Power distribution cabinet microenvironment intelligent monitoring method and system

Abstract

The invention discloses an intelligent monitoring method and system for the microenvironment of a power distribution cabinet, and the method comprises the steps: collecting the multi-parameter data of the microenvironment of the power distribution cabinet in real time through a plurality of sensors disposed in the power distribution cabinet, and enabling the multi-parameter data to at least comprise temperature, humidity, voltage and current; transmitting the multi-parameter data to a processing platform through an internet of things network; on the processing platform, performing data fusion processing on the multi-parameter data to obtain comprehensive environment parameters; based on the comprehensive environmental parameters, performing environmental state evaluation by using a fuzzy logic algorithm, and outputting a security level; based on the time sequence data of the comprehensive environmental parameters, using a time sequence prediction model to carry out fault prediction, and outputting a parameter change trend; and performing anomaly detection based on at least one of the comprehensive environmental parameters, the security level and the parameter change trend, and sending out an alarm signal when an anomaly is detected. The invention aims to realize real-time accurate monitoring of the microenvironment of the power distribution cabinet, early warn various potential risks in time, avoid the situations of terminal strip corrosion, poor contact of a secondary line, short circuit, lightning breakdown, false alarm of a switching signal, false operation of a primary switch and the like caused by the microenvironment problem, improve the power supply reliability and guarantee the safety of a power grid.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of power distribution cabinets, and particularly relates to a power distribution cabinet micro-environment intelligent monitoring method and system. BACKGROUND

[0002] Traditional power distribution cabinets rely on manual inspection and local sensor monitoring, and have problems such as data collection lag and insufficient fault warning capability, and are difficult to cope with risks such as temperature fluctuations, humidity erosion and abnormal electrical parameters under complex working conditions. Especially for the real-time monitoring of the micro-environment inside the closed secondary cabinet of the outdoor switch and the box transformer and the DTU equipment cabinet, which are more dispersed and have more severe operating environments, due to the rainy and humid summer and autumn, the large temperature difference between the inside and outside of the switch cabinet in winter, the poor sealing of the cable interlayer and the like, all of which can cause serious condensation. Long-term condensation can cause terminal corrosion, poor secondary line contact and short circuit, and in extreme cases, lightning breakdown occurs. Especially the damage caused by internal condensation of the protection device is greater, which can cause false reporting of switch signals, or directly cause misoperation of primary switches, reducing power supply reliability and endangering the safety of the power grid. SUMMARY

[0003] In view of the problems in the prior art, the application provides a power distribution cabinet micro-environment intelligent monitoring method and system, which aims to realize real-time and accurate monitoring of the micro-environment of the power distribution cabinet, timely warning of various potential risks, and avoidance of terminal corrosion, poor secondary line contact, short circuit, lightning breakdown, switch signal false reporting, primary switch misoperation and the like caused by micro-environment problems, thereby improving power supply reliability and ensuring the safety of the power grid.

[0004] In order to solve the above technical problems, the application is implemented by the following technical scheme: According to a first aspect of the application, a power distribution cabinet micro-environment intelligent monitoring method is provided, comprising: Real-time collection of multi-parameter data of the micro-environment of the power distribution cabinet by a plurality of sensors deployed in the power distribution cabinet, wherein the multi-parameter data at least includes temperature, humidity, voltage and current; Transmitting the multi-parameter data to a processing platform through an Internet of Things network; Performing data fusion processing on the multi-parameter data at the processing platform to obtain comprehensive environmental parameters; Using a fuzzy logic algorithm to perform environmental state evaluation based on the comprehensive environmental parameters, and outputting a safety level; Using a time series prediction model to perform fault prediction based on time series data of the comprehensive environmental parameters, and outputting a parameter change trend; Based on at least one of the comprehensive environmental parameters, the safety level and the parameter change trend, performing anomaly detection, and issuing an alarm signal when an anomaly is detected.

[0005] In a possible implementation manner of the first aspect, the plurality of sensors include a power monitor, a temperature and humidity transmitter, and an infrared temperature sensor. The power monitor is configured to collect voltage and current data, the temperature and humidity transmitter is configured to collect temperature and humidity data, and the infrared temperature sensor is configured to collect device surface temperature data in a non-contact manner.

[0006] In a possible implementation manner of the first aspect, when the multi-parameter data is transmitted to the processing platform through the Internet of Things network, a MODBUS-RTU communication protocol is used, and data transmission is performed in a star topology network structure, and the baud rate is 9600 bps.

