Remote data transmission prediction method and system for cable thermal degradation gas

Abstract

The invention discloses a remote data transmission prediction method and system for cable thermal degradation gas, and relates to the technical field of cable fault detection, and the method comprises the steps: carrying out the high-precision synchronous collection and transmission of a plurality of gases released in the cable thermal degradation process; carrying out feature extraction on the collected data; and inputting the data into a multi-parameter prediction model for prediction analysis. According to the invention, cable thermal degradation gas data is synchronously collected in a high-precision manner, remote data transmission is realized by using a wireless technology, the limitation of traditional 4G communication is broken through, cross-region real-time monitoring is supported, and a global view is provided for safe operation of a power system. Abnormal fluctuation of the gas concentration can be accurately identified, real-time early warning is carried out on potential faults according to abnormal scores, and key decision support is provided for an electric power system. The power cable monitoring system has high self-adaptive capability, can be automatically adjusted to cope with different cable types and environmental conditions, has good expandability, and is suitable for various power cable monitoring scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of cable fault detection, and in particular to a remote data transmission prediction method and system for cable thermal degradation gas. Background Art

[0002] With the rapid development of the economy and society, the demand for electricity in the fields of industry, commerce and residential electricity consumption has exploded, and the stability and reliability of power transmission have received more and more attention. As a key equipment for power transmission, the safe and stable operation of power cables is particularly critical.

[0003] Power cables are usually laid in various complex environments, not only in open outdoor environments, but also in closed spaces such as underground pipelines. These cables need to work for a long time in different environments. However, due to natural aging, mechanical damage and external environmental factors, thermal degradation may occur when the power cables are running for a long time or the load is too large. Cable thermal degradation not only affects the normal operation of the cable, but may also cause serious consequences such as short circuits and fires, resulting in huge economic losses. Therefore, timely monitoring of the weak gases produced in the early stages of cable thermal degradation, so as to predict faults as early as possible and intervene manually, is of great significance to ensure the safe operation of the power system. Conventional 4G communications are limited in certain environments, so a solution based on wireless technology is needed to achieve efficient remote data acquisition and transmission. Therefore, it is extremely important to find a remote data transmission prediction method and system for cable thermal degradation gases. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: how to achieve efficient remote data acquisition and transmission based on wireless technology, timely monitor the weak gas generated in the early stage of cable thermal degradation, so as to predict faults as early as possible and conduct manual intervention to ensure the safe operation of the power system.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a remote data transmission prediction method for cable thermal degradation gases, comprising: high-precision synchronous collection and transmission of multiple gases released during the thermal degradation of the cable; feature extraction of the collected data; and inputting the data into a multi-parameter prediction model for predictive analysis.

[0007] As a preferred scheme of the remote data transmission prediction method of cable thermal degradation gas described in the present invention, the feature extraction includes dividing the gas data into time windows of a certain length, and performing statistical feature extraction on the gas data within a period of time, and the extraction specifically includes mean, standard deviation, skewness and kurtosis.

[0008] As a preferred solution of the remote data transmission prediction method for cable thermal degradation gas of the present invention, the mean value is expressed as:

[0009]

[0010] The standard deviation is expressed as:

[0011]

[0012] The skewness is expressed as:

[0013]

[0014] The kurtosis is expressed as:

[0015]

[0016] Among them, x(i) is the i-th sampling value, and N is the number of samples in that period of time.

[0017] As a preferred solution of the remote data transmission prediction method of cable thermal degradation gas described in the present invention, the multi-parameter prediction model includes time series analysis and isolation forest anomaly detection algorithm, the time series analysis includes autoregressive model and sliding average, and the autoregressive model defines the current gas concentration as a linear combination of gas concentrations at several past time points, and its formula is expressed as follows:

[0018] x(t)=φ1x(t-1)+φ2x(t-2)+...φ p x(tp)+∈(t)

[0019] Wherein, p is the model order, φ is the model coefficient, and ∈ is the noise term; the autoregressive model is used to obtain model parameters through server history fitting to predict future gas data. When the actual data differs greatly from the predicted value, it indicates that an abnormality has occurred.

