Ultra-low power consumption control method and system of high-voltage direct-current microammeter

Abstract

The invention relates to an ultra-low power consumption control method and system for a high-voltage direct-current microammeter, and belongs to the technical field of high-voltage direct-current microammeter control. The real-time working state information of the high-voltage direct-current microammeter in the target area is monitored and identified through the high-voltage direct-current microammeter monitoring model, and low-power-consumption control logic information is constructed, so that a traversal algorithm is introduced; traversing and classifying the identification result of the real-time working state information of the high-voltage direct-current microammeter in the target area to obtain a traversal classification result, and finally, performing control optimization on the traversal classification result based on the low-power-consumption control logic information. The real-time working state of the high-voltage direct-current microammeter in the target area is monitored through the artificial intelligence technology, so that the high-voltage direct-current microammeter is automatically controlled according to the real-time working state of the high-voltage direct-current microammeter in the target area, and the energy consumption of the high-voltage direct-current microammeter during working is reduced.

Description

Technical Field

[0001] This invention relates to the field of high voltage DC microammeter control technology, and in particular to an ultra-low power consumption control method and system for high voltage DC microammeters. Background Technology

[0002] The high-voltage DC microammeter is a high-voltage ammeter used to measure the AC and DC withstand voltage and leakage current of high-voltage electrical appliances or insulating materials. It is mainly used in conjunction with AC and DC tests of high-voltage test transformers and is an ideal instrument for testing AC and DC high-voltage leakage current. It overcomes the shortcomings of traditional pointer-type microammeters, such as large reading errors, poor anti-interference capabilities, and lack of protection against surge currents, making it an ideal replacement for traditional pointer-type ammeters. Features include: Reliable operation: Unaffected by discharge surges, it can work stably in complex testing environments.12 High accuracy: The accuracy varies between different models of high-voltage DC microammeters; for example, the GDSWB model has an accuracy of 0.2% ± 1 digit, and the ZGF-II model has a measurement accuracy of 0.5%.23 Clear display: Utilizing a digital display, the reading is intuitive, facilitating accurate data acquisition by operators.124 Stable indication: The numerical display remains stable during measurement, reducing reading errors.12 Large measuring range: Multiple measuring ranges are available, such as 1~1999μA for some, 0~199μA~1999μA for others, and even more ranges can be customized. Strong overload capacity: Some products have overload protection and can automatically switch ranges (gear shifting), capable of withstanding a certain degree of excessive current surges, but excessive current surges should still be avoided. Strong anti-interference capability: The instrument housing is made of lightweight metal, and some products use conductive glass for the display window, connected to the housing, ensuring complete shielding of the measurement system and effectively preventing stray currents from entering the meter. It has strong resistance to interference and surge currents. However, microammeters measure current, and their installation location is relatively special. Generally, they should not be moved after installation. Normally, they are simply turned on. If there is information exchange with the host computer within 20 seconds, they will continue to work. However, if there is no information exchange and they continue to work continuously, it will lead to excessive energy consumption. Summary of the Invention

[0003] This invention overcomes the shortcomings of the prior art and provides an ultra-low power consumption control method and system for high voltage DC microammeters.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] The first aspect of this invention provides an ultra-low power consumption control method for a high-voltage DC microammeter, comprising the following steps:

[0006] Obtain the real-time operating status information of the high-voltage DC microammeters in the target area, and construct a high-voltage DC microammeter monitoring model based on the real-time operating status information of the high-voltage DC microammeters in the target area;

[0007] The high-voltage DC microammeter monitoring model is used to monitor and identify the real-time operating status information of the high-voltage DC microammeter in the target area, and to construct low-power control logic information.

[0008] A traversal algorithm is introduced to traverse and classify the identification results of the real-time working status information of the high-voltage DC microammeters in the target area, and obtain the traversal and classification results.

[0009] The traversal and classification results are controlled and optimized based on the low-power control logic information.

[0010] Furthermore, in the ultra-low power consumption control method for high-voltage DC microammeters, the real-time operating status information of the high-voltage DC microammeter within the target area is obtained, specifically as follows:

[0011] The real-time operating parameter information of each high-voltage DC microammeter is obtained, and operating status evaluation index data is constructed. Based on the operating status evaluation index data, the operating status of each high-voltage DC microammeter is described.