[0007] In a possible implementation manner of the first aspect, when the multi-parameter data is subjected to data fusion processing, a modified weighted average algorithm is used, and the expression is as follows:

[0008] wherein, represents a comprehensive environmental parameter after fusion; represents a parameter value of an i th sensor; represents a weight coefficient of an i th sensor, and . In a possible implementation manner of the first aspect, when the environmental state is evaluated using a fuzzy logic algorithm, temperature, humidity, and insulation resistance are defined as input variables, a safety level is defined as an output variable, and inference calculation is performed through a fuzzy rule base.

[0009] In a possible implementation manner of the first aspect, when the fault prediction is performed using a time series prediction model, an ARIMA model is used, and the expression is as follows:

[0010]

[0011] wherein, represents a monitoring parameter value at a time t; is an autoregressive coefficient; is a moving average coefficient; is a backshift operator; is a difference number; is a white noise sequence.

[0012] In a possible implementation manner of the first aspect, when the anomaly detection is performed, an adaptive threshold algorithm is used, and the dynamic threshold calculation formula is as follows: ​​​

[0013] in, Indicates a dynamic threshold; This represents the mean of the parameter's historical data; This represents the standard deviation of the parameter's historical data; This is for adjusting the coefficient.

[0014] According to a second aspect of the present invention, a microenvironment intelligent monitoring system for a power distribution cabinet is provided, comprising: The data acquisition module is used to collect multi-parameter data of the microenvironment of the power distribution cabinet in real time through multiple sensors deployed in the power distribution cabinet. The multi-parameter data includes at least temperature, humidity, voltage and current. A data communication module is used to transmit the multi-parameter data through an Internet of Things (IoT) network; The data fusion processing module is used to perform data fusion processing on the received multi-parameter data to obtain comprehensive environmental parameters; The status assessment module is used to assess the environmental status based on the comprehensive environmental parameters using a fuzzy logic algorithm and output the safety level. The fault prediction module is used to predict faults based on the time series data of the comprehensive environmental parameters using a time series prediction model, and outputs the parameter change trend. The anomaly detection and alarm module is used to perform anomaly detection based on at least one of the comprehensive environmental parameters, the security level, and the parameter change trend, and to issue an alarm signal when an anomaly is detected.

[0015] In one possible implementation of the second aspect, when performing data fusion processing on the multi-parameter data, an improved weighted average algorithm is used, the expression of which is:

[0016] in, This represents the integrated environmental parameters after fusion; Indicates the first The parameter values ​​of each sensor; Indicates the first The weighting coefficients of each sensor, and .

[0017] In one possible implementation of the second aspect, when using a time series forecasting model for fault prediction, the ARIMA model is adopted, with the expression:

[0018] in, express The monitoring parameter values ​​at any given time; These are the autoregressive coefficients; The moving average coefficient; is a back-off operator; is a difference order; is a white noise sequence.

[0019] Compared with the prior art, the present application has at least the following beneficial effects: The power distribution cabinet micro-environment intelligent monitoring method provided by the present application realizes real-time and multi-parameter collaborative monitoring of the power distribution cabinet micro-environment. Through the multiple sensors deployed in the power distribution cabinet, key parameters such as temperature, humidity, voltage and current are synchronously collected, and data transmission is performed in combination with the Internet of Things network, effectively overcoming the data collection lag problem existing in traditional manual inspection and local sensor monitoring, and obtaining timely and complete data. Through data fusion processing to generate comprehensive environmental parameters, the actual state of the power distribution cabinet micro-environment can be more comprehensively and accurately reflected, and misjudgment or missed judgment caused by single parameter monitoring is avoided. The fuzzy logic algorithm is used for environmental state evaluation, and the safety level is output, which can adapt to the uncertainty and non-linear characteristics of the power distribution cabinet under complex working conditions, and realize accurate identification and grading of the micro-environment risk. Based on the time series prediction model, the potential abnormal change can be identified in advance according to the historical data trend of the parameters, and early warning of the fault is realized, so that the occurrence of problems such as terminal row corrosion, poor secondary line contact, short circuit and lightning breakdown caused by condensation and other reasons is effectively prevented. Through multi-dimensional abnormality detection of the comprehensive environmental parameters, the safety level and the parameter change trend, and timely sending of an alarm signal when an abnormality is found, a closed-loop management from monitoring, evaluation, prediction to alarm is formed, the operation and maintenance response speed is improved, the occurrence of switch signal false alarm and primary switch misoperation is avoided, and the power supply reliability is fundamentally improved, and the power grid safety is guaranteed. The present application is particularly suitable for monitoring the internal micro-environment of the closed secondary cabinet and the DTU equipment cabinet in the outdoor switch, the box transformer and other scenes with distributed dispersion and poor operating environment, and can effectively cope with multiple risks such as humidity erosion, temperature fluctuation and abnormal electrical parameters. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the specific embodiments of the present application, the drawings needed in the description of the specific embodiments will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creating laborious work.

