An Internet of Things control method and device applied to power system

Abstract

The present invention relates to an Internet of Things control method and device applied to a power system, and relates to the technical field of Internet of Things, and is used to solve the problem that the existing technology has a single function and cannot monitor electrical equipment in real time and accurately. The method includes: collecting the actual value of the circuit control parameter and the parameter to be detected of the electrical equipment; determining whether the actual value of the parameter to be detected reaches a preset threshold; when it is determined that the actual value of the parameter to be detected does not reach the preset threshold, taking the circuit control parameter as input, outputting the operation status information of the circuit through a preset neural network, and the operation status information is used to characterize whether the circuit has a fault, the aging degree of the electrical equipment in the circuit, and the theoretical value of the parameter to be detected; according to the operation status information, determining the new circuit control parameter from the correspondence between the pre-stored operation status information and the standard circuit control parameter. The technical solution provided by the present invention can improve the control accuracy of the parameters.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to an Internet of Things control method and system device applied to a power system. Background Art

[0002] In the era of the Internet of Things, every object is addressable, every object can communicate, and every object can be controlled. The Internet of Things technology has been widely used in all walks of life. With the application of Internet of Things technology in power facilities, the sensing detection and wireless transmission of environmental data have become important links affecting the realization of urban Internet of Things.

[0003] The current research on the Internet of Things control device mainly designs the power data acquisition system (usually various sensors) first, and then performs multi-tasking and remote monitoring on the data collected by the power data acquisition system.

[0004] The above method simply uses the collected data to perform data monitoring or execute thread task processing, such as controlling the switch to open or close, and detecting whether the current or voltage exceeds the threshold. However, the parameters of electrical equipment are easily interfered by many factors, which causes the actual output value to deviate from the expected value. The existing technology has a single function and cannot accurately monitor electrical equipment in real time. Summary of the invention

[0005] In view of the above analysis, the present invention aims to propose an Internet of Things control method and device applied to a power system to improve the parameter control accuracy.

[0006] The purpose of the present invention is mainly achieved through the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides an Internet of Things control method for a power system, comprising:

[0008] Collect the actual values ​​of circuit control parameters and parameters to be tested of electrical equipment;

[0009] Determine whether the actual value of the parameter to be detected reaches a preset threshold;

[0010] When it is determined that the actual value of the parameter to be detected does not reach the preset threshold value, the circuit control parameter is used as input, and the operation status information of the circuit is output through a preset neural network, wherein the operation status information is used to characterize whether the circuit is faulty, the aging degree of the electrical equipment in the circuit, and the theoretical value of the parameter to be detected;

[0011] According to the operation status information, new circuit control parameters are determined from the correspondence between the pre-stored operation status information and the standard circuit control parameters.

[0012] Further, the circuit control parameters include: PID parameters, one or more of input voltage, input current, input power, working electrical equipment current of electrical equipment in the circuit, external ambient temperature, circuit power factor, working electrical equipment voltage of electrical equipment in the circuit, and electrical equipment vibration frequency of the electrical equipment;

[0013] The parameters to be detected include: one or more of output voltage, output current and output power.

[0014] Further, the neural network includes: a primary neural network, a secondary neural network, a tertiary neural network and a quaternary neural network;

[0015] The primary neural network determines a circuit fault identifier of the circuit according to the electrical device current and / or the electrical device voltage, wherein the fault identifier is used to indicate whether the circuit is faulty;

[0016] When it is determined that the circuit has no faults, the secondary neural network determines an aging mark of the electrical equipment in the circuit according to the vibration frequency of the electrical equipment, wherein the aging mark is used to indicate whether the electrical equipment in the circuit is aged;

[0017] When it is determined that the electrical equipment in the circuit is aged, the three-level neural network determines the aging degree data of the electrical equipment according to the vibration frequency of the electrical equipment and the vibration frequency of the electrical equipment when it leaves the factory;

[0018] The four-level neural network outputs the operating status information according to one or more of the theoretical value of the parameter to be detected, the circuit fault identifier, the aging identifier, and the aging degree data.