[0012] By describing the working status, the real-time working status information of each high-voltage DC microammeter is obtained, and the real-time working status information of each high-voltage DC microammeter is statistically analyzed to obtain the real-time working status information of high-voltage DC microammeters in the target area.

[0013] Furthermore, in the ultra-low power consumption control method for high-voltage DC microammeters, a high-voltage DC microammeter monitoring model is constructed based on the real-time operating status information of the high-voltage DC microammeters within the target area, specifically as follows:

[0014] A high-voltage direct current microammeter monitoring model is constructed based on a deep neural network, and a genetic algorithm is introduced. A training time threshold is set, and the real-time working status information of the high-voltage direct current microammeter in the target area is input into the deep neural network for training based on the training time threshold.

[0015] When the training time threshold is reached, an attention mechanism is introduced to calculate the SHAP value corresponding to all data types of the real-time working status information of the high voltage DC microammeter in each target area, and set the SHAP threshold.

[0016] Obtain the data type corresponding to the SHAP value greater than the SHAP threshold, and input all data types of the real-time working status information of the high voltage DC microammeter in the target area into the attention mechanism;

[0017] Focusing attention on the data types corresponding to SHAP values ​​greater than the SHAP threshold, when the network parameters of the deep neural network reach the predetermined requirements, the high voltage DC microammeter monitoring model is output, and training is complete.

[0018] Furthermore, in the ultra-low power consumption control method for high-voltage DC microammeters, the real-time operating status information of high-voltage DC microammeters in the target area is monitored and identified through the high-voltage DC microammeter monitoring model, specifically as follows:

[0019] The real-time operating status information of the high-voltage DC microammeters in the target area within a preset time period is obtained, and the real-time operating status information of the high-voltage DC microammeters in the target area is input into the high-voltage DC microammeter monitoring model for status update.

[0020] By updating the status, the real-time operating status information of each high-voltage DC microammeter in the target area with the current timestamp is obtained, and the identification result of the real-time operating status information of the high-voltage DC microammeter in the target area is generated.

[0021] Furthermore, in the ultra-low power consumption control method for high-voltage DC microammeters, a traversal algorithm is introduced to traverse and classify the identification results of the real-time operating status information of high-voltage DC microammeters in the target area, and obtain the traversal and classification results, specifically:

[0022] A dataset is constructed based on the identification results of the real-time operating status information of the high-voltage DC microammeters in the target area. A traversal algorithm is introduced to traverse the real-time operating status information of each high-voltage DC microammeter in the dataset based on the traversal algorithm.

[0023] Calculate the Euclidean distance between the real-time operating status information of each high-voltage DC microammeter in the dataset;

[0024] Several data subsets are constructed, and data with the same Euclidean distance value are merged into the same data subset until the real-time working status information of each high-voltage DC microammeter in the dataset is allocated, and a traversal classification result is generated.

[0025] Furthermore, in the ultra-low power control method for high-voltage DC microammeters, the traversal classification results are optimized based on the aforementioned low-power control logic information, specifically including:

[0026] The control protocol information of each high voltage DC microammeter is obtained, and the control protocol information of each high voltage DC microammeter is parsed to obtain the parsed control protocol information of the high voltage DC microammeter.

[0027] Based on the low-power control logic information and the parsed control protocol information of the high-voltage DC microammeter, the control of each high-voltage DC microammeter in the traversal classification results is optimized.

[0028] A second aspect of the present invention provides an ultra-low power control system for a high-voltage DC microammeter, including a memory and a processor. The memory includes a program for an ultra-low power control method for a high-voltage DC microammeter. When the processor executes the program for the ultra-low power control method for a high-voltage DC microammeter, it implements the steps of the ultra-low power control method for a high-voltage DC microammeter as described in any one of the claims.

[0029] A third aspect of the present invention provides a computer-readable storage medium including a program for an ultra-low power control method of a high-voltage DC microammeter, wherein when the program for the ultra-low power control method of the high-voltage DC microammeter is executed by a processor, it implements the steps of the ultra-low power control method of the high-voltage DC microammeter as described in any one of the present invention.

