High-voltage electrical equipment remote monitoring system and method based on Internet of Things

Abstract

The invention relates to the technical field of high-voltage electrical equipment monitoring, in particular to a high-voltage electrical equipment remote monitoring system and method based on the Internet of Things. The sensor acquires data, the data acquisition and transmission module acquires and processes the data, generates a certificate to be audited and transmits the certificate to the data processing module, the data processing module executes auditing operation to avoid misjudgment of a data packet loss phenomenon, then de-noising and standardization processing are performed on the data, and the data quality is improved. The data analysis and prediction module constructs a fault prediction model, analyzes the processed data, predicts the equipment state, calculates the fault occurrence probability, generates a health state score, compares the health state score with a preset threshold value to assess the equipment health state, and according to the assessment result, the fault early warning and alarm module sends out early warning instructions of different levels. And the remote monitoring and control module is notified to take necessary measures. The beneficial technical effects of monitoring the equipment state in real time, discovering potential faults in advance and guaranteeing safe and stable operation of the equipment are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of high-voltage electrical equipment monitoring, and in particular to a high-voltage electrical equipment remote monitoring system and method based on the Internet of Things. Background Art

[0002] With the rapid development of the power industry, high-voltage electrical equipment, as an important part of the power grid, has a direct impact on the stability and safety of the power grid due to its operating status. However, due to the complex operating environment of high-voltage electrical equipment, diverse fault types and complex fault mechanisms, traditional manual inspections and regular maintenance methods are difficult to detect potential problems in a timely manner, which can easily lead to the expansion of equipment failures and cause serious consequences. In recent years, the rapid development of Internet of Things technology has provided new technical means for the intelligent monitoring of high-voltage electrical equipment. Through real-time collection, transmission, processing and analysis of equipment operation data, comprehensive perception of equipment operation status and fault prediction can be achieved.

[0003] The Chinese invention patent application with publication number CN115877144A discloses an intelligent management system for the status of high-voltage electrical equipment based on multi-spectral detection technology, including: a switch and a remote monitoring terminal. The switch processes the data after processing visible light, infrared and ultraviolet light, and transmits the processed data to the remote monitoring terminal through a TPC / IP network. The switch includes a front-end monitoring device and a main control server. The front-end monitoring device transmits the data to the switch through an optical terminal. The application reduces failures and maintenance costs, and can reduce equipment maintenance costs by 25% to 50%, and equipment accident rates by 75%. The economic benefits are very significant. The network-based high-voltage equipment ultraviolet and infrared imaging online monitoring system can realize remote transmission and monitoring of ultraviolet, infrared and visible light images, over-temperature, and corona exceeding standard alarm prompts, and can better detect and warn early corona, fever and other failures to ensure safe operation of equipment.

[0004] Although existing research has achieved certain results in data collection, transmission security and intelligent analysis, it still has shortcomings in data diversity processing, fault risk quantification analysis and application of intelligent prediction models. Especially in complex power scenarios, how to ensure the accuracy of data processing, the reliability of analysis results and the efficiency of the monitoring system is a key issue that needs to be solved urgently. Summary of the invention

[0005] The purpose of the present invention is to solve the problems existing in the background technology and to propose a remote monitoring system and method for high-voltage electrical equipment based on the Internet of Things.

[0006] The technical solution of the present invention is a remote monitoring method for high-voltage electrical equipment based on the Internet of Things, comprising the following specific implementation steps: S1. Acquire the temperature data, voltage data and current data of high-voltage electrical equipment in real time and generate the certificate to be audited; S2. Based on the certificate to be audited, audit the temperature data, voltage data and current data, and perform denoising and standardization on the temperature data, voltage data and current data to obtain processed temperature data, voltage data and current data; S3, perform abnormal analysis on temperature data, voltage data and current data, set dynamic thresholds, determine whether the temperature data, voltage data and current data are within the set dynamic threshold allowable range, if normal, perform subsequent predictions, if abnormal, immediately generate the first warning instruction, and then input it into the trained fault prediction model, the fault prediction model predicts the time series data of the high-voltage electrical equipment, outputs the expected state at the next moment, further calculates the difference between the expected state at the next moment and the expected observed value and converts it into the probability of fault occurrence; S4. Calculate the health status score and fault probability score of the high-voltage electrical equipment, and classify the equipment status according to the threshold of the health status score and the threshold of the fault probability score based on the equipment status classification rule, output the status level of the high-voltage electrical equipment, and implement the corresponding level of operation and maintenance operations according to the status level of the high-voltage electrical equipment; S5. Real-time display of temperature data, voltage data and current data of high-voltage electrical equipment, remote monitoring of the implementation status of high-voltage electrical equipment.

[0007] Preferably, the generation process of the first warning instruction is as follows: S21. Determine L T <m Tt <U T , L V <m Vt <U V and L A <m At <U A whether it is established; Among them, m Tt 、m Vt 、m At They represent the temperature data, voltage data and current data collected at time t respectively; L T , L V , L A Respectively represents the lowest value allowed for temperature data, voltage data or current data; U T , U V , U A Respectively represent the highest and lowest values ​​allowed for temperature data, voltage data or current data; L T , L V , L A , UT , U V , U A The calculation method is: ; In the formula, , , Respectively represent the lower mean values ​​of temperature data, voltage data and current data; , , Respectively represent the upper mean values ​​of temperature data, voltage data and current data; , , Respectively represent the lower standard deviation of temperature data, voltage data and current data; , , They represent the upper limit standard deviation of temperature data, voltage data and current data respectively; k is a coefficient that determines the sensitivity of detection; S22, if the above L T <m Tt <U T , L V <m Vt <U V and L A <m At <U A If all of these are true, the high-voltage electrical equipment is in normal working condition; Otherwise, the high-voltage electrical equipment is in a dangerous working state and the first warning instruction is output immediately.