[0021] Figure 1 is a flow chart of the power distribution cabinet micro-environment intelligent monitoring method of the present application; Figure 2 is an execution architecture schematic diagram of the power distribution cabinet micro-environment intelligent monitoring method of the present application. DETAILED DESCRIPTION

[0022] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the present application will be described clearly and completely below with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0023] As shown in Figure 1 and Figure 2 , the present application provides a power distribution cabinet micro-environment intelligent monitoring method. At the implementation level, a four-layer Internet of Things architecture is used to build a power distribution cabinet micro-environment intelligent monitoring system, which includes four logical layers: a perception layer, a network layer, a platform layer and an application layer. The perception layer is composed of multiple types of sensor nodes, including an electrical parameter acquisition unit, an environmental monitoring unit and a device state detection unit, which realize data acquisition functions through standard industrial interfaces. The network layer adopts a heterogeneous networking method, supports hybrid networking of wired Ethernet and wireless communication, realizes data transmission based on the TCP / IP protocol stack, and the network topology adopts a hybrid structure combining star and ring types. The platform layer builds a processing system with cloud computing and edge computing collaboration. The edge node completes data preprocessing and real-time analysis, the cloud platform is responsible for big data storage and deep mining, and the micro-service architecture is used to provide scalable data service capabilities. The application layer provides a human-computer interaction interface and business logic processing, supports Web and mobile access, and realizes visual display and intelligent early warning functions of monitoring data.

[0024] The power cabinet micro-environment intelligent monitoring method specifically includes the following steps: S1, real-time acquisition of multi-parameter data of the power distribution cabinet micro-environment by multiple sensors deployed in the power distribution cabinet, the multi-parameter data at least including temperature, humidity, voltage and current.

[0025] In an implementable manner, the multiple sensors include a power monitor, a temperature and humidity transmitter and an infrared temperature sensor; wherein the power monitor is used to acquire voltage and current data, the temperature and humidity transmitter is used to acquire temperature and humidity data, and the infrared temperature sensor is used to non-contact acquisition of device surface temperature data.

[0026] Specifically, the power monitor uses a PMW3000 high-precision power monitor. The device is equipped with a 0.2-grade precision current transformer and a voltage sampling circuit, supports a three-phase four-wire connection mode, has a measurement range of 0-400V AC voltage and 0-5A direct input current, and is equipped with an RS485 interface outputting MODBUS protocol data frames.

[0027] The temperature and humidity transmitter for temperature and humidity monitoring selects a HIH4000-003 transmitter, the humidity measurement range is 0-100%RH, the precision is ±3%RH, the temperature measurement range is -40-85℃, the precision is ±0.5℃, and the output signal is a 4-20mA analog quantity converted into a digital signal by an ADAM4017 module.

[0028] The infrared temperature sensor for infrared temperature monitoring adopts an OPTIS TX-100 non-contact sensor, the measurement range is -20-300℃, the precision is ±1℃, the 20:1 object distance ratio is configured, and the temperature data is directly output through an RS485 interface.

[0029] That is, the perception layer deploys a high-precision power monitor, a HIH4000 series temperature and humidity transmitter and an OPTIS series infrared temperature sensor, and real-time collection of three-phase voltage and current, cabinet temperature and humidity and equipment surface temperature data is performed.

[0030] In the embodiment, all sensors are connected to a Moxa 5150A serial server, the server is configured with 8 independent RS485 ports, each port is set to 9600bps baud rate, 8-bit data bit, 1-bit stop bit and no check mode, the data acquisition cycle is set to 500ms, and the original measurement value is transmitted in integer data format.