[0030] This invention addresses the shortcomings of the prior art and has the following beneficial effects:

[0031] This invention acquires real-time operating status information of high-voltage DC microammeters within a target area, constructs a monitoring model based on this information, and then uses this monitoring model to monitor and identify the real-time operating status of the high-voltage DC microammeters in the target area. Low-power control logic information is then constructed, and a traversal algorithm is introduced to traverse and classify the identification results of the real-time operating status information of the high-voltage DC microammeters in the target area, obtaining the traversal and classification results. Finally, control optimization is performed based on the traversal and classification results using the low-power control logic information. This invention uses artificial intelligence technology to monitor the real-time operating status of high-voltage DC microammeters within a target area, thereby automatically controlling the high-voltage DC microammeters based on their real-time operating status and reducing energy consumption during operation. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained from these drawings without creative effort.

[0033] Figure 1 The overall flowchart of the ultra-low power consumption control method for high voltage DC microammeters is shown;

[0034] Figure 2 A system block diagram of the ultra-low power control system for a high-voltage DC microammeter is shown. Detailed Implementation

[0035] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0036] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0037] like Figure 1 As shown, the first aspect of the present invention provides an ultra-low power consumption control method for a high-voltage DC microammeter, comprising the following steps:

[0038] S102: Obtain the real-time operating status information of the high-voltage DC microammeters in the target area, and construct a high-voltage DC microammeter monitoring model based on the real-time operating status information of the high-voltage DC microammeters in the target area.

[0039] S104: The real-time operating status information of the high voltage DC microammeter in the target area is monitored and identified through the high voltage DC microammeter monitoring model, and low power control logic information is constructed.

[0040] S106: Introduce a traversal algorithm to traverse and classify the identification results of the real-time working status information of the high-voltage DC microammeter in the target area, and obtain the traversal and classification results;

[0041] S108: Optimize the control of traversal classification results based on low-power control logic information.

[0042] It should be noted that this invention uses artificial intelligence technology to monitor the real-time operating status of the high-voltage DC microammeter within the target area, thereby automatically controlling the high-voltage DC microammeter based on its real-time operating status and reducing the energy consumption of the high-voltage DC microammeter during operation.

[0043] Furthermore, in the ultra-low power consumption control method for high-voltage DC microammeters, the real-time operating status information of the high-voltage DC microammeter within the target area is obtained, specifically as follows:

[0044] The real-time operating parameter information of each high-voltage DC microammeter is obtained, and the operating status evaluation index data is constructed. Based on the operating status evaluation index data, the operating status of each high-voltage DC microammeter is described.

[0045] By describing the working status, the real-time working status information of each high-voltage DC microammeter is obtained, and the real-time working status information of each high-voltage DC microammeter is statistically analyzed to obtain the real-time working status information of high-voltage DC microammeters in the target area.

[0046] It should be noted that real-time operating parameters include data such as current parameters, voltage parameters, and information interaction status information. Operating status evaluation index data includes operating parameter indicators when information interaction is in operation (e.g., "1" indicates information interaction is in progress) and indicators when information interaction is not in operation (e.g., "0" indicates no information interaction is in progress).

[0047] Furthermore, in the ultra-low power consumption control method for high-voltage DC microammeters, a monitoring model for the high-voltage DC microammeter is constructed based on the real-time operating status information of the high-voltage DC microammeter within the target area, specifically as follows:

[0048] A high-voltage direct current microammeter monitoring model is constructed based on a deep neural network, and a genetic algorithm is introduced. A training time threshold is set, and the real-time working status information of the high-voltage direct current microammeter in the target area is input into the deep neural network for training based on the training time threshold.

[0049] When the training time threshold is reached, an attention mechanism is introduced to calculate the SHAP value corresponding to all data types of the real-time working status information of the high voltage DC microammeter in each target area, and set the SHAP threshold.

[0050] Obtain the data types corresponding to SHAP values ​​greater than the SHAP threshold, and input all data types of real-time working status information of the high-voltage DC microammeters in the target area into the attention mechanism;

[0051] Focusing attention on data types with SHAP values ​​greater than the SHAP threshold, the training is completed when the network parameters of the deep neural network reach the predetermined requirements, outputting a high-voltage DC microammeter monitoring model.

