Estimation method and monitoring system for cable core temperature of power transmission line connector

Abstract

The invention belongs to the technical field of power system on-line monitoring and safety, and discloses a power transmission line connector core temperature estimation method and monitoring system, and the method comprises the steps: collecting the temperature values of multiple points outside a power transmission line connector through a temperature sensor; a current sensor is used for collecting the current of the cable, and data are sent to a remote centralized control center through a wireless sensor network; and outputting an estimated temperature value of the cable core of the power transmission line connector by using a program operation estimation algorithm stored in the centralized control center server, and comparing the estimated temperature value with a preset cable core temperature threshold value of the power transmission line connector. The temperature sensor and the current sensor are adopted, and estimation and remote monitoring of the temperature of the power transmission line connector are achieved based on the grouping coevolution fruit fly optimization algorithm and the generalized regression neural network algorithm. The power transmission line joint wire core temperature monitoring system overcomes the defects of low precision and poor real-time performance of a power cable joint wire core temperature indirect measurement method, and solves the problems of long calculation time, low precision and the like of an existing estimation model.

Description

Technical Field

[0001] The invention belongs to the technical field of online monitoring and safety of electric power systems, and in particular relates to an estimation method and a monitoring system for the temperature of a transmission line joint core. Background Art

[0002] At present, power cables are important components for building power systems to transmit electric energy. Ensuring the normal operation of power cables is a key factor in ensuring energy security. With the rapid advancement of urban modernization, underground cables have become the main mode of power transmission, but the maintenance of underground tunnel cables has become a major problem in the operation and maintenance of power systems. It is reported that fires caused by tunnel cables currently mainly occur at cable joints, so real-time monitoring of the core temperature of transmission line joints is an effective way to prevent tunnel cable safety accidents.

[0003] At present, the cable joint core temperature monitoring methods mainly adopt direct measurement method and indirect measurement method. The direct measurement method requires the temperature sensor to be buried in the power cable joint, which significantly increases the difficulty of power engineering construction. In addition, when the direct measurement sensor fails and needs maintenance, the power can only be cut off, and its practicality is very limited. The indirect measurement method is to infer the temperature of the power cable core by measuring the temperature of the cable joint sheath, or use surface acoustic wave detection technology. The common disadvantages are low measurement accuracy and poor real-time performance. It cannot accurately reflect the actual temperature of the cable joint, let alone the transient state of the cable joint core temperature.

[0004] Through the above analysis, the problems and defects of the prior art are as follows:

[0005] (1) Among the current methods for monitoring the core temperature of cable joints, the direct measurement method requires the temperature sensor to be buried in the power cable joint, which significantly increases the difficulty of power engineering construction. In addition, when the direct measurement sensor fails and needs maintenance, the only option is to cut off the power supply, which has very limited practicality.

[0006] (2) The existing indirect measurement method is to estimate the temperature of the power cable core by measuring the temperature of the cable joint sheath, or use surface acoustic wave detection technology. The measurement accuracy is low and the real-time performance is poor. It cannot accurately reflect the actual temperature of the cable joint, let alone the transient state of the cable joint core temperature. Summary of the invention

[0007] In view of the problems existing in the prior art, the present invention provides a method for estimating the wire core temperature of a transmission line joint and a monitoring system.

[0008] The present invention is implemented as follows: a method for estimating the core temperature of a transmission line joint, the method for estimating the core temperature of a transmission line joint comprising: setting a plurality of temperature sensors and current sensors outside the transmission line joint, using the temperature sensors and current sensors to respectively collect the temperature values ​​of multiple points outside the transmission line joint and the current size of the cable and send the data to a centralized control center; the centralized control center realizes the estimation and remote monitoring of the transmission line joint temperature based on a grouped co-evolutionary fruit fly optimization algorithm and a generalized regression neural network algorithm.

[0009] Further, the method for estimating the core temperature of the transmission line joint includes the following steps:

[0010] Step 1: collecting temperature values ​​of multiple points outside the transmission line joint through a temperature sensor;

[0011] Step 2: collecting the current of the cable through a current sensor;

[0012] Step 3: Send the collected data to the remote control center through the wireless sensor network;

[0013] Step 4: Use the program stored in the centralized control center server to run the estimation algorithm to output the estimated temperature value of the transmission line joint core, and compare it with the pre-set transmission line joint core temperature threshold.