[0031] The power monitor data frame contains 4 bytes of integer data, the function code 03 is used to read the holding register, and the function code 06 is used to write a single register, the temperature and humidity transmitter data address is from 0000H to 0001H, and the infrared temperature sensor needs to be modulated through an RS485 protocol converter.

[0032] The serial server configuration adopts an 8-port dual-network segment design, each Port port enables an independent network segment, the working mode is set to RS485 / 232, the data bit is configured to 8 bits, the stop bit is 1 bit, and the check bit is set to no check mode.

[0033] S2, transmitting the multi-parameter data to a processing platform through an Internet of Things network.

[0034] In an implementable manner, a MODBUS-RTU communication protocol is adopted, and data transmission is performed in a star-shaped topological network structure, and the baud rate is 9600bps.

[0035] Specifically, the micro-environment monitoring system adopts a MODBUS-RTU communication protocol as the core transmission protocol, the protocol adopts a master-slave star-shaped network structure, supports two baud rates of 9600bit / s and 4800bit / s.

[0036] The data communication module adopts a double network segment design. The main network segment is connected to the internal network through an Moxa 5150A series 8 serial server ETH0 interface, and is configured with a static IP address 192.168.1.x and a subnet mask 255.255.255.0. The backup network segment ETH1 interface reserves a PLC control channel. Data is transmitted at a baud rate of 9600 bps through the MODBUS-RTU protocol. Each port supports a packet length of 500 bytes and a packet interval of 50 ms.

[0037] The processing platform is provided with an edge computing module. The edge computing module is an EXware 703 industrial Internet of Things gateway. The gateway is configured with an Intel Atom x5-E3930 six-core processor with a main frequency of 1.8 GHz, 4 GB of DDR4 memory, and 32 GB of eMMC storage, and runs a Linux operating system. The gateway provides six RS485 interfaces, two gigabit Ethernet interfaces, and one CAN bus interface, supports simultaneous access to 28 sensor data streams, performs floating point format conversion and proportional operation on the collected integer data, and adopts HTTPS / TLS encrypted transmission for communication security, sets the QoS level of the MQTT protocol to 1, maintains a connection heartbeat interval of 60 seconds, and configures the data upload frequency to be adjustable within 1-5 seconds.

[0038] S3. The processing platform performs data fusion processing on the multi-parameter data to obtain a comprehensive environmental parameter.

[0039] In an implementation manner, the multi-parameter data is processed by using a modified weighted average algorithm, and the expression is as follows:

[0040] wherein, represents the comprehensive environmental parameter after fusion; represents a parameter value of an i th sensor; represents a weight coefficient of an i th sensor, and .

[0041] ​​Specifically, the software platform is built with a distributed microservice architecture. In the software platform, the data access layer uses Apache Kafka message queue to process sensor data stream, a 3-node cluster is configured to achieve high availability, and a single node supports processing 10,000 monitoring data per second. The data parsing service is developed based on the Spring Boot framework, adopts a multi-thread asynchronous processing mode, parses the MODBUS-RTU protocol data frame, and completes the data format conversion from integer to floating point number. The data storage adopts a combination scheme of time series database InfluxDB and relational MySQL. InfluxDB is responsible for storing real-time monitoring data such as voltage, current and temperature, and sets a 30-day data retention policy. MySQL stores device metadata, alarm records and user information. The security mechanism adopts OAuth2.0 authentication and authorization, the data transmission uses AES-256 encryption algorithm, and the operation log records complete audit trail. The data backup strategy adopts a combination of full backup and incremental backup. Full backup is performed every morning, incremental backup is performed every 4 hours, and backup data retention period is 90 days S4, based on the comprehensive environmental parameters, using fuzzy logic algorithm for environmental state evaluation, output safety level.

[0042] In an implementable manner, the environmental state evaluation uses a fuzzy logic algorithm, defines three input variables (temperature, humidity, and insulation resistance) and an output variable (safety level). Through fuzzy rule base reasoning calculation, intelligent evaluation of the environmental state is realized. The algorithm is implemented using Python scientific computing stack, using NumPy for numerical operation, Pandas for time series processing, and Scikit-learn for machine learning model construction. The real-time analysis frequency is set to perform a complete evaluation every minute.

[0043] S5, based on the time series data of the comprehensive environmental parameters, using a time series prediction model for fault prediction, outputting parameter change trend.