[0052] It's important to note that SHAP values ​​are a method for interpreting predictions from machine learning models. They are based on Shapley values, a concept in game theory used to quantify each player's contribution to the game's outcome. In the context of machine learning, features are considered players, and the game is the model's prediction. SHAP values ​​interpret the model by calculating the marginal contribution of features—that is, the impact of adding a feature to the model on the prediction result. These marginal contributions are obtained by averaging over all possible feature combinations, thus ensuring fairness. SHAP values ​​are characterized by consistency, local interpretability, and global interpretability. They can be used for feature importance ranking, interpreting individual predictions, and anomaly detection, among other things. The data types corresponding to SHAP values ​​greater than the SHAP threshold are obtained. All data types of real-time operating status information of the high-voltage DC microammeter in the target area are input into the attention mechanism, focusing attention on the data types corresponding to SHAP values ​​greater than the SHAP threshold. This allows the model to focus its attention on this type of data during training. Since different operating states are related to different operating parameters, such as current state being related to current and voltage state being related to voltage parameters, this avoids interference with the model during prediction under different operating states (such as current state and information interaction state), thus improving the model's prediction accuracy.

[0053] Furthermore, in the ultra-low power consumption control method for high-voltage DC microammeters, the real-time operating status information of the high-voltage DC microammeters in the target area is monitored and identified through a high-voltage DC microammeter monitoring model, specifically as follows:

[0054] The system acquires the real-time operating status information of the high-voltage DC microammeters in the target area within a preset time period, and inputs the real-time operating status information of the high-voltage DC microammeters in the target area into the high-voltage DC microammeter monitoring model for status updates.

[0055] By updating the status, the real-time operating status information of each high-voltage DC microammeter in the target area with the current timestamp is obtained, and the identification result of the real-time operating status information of the high-voltage DC microammeter in the target area is generated.

[0056] Furthermore, in the ultra-low power consumption control method for high-voltage DC microammeters, a traversal algorithm is introduced to traverse and classify the identification results of the real-time operating status information of high-voltage DC microammeters in the target area, and obtain the traversal and classification results, specifically:

[0057] A dataset is constructed based on the identification results of the real-time working status information of the high voltage DC microammeters in the target area. A traversal algorithm is introduced to traverse the real-time working status information of each high voltage DC microammeter in the dataset.

[0058] Calculate the Euclidean distance between the real-time operating status information of each high-voltage DC microammeter in the dataset;

[0059] Several data subsets are constructed, and data with the same Euclidean distance value are merged into the same data subset until the real-time working status information of each high-voltage DC microammeter in the dataset is allocated, and the traversal classification result is generated.

[0060] It's important to note that in computer science, traversal refers to accessing every element in a data structure, such as an array, list, tree, or graph. Traversal algorithms ensure that each element is visited at least once, and operations such as searching, calculating, and updating can be performed during the access process. Different data structures require different traversal methods. This method allows for categorization based on the working state, enabling targeted control.

[0061] Furthermore, in the ultra-low power control method for high-voltage DC microammeters, the control optimization of the traversal classification results is based on low-power control logic information, specifically including:

[0062] The control protocol information of each high voltage DC microammeter is obtained, and the control protocol information of each high voltage DC microammeter is parsed to obtain the parsed control protocol information of the high voltage DC microammeter.

[0063] Based on low-power control logic information and the parsed control protocol information of the high-voltage DC microammeter, the control of each high-voltage DC microammeter in the traversal classification results is optimized.

[0064] It should be noted that low-power control logic information, such as that of a high-voltage DC microammeter, normally involves direct power-on. If there is communication with the host computer within 20 seconds, it continues to operate. If there is no communication with the host computer after 20 seconds, it enters low-power mode. When entering low-power mode, the external power supply is first disconnected using a program-controlled switch. The microcontroller is still operating, and it can also be programmed to enter low-power mode. Furthermore, a wake-up mode can be set: after the fiber optic cable receives a communication signal, a wake-up command is given to the microcontroller, waking it up, and then the microcontroller wakes up the external power supply. Various control logic settings are possible, depending on actual needs; this method does not impose excessive restrictions.

[0065] In addition, this method also includes:

[0066] The thickness parameters of the electromagnetic shield are initialized. Based on the thickness parameters of the electromagnetic shield, the real-time operating condition data of the high voltage DC microammeter is obtained. The anti-interference capability data of the high voltage DC microammeter under different operating conditions is obtained through big data. An anti-interference capability data prediction model is constructed based on a deep neural network.

