Intelligent circuit breaker based on Internet of Things

Abstract

The invention discloses an Internet of Things intelligent circuit breaker, and relates to the technical field of circuit breakers, the Internet of Things intelligent circuit breaker comprises a circuit breaker, a mutual inductor is arranged on the left side of an inner cavity of the circuit breaker, a chip module is arranged at the bottom of the left side of the inner cavity of the circuit breaker, and a communication interface is arranged at the bottom of the right side of the circuit breaker; the chip module comprises a calculation core and a storage core, the calculation core is electrically connected with the storage core, one end of the calculation core is electrically connected with a control instruction, and the other end of the calculation core is electrically connected with waveform data; the chip module uses an artificial intelligence technology to detect and analyze equipment load characteristics in high-frequency voltage and current waveform data so as to identify typical equipment such as household appliances, electric bicycles and the like, and the chip module mainly comprises two parts, namely a main control calculation core and a storage core, the calculation core is responsible for completing the functions of real-time feature extraction, algorithm application, load identification result export, external communication and the like of high-frequency waveform data, and the storage core is mainly responsible for storing and querying the load identification result.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of circuit breakers, in particular to an Internet of Things intelligent circuit breaker. BACKGROUND

[0002] The Internet of Things intelligent circuit breaker is an advanced electrical device integrated with Internet of Things technology, which not only has the protection functions of traditional circuit breakers such as overload and short-circuit protection, but also has intelligent characteristics, can monitor the running state of the electrical system in real time, and can be remotely controlled and managed through the network. This intelligent circuit breaker is usually equipped with a microprocessor and sensors, which can accurately measure key parameters such as current, voltage, power and temperature, and transmit these data to the cloud platform or user terminal through wireless or wired means, so that users can know the running state of the electrical system at any time and anywhere. In summary, the Internet of Things intelligent circuit breaker is a powerful and highly intelligent electrical device that not only provides reliable electrical protection, but also realizes remote monitoring, automatic control and fault warning functions, providing users with a safer, more convenient and intelligent electrical management experience. With the continuous development of Internet of Things technology, the application scenarios of intelligent circuit breakers will become more and more extensive, and their role in electrical management will become more and more important. However, the existing Internet of Things intelligent circuit breaker still has some shortcomings, such as insufficient specificity, which cannot accurately detect household appliances and electric bicycles, etc., resulting in certain limitations in use. Therefore, we propose an Internet of Things intelligent circuit breaker. SUMMARY

[0003] The purpose of the present application is to provide an Internet of Things intelligent circuit breaker to solve the problems raised in the background.

[0004] To achieve the above purpose, the present application provides the following technical scheme:

[0005] An Internet of Things intelligent circuit breaker, comprising a circuit breaker and a chip module.

[0006] The inner cavity left side of the circuit breaker is provided with a mutual inductor, the inner cavity left side bottom of the circuit breaker is provided with a chip module, and the right side bottom of the circuit breaker is provided with a communication interface.

[0007] The chip module comprises a computing core and a storage core, and the computing core and the storage core are electrically connected, one end of the computing core is electrically connected with a control instruction, and the other end of the computing core is electrically connected with waveform data.

[0008] Further, a serial peripheral interface is adopted between the computing core and the storage core, and a serial peripheral interface is adopted between the computing core and the waveform data.

[0009] Further, a general-purpose input-output connection is adopted between the computing core and the control instruction.

[0010] Furthermore, the surfaces of all ferrous metal parts inside the circuit breaker are coated with an anti-corrosion layer.

[0011] Compared with the prior art, the beneficial effects of the present invention are:

[0012] This IoT smart circuit breaker uses artificial intelligence technology in its chip module to identify typical devices such as home appliances and electric bicycles by detecting and analyzing the equipment load characteristics in high-frequency voltage and current waveform data. The chip module mainly consists of two parts: a main control computing core and a storage core. The computing core is responsible for real-time feature extraction of high-frequency waveform data, algorithm application, load identification result export, and external communication. The storage core is mainly responsible for storing and querying the load identification results. Attached Figure Description

[0013] Figure 1 This is a schematic diagram of the structure of the present invention;

[0014] Figure 2 This is a schematic diagram of the chip module of the present invention;

[0015] Figure 3 This is a schematic diagram of the communication format of the original waveform of this invention;

[0016] Figure 4 This is a schematic diagram of the metering configuration parameter format of the present invention.

