Mutual inductor data testing method based on artificial intelligence
Through the transformer data testing method based on artificial intelligence, the problem of traditional testing methods taking time and inability to monitor in real time is solved, efficient and accurate transformer data testing and prediction is achieved, and the stability and safety of the power system are improved.
Patent Information
- Application Number
- CN202410932888.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-12
- Publication Date
- 2024-11-29
AI Technical Summary
Traditional transformer data testing methods rely on manual inspection and offline testing, resulting in large workload, long time-consuming and inability to monitor in real time, and cannot meet the high requirements of power systems for testing efficiency, accuracy and anti-interference capabilities.
Using transformer data testing method based on artificial intelligence, send test instructions through artificial intelligence modules, monitor real-time data, generate active test values, compare calibration and active values, detect data differences, confirm faults and issue alarms, establish prediction models, and predict State change trends, using deep learning to improve testing efficiency and accuracy.
Unmanned automation and real-time online transformer data testing are realized, which reduces manual workload, improves testing efficiency and accuracy, predicts changes in insulation state, avoids equipment failures and safety accidents, and improves the stability and reliability of the power system.
Smart Images

Figure CN119044871A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of mutual inductor, and in particular to a mutual inductor data testing method based on artificial intelligence. Background Art
[0002] The main function of the transformer is to convert high voltage or large current into standard low voltage or standard small current in proportion. The standard low voltage is 100V, and the standard small current is 5A or 10A, both of which refer to the rated value, so as to realize the standardization and miniaturization of measuring instruments, protection equipment and automatic control equipment. At the same time, the transformer can also be used to isolate the high voltage system to ensure the safety of people and equipment. The transformer is mainly divided into two types, voltage transformer and current transformer. The primary winding of the voltage transformer is connected in parallel with the measured circuit, while the primary winding of the current transformer needs to be connected in series with the measured circuit.
[0003] The mutual inductor is a common electrical equipment, mainly used for electric energy measurement and protection of power systems such as substations and power plants. Its basic principle is to convert the electric energy of high-voltage lines into low-voltage signal output through electromagnetic induction, thereby realizing electric energy measurement and control. The mutual inductor is mainly composed of iron core, winding, insulating material, etc., among which the iron core plays the role of magnetic circuit conduction, and the winding is responsible for the conversion of electromagnetic induction. Under normal circumstances, the input end of the mutual inductor is connected to the high-voltage circuit, and the output end is connected to the corresponding measurement and protection device.
[0004] The traditional data testing method of transformers mainly relies on manual inspection and offline testing. Although this method has a certain degree of accuracy, it has problems such as large workload, long time consumption, and inability to monitor in real time. However, with the rapid development of the power system, there are more and more modification and expansion projects, and the requirements for power equipment parameter test results and data management will become higher and higher. Under this trend, higher requirements are also placed on the test efficiency, test accuracy and anti-interference ability of the test equipment. Therefore, the above-mentioned manual inspection and offline testing not only require a large number of testers, but also require offline testing to affect the normal operation of the power system, so it cannot meet the data testing of a large number of transformers. Summary of the invention
[0005] The purpose of the present invention is to provide a transformer data testing method based on artificial intelligence to solve the problems raised in the above background technology.
[0006] To achieve the above object, the present invention provides the following technical solution: a transformer data testing method based on artificial intelligence, comprising the following steps:
[0007] S1. Send test instructions to the transformer according to the preset artificial intelligence module, and the test instructions detect the key operating data of the transformer in sequence;
[0008] S2. The artificial intelligence module calls the calibration value of the transformer operation data to generate a calibration test value;
[0009] S3. The artificial intelligence module monitors the real-time operation data of the transformer and generates activity test values;
[0010] S4. Compare the calibration test value and the activity test value to obtain the data of the transformer operation and generate the data difference result;
[0011] S5. Based on the data difference result as a sample, the artificial intelligence module confirms the fault at the corresponding data location according to the program analysis and issues a fault alarm;
[0012] S6. The artificial intelligence module calls the historical test data of the transformer in the same working section, analyzes the historical test data, and extracts data patterns from it;
[0013] S7. The artificial intelligence module uses the calibration test values, active test values and historical test data to establish a prediction model to predict the changing trend of the transformer status.