[0067] The anti-interference capability data of the high voltage DC microammeter under different operating conditions are input into the anti-interference capability data prediction model for training. Through training, an anti-interference capability data prediction model that meets the expectations is obtained.

[0068] The real-time operating condition data of the high-voltage DC microammeter is input into the real-time operating condition data of the high-voltage DC microammeter for prediction, and the anti-interference capability data under the real-time operating condition data of the high-voltage DC microammeter is obtained.

[0069] Set an anti-interference capability data threshold and determine whether the anti-interference capability data under the real-time operating condition data information of the high voltage DC microammeter is greater than the anti-interference capability data threshold.

[0070] When the anti-interference capability data under the real-time operating condition data of the high voltage DC microammeter is not greater than the anti-interference capability data threshold, the thickness parameter of the electromagnetic shield is increased until it is greater than the anti-interference capability data threshold.

[0071] When the anti-interference capability data under the real-time operating condition data of the high voltage DC microammeter is greater than the anti-interference capability data threshold, the thickness parameter of the electromagnetic shield is output, and data is collected according to the thickness parameter of the electromagnetic shield.

[0072] It should be noted that by adjusting the thickness parameter of the electromagnetic shield (e.g., permalloy + conductive silicone layer), power frequency interference and high-frequency noise are suppressed. When the anti-interference capability data under the real-time operating condition data of the high-voltage DC microammeter is not greater than the anti-interference capability data threshold, the thickness parameter of the electromagnetic shield is increased until it exceeds the anti-interference capability data threshold. When the anti-interference capability data under the real-time operating condition data of the high-voltage DC microammeter exceeds the anti-interference capability data threshold, the thickness parameter of the electromagnetic shield is output, and data is collected according to the thickness parameter of the electromagnetic shield. This enables ultra-low current detection (0.1pA) and stable operation in complex electromagnetic environments, suitable for high-precision scenarios such as partial discharge monitoring of nuclear power equipment, further improving the accuracy of data acquisition and the control accuracy of the high-voltage DC microammeter.

[0073] like Figure 2 As shown, the second aspect of the present invention provides an ultra-low power control system 4 for a high-voltage DC microammeter, including a memory 41 and a processor 42. The memory 41 includes a program for an ultra-low power control method for the high-voltage DC microammeter. When the ultra-low power control method program for the high-voltage DC microammeter is executed by the processor 42, it specifically includes the following steps:

[0074] Obtain real-time operating status information of high-voltage DC microammeters within the target area, and construct a high-voltage DC microammeter monitoring model based on the real-time operating status information of high-voltage DC microammeters within the target area;

[0075] The real-time operating status information of the high voltage DC microammeter in the target area is monitored and identified by the high voltage DC microammeter monitoring model, and low power control logic information is constructed.

[0076] A traversal algorithm is introduced to traverse and classify the identification results of the real-time working status information of the high-voltage DC microammeters in the target area, and obtain the traversal and classification results.

[0077] The traversal and classification results are optimized based on low-power control logic information.

[0078] It should be noted that this invention uses artificial intelligence technology to monitor the real-time operating status of the high-voltage DC microammeter within the target area, thereby automatically controlling the high-voltage DC microammeter based on its real-time operating status and reducing the energy consumption of the high-voltage DC microammeter during operation.

[0079] Furthermore, in the ultra-low power consumption control method for high-voltage DC microammeters, the real-time operating status information of the high-voltage DC microammeter within the target area is obtained, specifically as follows:

[0080] The real-time operating parameter information of each high-voltage DC microammeter is obtained, and the operating status evaluation index data is constructed. Based on the operating status evaluation index data, the operating status of each high-voltage DC microammeter is described.

[0081] By describing the working status, the real-time working status information of each high-voltage DC microammeter is obtained, and the real-time working status information of each high-voltage DC microammeter is statistically analyzed to obtain the real-time working status information of high-voltage DC microammeters in the target area.

[0082] It should be noted that real-time operating parameters include data such as current parameters, voltage parameters, and information interaction status information. Operating status evaluation index data includes operating parameter indicators when information interaction is in operation (e.g., "1" indicates information interaction is in progress) and indicators when information interaction is not in operation (e.g., "0" indicates no information interaction is in progress).