[0008] Preferably, the fault occurrence probability is generated as follows: S31, real-time high-voltage electrical equipment status data, i.e., time series data X t ={m Tt , m Vt , m At}, input into the trained fault prediction model, the fault prediction model predicts the time series data of high-voltage electrical equipment and outputs the expected state at the next moment ; S32. Calculate the expected state at the next moment The difference between the observed value and the expected value is converted into the probability of failure: ; In the formula, P (fault) represents the probability of fault occurrence, that is, the possibility of failure of high-voltage electrical equipment; X normal It indicates the normal working range or expected value of high-voltage electrical equipment; λ indicates the sensitivity coefficient, which is used to adjust the impact of the deviation between the predicted value and the normal value.

[0009] Preferably, the process of grading the device status according to the threshold of the health status score and the threshold of the fault possibility score is as follows: S41. Calculate the health status score HI of high-voltage electrical equipment: ; Where HI represents the health status score of high-voltage electrical equipment; m Tt 、m Vt and m At They represent characteristic indicators of temperature, voltage and current, i.e., normalized values ​​of temperature data, voltage data and current data; w1, w2 and w3 represent data weights of temperature, voltage and current, respectively, w1+w2+w3=1; S42. Calculate the fault probability score: P f =P(fault); S43. According to the equipment status classification rules, the status of high-voltage electrical equipment is classified into the following levels: If HI>T high And P f <T low , then the high-voltage electrical equipment is in normal health; If T mid ≤HI≤T high or T low ≤P f ≤T mid , if a minor abnormality occurs in the high-voltage electrical equipment, a third-level warning will be issued to notify the management personnel, who will decide whether to intervene; If HI <T high or P f ≥T mid , if a moderate abnormality occurs in the high-voltage electrical equipment, a secondary warning is issued, and operation and maintenance personnel are dispatched to intervene in maintenance; If the first warning instruction WI1 is received, the high-voltage electrical equipment has a serious abnormality, and the high-voltage electrical equipment is immediately shut down, a first-level warning is issued, and it is confirmed again whether the high-voltage electrical equipment is shut down, and the operation and maintenance personnel are dispatched, and the operation and maintenance personnel immediately intervene to inspect and repair; Among them, T high Indicates the high threshold of health status score; T mid Indicates the middle threshold of health status score; T low Indicates the low threshold for the failure likelihood score.

[0010] The technical solution of the present invention is a high-voltage electrical equipment remote monitoring system based on the Internet of Things, which is used for the above-mentioned high-voltage electrical equipment remote monitoring method based on the Internet of Things, including: The data acquisition and transmission module is used to perform system initialization operations with the data processing module during the system initialization phase, and to collect temperature data of high-voltage electrical equipment using a temperature sensor, voltage data of high-voltage electrical equipment using a voltage sensor, and current data of high-voltage electrical equipment using a current sensor during the remote monitoring phase, generate a certificate to be audited, and then transmit {certificate to be audited, temperature data, voltage data, current data} to the data processing module in real time; A data processing module is used to perform system initialization operations with the data acquisition and transmission module during the system initialization phase, and to audit the received temperature data, voltage data, and current data during the remote monitoring phase, and to pre-process the received temperature data, voltage data, and current data of the high-voltage electrical equipment to improve data quality, and then to save the processed temperature data, voltage data, and current data of the high-voltage electrical equipment, and to transmit the processed temperature data, voltage data, and current data of the high-voltage electrical equipment to the data analysis and prediction module; The data analysis and prediction module is used to analyze the operating conditions of high-voltage electrical equipment based on machine learning algorithms, identify abnormal data, and predict possible failure risks; The fault warning and alarm module is used to intelligently classify the status of high-voltage electrical equipment and intelligently dispatch operation and maintenance personnel; The remote monitoring and control module is used to remotely monitor high-voltage equipment and allow operation and maintenance personnel to remotely control and manage high-voltage electrical equipment.

[0011] Preferably, in the system initialization phase, the system initialization process in which the data acquisition and transmission module performs the system initialization operation is as follows: S61, the data processing module implements the following initialization settings: S6101. Randomly select a large prime number q, define two additive groups G1 and multiplicative groups G2 of order q, and select P and Q as two generators of group G1; Among them, q>3; S6102. Define a bilinear mapping e: G1×G1→G2; S6103, select and save random number s∈Z q * ={1, 2, ..., q-1}, calculate the audit check code CA = s × P; S6104. Define hash function H0: {0, 1} * →Z q * , hash function H1: {0, 1} * ×G1→G1, hash function H2: {0, 1} * →G1; S6105. Publicize system parameters {q, G1, G2, e, P, Q, H0, H1, H2, CA} to the data acquisition and transmission module; S62, the data acquisition and transmission module saves the system parameters {q, G1, G2, e, P, Q, H0, H1, H2, CA} and implements the following initialization settings: S6201, select random numbers x1∈Z for the temperature sensor, voltage sensor and current sensor inside the system respectively q * , x2∈Z q * , x3∈Z q * ; S6202, respectively calculating the permission application parameter PP1=x1×P for temperature data collection of the temperature sensor, the permission application parameter PP2=x2×P for voltage data collection of the voltage sensor, and the permission application parameter PP3=x3×P for current data collection of the current sensor; S6203. Build and save the identity group:<ID1,x1> ,<ID2,x2> ,<ID3,x3> ,<ID1,PP1> ,<ID2,PP2> ,<ID3,PP3> , and the identity group<ID1,PP1> ,<ID2,PP2> and<ID3,PP3> Transmit to the data processing module; Among them, ID1, ID2, and ID3 represent the device numbers of the temperature sensor, voltage sensor, and current sensor respectively; S63: Data processing module saves identity group<ID1,PP1> ,<ID2,PP2> and<ID3,PP3> , and continue with the following operations: S6301, calculate the authority parameter A1=s×H1(ID1||PP1) for temperature data collection of the temperature sensor, the authority parameter A2=s×H1(ID2||PP2) for voltage data collection of the voltage sensor, and the authority parameter A3=s×H1(ID3||PP3) for current data collection of the current sensor; Among them, || represents a cascade operation; S6302, build permission association group:<ID1,A1> ,<ID2,A2> and<ID3,A3> , and associate the permissions with the group:<ID1,A1> ,<ID2,A2> and<ID3,A3> Transmit to the data acquisition and transmission module to complete the system initialization process.