[0014] Furthermore, in step one, real-time data of the skin temperature of the cable, the sheath temperature of the cable connector, and the ambient temperature are collected by a temperature sensor.

[0015] Furthermore, in step three, the collected cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data are sent to a remote control center via a wireless sensor network; wherein the wireless sensor network includes a collection node, a router and a coordinator connected to a temperature sensor or a current sensor.

[0016] Furthermore, in step four, the estimation algorithm is run through the program stored in the remote centralized control center server, and the real-time collected cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data are brought into the trained group co-evolution fruit fly optimization algorithm-generalized regression neural network to output the estimated temperature value of the transmission line joint core; the estimated temperature value of the transmission line joint core is compared with the pre-set transmission line joint core temperature threshold. If the estimated temperature value is higher than the core temperature threshold, an alarm message is issued in the centralized control center, and the staff handles it in time or the power grid dispatching system intelligently adjusts the dispatching plan.

[0017] Furthermore, the grouped co-evolutionary fruit fly optimization algorithm-generalized regression neural network includes:

[0018] The input layer is used to pass the input samples to the pattern layer. The neurons in the input layer are cable skin temperature, cable joint sheath temperature, ambient temperature and cable current.

[0019] The pattern layer is used to calculate the value of the Gauss function of each sample in the test sample and the training sample. The number of neurons in the pattern layer is equal to the number of training samples n. Among them, the transfer function of the pattern layer is:

[0020]

[0021] In the formula, p i is the transfer function value of the i-th neuron in the pattern layer, σ is the smoothing factor value of the grouped co-evolutionary fruit fly optimization algorithm-generalized regression neural network, X i is the learning sample corresponding to the i-th neuron.

[0022] The summation layer is used to sum the outputs of the neurons in the pattern layer. The number of neurons is equal to the output sample dimension k plus 1.

[0023] Among them, the first neuron of the summation layer performs arithmetic summation on the outputs of all pattern layer neurons, and the transfer function is:

[0024]

[0025] In the formula, S D is the transfer function value of the first neuron in the summation layer.

[0026] The remaining K neurons in the summation layer perform weighted summation of the outputs of neurons in all pattern layers, and the connection weight between the i-th neuron in the pattern layer and the j-th neuron in the summation layer is the j-th element in the i-th output sample;

[0027]

[0028] The value of the neuron in the output layer is the weighted sum of the sum layer divided by the arithmetic sum;

[0029]

[0030] Furthermore, the training process of the grouped co-evolutionary fruit fly optimization algorithm-generalized regression neural network is as follows:

[0031] Select the first transmission line section, install temperature sensors at the transmission line joint core, cable skin, cable joint sheath and around the cable, and install current sensors on the cable; collect the core temperature, cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data at the cable joint of the first transmission line section, and select a period of experimental data as a training set;

[0032] Bring the training set into the grouped co-evolutionary fruit fly optimization algorithm-generalized regression neural network for training to obtain the trained neural network;

[0033] Select the second transmission line section, install temperature sensors at the transmission line joint core, cable skin, cable joint sheath and around the cable, and install current sensors on the cable;

[0034] Collect the wire core temperature, cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data at the cable joint of the second transmission line section, and select a short period of time to collect experimental data as a test set;

[0035] The cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data are brought into the trained neural network for calculation to obtain the estimated cable joint core temperature; the temperature is compared with the data of the measuring core temperature sensor installed at the joint of the second transmission line section, and the training ends if the error is less than 0.5%;

[0036] Otherwise, the training set sample length is expanded and training is continued until the test set experimental data is brought in to verify that the result meets the error requirement, and then the training ends.

[0037] Further, expanding the sample size of the training set includes:

[0038] (1) Extend the time period for sampling the training set samples. If the time for sampling the core temperature, cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data at the cable joint of the first transmission line section is 24 hours, then the sampling time is extended to 48 hours, or 72 hours...;

[0039] (2) Increase the sampling frequency of training set samples. If the first interception of the wire core temperature, cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data at the cable joint of the first transmission line section is 24 hours, and the sampling is once every 10 minutes, then the sampling frequency will be increased to once every 5 minutes, or once every 2 minutes...