[0019] Further, detecting whether the vibration frequency of the electrical equipment is less than a preset value;

[0020] When the vibration frequency of the electrical device is not less than the preset value, determining a ratio of the vibration frequency of the electrical device to the vibration frequency of the electrical device when it leaves the factory and a first identifier;

[0021] The aging degree data includes: a ratio of the vibration frequency of the electrical equipment to the vibration frequency of the electrical equipment when it leaves the factory and the first identifier.

[0022] Further, when the vibration frequency of the electrical device is less than the preset value, a second flag is determined;

[0023] The aging degree data also includes: the second identifier.

[0024] Further, when it is determined that the actual value of the parameter to be detected reaches the threshold value, the collected circuit control parameter is set as a standard circuit control parameter;

[0025] The operating status information output by the neural network is stored correspondingly to the standard circuit control parameters.

[0026] In a second aspect, an Internet of Things control device applied to a power system includes: an acquisition module, a detection module, a neural network module and a parameter determination module;

[0027] The acquisition module is used to acquire actual values ​​of circuit control parameters and parameters to be detected;

[0028] The detection module is used to determine whether the parameter to be detected reaches a preset threshold;

[0029] The neural network module is used to output circuit operation status information using the circuit control parameter as input when it is determined that the actual value of the parameter to be detected does not reach the preset threshold value, wherein the circuit operation status information is used to characterize whether the circuit has a fault, the aging degree of the electrical equipment in the circuit, and the theoretical value of the parameter to be detected;

[0030] The parameter determination module is used to determine new circuit control parameters according to the operating state information from the correspondence between the pre-stored operating state information and the standard circuit control parameters.

[0031] Further, the circuit control parameters include: PID parameters, one or more of input voltage, input current, input power, electrical equipment current of the electrical equipment in the circuit, electrical equipment voltage of the electrical equipment in the circuit, and electrical equipment vibration frequency of the electrical equipment in the circuit;

[0032] The parameters to be detected include: one or more of output voltage, output current and output power.

[0033] Further, the neural network module includes: a primary neural network, a secondary neural network, a tertiary neural network and a quaternary neural network;

[0034] The primary neural network determines a circuit fault identifier of the circuit according to the electrical device current and / or the electrical device voltage, wherein the fault identifier is used to indicate whether the circuit is faulty;

[0035] The secondary neural network is used to determine the aging mark of the electrical equipment in the circuit according to the vibration frequency of the electrical equipment when it is determined that the circuit has no fault, and the aging mark is used to indicate whether the electrical equipment in the circuit is aged;

[0036] The three-level neural network is used to determine the aging degree data of the electrical equipment according to the vibration frequency of the electrical equipment and the vibration frequency of the electrical equipment when it leaves the factory when determining that the electrical equipment in the circuit is aging;

[0037] The four-level neural network is used to output the operating status information according to the theoretical value of the parameter to be detected, the circuit fault identifier, the aging identifier and the aging degree data.

[0038] Furthermore, the three-level neural network is used to detect whether the vibration frequency of the electrical equipment is less than a preset value; when the vibration frequency of the electrical equipment is not less than the preset value, the ratio of the vibration frequency of the electrical equipment to the vibration frequency of the electrical equipment when it leaves the factory and a first identification are determined; the aging degree data includes: the ratio of the vibration frequency of the electrical equipment to the vibration frequency of the electrical equipment when it leaves the factory and the first identification.

[0039] Beneficial effects of the technical solution of the present invention:

[0040] 1. Utilize the powerful data acquisition capability of the Internet of Things to obtain PID parameters, input voltage, input current, input power, electrical equipment current of electrical equipment in the circuit, electrical equipment voltage of electrical equipment in the circuit, and electrical equipment vibration frequency of electrical equipment in the circuit, providing a large amount of data to improve the accuracy of parameter control. On this basis, the data processing capability of the multi-level neural network is utilized to efficiently process the large amount of acquired data. Ultimately, the circuit control parameters can be adjusted in real time from three dimensions: whether the circuit is faulty, the aging degree of the electrical equipment in the circuit, and the theoretical value of the parameter to be detected, thereby improving the accuracy of parameter control.