[0012] Preferably, the process of generating the certificate to be audited is as follows: S71. Generate a temperature identification certificate for the temperature data. The generation process is as follows: S7101, select a random number r1∈Zq * , calculate the first level certificate Cert 11 =r1×P; S7102, calculate the certificate generation parameter PG1 = H0 (m Tt ||ID1||PP1||Cert 11 ); Among them, m Tt Represents the temperature data collected at time t; S7103, Computing Level 2 Certificate Cert 12 =A1+PG1×r1×H2(CA)+x1×Q; S7104, generate temperature identification certificate Cert1=(Cert 11 , Cert 12 ); S72, generating a voltage identification certificate for the voltage data, the generation process of which is as follows: S7201, select a random number r2∈Z q * , calculate the first level certificate Cert 21 = r2 × P; S7202, calculate the certificate generation parameter PG2 = H0 (m Vt ||ID2||PP2||Cert 21 ); Among them, m Vt Represents the voltage data collected at time t; S7203, Computing Secondary Certificate Cert 22 =A2+PG2×r2×H2(CA)+x2×Q; S7204, generate voltage identification certificate Cert2=(Cert 21 , Cert 22 ); S73, generating a current identification certificate for the current data, the generation process of which is as follows: S7301, select a random number r3∈Z q * , calculate the first level certificate Cert 31 = r3 × P; S7302, calculate the certificate generation parameter PG3 = H0 (m At ||ID3||PP3||Cert 31 ); Among them, m At Represents the current data collected at time t; S7303, Computing Level 2 Certificate Cert 32=A3+PG3×r3×H2(CA)+x3×Q; S7304, generate current identification certificate Cert3=(Cert 31 , Cert 32 ); S74. Calculate the following certificates to be audited: ACert1=PG1×Cert 11 +PG2×Cert 21 +PG3×Cert 31 ; ACert2=Cert 12 +Cert 22 +Cert 32 .

[0013] Preferably, the audit process of auditing the received temperature data, voltage data and current data is as follows: S81. Calculate the first-level audit parameter PA1=e(ACert2, P); S82. Calculate the first auxiliary audit parameter AIG=H1(ID1||PP1)+H1(ID2||PP2)+H1(ID3||PP3); S83, calculate the second auxiliary audit parameter AⅡG=H2(CA); S84, calculate the third auxiliary audit parameter AⅢG=PP1+PP2+PP3; S85. Calculate the secondary audit parameter PA2 = e(AⅠG, CA)e(AⅡG, ACert1)e(Q, AⅢG); S86. If PA1=PA2, the received temperature data, voltage data and current data are audited and passed.

[0014] Compared with the prior art, the above technical solution of the present invention has the following beneficial technical effects: The present invention designs a remote monitoring system and method for high-voltage electrical equipment based on the Internet of Things. By combining the Internet of Things, data processing and deep learning technologies, an efficient, safe and intelligent high-voltage electrical equipment monitoring solution is provided, which not only improves the reliability and safety of equipment operation, but also significantly reduces the equipment maintenance cost. It has high technical value and practical application potential: (1) Efficient data collection and transmission mechanism: By installing sensors at key locations of high-voltage electrical equipment and setting reasonable sampling frequencies and transmission intervals, the temperature, voltage, and current data of the equipment can be effectively collected. The introduction of an authorization authentication mechanism not only enhances the security of data transmission, but also ensures the authenticity and integrity of the data, avoids the system being unaware of the loss of received data packets, and reduces potential safety hazards during data transmission. (2) Accurate data processing and audit mechanism: The data processing module adopts a layered audit method, combining primary audit parameters, auxiliary audit parameters and secondary audit parameters to effectively verify the legitimacy and accuracy of the data. This multi-level audit mechanism not only improves the reliability of the system, but also reduces the error rate in data processing; (3) Intelligent fault prediction based on LSTM model: Using long short-term memory network to model and predict time series data can capture the changing trend of equipment operation status. LSTM model is good at processing long-term dependencies, ensuring the accuracy of prediction results, and providing a scientific basis for the operation and maintenance of high-voltage electrical equipment; (4) Quantitative analysis of failure risks: By calculating the probability of failure, combined with health status scoring and risk scoring, quantitative analysis of equipment failure risks is achieved, equipment anomalies are identified in real time, and graded warnings are issued based on the degree of risk, thereby improving the pertinence and timeliness of equipment maintenance. (5) Flexible status classification and alarm mechanism: According to the health status score and the threshold of the failure probability, the system is divided into normal, slightly abnormal and moderately abnormal levels. Combined with the early warning instructions of different levels, the system can intelligently notify the management personnel or automatically perform emergency control, thus enhancing the safety of equipment operation and management efficiency; (6) Improving equipment management and operation and maintenance efficiency: By integrating sensor data, analysis results and intelligent prediction models, this method provides managers with real-time and accurate equipment operation information and maintenance recommendations, reducing unplanned downtime of equipment and extending equipment life. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a system architecture diagram of a high-voltage electrical equipment remote monitoring system based on the Internet of Things proposed by the present invention; Figure 2 This is the network structure diagram of the fault prediction model. DETAILED DESCRIPTION