[0040] Another object of the present invention is to provide a transmission line joint core temperature monitoring system using the transmission line joint core temperature estimation method, the transmission line joint core temperature monitoring system comprising:

[0041] Temperature sensor, used to collect temperature values ​​at multiple points outside the transmission line joint, including cable skin temperature, cable joint sheath temperature and ambient temperature;

[0042] A current sensor is used to collect the current value of the transmission line;

[0043] Each sensor is connected to a wireless sensor network node to form a wireless sensor network. The sensor data is transmitted to the coordinator wirelessly. The coordinator collects and fuses the data and sends it to the remote control center server. The server stores the trained grouped co-evolutionary fruit fly optimization algorithm-generalized regression neural network program and outputs the estimated value of the core temperature of the transmission line joint at the monitoring point.

[0044] The comparison component is used to compare the estimated value of the core temperature of the transmission line joint with a preset threshold value. If the estimated temperature value is higher than the core temperature threshold value, an alarm message is sent to the staff through the centralized control center, and the dispatch plan is adjusted according to the dispatch plan.

[0045] Another object of the present invention is to provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method for estimating the core temperature of a transmission line joint.

[0046] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to execute the steps of the method for estimating the core temperature of a transmission line joint.

[0047] Another object of the present invention is to provide an information data processing terminal, which is used to implement the transmission line joint core temperature monitoring system.

[0048] In combination with the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solutions to be protected by the present invention are as follows:

[0049] First, the present invention provides a method for estimating the core temperature of a transmission line joint and a monitoring system. The indirect measurement method is adopted to avoid the confusion of burying direct measurement sensors and the disadvantages of power outages required for maintenance, and has the advantages of simple operation, convenient deployment, and convenient maintenance. Compared with other indirect measurement methods, the transmission line joint core temperature monitoring system of the present invention uses a variety of sensors to measure the cable skin temperature, cable joint sheath temperature, ambient temperature, and cable current. It is easy to install, maintain, and have complete data. It uses wireless sensor networking for data transmission, avoiding on-site wiring and easy installation. The data is transmitted to the centralized control center through a coordinator, and is estimated through the grouped collaborative evolution fruit fly optimization algorithm-generalized regression neural network algorithm, which is faster and more accurate. Compared with other estimation algorithms, its accuracy is improved by more than 15%.

[0050] The present invention adopts temperature sensors and current sensors, and realizes the estimation and remote monitoring of the transmission line joint temperature based on the grouped co-evolutionary fruit fly optimization algorithm and the generalized regression neural network algorithm. The transmission line joint core temperature monitoring system of the present invention overcomes the main shortcomings of the existing indirect measurement method of the power cable joint core temperature, such as low accuracy and poor real-time performance, and also solves the problems of long calculation time and low accuracy of the existing estimation model.

[0051] Second, as auxiliary evidence of the inventiveness of the present invention, it is also reflected in the following important aspects:

[0052] (1) The expected benefits and commercial value of the technical solution of the present invention after transformation are as follows: the standardized product formed after the technical solution of the present invention is transformed can be implemented in all tunnel cables, and the market is huge, and the market is expected to exceed 5 billion yuan per year.

[0053] (2) The technical solution of the present invention fills the technical gap in the industry at home and abroad: The technical solution of the present invention mainly adopts wireless sensor networks to realize multi-point data collection. In domestic and foreign research and products, wireless sensor networks have not been used to measure complex tunnel environment parameters.

[0054] (3) The technical solution of the present invention solves a technical problem that people have been eager to solve but have never succeeded in solving: in tunnel cable monitoring systems, engineers have always hoped to have a more accurate and reliable measurement method to measure cable parameters such as temperature and current. The technical solution of the present invention embodies the advantages of high precision and high robustness.

[0055] Third, the method for estimating the core temperature of the transmission line joint of the present invention is to set multiple temperature sensors and current sensors outside the transmission line joint to collect the temperature values ​​and cable current values ​​of multiple points at the cable joint, and send these data to the remote control center through the wireless sensor network. The control center performs data processing and analysis based on the grouped co-evolution fruit fly optimization algorithm and the generalized regression neural network algorithm to achieve accurate estimation and remote monitoring of the transmission line joint temperature. This method effectively improves the accuracy and reliability of transmission line temperature monitoring.

[0056] In the specific workflow, first, the temperature sensor collects the external skin temperature, sheath temperature and ambient temperature of the transmission line joint in real time, while the current sensor monitors the current of the cable. These real-time data are transmitted to the remote control center through the wireless sensor network. The server of the control center runs the stored estimation algorithm and outputs the estimated temperature value of the transmission line joint core. By comparing the estimated temperature value with the preset temperature threshold, the control center can issue an alarm message when the temperature exceeds the safety threshold, prompting the staff to deal with it in time or intelligently control it by the power grid dispatching system.