[0041] 2. Check whether the electrical equipment is aged by detecting its vibration frequency. Then use the ratio of the current vibration frequency of the electrical equipment to the vibration frequency of the electrical equipment when it leaves the factory to quantify the degree of aging of the electrical equipment so that the operation and maintenance personnel can replace the electrical equipment in time, thereby maintaining the efficient operation of the power system.

[0042] Other features and advantages of the present invention will be described in the following description, and part of them will become obvious from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings are only for the purpose of illustrating particular embodiments and are not to be considered limiting of the present invention. Like reference symbols denote like components throughout the drawings.

[0044] Figure 1A flowchart of an Internet of Things control method applied to a power system provided by an embodiment of the present invention;

[0045] Figure 2 A schematic diagram of the structure of an Internet of Things control device applied to a power system provided by an embodiment of the present invention;

[0046] Figure 3 A schematic diagram of the structure of an Internet of Things control system applied to a power system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0048] In engineering practice, the most widely used regulator control law is proportional, integral, and differential control, referred to as PID control, also known as PID regulation. This controller has become one of the main technologies of industrial control due to its simple structure, good stability, reliable operation, and convenient adjustment. When the structure and parameters of the controlled object cannot be fully mastered, or an accurate mathematical model cannot be obtained, other technologies of control theory are difficult to adopt, and the structure and parameters of the system controller must be determined by experience and on-site debugging. At this time, it is most convenient to apply PID control technology. That is, when we do not fully understand a system and a controlled object, or cannot obtain system parameters through effective measurement methods, PID control technology is most suitable. In the prior art, PID is usually adjusted manually by staff based on experience, so its adjustment effect is difficult to guarantee. In addition, multiple manual adjustments will reduce the adjustment efficiency.

[0049] In the power system, output power is the most important indicator that people pay attention to, but there are many factors that affect the output power, such as whether there are line problems and whether the electrical equipment is aging. The usual practice is to build detection systems for current, voltage and electrical equipment respectively, and then combine the experience of operation and maintenance personnel to adjust the current and voltage, and evaluate the aging degree of electrical equipment. However, the above scheme can only evaluate the current, voltage and one or more electrical equipment of one or more circuits separately, while the output power is usually completed by all circuits and electrical equipment in the entire system. Only the current, voltage and some electrical equipment of some circuits are tested, and comprehensive data cannot be mastered, so the output power cannot be adjusted in real time. In addition, the evaluation results in the prior art rely on manual experience.

[0050] In order to solve the above problems, an embodiment of the present invention provides an Internet of Things control method applied to a power system, where the power system includes multiple circuits. Figure 1As shown, the Internet of Things control method provided in this embodiment includes the following steps:

[0051] Step 101: Collect actual values ​​of circuit control parameters and parameters to be detected in electrical equipment.

[0052] In an embodiment of the present invention, circuit control parameters include: PID parameters, one or more of the input voltage, input current, input power of the power system, the electrical equipment current of the electrical equipment in the circuit, the electrical equipment voltage of the electrical equipment in the circuit, and the electrical equipment vibration frequency of the electrical equipment in the circuit. Parameters to be detected include: one or more of the output voltage, output current and output power of the power system. It should be noted that in an embodiment of the present invention, the electrical equipment is a device that generates vibration at a specific frequency after power-on, including: one or more of a transformer, a reactor, a mutual inductor, a contactor, a circuit breaker, a measuring instrument, a distribution box, a control cabinet, lighting, an exhaust fan, a switching power supply, a compressor, an electric furnace and a motor.

[0053] Step 102: Determine whether the parameter to be detected reaches a preset threshold.

[0054] In the embodiment of the present invention, the preset threshold is used to measure whether the circuit operates normally; when the parameter to be detected reaches the preset threshold, it means that the circuit operates normally, otherwise the circuit operates abnormally.

[0055] Step 103: When it is determined that the actual value of the parameter to be detected does not reach the preset threshold, the circuit control parameter is used as input and the operation status information of the circuit is output through the neural network.

[0056] In the embodiment of the present invention, the operation status information is used to characterize whether the circuit has a fault, the aging degree of the electrical equipment in the circuit, and the theoretical value of the parameter to be detected.