[0016] Embodiment 1, as Figure 1 As shown, the present invention proposes a remote monitoring system for high-voltage electrical equipment based on the Internet of Things, including a data acquisition and transmission module, a data processing module, a data analysis and prediction module, a fault warning and alarm module and a remote monitoring and control module.

[0017] The data acquisition and transmission module is used to perform system initialization operations with the data processing module during the system initialization phase, and to collect temperature data of high-voltage electrical equipment using a temperature sensor, voltage data of high-voltage electrical equipment using a voltage sensor, and current data of high-voltage electrical equipment using a current sensor during the remote monitoring phase, to generate a certificate to be audited, and then to transmit {certificate to be audited, temperature data, voltage data, current data} to the data processing module in real time; The data processing module is used to perform system initialization operations with the data acquisition and transmission module during the system initialization phase, and to audit the received temperature data, voltage data and current data during the remote monitoring phase, and to pre-process the received temperature data, voltage data and current data of the high-voltage electrical equipment to improve the data quality, and then save the processed temperature data, voltage data and current data of the high-voltage electrical equipment, and transmit the processed temperature data, voltage data and current data of the high-voltage electrical equipment to the data analysis and prediction module; The data analysis and prediction module is used to analyze the operating conditions of high-voltage electrical equipment based on machine learning algorithms, identify abnormal data, and predict possible failure risks; The fault warning and alarm module is used to intelligently classify the status of high-voltage electrical equipment and intelligently dispatch operation and maintenance personnel; The remote monitoring and control module is used to remotely monitor high-voltage equipment and allow operation and maintenance personnel to remotely control and manage high-voltage electrical equipment, including but not limited to adjusting operating parameters and resetting equipment operations.

[0018] Embodiment 2, a high-voltage electrical equipment remote monitoring method based on the Internet of Things proposed by the present invention, which is used to execute a high-voltage electrical equipment remote monitoring system based on the Internet of Things proposed in Embodiment 1, and includes the following specific implementation steps: System initialization phase: S11. Install temperature sensors, voltage sensors and current sensors at key locations of high-voltage electrical equipment. Each sensor must be calibrated after installation to eliminate errors and ensure the accuracy of collected data.

[0019] S12. Set the sampling frequency and data transmission interval of the sensor according to the normal working range of the high-voltage electrical equipment.

[0020] S13, the data processing module implements the following initialization settings: S1301. Randomly select a large prime number q, q>3, define two additive groups G1 and multiplicative groups G2 of order q, and select P and Q as two generators of group G1; S1302, define a bilinear mapping e: G1×G1→G2; S1303, select and save random number s∈Z q* ={1, 2, ..., q-1}, calculate the audit check code CA = s × P; S1304. Define hash function H0: {0, 1} * →Z q * , hash function H1: {0, 1} * ×G1→G1, hash function H2: {0, 1} * →G1; S1305. Publish system parameters {q, G1, G2, e, P, Q, H0, H1, H2, CA} to the data acquisition and transmission module.

[0021] S14, the data acquisition and transmission module saves the system parameters {q, G1, G2, e, P, Q, H0, H1, H2, CA} and implements the following initialization settings: S1401, select random numbers x1∈Z for the temperature sensor, voltage sensor and current sensor inside the system respectively q * , x2∈Z q * , x3∈Z q * ; S1402, respectively calculating the permission application parameter PP1=x1×P for temperature data collection of the temperature sensor, the permission application parameter PP2=x2×P for voltage data collection of the voltage sensor, and the permission application parameter PP3=x3×P for current data collection of the current sensor; S1403, constructing an identity group:<ID1,x1> ,<ID2,x2> ,<ID3,x3> ,<ID1,PP1> ,<ID2,PP2> ,<ID3,PP3> , and group the identity<ID1,PP1> ,<ID2,PP2> and<ID3,PP3> Transmit to the data processing module; Among them, ID1, ID2, and ID3 represent the device numbers of the temperature sensor, voltage sensor, and current sensor, respectively.

[0022] S15: Data processing module saves identity group<ID1,PP1> ,<ID2,PP2> and<ID3,PP3> , and continue with the following operations: S1501, calculate the authority parameter A1=s×H1(ID1||PP1) for temperature data collection of the temperature sensor, the authority parameter A2=s×H1(ID2||PP2) for voltage data collection of the voltage sensor, and the authority parameter A3=s×H1(ID3||PP3) for current data collection of the current sensor; Among them, || represents a cascade operation; S1502, build permission association group:<ID1,A1> ,<ID2,A2> and<ID3,A3> , and associate the permissions with the group:<ID1,A1> ,<ID2,A2> and<ID3,A3> Transmit to the data acquisition and transmission module.

[0023] Remote monitoring stage: S21, the temperature sensor, the voltage sensor and the current sensor respectively collect the temperature data, the voltage data and the current data of the high-voltage electrical equipment according to the preset frequency.