[0057] By using the grouped co-evolutionary fruit fly optimization algorithm and the generalized regression neural network algorithm, the present invention can make full use of historical data and real-time data for model training and temperature estimation. The input layer accepts data such as cable skin temperature, cable joint sheath temperature, ambient temperature and cable current. After calculation by the pattern layer and the summation layer, the output layer provides an accurate temperature estimation value. During the training process, the accuracy and robustness of the model are ensured by gradually increasing the sample size of the training set and adjusting the sampling frequency. This algorithm combines the global search capability of the optimization algorithm and the nonlinear mapping capability of the neural network, which greatly improves the accuracy of temperature estimation.

[0058] Compared with the prior art, the present invention has achieved significant technical progress in many aspects. First, real-time data transmission and remote monitoring are achieved through wireless sensor networks, reducing the cost and risk of manual inspections. Secondly, the combination of the grouped collaborative evolution fruit fly optimization algorithm and the generalized regression neural network algorithm makes temperature estimation more accurate and efficient. Finally, the system can provide timely warnings and automatic regulation, improving the safety and stability of power grid operation. This method is not only suitable for temperature monitoring of transmission line joints, but can also be extended to other high-temperature environments. Remote monitoring and fault prediction fields have broad application prospects.

[0059] Fourth, the present invention introduces multiple temperature sensors and current sensors, and sets these sensors outside the transmission line joint to collect the temperature and current data of the transmission line joint in real time. Through the wireless sensor network, these data are transmitted to the remote control center. In the control center, the grouped co-evolution fruit fly optimization algorithm and the generalized regression neural network algorithm are used for data processing and analysis, and finally the accurate estimation and remote monitoring of the core temperature of the transmission line joint are realized. The introduction of these main parameters and the design of the data processing flow solve the problem of inaccurate and untimely temperature monitoring of the transmission line joint in the prior art.

[0060] In terms of specific algorithms, the grouped co-evolutionary fruit fly optimization algorithm can effectively process and optimize the data collected by the sensors, while the generalized regression neural network algorithm uses these optimized data to perform nonlinear mapping and estimation of temperature. This algorithm combination not only improves the efficiency of data processing, but also significantly improves the accuracy of temperature estimation. By introducing these advanced algorithms, the present invention overcomes the technical bottlenecks of limited data processing capabilities and low estimation accuracy in traditional methods, ensuring the reliability and accuracy of transmission line joint temperature monitoring.

[0061] In terms of mathematical model, the present invention constructs a neural network structure based on input layer, pattern layer, summation layer and output layer. In the input layer, the data of temperature sensor and current sensor are used as input variables; in the pattern layer, the intermediate output is generated by calculating the Gauss function value of the test sample and the training sample; the summation layer performs weighted summation on the output of the pattern layer; finally, the output layer provides an estimate of the core temperature. This mathematical model not only accurately simulates the complex relationship of temperature change, but also improves the accuracy and robustness of the model by continuously expanding the training set and adjusting the sampling frequency, thereby solving the problem that the traditional monitoring method cannot dynamically adapt to environmental changes.

[0062] The remarkable technical progress of the present invention is reflected in many aspects. First, real-time monitoring and data transmission are achieved through wireless sensor networks, which significantly reduces the cost and risk of manual inspections. Secondly, the combination of the grouped collaborative evolution fruit fly optimization algorithm and the generalized regression neural network algorithm greatly improves the accuracy and efficiency of temperature estimation. In addition, the system has automatic early warning and intelligent control functions, which can promptly issue an alarm and perform corresponding processing when the temperature is abnormal, ensuring the safety and stability of the power grid operation. In general, the present invention has achieved a technological leap from traditional manual inspections to intelligent remote monitoring in the field of transmission line joint temperature monitoring, and has broad application prospects and promotion value. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0064] Figure 1 is a flow chart of a method for estimating the core temperature of a transmission line joint provided by an embodiment of the present invention;

[0065] Figure 2 It is a principle diagram of a method for estimating the core temperature of a transmission line joint provided by an embodiment of the present invention;

[0066] Figure 3 It is a structural block diagram of a transmission line joint core temperature monitoring system provided by an embodiment of the present invention;

[0067] Figure 4 It is a schematic diagram of the GRNN neural network structure provided by an embodiment of the present invention;

[0068] Figure 5 It is a schematic diagram of the installation positions of various sensors at the joints of the power transmission lines provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0069] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0070] In view of the problems existing in the prior art, the present invention provides a method for estimating the wire core temperature of a transmission line joint and a monitoring system. The present invention is described in detail below in conjunction with the accompanying drawings.