[0044] In an implementable manner, the fault prediction algorithm adopts time series analysis, and establishes a parameter change trend prediction model based on an ARIMA model. The model expression is:

[0045] wherein, represents the monitoring parameter value at time t; is the autoregressive coefficient; is the moving average coefficient; is the backshift operator; is the difference number; is the white noise sequence.

[0046] S6、based on the comprehensive environmental parameters, the security level and the parameter trend of at least one, carry out abnormal detection, and send an alarm signal when detecting an abnormality.

[0047] In an implementation manner, the abnormality detection adopts an adaptive threshold algorithm, and a dynamic threshold calculation formula is as follows:

[0048] The dynamic threshold is represented by T (t) ; The mean of the parameter historical data is represented by μ (t) ; The standard deviation of the parameter historical data is represented by σ (t) ; The adjustment coefficient is 2.5.

[0049] The application layer develops a configuration monitoring platform based on Jmobile Studio, adopts a Grid Layout to construct a Web display interface, and realizes real-time data table, trend curve and remote control functions.

[0050] In an embodiment, the application provides a power distribution cabinet micro-environment intelligent monitoring system, which specifically comprises a data acquisition module, a data communication module, a data fusion processing module, a state evaluation module, a fault prediction module and an abnormality detection and alarm module, and each module is configured as follows: The data acquisition module is used for acquiring multi-parameter data of the micro-environment of the power distribution cabinet in real time through a plurality of sensors arranged in the power distribution cabinet, and the multi-parameter data at least includes temperature, humidity, voltage and current.

[0051] Specifically, the plurality of sensors include a power monitor, a temperature and humidity transmitter and an infrared temperature sensor. The power monitor is used for acquiring voltage and current data, the temperature and humidity transmitter is used for acquiring temperature and humidity data, and the infrared temperature sensor is used for non-contact acquisition of device surface temperature data.

[0052] The data communication module is used for transmitting the multi-parameter data through an Internet of Things network.

[0053] Specifically, when the multi-parameter data is transmitted to a processing platform through the Internet of Things network, a MODBUS-RTU communication protocol is adopted, data transmission is performed in a star topology network structure, and the baud rate is 9600 bps.

[0054] The data fusion processing module is used for performing data fusion processing on the received multi-parameter data to obtain comprehensive environmental parameters.

[0055] Specifically, when the multi-parameter data is subjected to data fusion processing, an improved weighted average algorithm is adopted, and the expression is as follows:​

[0056] in, This represents the integrated environmental parameters after fusion; Indicates the first The parameter values ​​of each sensor; Indicates the first The weighting coefficients of each sensor, and .

[0057] The status assessment module is used to assess the environmental status based on the comprehensive environmental parameters using a fuzzy logic algorithm and output the safety level.

[0058] Specifically, when using fuzzy logic algorithms to assess environmental conditions, temperature, humidity, and insulation resistance are defined as input variables, and safety level is defined as the output variable. Reasoning calculations are then performed using a fuzzy rule base.

[0059] The fault prediction module is used to predict faults based on the time series data of the comprehensive environmental parameters using a time series prediction model, and outputs the parameter change trend.

[0060] Specifically, when using time series forecasting models for fault prediction, the ARIMA model is adopted, and its expression is:

[0061] in, express The monitoring parameter values ​​at any given time; These are the autoregressive coefficients; The moving average coefficient; For backoff operator; The degree of the difference; It is a white noise sequence.

[0062] The anomaly detection and alarm module is used to perform anomaly detection based on at least one of the comprehensive environmental parameters, the security level, and the parameter change trend, and to issue an alarm signal when an anomaly is detected.

[0063] Specifically, when performing anomaly detection, an adaptive threshold algorithm is used, and the dynamic threshold calculation formula is as follows:

[0064] in, Indicates a dynamic threshold; This represents the mean of the parameter's historical data; This represents the standard deviation of the parameter's historical data; This is for adjusting the coefficient.

[0065] All the related contents of the steps involved in the foregoing embodiment of the power distribution cabinet micro-environment intelligent monitoring method can be cited to the function description of the function modules corresponding to the power distribution cabinet micro-environment intelligent monitoring device in the embodiment of the application, and will not be repeated here. The division of the modules in the embodiment of the application is illustrative, and is only a logical function division. In actual implementation, another division mode can be used. In addition, the function modules in each embodiment of the application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module. The integrated modules can be realized in the form of hardware or in the form of software function modules.