[0057] In an embodiment of the present invention, by comparing the theoretical value with the preset threshold value, it is possible to determine whether there is an abnormality in the entire circuit, and then eliminate it in the order of circuit failure and electrical aging. After determining that the above abnormality is not caused by circuit failure and electrical aging, the circuit control parameters are adjusted to avoid accidents. For example, when a circuit is broken or part of the electrical circuit is broken, if the voltage and current are simply increased, the temperature at the broken or aged part will rise sharply, and even cause a fire. The above process of determining the circuit control parameters is progressive, so a multi-level neural network model is adopted to realize the intelligence of each link.

[0058] Specifically, the primary neural network determines a circuit fault identifier of the circuit based on the electrical equipment current and / or the electrical equipment voltage, and the fault identifier is used to indicate whether the circuit is faulty.

[0059] When it is determined that the circuit is fault-free, the secondary neural network determines the aging mark of the electrical equipment in the circuit based on the vibration frequency of the electrical equipment, and the aging mark is used to indicate whether the electrical equipment in the circuit is aged. When it is determined that the electrical equipment in the circuit is aged, the tertiary neural network determines the aging degree data of the electrical equipment based on the vibration frequency of the electrical equipment and the vibration frequency of the electrical equipment when it leaves the factory. The fourth-level neural network outputs the operating status information based on one or more of the theoretical value of the parameter to be detected, the circuit fault mark, the aging mark, and the aging degree data.

[0060] The first-level neural network can adopt a neural network model such as a BP neural network and a feedforward neural network. The output is the current and voltage of the electrical equipment and the circuit fault identification. Among them, the circuit fault identification is used to indicate whether the circuit is faulty.

[0061] The secondary neural network adopts neural network models such as BP neural network and feedforward neural network. It takes the vibration frequency of electrical equipment and the circuit fault-free mark as input and the aging mark as output. Among them, the aging mark is used to indicate whether the electrical equipment is aging.

[0062] The three-level neural network adopts neural network models such as BP neural network and feedforward neural network. The vibration frequency of the electrical equipment, the vibration frequency of the electrical equipment when it leaves the factory and the mark of the electrical equipment not being aged are input, and the aging degree data is output.

[0063] The four-level neural network adopts neural network models such as BP neural network and feedforward neural network, takes one or more of the theoretical value of the parameter to be detected, circuit fault mark, aging mark and aging degree data as input, and takes the operation status information as output.

[0064] It should be noted that, except for the first-level neural network, other levels of neural networks can directly use the data output by other neural networks as input for training.

[0065] Among them, the specific process of the three-level neural network to determine the aging degree data is as follows:

[0066] Detect whether the vibration frequency of electrical equipment is less than the preset value;

[0067] When the vibration frequency of the electrical equipment is not less than a preset value, determining a ratio of the vibration frequency of the electrical equipment to the vibration frequency of the electrical equipment when it leaves the factory and a first identifier;

[0068] The aging degree data includes: the ratio of the vibration frequency of the electrical equipment to the vibration frequency of the electrical equipment when it leaves the factory and the first mark. When the vibration frequency of the electrical equipment is less than a preset value, a second mark is determined; the aging degree data also includes: the second mark.

[0069] In an embodiment of the present invention, the preset value is a standard for measuring the degree of aging. Usually, electrical equipment needs to operate at rated power. When the electrical equipment is aged, its actual power is often inconsistent with the rated power. If the actual power is greater than the rated power, the electrical equipment will be burned out due to long-term overload operation. If the actual power is less than the rated power, the output power of the electrical equipment will become smaller or even unable to operate. For electrical equipment, its rated power is a range, and as the degree of aging increases, its actual power will change in the direction of exceeding this range. Therefore, the first mark is used to characterize that although the corresponding electrical equipment is aged, its actual power can be maintained within the rated power range by adjusting parameters, thereby ensuring the overall output power. The second mark is used to characterize that the corresponding electrical equipment is aged, and its actual power cannot be maintained within the rated power range by adjusting parameters, and these equipment can only be replaced. Through the above method, it is possible to maximize the use of each electrical equipment, while also reducing the maintenance frequency and equipment replacement frequency of the operation and maintenance personnel, thereby improving the operation and maintenance efficiency and reducing the operation and maintenance costs.