[0071] like Figure 1 As shown, the method for estimating the core temperature of a transmission line joint provided by an embodiment of the present invention comprises the following steps:

[0072] S101, setting a plurality of temperature sensors and current sensors outside the transmission line joint;

[0073] S102, using temperature sensors and current sensors to collect temperature values ​​at multiple points outside the transmission line joint and current magnitude of the cable, and sending the data to a remote centralized control center;

[0074] S103, using the remote control center based on the grouped co-evolutionary fruit fly optimization algorithm and the generalized regression neural network algorithm to estimate and remotely monitor the temperature of the transmission line joints.

[0075] As a preferred embodiment, Figure 2 As shown, the method for estimating the core temperature of a transmission line joint provided by an embodiment of the present invention specifically includes the following steps:

[0076] 1. The temperature sensor is used to collect the temperature values ​​of multiple points outside the transmission line joint, specifically collecting real-time data such as the skin temperature of the cable, the sheath temperature of the cable joint, and the ambient temperature;

[0077] 2. Collect the current of the cable through the current sensor;

[0078] 3. Through the wireless sensor network, including the acquisition nodes, routers, and coordinators connected to the temperature sensor or current sensor, the collected cable skin temperature, cable joint sheath temperature, ambient temperature, and cable current data are sent to the remote control center;

[0079] 4. Run the estimation algorithm through the program stored in the centralized control center server, specifically, bring the real-time collected cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data into the trained grouped co-evolutionary fruit fly optimization algorithm-generalized regression neural network, and output the estimated temperature value of the transmission line joint core;

[0080] 5. Compare the estimated temperature value with the pre-set core temperature threshold of the transmission line joint. If the estimated temperature value is higher than the core temperature threshold, an alarm message will be issued at the control center for timely processing by the staff. The power grid dispatching system can also intelligently adjust the dispatching plan to reduce the load of the alarm line to eliminate safety hazards.

[0081] like Figure 3 As shown, the neural network provided by the embodiment of the present invention includes:

[0082] (1) Input layer

[0083] The input layer passes the input samples to the pattern layer. The neurons in the input layer are the cable skin temperature, cable joint sheath temperature, ambient temperature and cable current.

[0084] (2) Model layer

[0085] The pattern layer calculates the value of the Gauss function of each sample in the test sample and the training sample. The number of neurons in the pattern layer is equal to the number of training samples n. The transfer function of the pattern layer is:

[0086]

[0087] In the formula, p i represents the transfer function value of the i-th neuron in the pattern layer, σ represents the smoothing factor value (Spread) of the grouped co-evolutionary fruit fly optimization algorithm-generalized regression neural network, X i Represents the learning sample corresponding to the i-th neuron.

[0088] (3) Sum layer

[0089] The summation layer sums the outputs of the neurons in the pattern layer, and the number of neurons is equal to the output sample dimension k plus 1.

[0090] In the first part, the first neuron in the summation layer performs arithmetic summation on the outputs of all pattern layer neurons, and the transfer function is:

[0091]

[0092] In the formula, S D is the transfer function value of the first neuron in the summation layer.

[0093] In the second part, the remaining K neurons in the summation layer perform weighted summation of the outputs of neurons in all pattern layers, and the connection weight between the i-th neuron in the pattern layer and the j-th neuron in the summation layer is the j-th element in the i-th output sample.