[0020] As a preferred solution of the remote data transmission prediction method for cable thermal degradation gas of the present invention, wherein: the sliding average smoothes the gas concentration, and the formula is expressed as:

[0021]

[0022] Among them, k is the sliding window size.

[0023] As a preferred embodiment of the remote data transmission prediction method for thermally degraded gas in cables of the present invention, the isolation forest anomaly detection algorithm randomly selects one feature from all the features of the data, randomly selects a split point on the selected feature, and splits the data into two parts. This process continues until each data point is isolated individually or the tree reaches a preset maximum depth. For a given data point x, its expected path length h(x) in the isolation tree can be approximated as:

[0024]

[0025] Where n is the number of samples in the dataset and H(i) is the i-th harmonic number, which is defined as:

[0026] H(i)=lni+γ

[0027] Here, γ is the Euler constant.

[0028] As a preferred solution of the remote data transmission prediction method for cable thermal degradation gas of the present invention, the abnormality score can be calculated according to the expected path length, and the shorter the path, the higher the abnormal probability of the point, which can be calculated by the following formula:

[0029]

[0030] Where s(x,n) is the anomaly score of data point x, h(x) is the path length of data point x, and c(n) is the average path length used for regularization, which represents the expected path length of normal data points. c(n) can be calculated according to the following formula:

[0031]

[0032] The anomaly score ranges from 0 to 1. A value close to 0 indicates that the data point is normal, and a value close to 1 indicates that the data point is abnormal.

[0033] In the second aspect, another object of the present invention is to provide a remote data transmission prediction system for cable thermal degradation gas, comprising: a multi-channel gas acquisition module, a WIFI transmission module, a data storage module and a remote server; the multi-channel gas acquisition module is used to perform high-precision synchronous acquisition of multiple gases released during the thermal degradation of the cable; the data analysis module is used to extract features from the multi-channel gas acquisition data, and input the data into the model for prediction and analysis; the data storage module is used to store the data locally; the WIFI transmission module is used to transmit and send the collected gas data to a remote server; the monitoring and alarm module is used to receive data transmitted by WIFI transmission, and integrate a multi-parameter prediction model to monitor the thermal degradation status of the cable in real time and provide fault warning.

[0034] In a third aspect, a computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the remote data transmission prediction method for thermally degraded gas of a cable are implemented as described above.

[0035] In a fourth aspect, a computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for remote data transmission prediction of thermally degraded gas in cables as described above.

[0036] Beneficial effects of the present invention: The remote data transmission prediction method and system of cable thermal degradation gas provided by the present invention collects cable thermal degradation gas data synchronously with high precision, and realizes remote data transmission by using wireless technology, breaking through the limitations of traditional 4G communication, supporting cross-regional real-time monitoring, and providing a global perspective for the safe operation of the power system. By adopting time window division and statistical feature (such as mean, standard deviation, skewness and kurtosis) extraction, the gas data is analyzed from multiple dimensions, the recognition accuracy of the cable thermal degradation process is improved, and the change characteristics of different stages can be accurately captured. By using the autoregressive model (AR) and the sliding average model for time series prediction, the future gas concentration changes can be accurately predicted, and the possible failure risks of the cable can be identified in advance, so as to achieve timely warning and intervention. Combined with the isolation forest algorithm for unsupervised anomaly detection, the abnormal fluctuations of gas concentration can be accurately identified, and real-time warning of potential faults can be given according to the abnormal score, providing key decision support for the power system. It has strong adaptive ability, can automatically adjust to deal with different cable types and environmental conditions, and has good scalability, suitable for various power cable monitoring scenarios, and enhances the long-term stability and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0038] Figure 1 An overall flow chart of a remote data transmission prediction method for cable thermal degradation gas provided by one embodiment of the present invention;