[0083] Furthermore, in the ultra-low power consumption control method for high-voltage DC microammeters, a monitoring model for the high-voltage DC microammeter is constructed based on the real-time operating status information of the high-voltage DC microammeter within the target area, specifically as follows:

[0084] A high-voltage direct current microammeter monitoring model is constructed based on a deep neural network, and a genetic algorithm is introduced. A training time threshold is set, and the real-time working status information of the high-voltage direct current microammeter in the target area is input into the deep neural network for training based on the training time threshold.

[0085] When the training time threshold is reached, an attention mechanism is introduced to calculate the SHAP value corresponding to all data types of the real-time working status information of the high voltage DC microammeter in each target area, and set the SHAP threshold.

[0086] Obtain the data types corresponding to SHAP values ​​greater than the SHAP threshold, and input all data types of real-time working status information of the high-voltage DC microammeters in the target area into the attention mechanism;

[0087] Focusing attention on data types with SHAP values ​​greater than the SHAP threshold, the training is completed when the network parameters of the deep neural network reach the predetermined requirements, outputting a high-voltage DC microammeter monitoring model.

[0088] It's important to note that SHAP values ​​are a method for interpreting predictions from machine learning models. They are based on Shapley values, a concept in game theory used to quantify each player's contribution to the game's outcome. In the context of machine learning, features are considered players, and the game is the model's prediction. SHAP values ​​interpret the model by calculating the marginal contribution of features—that is, the impact of adding a feature to the model on the prediction result. These marginal contributions are obtained by averaging over all possible feature combinations, thus ensuring fairness. SHAP values ​​are characterized by consistency, local interpretability, and global interpretability. They can be used for feature importance ranking, interpreting individual predictions, and anomaly detection, among other things. The data types corresponding to SHAP values ​​greater than the SHAP threshold are obtained. All data types of real-time operating status information of the high-voltage DC microammeter in the target area are input into the attention mechanism, focusing attention on the data types corresponding to SHAP values ​​greater than the SHAP threshold. This allows the model to focus its attention on this type of data during training. Since different operating states are related to different operating parameters, such as current state being related to current and voltage state being related to voltage parameters, this avoids interference with the model during prediction under different operating states (such as current state and information interaction state), thus improving the model's prediction accuracy.

[0089] Furthermore, in the ultra-low power consumption control method for high-voltage DC microammeters, the real-time operating status information of the high-voltage DC microammeters in the target area is monitored and identified through a high-voltage DC microammeter monitoring model, specifically as follows:

[0090] The system acquires the real-time operating status information of the high-voltage DC microammeters in the target area within a preset time period, and inputs the real-time operating status information of the high-voltage DC microammeters in the target area into the high-voltage DC microammeter monitoring model for status updates.

[0091] By updating the status, the real-time operating status information of each high-voltage DC microammeter in the target area with the current timestamp is obtained, and the identification result of the real-time operating status information of the high-voltage DC microammeter in the target area is generated.

[0092] Furthermore, in the ultra-low power consumption control method for high-voltage DC microammeters, a traversal algorithm is introduced to traverse and classify the identification results of the real-time operating status information of high-voltage DC microammeters in the target area, and obtain the traversal and classification results, specifically:

[0093] A dataset is constructed based on the identification results of the real-time working status information of the high voltage DC microammeters in the target area. A traversal algorithm is introduced to traverse the real-time working status information of each high voltage DC microammeter in the dataset.

[0094] Calculate the Euclidean distance between the real-time operating status information of each high-voltage DC microammeter in the dataset;

[0095] Several data subsets are constructed, and data with the same Euclidean distance value are merged into the same data subset until the real-time working status information of each high-voltage DC microammeter in the dataset is allocated, and the traversal classification result is generated.

[0096] It's important to note that in computer science, traversal refers to accessing every element in a data structure, such as an array, list, tree, or graph. Traversal algorithms ensure that each element is visited at least once, and operations such as searching, calculating, and updating can be performed during the access process. Different data structures require different traversal methods. This method allows for categorization based on the working state, enabling targeted control.

[0097] Furthermore, in the ultra-low power control method for high-voltage DC microammeters, the control optimization of the traversal classification results is based on low-power control logic information, specifically including:

[0098] The control protocol information of each high voltage DC microammeter is obtained, and the control protocol information of each high voltage DC microammeter is parsed to obtain the parsed control protocol information of the high voltage DC microammeter.