[0066] In an embodiment, after completing the Internet of Things-based power distribution cabinet micro-environment intelligent monitoring terminal prototype, different seasons, different operating environments, different manufacturers' switches, box transformers, etc. are selected for pilot function testing, especially in summer and autumn when it is rainy and humid, and in winter when the temperature difference between the inside and outside is large. Since the cable interlayer is not tightly sealed, condensation and other conditions are easily formed. Real-time detection of the fluctuation changes of the voltage and current load of the ring network cabinet, the electric operating mechanism cabinet, the secondary terminal wiring cabinet, and the DTU equipment cabinet temperature and humidity, when the parameter value reaches the threshold value, the corresponding alarm signal is sent in time, and the operating state of the important devices and key parts in the switch cabinet of the outdoor power distribution equipment is monitored and prevented.

[0067] The system is put into operation for 90 days, and 28 sets of monitoring terminals are deployed. During the operation period, more than 5 million pieces of monitoring data are collected, 127 effective alarms are triggered, and 3 false alarms are triggered. The operation and maintenance personnel process the alarm events through the Web platform, and the average response time is shortened from 45 minutes to 5 minutes, and the fault processing efficiency is improved by 88%.

[0068] As can be seen from the above embodiment, the application realizes comprehensive real-time monitoring of the operating state of the power distribution cabinet by integrating multiple types of high-precision sensors and Internet of Things architecture. A four-layer Internet of Things structure is adopted, combined with MODBUS-RTU communication protocol and edge computing technology, to build a complete data acquisition, transmission and analysis system. The hardware design selects specific models of power monitors, temperature and humidity transmitters and infrared sensors to ensure the accuracy and reliability of data acquisition. The software platform uses a distributed micro-service architecture and intelligent analysis algorithms to realize efficient data processing and fault warning functions.

[0069] The test results show that the system performs excellently in response speed, measurement accuracy and communication stability. Actual application improves the operation and maintenance efficiency and fault warning capability.

[0070] In one embodiment, functional testing employs a combination of black-box and white-box testing, constructing a test suite containing 128 test cases. The test environment simulates the actual operating conditions of a power distribution cabinet, configured with a three-phase programmable power supply outputting 0-400V AC voltage, a precision current source providing 0-5A test current, and a constant temperature and humidity chamber simulating ambient temperature changes from -20℃ to 85℃. Communication testing uses MODBUS Poll software to simulate the master station device, verifying the integrity of serial server data transmission. Test data packet lengths increase from 64 bytes to 1024 bytes, checking data packet loss rate and bit error rate. Security functional testing includes permission verification testing, data encryption testing, and fault injection testing, simulating abnormal scenarios such as unauthorized access, data tampering, and network interruption. The test cases cover all 28 monitoring functions, including core functions such as voltage and current monitoring, temperature and humidity acquisition, insulation resistance calculation, and power quality analysis. Each test case clearly defines the input conditions, expected output, and pass criteria, and uses boundary value analysis and equivalence class partitioning methods to design the test data.

[0071] Performance testing employed load testing and stress testing methods to evaluate the system's performance under normal and extreme conditions. The tests used JMeter to simulate concurrent access from multiple users, gradually increasing the number of concurrent users from 50 to 500, and monitoring changes in system response time and throughput. Endurance testing ran continuously for 72 hours, recording system performance metrics every 5 minutes, including CPU utilization, memory usage, and network latency. Table 1 System response time test results

[0072] Data acquisition accuracy test results show that the voltage measurement error does not exceed ±0.5%, the current measurement error remains within ±0.2%, the temperature measurement accuracy reaches ±0.5℃, and the humidity measurement error is controlled within ±3%RH. In the communication performance test, the MODBUS-RTU protocol transmission success rate reaches 99.99%, the data packet transmission delay is less than 200ms, and the network interruption recovery time does not exceed 3 seconds.

[0073] In this invention, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0074] Finally, it should be noted that the above-described embodiments are merely specific embodiments of the present application, which are used to illustrate the technical solutions of the present application, but not to limit the present application. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still make modifications or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some of the technical features, within the technical scope disclosed by the present application. The modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application.