[0039] Figure 2 A schematic diagram of the design of a remote data transmission prediction system for cable thermal degradation gas provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0041] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0042] Example 1

[0043] Reference Figure 1 , as one embodiment of the present invention, provides a remote data transmission prediction method for cable thermal degradation gas, comprising:

[0044] S1: High-precision synchronous collection and transmission of multiple gases released during cable thermal degradation;

[0045] Furthermore, three multi-channel gas acquisition modules perform high-precision synchronous acquisition of multiple gas components released during early cable thermal degradation. High-precision acquisition means that the sampling accuracy reaches more than 12 bits, and synchronous acquisition means that the data of multiple sensors are synchronously input to the main control ESP32 for real-time processing. The Wi-Fi wireless transmission module is integrated in the ESP32 chip, and the collected gas data is sent to the remote server via MQTT or HTTP protocol.

[0046] S2: Extract features from the collected data;

[0047] Furthermore, the gas data is divided into time windows of a certain length, and statistical features are extracted from the gas data within a period of time. The available features include mean, standard deviation, skewness, kurtosis, etc.

[0048] It should be noted that for a set of collected data x(t), which may be the changes in the concentration of thermally degraded gas in cables collected over a period of time, the statistical characteristics can be extracted by the following formula, where N is the number of samples within the period of time:

[0049] Mean

[0050]

[0051] Standard deviation σ:

[0052]

[0053] Skwness:

[0054]

[0055] Peak Kurtosis:

[0056]

[0057] S3: Input the data into the multi-parameter prediction model for prediction analysis.

[0058] Furthermore, the anomaly detection module uses algorithms to determine whether there are signs of cable thermal degradation based on the changing trends of multiple sensor data combined with historical data. When detecting the changing trends of sensor data, it detects the changing patterns of data over time, performs time series analysis on them, predicts future data changing trends, and compares actual values ​​with predicted values, so as to detect early cable thermal degradation phenomena as soon as possible.

[0059] Furthermore, the implementation method in time series analysis can use autoregressive model and moving average; the autoregressive model assumes that the current gas concentration is a linear combination of the gas concentrations at several past time points, and its formula is:

[0060] x(t)=φ1x(t-1)+φ2x(t-2)+...φ p x(tp)+∈(t)

[0061] Among them, p is the model order, φ is the model coefficient, and ∈ is the noise term.

[0062] It should be noted that the autoregressive model can obtain model parameters through server history fitting and be used to predict future gas data. If the actual data differs greatly from the predicted value, it indicates that an anomaly may have occurred;

[0063] Furthermore, the moving average can smooth the gas concentration, eliminating short-term fluctuations and highlighting long-term

[0064]

[0065] It should be noted that the sliding average can assist in identifying sudden changes or rising trends in gas concentrations that may be early signs of cable thermal degradation; combined with statistical feature extraction and time series analysis, the data is input into anomaly detection algorithms to determine whether it is abnormal;

[0066] Furthermore, anomaly detection algorithms such as Isolation Forest can be used to detect based on statistical features and time series analysis; Isolation Forest anomaly detection algorithm can isolate data points by recursively splitting data. By constructing multiple random trees, the path length of the data point in the tree is measured to detect anomalies.

[0067] It should be noted that in the isolation forest algorithm, a random selection is made from all the features of the data, and a split point is randomly selected on the selected feature to split the data into two parts. This process continues until each data point is isolated individually or the tree reaches a preset maximum depth. For a given data point x, its expected path length h(x) in the isolation tree can be approximated as:

[0068]

[0069] Where n is the number of samples in the dataset and H(i) is the i-th harmonic number, which is defined as:

[0070] H(i)=lni+γ

[0071] Where γ is Euler's constant, which is approximately 0.57721.