[0014] In a further embodiment, the calculation formula of the prediction model in S7 is as follows:
[0015] Y=f(WX+b)
[0016] Among them, Y is the output variable, X is the input variable, W and b are the weight and bias of the neural network, and f is the activation function. The deep learning prediction of artificial intelligence can effectively improve the prediction of the test trend of the transformer data test for a period of time in the future, and can provide predictive suggestions for the transformer data test to ensure the stability and efficiency of the transformer data test.
[0017] In a further embodiment, the formula for the data difference in S4 is as follows:
[0018]
[0019] Among them, α is the data difference, F is the active test value at the current moment (1, 2, 3, ..., n is the different active test values at the current moment), β is the calibration test value, and n is the number of data. By calculating the difference, abnormal data monitoring of the transformer data test is completed to ensure the efficiency and stability of the transformer data test.
[0020] In a further embodiment, the active test values establish data storage, and the stored data forms historical test data. Based on the reference mapping of the historical test data, the artificial intelligence module obtains the corresponding historical test data, establishes a prediction model, and predicts the future operating trend of the transformer. Through deep learning of the transformer data test, the data test status in the future period is predicted, which can effectively and timely provide staff with more effective data testing suggestions.
[0021] In a further embodiment, a transformer data abnormality fault is detected in S5, and the data difference is used to confirm that the active test value exceeds the range of the corresponding calibration test value, and the data is confirmed to be abnormal, and a fault alarm message is issued.
[0022] In a further embodiment, the fault alarm in S5 includes a sound alarm, a fault light alarm and a fault information feedback alarm.
[0023] In a further embodiment, after the fault alarm in S5, the artificial intelligence module generates corresponding processing suggestions corresponding to the fault alarm.
[0024] In a further embodiment, the test indicators included in the test instruction include current, voltage, resistance, temperature, vibration and test speed of the transformer operation.
[0025] An artificial intelligence-based mutual inductor, comprising an artificial intelligence module, a test sensor, a fault alarm lamp, a fault alarm buzzer, a wireless communication module and a built-in battery;
[0026] The artificial intelligence module is used to detect and analyze various status data generated during the operation of the transformer, confirm faults based on data detection and analysis, and generate data test suggestions for future operation trends;
[0027] The test sensor is used to complete the test instructions issued by the artificial intelligence module and monitor various status data of the transformer in real time;
[0028] The built-in battery is used to independently power the mutual inductor, and the built-in battery is a rechargeable lithium battery.
[0029] In a further embodiment, the fault alarm light and the fault alarm buzzer are used to emit a fault alarm light and an alarm sound when the mutual inductor detects a fault through the artificial intelligence module;
[0030] The wireless communication module is used by the artificial intelligence module to transmit the detected data and fault alarms to the staff's smart devices through wireless transmission.
[0031] Compared with the prior art, the present invention has the following beneficial effects:
[0032] 1. The present invention integrates artificial intelligence technology into the data test of power transformers, utilizes the powerful computing power of artificial intelligence, replaces manual inspection and offline detection, and can realize unmanned automation and real-time online transformer data testing, thereby meeting the synchronous data test of a large number of transformers, improving the test efficiency and reducing the manual workload;
[0033] 2. In the present invention, artificial intelligence can monitor and analyze the operating data of the transformer in real time, thereby realizing real-time evaluation of the transformer status. It can use machine learning algorithms to monitor the current, temperature, vibration and other parameters of the voltage transformer, and detect and warn abnormal data by establishing a data model. This method can greatly improve the monitoring accuracy of the insulation status and reduce the workload and time cost of manual inspections.
[0034] 3. The present invention uses the deep learning ability of artificial intelligence to retrieve the historical status data of the transformer and the current detection data for comparative analysis. By analyzing the historical data of the transformer, the rules and patterns are extracted from them to predict its future insulation state. By establishing a prediction model, the change trend of the insulation state of the electrical watermark-free transformer can be predicted in advance, and corresponding maintenance measures can be taken in time to avoid equipment failures and safety accidents caused by the deterioration of the insulation state.