[0024] S22, the data acquisition and transmission module acquires the collected temperature data, voltage data and current data of the high-voltage electrical equipment, and performs the following operations: S2201: Generate a temperature identification certificate for the temperature data. The generation process is as follows: (1) Select a random number r1∈Z q * , calculate the first level certificate Cert 11 =r1×P; (2) Calculate the certificate generation parameters PG1 = H0(m Tt ||ID1||PP1||Cert 11 ); Among them, m Tt Represents the temperature data collected at time t; (3) Calculate the secondary certificate Cert 12 =A1+PG1×r1×H2(CA)+x1×Q; (4) Generate temperature identification certificate Cert1=(Cert 11 , Cert 12 ); S2202: Generate a voltage identification certificate for the voltage data. The generation process is as follows: (1) Select a random number r2∈Z q * , calculate the first level certificate Cert 21 = r2 × P; (2) Calculate the certificate generation parameters PG2 = H0(m Vt ||ID2||PP2||Cert 21 ); Among them, m Vt Represents the voltage data collected at time t; (3) Calculate the secondary certificate Cert 22 =A2+PG2×r2×H2(CA)+x2×Q; (4) Generate voltage identification certificate Cert2=(Cert 21 , Cert 22); S2203, generating a current identification certificate for the current data, the generation process of which is as follows: (1) Select a random number r3∈Z q * , calculate the first level certificate Cert 31 = r3 × P; (2) Calculate the certificate generation parameters PG3 = H0(m At ||ID3||PP3||Cert 31 ); Among them, m At Represents the current data collected at time t; (3) Calculate the secondary certificate Cert 32 =A3+PG3×r3×H2(CA)+x3×Q; (4) Generate current identification certificate Cert3=(Cert 31 , Cert 32 ); S2204. Calculate the following certificates to be audited: ACert1=PG1×Cert 11 +PG2×Cert 21 +PG3×Cert 31 ; ACert2=Cert 12 +Cert 22 +Cert 32 ; S2205, transmit {(ACert1, ACert2), m Tt , m Vt , m At}The data is transmitted to the data processing module.

[0025] S23, the data processing module receives {(ACert1, ACert2), m Tt , m Vt , m At}, and do the following: S2301, for {(ACert1, ACert2), m Tt , m Vt , m At}Perform audit operations. The specific operation process is as follows: (1) Calculate the first-level audit parameter PA1 = e(ACert2, P); (2) Calculate the first auxiliary audit parameter AIG = H1(ID1||PP1)+H1(ID2||PP2)+H1(ID3||PP3); (3) Calculate the second auxiliary audit parameter AⅡG=H2(CA); (4) Calculate the third auxiliary audit parameter AⅢG=PP1+PP2+PP3; (5) Calculate the secondary audit parameter PA2 = e(AⅠG, CA)e(AⅡG, ACert1)e(Q, AⅢG); (6) If PA1=PA2, the audit is passed and S2302 is executed; S2302, denoising the temperature data, voltage data and current data to remove the noise that may be generated during the acquisition process: ; In the formula, represents the temperature data, voltage data or current data after denoising at time t; X(t) represents the original temperature data, voltage data or current data collected at time t; N represents the size of the sliding window, that is, the number of sampling points, which is used to control the smoothness. In this embodiment, 5 sampling points are used; S2303. To make the data have the same dimension and make the data collected by different sensors consistent, the temperature data, voltage data and current data are standardized: ; ; ; In the formula, X' represents the temperature data, voltage data or current data after standardization; μ represents the mean value of the data; δ represents the standard deviation of the data; represents the i-th data point after denoising; Num represents the number of data points; S2304, transmitting the processed temperature data, voltage data and current data to the data analysis and prediction module.