[0017] In the diagram: 1. Circuit breaker; 2. Current transformer; 3. Chip module; 4. Communication interface. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Example 1:

[0020] Please see Figures 1-4 The present invention provides a technical solution: an Internet of Things smart circuit breaker, comprising a circuit breaker 1 and a chip module 3;

[0021] A current transformer 2 is installed on the left side of the inner cavity of circuit breaker 1. A chip module 3 is installed at the bottom left side of the inner cavity of circuit breaker 1. The working power of chip module 3 is provided by the host hardware, and the voltage should meet (3.3±0.3)V. The communication between chip module 3 and host hardware adopts DL / T 698.45. A communication interface 4 is installed at the bottom right side of circuit breaker 1.

[0022] Get configuration parameters

[0023] The module actively requests metering parameter configuration from the outside. The outside needs to correctly respond to the metering parameter configuration request according to the DL / T 698.45-2017 Object-oriented Electricity Information Data Exchange Protocol.

[0024] The chip module sends a request for getting configuration parameters and a response example as follows:

[0025] n module request message: 681700430511111111111100EB 2605010048040200009A 3716

[0026] n external reply message: 687A 00C30511111111111100DD 7A 850101480402000102050101

[0027] 02045800060000000006FF FF FF FF 010306141C 868006 140F E52006140E72A0010306035AA15806035C 15400603 5B F228010306BA 20D93106BA 20D93106BA20D931010102 025800060000000006FF FF FF FF 0600000000110C 12008011030000806616

[0028] The module obtains real-time sampled voltage and current waveform data from the outside through SPI, and the sampling frequency is required to be not less than 6400 Hz. Mode 1 is used in the SPI communication process, and the chip module acts as a slave. The outside needs to provide three GPIOs of SCK, MOSI and CS. The SCK pin provides a clock signal for SPI communication. For single-phase data scenarios, the SPI rate is required to be not less than 2 Mbps, and for three-phase scenarios, the SPI rate is required to be not less than 6 Mbps. MOSI is a data input line. CS is the SPI chip selection signal.

[0029] The chip module requires the outside to transmit raw AD values to the non-intrusive load identification chip module without other preprocessing, so as to ensure effective precision and original signal characteristics. The communication format definition of SPI waveform data is referred to Figure 3 .

[0030] The chip module requires the outside to provide calculation configuration parameters to the chip module. The specific parameter format is referred to Figure 4 .

[0031] 3) Event reporting

[0032] When the module detects the charging of the electric vehicle, it actively notifies the outside through event reporting.

[0033] The request and response examples are as follows:

[0034] n Module request message: 6895008305111111111111f9285788020001601203000500604002

[0035] 000060410200006042020000202a 0200013421020006 20220200201e 0200202002002024020033000200331d 02 0601011c 07e7030c 12000a 1c 07e7030c 12000a 1c07e703 0c 12000a 550705111111111111010606000000b91c 07e7 030c 061224005507051111111111110101020251430002 00110016010000783516

[0036] n External reply message: 6818000305111111111111f98a b6080203016012030000346316;

[0037] The chip module 3 includes a computing core and a storage core, and the computing core is electrically connected with the storage core. One end of the computing core is electrically connected with a control instruction, and the other end of the computing core is electrically connected with waveform data. The chip module 3 utilizes artificial intelligence technology to detect and analyze the equipment load characteristics in high-frequency voltage and current waveform data, thereby realizing the identification of typical equipment such as electric bicycles. The computing core is responsible for real-time feature extraction of high-frequency waveform data, algorithm application, load identification result derivation, and external communication functions. The storage core is mainly responsible for the storage and query of the load identification result;

[0038] The chip module 3 has the ability to identify the operation of electric bicycles, and the overall identification accuracy is greater than 98%, and the recall rate is greater than 90%. The calculation method and test method are as follows:

[0039] Load identification accuracy calculation method

[0040] In binary classification problems, the Confusion Matrix is usually used to measure the performance of the model, which includes the following four key terms:

[0041] 1) True Positives (TP): Represents the number of positive class samples that the model correctly predicted. That is, the number of samples that are actually positive class and correctly classified as positive class by the model.