[0035] 4. The present invention utilizes artificial intelligence technology to realize intelligent control and management of transformers. By connecting the controller and the automation system, automatic control and adjustment of the transformers can be realized to improve the stability and reliability of the power system. At the same time, based on big data and machine learning algorithms, the power system can be optimized and optimized to improve the comprehensive benefits of the power grid and enhance the accuracy and efficiency of transformer data testing. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] Figure 1 It is a schematic diagram of the process framework of the transformer data testing method of the present invention. DETAILED DESCRIPTION
[0037] The following will be described clearly and completely in conjunction with the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0038] Embodiment 1
[0039] See also Figure 1 This embodiment provides a transformer data testing method based on artificial intelligence, a transformer data testing method based on artificial intelligence, comprising the following steps:
[0040] S1. Send test instructions to the transformer according to the preset artificial intelligence module. The test instructions detect the key operating data of the transformer in sequence. The test instructions are sent to the test sensor. The test sensor receives the test instruction signal and starts to intercept the test data within a period of time and transmit it to the artificial intelligence module. Then the artificial intelligence module can analyze and judge according to the transmitted data, and then complete the transformer data test. The process does not require manual intervention and does not require shutdown detection, which can achieve more efficient and convenient data testing.
[0041] S2. The artificial intelligence module calls the calibration value of the transformer operation data to generate a calibration test value. The calibration test value is a range of data test specification values with positive and negative differences, which is the difference range allowed for real-time data in transformer data testing;
[0042] S3. The artificial intelligence module monitors the real-time operation data of the transformer and generates an activity test value. The activity test value refers to the real-time phased data detected by the test sensor after the artificial intelligence module issues a test instruction, such as one-minute fluctuation data. This data is a real-time activity test value. The difference between the test value and the calibration test value is calculated to confirm whether there is any abnormality in the data of the transformer data test;
[0043] S4. Compare the calibration test value and the activity test value to obtain the data of the transformer operation, generate the data difference result, and use the data difference result as the judgment indicator of the transformer data test. The artificial intelligence module can timely analyze and judge whether the transformer data test is abnormal based on the data difference, and then confirm the abnormal fault and complete the feedback in time;
[0044] S5. Based on the data difference result as a sample, the artificial intelligence module confirms the fault at the corresponding data location according to the program analysis and issues a fault alarm. The abnormal data location is confirmed and located through the transformer data test, so that the fault location and fault type can be confirmed in time. The artificial intelligence module provides timely feedback on the fault, thereby ensuring the subsequent manual timely inspection and maintenance of the power transformer and power system, and ensuring the safety of use;
[0045] S6. The artificial intelligence module calls the historical test data of the same working section of the transformer, analyzes the historical test data, extracts data rules from it, and calls the historical test data through deep learning of artificial intelligence. It can effectively confirm the rules and trends of transformer data testing, thereby improving the predictability of transformer data testing, and can provide staff with optimization of future transformer data testing, reduce manual workload, and improve the safety and accuracy of transformer data testing;
[0046] S7. The artificial intelligence module uses calibration test values, active test values and historical test data to establish a prediction model to predict the changing trend of the transformer status. The use of artificial intelligence technology can realize the intelligent processing and analysis of transformer data. Through machine learning algorithms, the transformer data is analyzed and modeled, abnormal values and trend changes are found, abnormal events are identified, data prediction and decision-making are realized, and the transformer data testing method can be better optimized, reducing manual workload, while improving the accuracy and efficiency of data testing.
[0047] Embodiment 2
[0048] See also Figure 1 , further improvements are made on the basis of the first embodiment:
[0049] The calculation formula of the prediction model in S7 is as follows:
[0050] Y=f(WX+b)
[0051] Among them, Y is the output variable, X is the input variable, W and b are the weight and bias of the neural network, and f is the activation function. This calculation formula uses the neural network technology of the artificial intelligence module to adjust the values of weight and bias by training the neural network, so as to predict the future operation trend of the transformer data test.
[0052] The formula for data difference in S4 is as follows:
[0053]
[0054] Among them, α is the data difference, F is the active test value at the current moment (1, 2, 3, ..., n is the different active test values at the current moment), β is the calibration test value, and n is the number of data. This formula can help us understand the degree of discreteness of the data. If the standard deviation is small, it means that the data is relatively concentrated; if the standard deviation is large, it means that the data is relatively scattered. Then, the data difference can be used to timely confirm whether the data after the data test is within the calibration data range. Based on big data and machine learning algorithms, the power system can be optimized and optimized to improve the comprehensive benefits of the power grid and improve the accuracy and efficiency of transformer data testing.