[0094]

[0095] (4) Output layer

[0096] The value of the output layer neuron is the weighted sum of the sum layer divided by the arithmetic sum, that is:

[0097]

[0098] The training process of the grouped collaborative evolution fruit fly optimization algorithm-generalized regression neural network provided by the embodiment of the present invention is as follows:

[0099] Select the first transmission line section, install temperature sensors at the transmission line joint core, cable skin, cable joint sheath, and around the cable, and install current sensors on the cable; collect the core temperature, cable skin temperature, cable joint sheath temperature, ambient temperature, and cable current data at the cable joint of the first transmission line section, and select a period of experimental data as a training set;

[0100] Bring the training set into the grouped co-evolutionary fruit fly optimization algorithm-generalized regression neural network for training to obtain the trained neural network;

[0101] Select the second transmission line section, install temperature sensors at the transmission line joint core, cable skin, cable joint sheath, and around the cable, and install current sensors on the cable;

[0102] Collect the wire core temperature, cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data at the cable joint of the second transmission line section, and select a short period of time to collect experimental data as a test set;

[0103] The cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data are brought into the trained neural network for calculation to obtain the estimated cable joint core temperature; the data is compared with the measurement core temperature sensor installed at the joint of the second transmission line section, and the training ends when the error is less than 0.5%;

[0104] Otherwise, the training set sample length is expanded and training is continued until the test set experimental data is brought in to verify that the result meets the error requirement, and then the training ends.

[0105] The method for expanding the sample size of the training set provided by the embodiment of the present invention includes:

[0106] Method 1: Extend the time period for intercepting training set samples. For example, the time for intercepting the core temperature, cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data at the cable joint of the first transmission line section is 24 hours. After the time is extended, the interception time is 48 hours, or 72 hours...;

[0107] Method 2: Increase the sampling frequency of training set samples. For example, the first time the core temperature, cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data of the cable joint of the first transmission line section are intercepted, the sampling time is 24 hours, and the sampling is once every 10 minutes. After increasing the sampling frequency, the sampling frequency will be once every 5 minutes, or once every 2 minutes...

[0108] like Figure 4 As shown, the transmission line joint core temperature monitoring system provided by the embodiment of the present invention includes:

[0109] Temperature sensor 1, used to collect temperature values ​​at multiple points outside the transmission line joint, including cable skin temperature, cable joint sheath temperature, and ambient temperature;

[0110] Current sensor 2, used to collect the current value of the transmission line;

[0111] Each sensor is connected to a wireless sensor network node to form a wireless sensor network. The sensor data is transmitted to the coordinator wirelessly. The coordinator collects and fuses the data and sends it to the remote control center server. The server stores the trained grouped co-evolutionary fruit fly optimization algorithm-generalized regression neural network program and outputs the estimated value of the core temperature of the transmission line joint at the monitoring point.

[0112] The comparison component is used to compare the estimated temperature value with the pre-set transmission line joint core temperature threshold. If the estimated temperature value is higher than the core temperature threshold, an alarm message is sent to the staff through the centralized control center, and the dispatch plan is adjusted according to the dispatch plan to reduce the current load of the line.

[0113] The technology of the invention is mainly used for measuring the temperature of tunnel cable joints.

[0114] The embodiment of the present invention selects the first transmission line section and the second transmission line section, buries the temperature sensor Pt100 at the cable joint, sticks and fixes the temperature sensor DS18B20 on the cable skin and the cable joint sheath, and arbitrarily deploys the temperature sensor DS18B20 within 2 meters from the transmission line joint to measure the wire core temperature, cable skin temperature, cable joint sheath temperature, and ambient temperature at the cable joint; installs the AKH-0.66K open-type current transformer on the cable as a current sensor;

[0115] All sensors are connected to wireless sensor network nodes to form a wireless sensor network. The wireless sensor network nodes are composed of chips such as CC2530, CC2531, CC2533, or CC2538 and power supply circuits.

[0116] All sensor nodes communicate wirelessly with the coordinator, which is composed of CC2530, CC2531, CC2533, CC2538 and other chips and power supply circuits;

[0117] The coordinator is connected to the 3G module, or the 4G module, or the 5G module, and communicates with the centralized control center server;

[0118] The centralized control center collects and stores in real time the raw data collected by the sensors deployed in the first transmission line section and the second transmission line section, the data of the first transmission line section is used as a training set, and the data of the second transmission line section is used as a test set;

[0119] The data of the first transmission line section is used to train the grouped co-evolutionary fruit fly optimization algorithm-generalized regression neural network, and the trained network is tested with the data of the second transmission line section until the test error is less than 0.5%.

[0120] The embodiment of the present invention determines the transmission line joints that need to be monitored. In actual engineering, if there are multiple cable joints on a trunk line, only one of the joints can be selected as the monitoring object. However, for joints on different phase lines on the same trunk line, each phase line joint must be monitored.