[0026] S24, the data analysis and prediction module receives the processed temperature data, voltage data and current data, and implements the following operation process: S2401. Analyze whether the temperature data, voltage data, and current data are abnormal: Judge L T <m Tt <U T , L V <m Vt <U V and L A <m At <U A whether it is established; If all the above conditions are met, the high-voltage electrical equipment is in normal working condition, and then S2402 is executed; On the contrary, the high-voltage electrical equipment is in a dangerous working state, and the first warning instruction WI1 is immediately issued to the fault early warning and alarm module; Among them, m Tt 、m Vt 、m At They represent the temperature data, voltage data and current data collected at time t respectively; L T , L V , L A Respectively represents the lowest value allowed for temperature data, voltage data or current data; U T , U V , U A Respectively represent the highest and lowest values ​​allowed for temperature data, voltage data or current data; L T , L V , L A , U T , U V , U A The calculation method is: ; In the formula, , , Respectively represent the lower mean values ​​of temperature data, voltage data and current data; , , Respectively represent the upper mean values ​​of temperature data, voltage data and current data; , , Respectively represent the lower standard deviation of temperature data, voltage data and current data; , , They represent the upper limit standard deviation of temperature data, voltage data and current data respectively; k is a coefficient that determines the sensitivity of detection. In this embodiment, k is set to 2; S2402, real-time high-voltage electrical equipment status data, i.e., time series data X t ={m Tt , m Vt , m At}, input into the trained fault prediction model, the fault prediction model predicts the time series data of high-voltage electrical equipment and outputs the expected state at the next moment : It should be noted that the fault prediction model adopts the LSTM (Long Short-Term Memory) model architecture, such as Figure 2As shown in the figure, the LSTM model is specially used to process time series data. It has the ability to remember and process long-term dependent information and is suitable for predicting the changing trend of equipment status. Its specific structure is as follows: (1) Forget gate: controls the part of historical information that the current unit needs to forget: ; In the formula, f t Represents the output of the forget gate, which takes a value between 0 and 1 and determines the forgetting ratio of the information at the previous moment; W f Represents the weight matrix of the forget gate, which is used to adjust the influence weight of the previous hidden state and the current input data; h t-1 Indicates the hidden state of the previous moment, containing information of the past moment; X t Indicates the current input data; b f Represents the bias term of the forget gate; (2) Input gate: Determine the information update at the current moment: ; ; In the formula, i t Represents the output of the input gate, which controls the proportion of new information added to the cell state; represents the candidate cell state, which determines the content of the new information to be added; Wi and WC represent the weight matrices of the input gate and the candidate cell state, respectively, which control the influence of the current input and hidden input state on the information update; b i and b C Represent the bias terms of the input gate and candidate cell state respectively; (3) Cell state update: Combine the forget gate and input gate to update the current cell state: ; In the formula, C t Represents the current cell state, that is, the stored long-term information; C t-1 Indicates the cell state at the previous moment; (4) Output gate: controls the current cell state output: ; ; In the formula, o t Represents the output of the output gate, which is used to determine the output ratio of the cell state; h t Indicates the current hidden state; W o Represents the weight matrix of the output gate, which is used to determine the proportion of the current state; b o represents the bias term of the output gate; (5) Fully connected layer: Add a linear transformation to calculate the expected state at the next moment : ; In the formula, , Both represent the expected state at the next moment; W h represents the weight matrix of the fully connected layer; b h represents the bias term of the fully connected layer; S2403. In order to further evaluate the probability of possible equipment failure, the difference between the expected state and the expected observed value at the next moment is calculated and converted into the probability of failure: ; In the formula, P (fault) represents the probability of fault occurrence, that is, the possibility of failure of high-voltage electrical equipment; X normal It indicates the normal working range or expected value of high-voltage electrical equipment; λ indicates the sensitivity coefficient, which is used to adjust the impact of the deviation between the predicted value and the normal value; S2404, transmitting the probability of fault occurrence P (fault), temperature data, voltage data and current data to the fault warning and alarm module.

[0027] S25, the fault early warning and alarm module receives the first warning instruction WI1, the probability of fault occurrence P(fault), temperature data, voltage data and current data, and performs the following operations: S2501. Calculate the health status score HI of high-voltage electrical equipment: ; Where HI represents the health status score of high-voltage electrical equipment; m Tt 、m Vt and m At They represent the characteristic indicators of temperature, voltage and current, i.e. the normalized values ​​of temperature data, voltage data and current data respectively; w1, w2 and w3 represent the data weights of temperature, voltage and current, i.e., they reflect the influence of temperature, voltage and current characteristics on the health status of high-voltage electrical equipment, w1+w2+w3=1; S2502, calculate the probability of failure score: P f =P(fault); S2503. Classify the status of high-voltage electrical equipment according to the equipment status classification rules: If HI>T high And P f <T low , then the high-voltage electrical equipment is in normal health; If T mid ≤HI≤T high or T low ≤Pf ≤T mid , if a slight abnormality occurs in the high-voltage electrical equipment, the fault warning and alarm module will send a three-level warning to the remote monitoring and control module, and the remote monitoring and control module will notify the management personnel, who will decide whether to intervene; If HI <T high or P f ≥T mid , then the high-voltage electrical equipment has a moderate abnormality, the fault warning and alarm module sends a secondary warning to the remote monitoring and control module, the remote monitoring and control module dispatches the operation and maintenance personnel, and the operation and maintenance personnel intervene in the maintenance; If the first warning instruction WI1 is received, the high-voltage electrical equipment has a serious abnormality, the fault warning and alarm module immediately shuts down the high-voltage electrical equipment, and sends a first-level warning to the remote monitoring and control module, the remote monitoring and control module immediately confirms whether the high-voltage electrical equipment is shut down, and dispatches the operation and maintenance personnel, who immediately intervene to check and repair; Among them, T high represents the high threshold of the health status score, which is 0.8 in this embodiment; mid represents the middle threshold of the health status score, which is 0.5 in this embodiment; T low Indicates the low threshold of the fault possibility score, which is 0.3 in this embodiment.

[0028] S26. The remote monitoring and control module displays the temperature data, voltage data and current data of the high-voltage electrical equipment in real time.

[0029] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited thereto, and various changes can be made within the knowledge scope of technicians in the relevant technical field without departing from the purpose of the present invention.

Claims

1. A remote monitoring method for high-voltage electrical equipment based on the Internet of Things, characterized in that: The specific implementation steps include the following: S1. Real-time collection of temperature data, voltage data and current data of high-voltage electrical equipment to generate a certificate to be audited; S2. Based on the certificate to be audited, audit the temperature data, voltage data and current data, and perform denoising and standardization on the temperature data, voltage data and current data to obtain processed temperature data, voltage data and current data; S3, perform abnormal analysis on temperature data, voltage data and current data, set dynamic thresholds, determine whether the temperature data, voltage data and current data are within the set dynamic threshold allowable range, if normal, perform subsequent predictions, if abnormal, immediately generate the first warning instruction, and then input it into the trained fault prediction model, the fault prediction model predicts the time series data of the high-voltage electrical equipment, outputs the expected state at the next moment, further calculates the difference between the expected state at the next moment and the expected observed value and converts it into the probability of fault occurrence; S4. Calculate the health status score and fault probability score of the high-voltage electrical equipment, and classify the equipment status according to the threshold of the health status score and the threshold of the fault probability score based on the equipment status classification rule, output the status level of the high-voltage electrical equipment, and implement the corresponding level of operation and maintenance operations according to the status level of the high-voltage electrical equipment; S5. Real-time display of temperature data, voltage data and current data of high-voltage electrical equipment, remote monitoring of the implementation status of high-voltage electrical equipment.