[0099] Based on low-power control logic information and the parsed control protocol information of the high-voltage DC microammeter, the control of each high-voltage DC microammeter in the traversal classification results is optimized.

[0100] It should be noted that low-power control logic information, such as that of a high-voltage DC microammeter, normally involves direct power-on. If there is communication with the host computer within 20 seconds, it continues to operate. If there is no communication with the host computer after 20 seconds, it enters low-power mode. When entering low-power mode, the external power supply is first disconnected using a program-controlled switch. The microcontroller is still operating, and it can also be programmed to enter low-power mode. Furthermore, a wake-up mode can be set: after the fiber optic cable receives a communication signal, a wake-up command is given to the microcontroller, waking it up, and then the microcontroller wakes up the external power supply. Various control logic settings are possible, depending on actual needs; this method does not impose excessive restrictions.

[0101] In addition, this method also includes:

[0102] The thickness parameters of the electromagnetic shield are initialized. Based on the thickness parameters of the electromagnetic shield, the real-time operating condition data of the high voltage DC microammeter is obtained. The anti-interference capability data of the high voltage DC microammeter under different operating conditions is obtained through big data. An anti-interference capability data prediction model is constructed based on a deep neural network.

[0103] The anti-interference capability data of the high voltage DC microammeter under different operating conditions are input into the anti-interference capability data prediction model for training. Through training, an anti-interference capability data prediction model that meets the expectations is obtained.

[0104] The real-time operating condition data of the high-voltage DC microammeter is input into the real-time operating condition data of the high-voltage DC microammeter for prediction, and the anti-interference capability data under the real-time operating condition data of the high-voltage DC microammeter is obtained.

[0105] Set an anti-interference capability data threshold and determine whether the anti-interference capability data under the real-time operating condition data information of the high voltage DC microammeter is greater than the anti-interference capability data threshold.

[0106] When the anti-interference capability data under the real-time operating condition data of the high voltage DC microammeter is not greater than the anti-interference capability data threshold, the thickness parameter of the electromagnetic shield is increased until it is greater than the anti-interference capability data threshold.

[0107] When the anti-interference capability data under the real-time operating condition data of the high voltage DC microammeter is greater than the anti-interference capability data threshold, the thickness parameter of the electromagnetic shield is output, and data is collected according to the thickness parameter of the electromagnetic shield.

[0108] It should be noted that by adjusting the thickness parameter of the electromagnetic shield (e.g., permalloy + conductive silicone layer), power frequency interference and high-frequency noise are suppressed. When the anti-interference capability data under the real-time operating condition data of the high-voltage DC microammeter is not greater than the anti-interference capability data threshold, the thickness parameter of the electromagnetic shield is increased until it exceeds the anti-interference capability data threshold. When the anti-interference capability data under the real-time operating condition data of the high-voltage DC microammeter exceeds the anti-interference capability data threshold, the thickness parameter of the electromagnetic shield is output, and data is collected according to the thickness parameter of the electromagnetic shield. This enables ultra-low current detection (0.1pA) and stable operation in complex electromagnetic environments, suitable for high-precision scenarios such as partial discharge monitoring of nuclear power equipment, further improving the accuracy of data acquisition and the control accuracy of the high-voltage DC microammeter.

[0109] A third aspect of the present invention provides a computer-readable storage medium including a program for an ultra-low power control method of a high-voltage DC microammeter, wherein when the program for the ultra-low power control method of the high-voltage DC microammeter is executed by a processor, it implements any one of the steps of the ultra-low power control method of the high-voltage DC microammeter.

[0110] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0111] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0112] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0113] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0114] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0115] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for controlling the ultra-low power consumption of a high-voltage DC microammeter, characterized in that, Includes the following steps: Obtain the real-time operating status information of the high-voltage DC microammeters in the target area, and construct a high-voltage DC microammeter monitoring model based on the real-time operating status information of the high-voltage DC microammeters in the target area; The high-voltage DC microammeter monitoring model is used to monitor and identify the real-time operating status information of the high-voltage DC microammeter in the target area, and to construct low-power control logic information. A traversal algorithm is introduced to traverse and classify the identification results of the real-time working status information of the high-voltage DC microammeters in the target area, and obtain the traversal and classification results. The traversal and classification results are controlled and optimized based on the low-power control logic information.