[0121] At the transmission line joint to be monitored, a fixed temperature sensor DS18B20 is attached to the cable skin and cable joint sheath respectively. The temperature sensor DS18B20 is deployed at any position within 2 meters from the transmission line joint to measure the cable skin temperature, cable joint sheath temperature and ambient temperature at the cable joint. An AKH-0.66K open-type current transformer is installed on the cable as a current sensor.

[0122] All temperature sensors and current sensors are connected to wireless sensor network nodes to form a wireless sensor network. The wireless sensor network nodes are composed of chips such as CC2530, CC2531, CC2533, or CC2538 and power supply circuits.

[0123] All wireless sensor network nodes communicate wirelessly with the coordinator, which is composed of chips such as CC2530, CC2531, CC2533, or CC2538 and power supply circuits;

[0124] The coordinator is connected to the 3G module, or the 4G module, or the 5G module, and communicates with the centralized control center server;

[0125] The centralized control center collects and stores the raw data collected by sensors deployed in the transmission line section to be tested in real time, and feeds the above data into the trained grouped co-evolutionary fruit fly optimization algorithm-generalized regression neural network;

[0126] The algorithm program based on the grouped co-evolutionary fruit fly optimization algorithm-generalized regression neural network stored in the centralized control center server runs and estimates the wire core temperature at the joint of the transmission line to be tested in real time;

[0127] The estimated core temperature at the transmission line joint to be tested is compared with the threshold temperature at that point. If it is higher than the threshold temperature, the centralized control center server will alert the staff and initiate the emergency plan to adjust the grid dispatch plan;

[0128] The centralized control center server stores the real-time estimated data of the joint temperature of each transmission line section within the monitoring range and allows historical query.

[0129] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented using a dedicated logic unit; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. A person of ordinary skill in the art will understand that the above-mentioned devices and methods can be implemented using computer executable instructions and / or contained in a processor control code, for example, such codes are provided on a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The device and its modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0130] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principle of the present invention should be covered by the protection scope of the present invention.

Claims

1. A method for estimating the core temperature of a transmission line joint. It is characterized in that The method for estimating the core temperature of a transmission line joint includes: setting a plurality of temperature sensors and current sensors outside the transmission line joint, using the temperature sensors and current sensors to respectively collect the temperature values ​​of multiple points outside the transmission line joint and the current size of the cable and send the data to a centralized control center; the centralized control center realizes the estimation and remote monitoring of the transmission line joint temperature based on a grouped co-evolutionary fruit fly optimization algorithm and a generalized regression neural network algorithm.

2. The method for estimating the core temperature of a transmission line joint according to claim 1, It is characterized in that The method for estimating the core temperature of the transmission line joint includes the following steps: Step 1: collecting temperature values ​​of multiple points outside the transmission line joint through a temperature sensor; Step 2: collecting the current of the cable through a current sensor; Step 3: Send the collected data to the remote control center through the wireless sensor network; Step 4: Use the program stored in the centralized control center server to run the estimation algorithm to output the estimated temperature value of the transmission line joint core, and compare it with the pre-set transmission line joint core temperature threshold.

3. The method for estimating the core temperature of a transmission line joint according to claim 2, It is characterized in that In step 1, real-time data of the cable skin temperature, the cable connector sheath temperature, and the ambient temperature are collected through temperature sensors.

4. The method for estimating the core temperature of a transmission line joint according to claim 2, It is characterized in that In step three, the collected cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data are sent to a remote control center via a wireless sensor network; wherein the wireless sensor network includes a collection node connected to a temperature sensor or a current sensor, a router and a coordinator.

5. The method for estimating the core temperature of a transmission line joint according to claim 2, It is characterized in that In step 4, the estimation algorithm is run through the program stored in the remote centralized control center server, and the real-time collected cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data are brought into the trained group co-evolution fruit fly optimization algorithm-generalized regression neural network to output the estimated temperature value of the transmission line joint core; the estimated temperature value of the transmission line joint core is compared with the pre-set transmission line joint core temperature threshold. If the estimated temperature value is higher than the core temperature threshold, an alarm message is issued in the centralized control center, and the staff handles it in time or the power grid dispatching system intelligently adjusts the dispatching plan.