[0055] The active test values establish data storage, and the stored data forms historical test data. Based on the reference mapping of the historical test data, the artificial intelligence module obtains the corresponding historical test data, establishes a prediction model, and predicts the future operating trend of the transformer. By collecting and storing data, more reference data is accumulated for the artificial intelligence module, so that the artificial intelligence module can have sufficient learning samples in the deep learning process, thereby improving the intelligence of the artificial intelligence module.
[0056] In S5, an abnormal transformer data fault is detected, and the data difference is used to confirm that the active test value exceeds the range of the corresponding calibrated test value. The data is confirmed to be abnormal and a fault alarm is issued. The fault alarm in S5 includes a sound alarm, a fault light alarm and a fault information feedback alarm. After the fault alarm in S5, the artificial intelligence module generates corresponding processing suggestions for the corresponding fault alarm. Artificial intelligence technology can diagnose and locate the fault of the transformer. By analyzing and comparing the voltage transformer fault data, it can accurately determine the fault type and location, and provide corresponding processing suggestions. This method can greatly improve the efficiency and accuracy of fault handling, and avoid the uncertainty caused by subjective judgment and experience dependence in traditional manual diagnosis.
[0057] The test instructions contain test indicators including the current, voltage, resistance, temperature, vibration and test speed of the transformer operation. It can monitor various data during the operation of the transformer in real time to ensure the stability and safety of the transformer operation process.
[0058] Embodiment 3
[0059] See also Figure 1 , an artificial intelligence-based mutual inductor, comprising an artificial intelligence module, a test sensor, a fault alarm lamp, a fault alarm buzzer, a wireless communication module and a built-in battery;
[0060] The artificial intelligence module is used to detect and analyze various status data generated during the operation of the transformer, confirm faults based on data detection and analysis, and generate data test suggestions for future operation trends. The application of artificial intelligence in transformer data testing is of great significance. It can not only realize real-time monitoring and evaluation of voltage transformers, but also provide early warning of insulation state changes of equipment through analysis and prediction of historical data. At the same time, it can also realize fault diagnosis and location, and provide accurate suggestions for fault handling. Therefore, strengthening the application research of artificial intelligence technology in power systems has an important role in improving the operating reliability and safety of power equipment.
[0061] The test sensor is used to complete the test instructions issued by the artificial intelligence module and monitor the status data of the transformer in real time. The transformer performs data testing through the test sensor to achieve real-time data testing and improve the convenience of testing;
[0062] The built-in battery is used to independently power the transformer, and the built-in battery is a rechargeable lithium battery. It uses built-in battery technology to provide internal power, and with high-precision hardware and corresponding artificial intelligence modules, it forms a device that can complete transformer testing and subsequent measurement tests in a light, efficient, accurate and reliable manner. It will reduce the types and quantity of equipment configurations in the team, and is no longer restricted by power points, thereby improving the convenience of using transformers.
[0063] The fault alarm light and fault alarm buzzer are used to emit fault alarm lights and alarm sounds when the mutual inductor detects a fault through the artificial intelligence module. The wireless communication module is used for the artificial intelligence module to transmit the detected data and fault alarm to the staff's smart device through wireless transmission. By using the on-site sound and light alarm and the wireless communication module to transmit the fault information to the staff's mobile or fixed smart device, faults occurring in the mutual inductor data test can be confirmed in a timely manner, and maintenance suggestions can be given in a timely manner to ensure the safety of the mutual inductor.
[0064] During the transformer data test, the transformer operates normally. At this time, the artificial intelligence module issues a test command. At this time, the test sensor in the transformer receives the test command and starts to test the transformer data. Then, the detected data is transmitted to the artificial intelligence module. While issuing the test command, the artificial intelligence module will call the calibration range of the transformer test data. After the detected data is transmitted to the artificial intelligence module, the detected data and the calibration data are compared and analyzed. The difference in data is determined by calculation, and then the difference is confirmed whether it exceeds the calibration data range. When the detected data is within the calibration data range, it means that the transformer is safe and stable. When the data difference exceeds the calibration data range, it is confirmed that there is data abnormality, and then the above process is repeated again. The test sensor at the corresponding position of the abnormal data is tested again to obtain test data, and then the test difference is calculated again to confirm whether the test difference exceeds the calibration data range. If it still exceeds the calibration data range, the artificial intelligence module generates a fault alarm. Through the fault alarm light, fault alarm buzzer and wireless communication module, the alarm information is sent to the staff in the form of light, sound and information to prompt timely maintenance. In this process, the artificial intelligence module generates maintenance suggestions for the corresponding position fault based on past experience;
[0065] After the transformer data is tested, the artificial intelligence module will call a large amount of historical data on the transformer's previous operating status, use the deep learning ability of the artificial intelligence module to combine the historical data with the current real-time data, and then establish a prediction model to generate a prediction of the status data of the subsequent transformer operation, so as to facilitate the staff to make early judgments on the transformer test data in the future, and then achieve early maintenance and control, further improving the safety of the transformer in the power monitoring process;
[0066] By using artificial intelligence technology, intelligent control and management of transformers can be achieved. By connecting controllers and automation systems, automatic control and adjustment of transformers can be achieved, thereby improving the stability and reliability of the power system.