2. The ultra-low power consumption control method for the high-voltage DC microammeter according to claim 1, characterized in that, Obtain real-time operating status information of the high-voltage DC microammeter within the target area, specifically: The real-time operating parameter information of each high-voltage DC microammeter is obtained, and operating status evaluation index data is constructed. Based on the operating status evaluation index data, the operating status of each high-voltage DC microammeter is described. By describing the working status, the real-time working status information of each high-voltage DC microammeter is obtained, and the real-time working status information of each high-voltage DC microammeter is statistically analyzed to obtain the real-time working status information of high-voltage DC microammeters in the target area.

3. The ultra-low power consumption control method for the high-voltage DC microammeter according to claim 1, characterized in that, A high-voltage DC microammeter monitoring model is constructed based on the real-time operating status information of the high-voltage DC microammeters within the target area, specifically as follows: A high-voltage direct current microammeter monitoring model is constructed based on a deep neural network, and a genetic algorithm is introduced. A training time threshold is set, and the real-time working status information of the high-voltage direct current microammeter in the target area is input into the deep neural network for training based on the training time threshold. When the training time threshold is reached, an attention mechanism is introduced to calculate the SHAP value corresponding to all data types of the real-time working status information of the high voltage DC microammeter in each target area, and set the SHAP threshold. Obtain the data type corresponding to the SHAP value greater than the SHAP threshold, and input all data types of the real-time working status information of the high voltage DC microammeter in the target area into the attention mechanism; Focusing attention on the data types corresponding to SHAP values ​​greater than the SHAP threshold, when the network parameters of the deep neural network reach the predetermined requirements, the high voltage DC microammeter monitoring model is output, and training is complete.

4. The ultra-low power consumption control method for the high-voltage DC microammeter according to claim 1, characterized in that, The high-voltage DC microammeter monitoring model is used to monitor and identify the real-time operating status information of the high-voltage DC microammeters in the target area, specifically as follows: The real-time operating status information of the high-voltage DC microammeters in the target area within a preset time period is obtained, and the real-time operating status information of the high-voltage DC microammeters in the target area is input into the high-voltage DC microammeter monitoring model for status update. By updating the status, the real-time operating status information of each high-voltage DC microammeter in the target area with the current timestamp is obtained, and the identification result of the real-time operating status information of the high-voltage DC microammeter in the target area is generated.

5. The ultra-low power consumption control method for the high-voltage DC microammeter according to claim 1, characterized in that, A traversal algorithm is introduced to traverse and classify the identification results of the real-time operating status information of the high-voltage DC microammeters in the target area, and obtain the traversal and classification results, specifically: A dataset is constructed based on the identification results of the real-time operating status information of the high-voltage DC microammeters in the target area. A traversal algorithm is introduced to traverse the real-time operating status information of each high-voltage DC microammeter in the dataset based on the traversal algorithm. Calculate the Euclidean distance between the real-time operating status information of each high-voltage DC microammeter in the dataset; Several data subsets are constructed, and data with the same Euclidean distance value are merged into the same data subset until the real-time working status information of each high-voltage DC microammeter in the dataset is allocated, and a traversal classification result is generated.

6. The ultra-low power consumption control method for the high-voltage DC microammeter according to claim 1, characterized in that, Based on the aforementioned low-power control logic information, the traversal and classification results are controlled and optimized, specifically including: The control protocol information of each high voltage DC microammeter is obtained, and the control protocol information of each high voltage DC microammeter is parsed to obtain the parsed control protocol information of the high voltage DC microammeter. Based on the low-power control logic information and the parsed control protocol information of the high-voltage DC microammeter, the control of each high-voltage DC microammeter in the traversal classification results is optimized.

7. An ultra-low power consumption control system for a high-voltage DC microammeter, characterized in that, The device includes a memory and a processor. The memory includes a program for an ultra-low power control method for a high-voltage DC microammeter. When the processor executes the program for the ultra-low power control method for a high-voltage DC microammeter, it implements the steps of the ultra-low power control method for a high-voltage DC microammeter as described in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, The system includes a low-power control method program for a high-voltage DC microammeter, wherein when the program is executed by a processor, it implements the steps of the low-power control method for a high-voltage DC microammeter as described in any one of claims 1-6.

Images