2. A remote monitoring method for high-voltage electrical equipment based on the Internet of Things according to claim 1, characterized in that: The generation process of the first warning instruction is as follows: S21. Determine L T <m Tt <U T , L V <m Vt <U V and L A <m At <U A whether it is established; Among them, m Tt 、m Vt 、m At They represent the temperature data, voltage data and current data collected at time t respectively; L T , L V , L A Respectively represents the lowest value allowed for temperature data, voltage data or current data; U T , U V , U A Respectively represent the highest and lowest values ​​allowed for temperature data, voltage data or current data; L T , L V , L A , U T , U V , U A The calculation method is: ； In the formula, , , Respectively represent the lower mean values ​​of temperature data, voltage data and current data; , , Respectively represent the upper mean values ​​of temperature data, voltage data and current data; , , Respectively represent the lower standard deviation of temperature data, voltage data and current data; , , They represent the upper limit standard deviation of temperature data, voltage data and current data respectively; k is a coefficient that determines the sensitivity of detection; S22, if the above L T <m Tt <U T , L V <m Vt <U V and L A <m At <U A If all of these are true, the high-voltage electrical equipment is in normal working condition; Otherwise, the high-voltage electrical equipment is in a dangerous working state and the first warning instruction is output immediately.

3. A remote monitoring method for high-voltage electrical equipment based on the Internet of Things according to claim 1, characterized in that: The probability of failure occurrence is generated as follows: S31, real-time high-voltage electrical equipment status data, i.e., time series data X t ={m Tt , m Vt , m At }, input into the trained fault prediction model, the fault prediction model predicts the time series data of high-voltage electrical equipment and outputs the expected state at the next moment ; S32. Calculate the expected state at the next moment The difference between the observed value and the expected value is converted into the probability of failure: ； In the formula, P (fault) represents the probability of fault occurrence, that is, the possibility of failure of high-voltage electrical equipment; X normal It indicates the normal working range or expected value of high-voltage electrical equipment; λ indicates the sensitivity coefficient, which is used to adjust the impact of the deviation between the predicted value and the normal value.

4. A method for remote monitoring of high-voltage electrical equipment based on the Internet of Things according to claim 1, characterized in that: The process of classifying the device status according to the threshold of the health status score and the threshold of the fault possibility score is as follows: S41. Calculate the health status score HI of high-voltage electrical equipment: ； Where HI represents the health status score of high-voltage electrical equipment; m Tt 、m Vt and m At They represent characteristic indicators of temperature, voltage and current, i.e., normalized values ​​of temperature data, voltage data and current data; w1, w2 and w3 represent data weights of temperature, voltage and current, respectively, w1+w2+w3=1; S42. Calculate the fault probability score: P f =P(fault); S43. According to the equipment status classification rules, the status of high-voltage electrical equipment is classified into the following levels: If HI>T high And P f <T low , then the high-voltage electrical equipment is in normal health; If T mid ≤HI≤T high or T low ≤P f ≤T mid , if a minor abnormality occurs in the high-voltage electrical equipment, a third-level warning will be issued to notify the management personnel, who will decide whether to intervene; If HI <T high or P f ≥T mid , if a moderate abnormality occurs in the high-voltage electrical equipment, a secondary warning is issued, and operation and maintenance personnel are dispatched to intervene in maintenance; If the first warning instruction WI1 is received, the high-voltage electrical equipment has a serious abnormality, and the high-voltage electrical equipment is immediately shut down, a first-level warning is issued, and it is confirmed again whether the high-voltage electrical equipment is shut down, and the operation and maintenance personnel are dispatched, and the operation and maintenance personnel immediately intervene to inspect and repair; Among them, T high Indicates the high threshold of health status score; T mid represents the middle threshold of health status score; T low Indicates the low threshold for the failure likelihood score.

5. A high-voltage electrical equipment remote monitoring system based on the Internet of Things, which is used to execute a high-voltage electrical equipment remote monitoring method based on the Internet of Things as claimed in any one of claims 1 to 4, characterized in that: include: The data acquisition and transmission module is used to perform system initialization operations with the data processing module during the system initialization phase, and to collect temperature data of high-voltage electrical equipment using a temperature sensor, voltage data of high-voltage electrical equipment using a voltage sensor, and current data of high-voltage electrical equipment using a current sensor during the remote monitoring phase, generate a certificate to be audited, and then transmit {certificate to be audited, temperature data, voltage data, current data} to the data processing module in real time; A data processing module is used to perform system initialization operations with the data acquisition and transmission module during the system initialization phase, and to audit the received temperature data, voltage data, and current data during the remote monitoring phase, and to pre-process the received temperature data, voltage data, and current data of the high-voltage electrical equipment to improve data quality, and then to save the processed temperature data, voltage data, and current data of the high-voltage electrical equipment, and to transmit the processed temperature data, voltage data, and current data of the high-voltage electrical equipment to the data analysis and prediction module; The data analysis and prediction module is used to analyze the operating conditions of high-voltage electrical equipment based on machine learning algorithms, identify abnormal data, and predict possible failure risks; The fault warning and alarm module is used to intelligently classify the status of high-voltage electrical equipment and intelligently dispatch operation and maintenance personnel; The remote monitoring and control module is used to remotely monitor high-voltage equipment and allow operation and maintenance personnel to remotely control and manage high-voltage electrical equipment.