[0070] Step 104: According to the operation status information, determine new circuit control parameters from the correspondence between the pre-stored operation status information and the standard circuit control parameters.

[0071] In the embodiment of the present invention, the correspondence between the operating status information and the standard circuit control parameters may be stored from two aspects.

[0072] First, during the training of the neural network model, the operation and maintenance personnel will mark the training results based on their experience and actual conditions. For example, if the input circuit control parameter is a and the output power is b, if b meets the threshold set by the operation and maintenance personnel, the operation and maintenance personnel will mark the training result as "meets the requirements" and store a and b accordingly. The above method can not only help improve the training accuracy of the model, but also continuously improve the correspondence between the operating status information and the standard circuit control parameters while the model is being trained.

[0073] Second, when it is determined that the actual value of the parameter to be detected reaches the threshold, the collected circuit control parameter is set as the standard circuit control parameter. The operating status information output by the neural network is stored corresponding to the standard circuit control parameter. In this way, the neural network in the embodiment of the present application can learn and work at the same time, which can not only save training time, but also solve the problem of insufficient training samples and inaccurate models. In addition, adjusting the circuit control parameters according to the operating status information is essentially based on the current loss and usage of each electrical equipment, and the circuit control parameters are adjusted in real time as a whole, so it is more scientific and effective.

[0074] like Figure 2As shown, the embodiment of the present invention further provides an Internet of Things control device, including: a collection module 201, a detection module 202, a neural network module 203 and a parameter determination module 204;

[0075] The acquisition module 201 is used to acquire the actual values ​​of the circuit control parameters and the parameters to be detected;

[0076] The detection module 202 is used to determine whether the parameter to be detected reaches a preset threshold;

[0077] The neural network module 203 is used to output the circuit operation status information by taking the circuit control parameter as input when it is determined that the actual value of the parameter to be detected does not reach the preset threshold value. The operation status information is used to characterize whether the circuit has a fault, the aging degree of the electrical equipment in the circuit and the theoretical value of the parameter to be detected;

[0078] The parameter determination module 204 is used to determine new circuit control parameters according to the operation status information from the correspondence between the pre-stored operation status information and the standard circuit control parameters.

[0079] In an embodiment of the present invention, the circuit control parameters include: PID parameters, one or more of input voltage, input current, input power, electrical equipment current of the electrical equipment in the circuit, electrical equipment voltage of the electrical equipment in the circuit and electrical equipment vibration frequency of the electrical equipment in the circuit; the parameters to be detected include: one or more of output voltage, output current and output power.

[0080] In the embodiment of the present invention, the neural network module 203 includes: a primary neural network, a secondary neural network, a tertiary neural network and a quaternary neural network;

[0081] The first-level neural network is used to determine the circuit fault identification of the circuit based on the current and / or voltage of the electrical equipment, and the fault identification is used to indicate whether the circuit is faulty; the second-level neural network is used to determine the aging identification of the electrical equipment in the circuit based on the vibration frequency of the electrical equipment when it is determined that the circuit is not faulty, and the aging identification is used to indicate whether the electrical equipment in the circuit is aged; the third-level neural network is used to determine the aging degree data of the electrical equipment based on the vibration frequency of the electrical equipment and the vibration frequency of the electrical equipment when it leaves the factory when it is determined that the electrical equipment in the circuit is aged; the fourth-level neural network is used for the neural network to output operating status information based on the theoretical value of the parameter to be detected, the circuit fault identification, the aging identification and the aging degree data.

[0082] In an embodiment of the present invention, a four-level neural network is used to detect whether the vibration frequency of the electrical equipment is less than a preset value; when the vibration frequency of the electrical equipment is not less than the preset value, the ratio of the vibration frequency of the electrical equipment to the vibration frequency of the electrical equipment when it leaves the factory and a first identification are determined; the aging degree data includes: the ratio of the vibration frequency of the electrical equipment to the vibration frequency of the electrical equipment when it leaves the factory and the first identification.