6. The method for estimating the core temperature of a transmission line joint according to claim 5, It is characterized in that Grouped Co-evolutionary Fruit Fly Optimization Algorithm-Generalized Regression Neural Network includes: The input layer is used to pass the input samples to the pattern layer. The neurons in the input layer are the cable skin temperature, cable joint sheath temperature, ambient temperature and cable current. The pattern layer is used to calculate the value of the Gauss function of each sample in the test sample and the training sample. The number of neurons in the pattern layer is equal to the number of training samples n. Among them, the transfer function of the pattern layer is: In the formula, p i is the transfer function value of the i-th neuron in the pattern layer, σ is the smoothing factor value of the grouped co-evolutionary fruit fly optimization algorithm-generalized regression neural network, X i is the learning sample corresponding to the i-th neuron; The summation layer is used to sum the outputs of the neurons in the pattern layer. The number of neurons is equal to the output sample dimension k plus 1. Among them, the first neuron of the summation layer performs arithmetic summation on the outputs of all pattern layer neurons, and the transfer function is: In the formula, S D is the transfer function value of the first neuron in the summation layer; The remaining K neurons in the summation layer perform weighted summation of the outputs of neurons in all pattern layers, and the connection weight between the i-th neuron in the pattern layer and the j-th neuron in the summation layer is the j-th element in the i-th output sample; The value of the neuron in the output layer is the weighted sum of the sum layer divided by the arithmetic sum; Among them, the training process of the grouped co-evolutionary fruit fly optimization algorithm-generalized regression neural network is as follows: Select the first transmission line section, install temperature sensors at the transmission line joint core, cable skin, cable joint sheath and around the cable, and install current sensors on the cable; collect the core temperature, cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data at the cable joint of the first transmission line section, and select a period of experimental data as a training set; Bring the training set into the grouped co-evolutionary fruit fly optimization algorithm-generalized regression neural network for training to obtain the trained neural network; Select the second transmission line section, install temperature sensors at the transmission line joint core, cable skin, cable joint sheath and around the cable, and install current sensors on the cable; Collect the wire core temperature, cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data at the cable joint of the second transmission line section, and select a short period of time to collect experimental data as a test set; The cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data are brought into the trained neural network for calculation to obtain the estimated cable joint core temperature; the temperature is compared with the data of the measuring core temperature sensor installed at the joint of the second transmission line section, and the training ends if the error is less than 0.5%; Otherwise, the training set sample length is expanded to continue training until the test set experimental data is brought in to verify that the result meets the error requirement, and then the training ends; Among them, expanding the sample size of the training set includes: (1) Extend the time period for sampling the training set samples. If the first sampling time for sampling the core temperature, cable skin temperature, cable joint sheath temperature, ambient temperature, and cable current data at the cable joint of the first transmission line section is 24 hours, then the sampling time is extended to 48 hours, or 72 hours. (2) Increase the sampling frequency of the training set samples. If the time for first intercepting the wire core temperature, cable skin temperature, cable joint sheath temperature, ambient temperature and cable current data at the cable joint of the first transmission line section is 24 hours, and the data is sampled every 10 minutes, then the sampling frequency will be increased to once every 5 minutes, or once every 2 minutes.

7. A transmission line joint core temperature monitoring system using the transmission line joint core temperature estimation method according to any one of claims 1 to 6, It is characterized in that The transmission line joint core temperature monitoring system includes: Temperature sensor, used to collect temperature values ​​at multiple points outside the transmission line joint, including cable skin temperature, cable joint sheath temperature and ambient temperature; A current sensor is used to collect the current value of the transmission line; Each sensor is connected to a wireless sensor network node to form a wireless sensor network. The sensor data is transmitted to the coordinator wirelessly. The coordinator collects and fuses the data and sends it to the remote control center server. The server stores the trained grouped co-evolutionary fruit fly optimization algorithm-generalized regression neural network program and outputs the estimated value of the core temperature of the transmission line joint at the monitoring point. The comparison component is used to compare the estimated value of the core temperature of the transmission line joint with a preset threshold value. If the estimated temperature value is higher than the core temperature threshold value, an alarm message is sent to the staff through the centralized control center, and the dispatch plan is adjusted according to the dispatch plan.

8. A computer device, It is characterized in that The computer device includes a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, the processor executes the steps of the method for estimating the core temperature of a transmission line joint as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to execute the steps of the method for estimating the core temperature of a transmission line joint as claimed in any one of claims 1 to 6.

10. An information data processing terminal, It is characterized in that The information data processing terminal is used to implement the transmission line joint core temperature monitoring system as described in claim 7.

Images