6. A high-voltage electrical equipment remote monitoring system based on the Internet of Things according to claim 5, characterized in that: During the system initialization phase, the data acquisition and transmission module performs system initialization operations. The system initialization process is as follows: S61, the data processing module implements the following initialization settings: S6101. Randomly select a large prime number q, define two additive groups G1 and multiplicative groups G2 of order q, and select P and Q as two generators of group G1; Among them, q>3; S6102. Define a bilinear mapping e: G1×G1→G2; S6103, select and save random number s∈Z q * ={1, 2, ..., q-1}, calculate the audit check code CA = s × P; S6104. Define hash function H0: {0, 1} * →Z q * , hash function H1: {0, 1} * ×G1→G1, hash function H2: {0, 1} * →G1; S6105. Publicize system parameters {q, G1, G2, e, P, Q, H0, H1, H2, CA} to the data acquisition and transmission module; S62, the data acquisition and transmission module saves the system parameters {q, G1, G2, e, P, Q, H0, H1, H2, CA} and implements the following initialization settings: S6201, select random numbers x1∈Z for the temperature sensor, voltage sensor and current sensor inside the system respectively q * , x2∈Z q * , x3∈Z q * ; S6202, respectively calculating the permission application parameter PP1=x1×P for temperature data collection of the temperature sensor, the permission application parameter PP2=x2×P for voltage data collection of the voltage sensor, and the permission application parameter PP3=x3×P for current data collection of the current sensor; S6203. Build and save the identity group:<ID1,x1> ,<ID2,x2> ,<ID3,x3> ,<ID1,PP1> ,<ID2,PP2> ,<ID3,PP3> , and the identity group<ID1,PP1> ,<ID2,PP2> and<ID3,PP3> Transmit to the data processing module; Among them, ID1, ID2, and ID3 represent the device numbers of the temperature sensor, voltage sensor, and current sensor respectively; S63: Data processing module saves identity group<ID1,PP1> ,<ID2,PP2> and<ID3,PP3> , and continue with the following operations: S6301, calculate the authority parameter A1=s×H1(ID1||PP1) for temperature data collection of the temperature sensor, the authority parameter A2=s×H1(ID2||PP2) for voltage data collection of the voltage sensor, and the authority parameter A3=s×H1(ID3||PP3) for current data collection of the current sensor; Among them, || represents a cascade operation; S6302, build permission association group:<ID1,A1> ,<ID2,A2> and<ID3,A3> , and associate the permissions with the group:<ID1,A1> ,<ID2,A2> and<ID3,A3> Transmit to the data acquisition and transmission module to complete the system initialization process.

7. A high-voltage electrical equipment remote monitoring system based on the Internet of Things according to claim 6, characterized in that: The process of generating the audit certificate is as follows: S71. Generate a temperature identification certificate for the temperature data. The generation process is as follows: S7101, select a random number r1∈Z q * , calculate the first level certificate Cert 11 =r1×P; S7102, calculate the certificate generation parameter PG1 = H0 (m Tt ||ID1||PP1||Cert 11 ); Among them, m Tt Represents the temperature data collected at time t; S7103, Computing Level 2 Certificate Cert 12 =A1+PG1×r1×H2(CA)+x1×Q; S7104, generate temperature identification certificate Cert1=(Cert 11 , Cert 12 ); S72, generating a voltage identification certificate for the voltage data, the generation process of which is as follows: S7201, select a random number r2∈Z q * , calculate the first level certificate Cert 21 = r2 × P; S7202, calculate the certificate generation parameter PG2 = H0 (m Vt ||ID2||PP2||Cert 21 ); Among them, m Vt Represents the voltage data collected at time t; S7203, Computing Secondary Certificate Cert 22 =A2+PG2×r2×H2(CA)+x2×Q; S7204, generate voltage identification certificate Cert2=(Cert 21 , Cert 22 ); S73, generating a current identification certificate for the current data, the generation process of which is as follows: S7301, select a random number r3∈Z q * , calculate the first level certificate Cert 31 = r3 × P; S7302, calculate the certificate generation parameter PG3 = H0 (m At ||ID3||PP3||Cert 31 ); Among them, m At Represents the current data collected at time t; S7303, Computing Level 2 Certificate Cert 32 =A3+PG3×r3×H2(CA)+x3×Q; S7304, generate current identification certificate Cert3=(Cert 31 , Cert 32 ); S74. Calculate the following certificates to be audited: ACert1=PG1×Cert 11 +PG2×Cert 21 +PG3×Cert 31 ; ACert2=Cert 12 +Cert 22 +Cert 32 。 8. A high-voltage electrical equipment remote monitoring system based on the Internet of Things according to claim 7, characterized in that: The audit process for auditing the received temperature data, voltage data, and current data is as follows: S81. Calculate the first-level audit parameter PA1=e(ACert2, P); S82. Calculate the first auxiliary audit parameter AIG=H1(ID1||PP1)+H1(ID2||PP2)+H1(ID3||PP3); S83, calculate the second auxiliary audit parameter AⅡG=H2(CA); S84, calculate the third auxiliary audit parameter AⅢG=PP1+PP2+PP3; S85. Calculate the secondary audit parameter PA2 = e(AⅠG, CA)e(AⅡG, ACert1)e(Q, AⅢG); S86. If PA1=PA2, the received temperature data, voltage data and current data are audited and passed.

Images