[0072] Furthermore, the anomaly score can be calculated based on the path length. The shorter the path, the higher the probability of anomaly. It can be calculated by the following formula:

[0073]

[0074] Where s(x,n) is the anomaly score of data point x, and h(x) is the path length of data point x. c(n) is the average path length used for regularization, which represents the expected path length of normal data points. c(n) can be calculated according to the following formula:

[0075]

[0076] It should be noted that the anomaly score ranges from 0 to 1, where a value close to 0 indicates that the data point is normal, and a value close to 1 indicates that the data point is abnormal.

[0077] Example 2

[0078] See also Figure 2, which is an embodiment of the present invention, provides a remote data transmission prediction system for cable thermal degradation gas, including: a multi-channel gas acquisition module, a WIFI transmission module, a data storage module and a remote server; the multi-channel gas acquisition module is used for high-precision synchronous acquisition of multiple gases released during the thermal degradation of the cable; the data storage module is used for local storage of data; the WIFI transmission module is used for transmitting and sending the collected gas data to the remote server; the monitoring and alarm module is used for receiving data transmitted by the WIFI transmission, and integrating a multi-parameter prediction model to monitor the thermal degradation status of the cable in real time and provide fault warning.

[0079] The main control CPU uses the ESP32 chip, which is connected to three multi-channel gas acquisition modules through its built-in ADC interface, namely the ADC1 module, ADC2 module and ADC3 module; the three multi-channel gas acquisition modules perform high-precision synchronous acquisition of multiple gas components released during the early thermal degradation of the cable. The high-precision acquisition refers to the sampling accuracy reaching more than 12 bits, and the synchronous acquisition refers to the synchronous input of data from multiple sensors to ESP32 for real-time processing;

[0080] The Wi-Fi wireless transmission module is integrated in the ESP32 chip, and the collected gas data is sent to the remote server via the MQTT or HTTP protocol. The TX port of the Wi-Fi module is connected to the communication port of ESP32 to achieve wireless data transmission. The Wi-Fi communication module is integrated in the ESP32 chip, and is used to cache data in the local storage module when the network cannot be connected in real time due to external factors such as environmental changes, and transmit the stored data to the remote server via Wi-Fi when the network is restored;

[0081] The data storage module is connected to the SPI interface of ESP32 and uses an SD card for local data storage to ensure that the collected cable thermal degradation characteristic gas data will not be lost when the network is unstable;

[0082] The remote server is responsible for receiving the data transmitted by the Wi-Fi module and integrating a multi-parameter prediction model to monitor the thermal degradation status of the cable in real time and provide fault warnings.

[0083] The data analysis module processes and extracts features from the multi-channel gas collection data from ESP32, and inputs the data into the model for prediction and analysis.

[0084] Example 3

[0085] An embodiment of the present invention is different from the first two embodiments in that:

[0086] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0087] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0088] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0089] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0090] Example 4

[0091] An embodiment of the present invention provides a remote data transmission prediction method for thermally degraded gas in cables. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0092] Different types of power cables (such as high-voltage cables and low-voltage cables) were selected, as well as the working conditions of the cables under different loads and environmental conditions. The temperature in the laboratory environment was maintained at 25℃±2℃ to simulate the common cable working environment. The humidity was maintained within the range of 50%±10%. The load currents of the cables were 50%, 75%, and 100% of the rated load, respectively. The data collection time for each set of experiments was 48 hours, and the data was collected once a minute.

[0093] Table 1: Anomaly detection and prediction analysis results

[0094]

[0095] Table 2: Cable thermal degradation gas concentration data and prediction results

[0096]

[0097] In the experiment, the gas concentration of the cable under different loads gradually increased as the degradation process progressed. From the early to the late stage, the concentrations of CO, CO2, and CH4 increased significantly, reflecting the intensification of thermal degradation of the cable. By comparing the predicted values ​​of the multi-parameter prediction model with the actual values, it was found that the prediction error was small in the normal and initial degradation stages. As the cable degradation intensified, the error gradually increased, but it was still within an acceptable range, indicating that the prediction model has a high accuracy. The experimental results show that the cable entered the critical failure stage after 30 hours, and the abnormality score rose sharply, indicating that the system can accurately detect abnormal changes in the cable.

