input feature vector is a column vector containing T data points, with each element corresponding to the value from the first sampling time point to the Tth sampling time point. The input and output are normalized to the interval [0, 1].

4. The method for synchronous measurement of mechanical parameters for fault monitoring of multi-break circuit breakers according to claim 3, characterized in that, The formulas for normalizing the input and output to the interval [0, 1] are as follows: , in, and These are the state values ​​before and after normalization, respectively. and To determine the minimum and maximum values ​​of the crystal oscillator frequency deviation, the acquired timing data is mapped to [...]. , ] interval.

5. The method for synchronous measurement of mechanical parameters for fault monitoring of multi-break circuit breakers according to claim 1, characterized in that, The method for constructing the LSTM network described in step 2.5.3 is as follows: Divide the training dataset and the measurement dataset according to a certain ratio; The LSTM network is trained using the training dataset, and the parameter update iteration formula is as follows: ， ， ， ， ， ， in, , and These represent the output states of the forget gate, input gate, and output gate at time t, respectively. This represents the state of the memory unit at time t. Let be the input feature vector at time t. This represents the output feature vector at time t-1. , , , This represents the weight matrix for each type of gate. , , , Represents the bias matrix for various gate types. This represents the sigmoid activation function; The Adam optimizer is applied, and the network parameters are adjusted based on the MAE evaluation metric. The optimization is continued until a high-precision LSTM network is obtained, and the accuracy of the model is verified using a test dataset.

6. The method for synchronous measurement of mechanical parameters for fault monitoring of multi-break circuit breakers according to claim 5, characterized in that, The calculation formula for the MAE evaluation index is as follows: , Where i is the data number and N is the total number of data points. The predicted frequency deviation is represented by y, which is the actual data.

7. The method for synchronous measurement of mechanical parameters for fault monitoring of multi-break circuit breakers according to claim 1, characterized in that, The formula for inverse normalization of the output described in step 2.5.4 is as follows: , in, This represents the predicted frequency deviation after inverse normalization. This represents the actual output value of the LSTM network. This indicates the maximum value of the crystal oscillator frequency deviation. This represents the minimum value of the crystal oscillator frequency deviation.

8. The method for synchronous measurement of mechanical parameters for fault monitoring of multi-break circuit breakers according to claim 1, characterized in that, The conditions for the GPS module to work normally as described in step three are: , in, The current received UTC time is set to the last received UTC time. The last received UTC time was set to .

9. A system employing the synchronous measurement method for mechanical parameters of multi-break circuit breaker fault monitoring as described in any one of claims 1-8, characterized in that, include: The system includes one main measurement unit, six slave measurement units, a host computer, and a GPS module. The main measurement unit is used to send a synchronization clock to the slave measurement units, predict and compensate for the frequency deviation of the crystal oscillator, synchronize the frequency of the main measurement unit with the frequency of the slave measurement units, receive real data from each slave measurement unit, and finally transmit the data to the host computer. The six measurement slave units are connected to the phase operating mechanism of each phase circuit breaker to synchronously collect current and displacement signals from the multi-break circuit breaker, including circuit breaker travel displacement signals, opening and closing solenoid valve current signals, and energy storage motor operating current signals, and then send them to the measurement host after processing; the GPS module is used to synchronize and calibrate the measurement host; the host computer is used to receive the signals sent by the measurement slave units, process them, and generate acquisition curves.

10. A storage medium storing a computer program, characterized in that, When the computer program is run by the processor, it executes the steps of the synchronous measurement method for mechanical parameters of multi-break circuit breaker fault monitoring as described in any one of claims 1 to 8.

Images