Claims

1. A method for intelligent monitoring of the microenvironment of a power distribution cabinet, characterized in that, include: Multiple sensors deployed inside the power distribution cabinet are used to collect multi-parameter data of the microenvironment of the power distribution cabinet in real time. The multi-parameter data includes at least temperature, humidity, voltage and current. The multi-parameter data is transmitted to the processing platform via an Internet of Things (IoT) network. On the processing platform, the multi-parameter data is fused to obtain comprehensive environmental parameters. Based on the comprehensive environmental parameters, a fuzzy logic algorithm is used to assess the environmental status and output the safety level. Based on the time series data of the comprehensive environmental parameters, a time series prediction model is used to predict faults and output the parameter change trend. Anomaly detection is performed based on at least one of the comprehensive environmental parameters, the safety level, and the parameter change trend, and an alarm signal is issued when an anomaly is detected.

2. The intelligent monitoring method for the microenvironment of a power distribution cabinet according to claim 1, characterized in that, The multiple sensors include a power monitor, a temperature and humidity transmitter, and an infrared temperature sensor; The power monitoring instrument is used to collect voltage and current data, the temperature and humidity transmitter is used to collect temperature and humidity data, and the infrared temperature sensor is used to collect surface temperature data of the equipment in a non-contact manner.

3. The intelligent monitoring method for the microenvironment of a power distribution cabinet according to claim 2, characterized in that, When transmitting the multi-parameter data to the processing platform via the Internet of Things network, the MODBUS-RTU communication protocol is used, and data transmission is performed in a star topology network structure with a baud rate of 9600bps.

4. The intelligent monitoring method for the microenvironment of a power distribution cabinet according to claim 1, characterized in that, When performing data fusion processing on the multi-parameter data, an improved weighted average algorithm is used, the expression of which is: in, This represents the integrated environmental parameters after fusion; Indicates the first The parameter values ​​of each sensor; Indicates the first The weighting coefficients of each sensor, and .

5. The intelligent monitoring method for the microenvironment of a power distribution cabinet according to claim 1, characterized in that, When using fuzzy logic algorithms for environmental condition assessment, temperature, humidity, and insulation resistance are defined as input variables, and safety level is defined as the output variable. Reasoning calculations are then performed using a fuzzy rule base.

6. The intelligent monitoring method for the microenvironment of a power distribution cabinet according to claim 1, characterized in that, When using time series forecasting models for fault prediction, the ARIMA model is adopted, and its expression is: in, express The monitoring parameter values ​​at any given time; These are the autoregressive coefficients; The moving average coefficient; For backoff operator; The degree of the difference; It is a white noise sequence.

7. The intelligent monitoring method for the microenvironment of a power distribution cabinet according to claim 1, characterized in that, When performing anomaly detection, an adaptive threshold algorithm is used. The dynamic threshold calculation formula is as follows: in, Indicates a dynamic threshold; This represents the mean of the parameter's historical data; This represents the standard deviation of the parameter's historical data; This is for adjusting the coefficient.

8. A micro-environment intelligent monitoring system for a power distribution cabinet, characterized in that, include: The data acquisition module is used to collect multi-parameter data of the microenvironment of the power distribution cabinet in real time through multiple sensors deployed in the power distribution cabinet. The multi-parameter data includes at least temperature, humidity, voltage and current. A data communication module is used to transmit the multi-parameter data through an Internet of Things (IoT) network; The data fusion processing module is used to perform data fusion processing on the received multi-parameter data to obtain comprehensive environmental parameters; The status assessment module is used to assess the environmental status based on the comprehensive environmental parameters using a fuzzy logic algorithm and output the safety level. The fault prediction module is used to predict faults based on the time series data of the comprehensive environmental parameters using a time series prediction model, and outputs the parameter change trend. The anomaly detection and alarm module is used to perform anomaly detection based on at least one of the comprehensive environmental parameters, the security level, and the parameter change trend, and to issue an alarm signal when an anomaly is detected.

9. The intelligent monitoring system for the microenvironment of a power distribution cabinet according to claim 8, characterized in that, When performing data fusion processing on the multi-parameter data, an improved weighted average algorithm is used, the expression of which is: in, This represents the integrated environmental parameters after fusion; Indicates the first The parameter values ​​of each sensor; Indicates the first The weighting coefficients of each sensor, and .

10. The intelligent monitoring system for the microenvironment of a power distribution cabinet according to claim 8, characterized in that, When using time series forecasting models for fault prediction, the ARIMA model is adopted, and its expression is: in, express The monitoring parameter values ​​at any given time; These are the autoregressive coefficients; The moving average coefficient; For backoff operator; The degree of the difference; It is a white noise sequence.

Images