[0067] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A transformer data testing method based on artificial intelligence, characterized in that: The following steps are involved: S1. Send test instructions to the transformer according to the preset artificial intelligence module, and the test instructions detect the key operating data of the transformer in sequence; S2. The artificial intelligence module calls the calibration value of the transformer operation data to generate a calibration test value; S3. The artificial intelligence module monitors the real-time operation data of the transformer and generates activity test values; S4. Compare the calibration test value and the activity test value to obtain the data of the transformer operation and generate the data difference result; S5. Based on the data difference result as a sample, the artificial intelligence module confirms the fault at the corresponding data location according to the program analysis and issues a fault alarm; S6. The artificial intelligence module calls the historical test data of the transformer in the same working section, analyzes the historical test data, and extracts data patterns from it; S7. The artificial intelligence module uses the calibration test values, active test values and historical test data to establish a prediction model to predict the changing trend of the transformer status.
2. The method for testing transformer data based on artificial intelligence according to claim 1, characterized in that: The calculation formula of the prediction model in S7 is as follows: Y=f(WX+b) Among them, Y is the output variable, X is the input variable, W and b are the weights and biases of the neural network, and f is the activation function.
3. The method for testing transformer data based on artificial intelligence according to claim 1, characterized in that: The formula for the data difference in S4 is as follows: Among them, α is the data difference, F is the active test value, β is the calibration test value, and n is the number of data.
4. The method for testing transformer data based on artificial intelligence according to claim 1, characterized in that: The active test values establish data storage, the stored data forms historical test data, based on the reference mapping of the historical test data, the artificial intelligence module obtains the corresponding historical test data, establishes a prediction model, and predicts the future operation trend of the transformer.
5. The method for testing transformer data based on artificial intelligence according to claim 1, characterized in that: In the S5, an abnormal fault of the transformer data is detected, and the data difference is used to confirm that the active test value exceeds the range of the corresponding calibration test value, and the data is confirmed to be abnormal, and a fault alarm information is issued.
6. The method for testing transformer data based on artificial intelligence according to claim 1, characterized in that: The fault alarm in S5 includes a sound alarm, a fault light alarm and a fault information feedback alarm.
7. The method for testing transformer data based on artificial intelligence according to claim 1, characterized in that: After the fault alarm in S5, the artificial intelligence module generates corresponding processing suggestions corresponding to the fault alarm.
8. The method for testing transformer data based on artificial intelligence according to claim 1, characterized in that: The test indicators included in the test instruction include the current, voltage, resistance, temperature, vibration and test speed of the transformer.
9. A mutual inductor based on artificial intelligence, applied to the mutual inductor data testing method according to any one of claims 1 to 8, characterized in that: It includes an artificial intelligence module, a test sensor, a fault warning light, a fault warning buzzer, a wireless communication module and a built-in battery; The artificial intelligence module is used to detect and analyze various status data generated during the operation of the transformer, confirm faults based on data detection and analysis, and generate data test suggestions for future operation trends; The test sensor is used to complete the test instructions issued by the artificial intelligence module and monitor various status data of the transformer in real time; The built-in battery is used to independently power the mutual inductor, and the built-in battery is a rechargeable lithium battery.
10. The mutual inductor based on artificial intelligence according to claim 9, characterized in that: The fault alarm light and the fault alarm buzzer are used to emit a fault alarm light and an alarm sound when the mutual inductor detects a fault through the artificial intelligence module; The wireless communication module is used by the artificial intelligence module to transmit the detected data and fault alarms to the staff's smart devices through wireless transmission.
Citation Information
Cited By
Mutual inductor online data testing method based on artificial intelligence
CN121959063A