[0083] In order to illustrate the feasibility of the technical solution of the present invention, the present invention provides an embodiment, such as Figure 3 As shown, it includes: the sensor on the electrical device uploads the circuit control parameters to the controller, and then the controller sends the circuit control parameters to the server where the neural network is located, and the server calculates (see Figure 1 Corresponding steps) will determine the new control parameters in the database and then be returned to the electrical equipment by the controller. It should be noted that the scope of application of the technical solution of the present application can be effectively increased by the controller. Among them, the controller adopts the chip of the STM32F103 series as the main controller, uses the ADC / DAC module of the controller to collect and output signals, realizes data communication through serial port, Ethernet and Bluetooth, and the software part of the server where the Internet of Things control system is located is designed and implemented using MFC (Microsoft Foundation Classes) or Qt program development framework. Android App is set on the electrical equipment to receive data, and an Ethernet data receiving program is designed in the communication part of the server where the Internet of Things control system is located.

[0084] Specifically, the hardware structure framework of the controller includes: the main control chip is STM32F103, the minimum system circuit, the power supply circuit, the operational amplifier circuit and the serial communication circuit. The power supply adopts the typical DC 24V voltage, which is converted into positive and negative 15V, 5V and 3.3 respectively through the power conversion circuit, which is used as the power supply source for the operational amplifier, communication chip and main control chip. According to the IO of the chip, an operational amplifier circuit with four analog inputs and two analog outputs can be designed. The input part can realize voltage acquisition, convert the acquisition signal from high voltage to 0 to 3.3V voltage readable by the chip, and can collect current signals, which are also converted into 0 to 3.3V voltage; the output part can be divided into voltage drive and current drive circuits. For the communication part, the TTL level of the main control chip is mainly converted into a level signal that meets the serial port, Bluetooth and Ethernet standards to realize wired and wireless data transmission.

[0085] The software part of the controller includes the embedded real-time operating system RT_thread4.0, including: analog quantity acquisition thread, serial communication thread, PID control thread, Bluetooth communication thread, Ethernet communication thread. The signal acquisition thread implements the sampling and filtering of analog quantity. The collected signal data and the calculated data are transmitted to the corresponding places through the serial port, Bluetooth and Ethernet threads. At the same time, the control command from the server where the Internet of Things control system is located is received through the communication thread; the signal, data and control instruction are combined with the control algorithm through the PID control thread to output the control signal to achieve the purpose of closed-loop control.

[0086] Those skilled in the art will appreciate that all or part of the process of the method in the above embodiment can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0087] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A control method for the Internet of Things applied to a power system, characterized in that: include: Collect the actual values ​​of circuit control parameters and parameters to be tested of electrical equipment; Determine whether the actual value of the parameter to be detected reaches a preset threshold; When it is determined that the actual value of the parameter to be detected does not reach the preset threshold value, the circuit control parameter is used as input, and the operation status information of the circuit is output through a preset neural network, wherein the operation status information is used to characterize whether the circuit is faulty, the aging degree of the electrical equipment in the circuit, and the theoretical value of the parameter to be detected; According to the operation status information, determine new circuit control parameters from the correspondence between the pre-stored operation status information and the standard circuit control parameters; The circuit control parameter is used as input and the circuit operation status information is output through a neural network, including: The neural network includes: a primary neural network, a secondary neural network, a tertiary neural network and a quaternary neural network; The primary neural network determines a circuit fault identifier of the circuit according to the electrical device current and / or the electrical device voltage, wherein the fault identifier is used to indicate whether the circuit is faulty; When it is determined that the circuit has no faults, the secondary neural network determines an aging mark of the electrical equipment in the circuit according to the vibration frequency of the electrical equipment, wherein the aging mark is used to indicate whether the electrical equipment in the circuit is aged; When it is determined that the electrical equipment in the circuit is aged, the three-level neural network determines the aging degree data of the electrical equipment according to the vibration frequency of the electrical equipment and the vibration frequency of the electrical equipment when it leaves the factory; The four-level neural network outputs the operating status information according to one or more of the theoretical value of the parameter to be detected, the circuit fault identifier, the aging identifier, and the aging degree data.