Claims

1. A remote data transmission prediction method for cable thermal degradation gas, characterized in that: include: High-precision synchronous collection and transmission of multiple gases released during cable thermal degradation; Extract features from the collected data; The data were input into a multi-parameter prediction model for predictive analysis.

2. The remote data transmission prediction method of cable thermal degradation gas according to claim 1, characterized in that: The feature extraction includes dividing the gas data into time windows of a certain length, and performing statistical feature extraction on the gas data within a period of time, wherein the extraction specifically includes mean, standard deviation, skewness and kurtosis.

3. The remote data transmission prediction method of cable thermal degradation gas according to claim 2, characterized in that: The mean is expressed as: The standard deviation is expressed as: The skewness is expressed as: The kurtosis is expressed as: Among them, x(i) is the i-th sampling value, and N is the number of samples in that period of time.

4. The remote data transmission prediction method of cable thermal degradation gas according to claim 3, characterized in that: The multi-parameter prediction model includes time series analysis and an isolated forest anomaly detection algorithm. The time series analysis includes an autoregressive model and a sliding average. The autoregressive model defines the current gas concentration as a linear combination of gas concentrations at several past time points. The formula is: x(t)=φ1x(t-1)+φ2x(t-2)+...φ p x(t-p)+∈(t) Wherein, p is the model order, φ is the model coefficient, and ∈ is the noise term; the autoregressive model is used to obtain model parameters through server history fitting to predict future gas data. When the actual data differs greatly from the predicted value, it indicates that an abnormality has occurred.

5. The remote data transmission prediction method of cable thermal degradation gas according to claim 4, characterized in that: The sliding average smoothes the gas concentration, and the formula is expressed as: Among them, k is the sliding window size.

6. The remote data transmission prediction method of cable thermal degradation gas according to claim 5, characterized in that: The isolation forest anomaly detection algorithm randomly selects one feature from all the features of the data, randomly selects a split point on the selected feature, and splits the data into two parts. This process continues until each data point is isolated individually or the tree reaches a preset maximum depth. For a given data point x, its expected path length h(x) in the isolation tree can be approximated as: Where n is the number of samples in the dataset and H(i) is the i-th harmonic number, which is defined as: H(i)=lni+γ Here, γ is the Euler constant.

7. The remote data transmission prediction method of cable thermal degradation gas according to claim 6, characterized in that: The anomaly score can be calculated based on the expected path length. The shorter the path, the higher the probability of anomaly. It can be calculated by the following formula: Where s(x,n) is the anomaly score of data point x, h(x) is the path length of data point x, and c(n) is the average path length used for regularization, which represents the expected path length of normal data points. c(n) can be calculated according to the following formula: The anomaly score ranges from 0 to 1. A value close to 0 indicates that the data point is normal, and a value close to 1 indicates that the data point is abnormal.

8. A system using the remote data transmission prediction method for cable thermal degradation gas according to any one of claims 1 to 7, characterized in that: include: Multi-channel gas acquisition module, data analysis module, WIFI transmission module, data storage module and remote server; The multi-channel gas collection module is used to perform high-precision synchronous collection of multiple gases released during the thermal degradation of the cable; The data analysis module is used to extract features from multi-channel gas acquisition data and input the data into the model for prediction and analysis; The data storage module is used to store data locally; The WIFI transmission module is used to transmit the collected gas data to a remote server; The monitoring alarm module is used to receive data transmitted by WIFI, and integrate a multi-parameter prediction model to monitor the thermal degradation state of the cable in real time and provide fault warning.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the remote data transmission prediction method for thermally degraded gas of a cable according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the remote data transmission prediction method for thermally degraded gas in a cable according to any one of claims 1 to 7 are implemented.

Images