[0042] 2) False Negatives (FN): Represents the number of positive class samples that the model failed to correctly predict. That is, the number of samples that are actually positive class but incorrectly classified as negative class by the model.

[0043] 3) False Positives (FP): Represents the number of negative class samples that the model incorrectly predicted. That is, the number of samples that are actually negative class but incorrectly classified as positive class by the model.

[0044] 4) True Negatives (TN): Represents the number of negative class samples that the model correctly predicted. That is, the number of samples that are actually negative class and correctly classified as negative class by the model.

[0045] Precision measures how many of the samples predicted as positive class by the model are actually true positive class samples. The calculation formula is:

[0046]

[0047] Recall measures the proportion of all true positive class samples that the model successfully predicted. The calculation formula is:

[0048]

[0049] Load recognition accuracy test method

[0050] D.1 Load recognition accuracy test requirements

[0051] Prepare common household appliances (air conditioner, electric kettle, electric rice cooker, electric oven, electric heater, microwave oven, electric stove, electric hair dryer, vacuum cleaner, refrigerator, washing machine, TV, etc.) and electric bicycles to form a test environment.

[0052] The household appliances combination runs as background appliances. After 15 seconds, insert the electric bicycle battery and observe whether it is correctly identified.

[0053] The electric bicycle battery should not be in full power state.

[0054] Observe whether there is a false alarm when the electric bicycle battery is not inserted.

[0055] D.2 Load recognition ability test method

[0056] (1) According to the number of background appliances, it is divided into 5 scenes, and each scene is tested 10 times.

[0057] a) no background appliances

[0058] b) 2 background appliances + electric bicycle

[0059] c) 4 background appliances + electric bicycle

[0060] d) 6 background appliances + electric bicycle

[0061] e) 8 background appliances + electric bicycle

[0062] (2) Calculate precision and recall from the 50 tests combined.

[0063] Preferably, a serial peripheral interface is used between the computing core and the storage core, and a serial peripheral interface is used between the computing core and the waveform data.

[0064] Preferably, a general-purpose input / output connection is used between the computing core and the control instructions.

[0065] Preferably, the surface of the ferrous metal parts in the circuit breaker 1 is provided with a plated corrosion-resistant layer.

[0066] The appliances mentioned herein are all connected to an external power source via wires.

[0067] Although embodiments of the present application have been shown and described, it is to be understood that various modifications, substitutions, replacements and changes can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. An Internet of Things (IoT) smart circuit breaker, characterized in that: Includes circuit breaker (1) and chip module (3); A current transformer (2) is provided on the left side of the inner cavity of the circuit breaker (1), a chip module (3) is provided at the bottom left side of the inner cavity of the circuit breaker (1), and a communication interface (4) is provided at the bottom right side of the circuit breaker (1). The chip module (3) includes a computing core and a storage core, which are electrically connected. One end of the computing core is electrically connected to control instructions, and the other end of the computing core is electrically connected to waveform data.

2. The IoT smart circuit breaker according to claim 1, characterized in that: The computing core and the storage core use a serial peripheral interface, and the computing core and the waveform data use a serial peripheral interface.

3. The IoT smart circuit breaker according to claim 1, characterized in that: The computing core and control commands are connected via a universal input / output connection.

4. The IoT smart circuit breaker according to claim 1, characterized in that: The surface of the ferrous metal parts inside the circuit breaker (1) is coated with an anti-corrosion layer.

Images