2. The method according to claim 1, characterized in that The circuit control parameters include: PID parameters, one or more of input voltage, input current, input power, working electrical equipment current of electrical equipment in the circuit, external ambient temperature, circuit power factor, working electrical equipment voltage of electrical equipment in the circuit, and electrical equipment vibration frequency; The parameters to be detected include: one or more of output voltage, output current and output power.

3. The method according to claim 1, characterized in that The three-level neural network determines the aging degree data of the electrical equipment according to the vibration frequency of the electrical equipment and the vibration frequency of the electrical equipment when it leaves the factory, including: Detecting whether the vibration frequency of the electrical equipment is less than a preset value; When the vibration frequency of the electrical device is not less than the preset value, determining a ratio of the vibration frequency of the electrical device to the vibration frequency of the electrical device when it leaves the factory and a first identifier; The aging degree data includes: a ratio of the vibration frequency of the electrical equipment to the vibration frequency of the electrical equipment when it leaves the factory and the first identifier.

4. The method according to claim 3, characterized in that The three-level neural network determines the aging degree data of the electrical equipment according to the vibration frequency of the electrical equipment and the vibration frequency of the electrical equipment when it leaves the factory, including: When the vibration frequency of the electrical equipment is less than the preset value, determining a second flag; The aging degree data also includes: the second identifier.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: When it is determined that the actual value of the parameter to be detected reaches the threshold, setting the collected circuit control parameter as a standard circuit control parameter; The operating status information output by the neural network is stored correspondingly to the standard circuit control parameters.

6. An Internet of Things control device applied to a power system, characterized in that: include: Acquisition module, detection module, neural network module and parameter determination module; The acquisition module is used to acquire actual values ​​of circuit control parameters and parameters to be detected; The detection module is used to determine whether the parameter to be detected reaches a preset threshold; The neural network module is used to output circuit operation status information using the circuit control parameter as input when it is determined that the actual value of the parameter to be detected does not reach the preset threshold value, wherein the circuit operation status information is used to characterize whether the circuit has a fault, the aging degree of the electrical equipment in the circuit, and the theoretical value of the parameter to be detected; The parameter determination module is used to determine new circuit control parameters according to the operating state information from the correspondence between the pre-stored operating state information and the standard circuit control parameters; The neural network module includes: a primary neural network, a secondary neural network, a tertiary neural network and a quaternary neural network; The primary neural network determines a circuit fault identifier of the circuit according to the electrical device current and / or the electrical device voltage, wherein the fault identifier is used to indicate whether the circuit is faulty; The secondary neural network is used to determine the aging mark of the electrical equipment in the circuit according to the vibration frequency of the electrical equipment when it is determined that the circuit has no fault, and the aging mark is used to indicate whether the electrical equipment in the circuit is aged; The three-level neural network is used to determine the aging degree data of the electrical equipment according to the vibration frequency of the electrical equipment and the vibration frequency of the electrical equipment when it leaves the factory when determining that the electrical equipment in the circuit is aging; The four-level neural network is used to output the operating status information according to the theoretical value of the parameter to be detected, the circuit fault identifier, the aging identifier and the aging degree data.

7. The device according to claim 6, characterized in that The circuit control parameters include: PID parameters, one or more of input voltage, input current, input power, electrical equipment current of electrical equipment in the circuit, electrical equipment voltage of electrical equipment in the circuit, and electrical equipment vibration frequency of electrical equipment in the circuit; The parameters to be detected include: one or more of output voltage, output current and output power.

8. The device according to claim 6, characterized in that The three-level neural network is used to detect whether the vibration frequency of the electrical equipment is less than a preset value; when the vibration frequency of the electrical equipment is not less than the preset value, determine the ratio of the vibration frequency of the electrical equipment to the vibration frequency of the electrical equipment when it leaves the factory and a first identifier; the aging degree data includes: the ratio of the vibration frequency of the electrical equipment to the vibration frequency of the electrical equipment when it leaves the factory and the first identifier.

Images