Full-link intelligent diagnosis method for power key business

Abstract

The invention discloses a full-link intelligent diagnosis method for power key business, and relates to the technical field of power business intelligent diagnosis, comprising the following steps: acquiring power business diagnosis data including power transmission line environment data and power generation data through acquisition equipment, preprocessing the acquired power business diagnosis data, and storing the preprocessed power business diagnosis data in a database; obtaining a power generation data weight, obtaining an influence index of the power generation data on the power business by using the power generation data weight, and obtaining an influence index of the power transmission line environment data on the power business by using the power transmission line environment data; according to the full-link intelligent diagnosis method for the power key business, the fiber bragg grating temperature sensor technology, the Hall voltage sensor technology, the Hall current sensor technology and the neural network algorithm technology are closely combined with the modern information technology; and the intelligent degree in the full-link intelligent diagnosis process of the power key business is obviously enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent diagnosis of electric power services, and in particular to a full-link intelligent diagnosis method for key electric power services. Background Art

[0002] As modern society becomes increasingly dependent on electricity, the scale and complexity of the power system have risen sharply. Key power services cover multiple links such as power generation, transmission, transformation, distribution and power consumption. Traditional diagnostic methods rely on manual inspections and simple instrument monitoring. When faced with such a large and complex system, on the one hand, manual inspections are inefficient and have long cycles, making it difficult to capture fault hazards in real time; on the other hand, simple instrument monitoring can only obtain limited data and cannot fully analyze the operating conditions of the entire business chain. Once a power system failure occurs, the impact range is wide and the harm is great. It may cause large-scale power outages, bringing serious impacts to industrial production and residents' lives. Therefore, in order to ensure the stable and reliable operation of the power system and meet the society's growing demand for power supply, a full-link intelligent diagnosis method for key power services has emerged, which solves the problems of low efficiency, inability to monitor in real time, and easy omission of hidden dangers in manual inspections, and ensures the stable operation of the power system.

[0003] Although the existing technology has made great progress in the direction of intelligent diagnosis of power business, there are still some problems that need to be optimized. In the full-link intelligent diagnosis process of power business, the existing technology cannot combine data from multiple links, resulting in the inability to accurately locate power business faults, extending the troubleshooting time and affecting the normal operation of the entire link of power business. Summary of the invention

[0004] The present invention aims to provide a full-link intelligent diagnosis method for key power services to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: a full-link intelligent diagnosis method for key power services, comprising the following steps:

[0006] Step 1: Obtain power business diagnostic data through acquisition equipment, where the power business diagnostic data includes transmission line environment data and power generation data, providing data support for full-link intelligent diagnosis of key power businesses;

[0007] Step 2: pre-process the collected power business diagnostic data to obtain the power generation data weight, paving the way for the subsequent acquisition of the impact index of the power generation data on the power business;

[0008] Step 3: Using the power generation data weight, obtain the impact index of power generation data on power business;

[0009] Step 4: Using the transmission line environment data, obtain the impact index of the transmission line environment data on the power business;

[0010] Step 5: Use the neural network algorithm to build a power business diagnosis and monitoring model, which provides a solution to the problem that traditional methods cannot combine multi-link data to accurately locate power business faults;

[0011] Step 6: Combine the power business diagnosis and monitoring model to conduct intelligent diagnosis of key power businesses;

[0012] Step 7: Send out corresponding signals according to the intelligent diagnosis results.

[0013] A further improvement of the technical solution of the present invention is that in step 1, the process of obtaining power business diagnostic data includes:

[0014] The acquisition equipment includes a fiber Bragg grating temperature sensor, a Hall voltage sensor, a Hall current sensor and an oscilloscope, the power transmission line environmental data is the power transmission line temperature, and the power generation data includes the stator voltage, stator current and output frequency of the generator;

[0015] A further improvement of the technical solution of the present invention is that in step 1, the process of obtaining the transmission line environment data includes:

[0016] The fiber Bragg grating temperature sensor is installed at the line clamp of the transmission line, and the temperature of the transmission line is collected by utilizing the temperature sensitivity of the fiber Bragg grating.

[0017] A further improvement of the technical solution of the present invention is that in step 1, the process of obtaining power generation data includes:

[0018] The Hall voltage sensor is connected in parallel with the generator to obtain the stator voltage of the generator based on the Hall effect;

[0019] The Hall current sensor is connected in series with the generator, and the stator current of the generator is obtained by utilizing the Hall effect;

[0020] The output electrical signal of the generator is input into an oscilloscope to obtain the waveform of the generator electrical signal, and the period of the generator electrical signal waveform in the horizontal direction is measured. According to the inverse relationship between the frequency and the period, the output frequency of the generator is calculated and obtained.

[0021] A further improvement of the technical solution of the present invention is that in step 2, the process of preprocessing the collected power business diagnosis data and obtaining the power generation data weight includes:

[0022] Clean the power business diagnosis data, remove abnormal values ​​and duplicate values ​​in the power business diagnosis data, and fill in the missing values ​​in the power business diagnosis data;

[0023] According to the impact of power generation data on power business, ten questionnaire questions are set, and questionnaire answers are set for the stator voltage, stator current and output frequency of the generator respectively. The questionnaire answers are set as important, general and unimportant. Questionnaire questions are distributed through the online questionnaire platform to obtain questionnaire results;

[0024] Assign 9 points, 6 points and 3 points to important, general and unimportant questionnaire answers respectively, convert the questionnaire results into data form, obtain the total score of the questionnaire results according to the number of questionnaire questions, and obtain the questionnaire data of the stator voltage, stator current and output frequency of the generator according to the assigned questionnaire answer scores. The calculation process of obtaining the weights of the stator voltage, stator current and output frequency of the generator is as follows:

[0025]

[0026]

[0027]

[0028] in, , and are the weights of the generator’s stator voltage, stator current and output frequency, respectively. is the total score of the questionnaire results, , and They are the questionnaire data of the stator voltage, stator current and output frequency of the generator respectively.

[0029] A further improvement of the technical solution of the present invention is that in step 3, the process of obtaining the influence index of power generation data on power business by using the power generation data weight includes:

[0030] Using the weights of the generator's stator voltage, stator current and output frequency, the impact index of power generation data on the power business is the impact index of the generator's stator voltage, stator current and output frequency on the electronic business respectively. The process of calculating the impact index of the generator's stator voltage, stator current and output frequency on the electronic business respectively is as follows:

[0031]

[0032]

[0033]

[0034] in, , and are the influence indexes of the generator’s stator voltage, stator current and output frequency on the electronic business, , and are the weights of the generator’s stator voltage, stator current and output frequency, respectively. , and are the stator voltage, stator current and output frequency of the generator respectively.

[0035] A further improvement of the technical solution of the present invention is that in step 4, the process of using the transmission line environment data to obtain the impact index of the transmission line environment data on the power business includes:

[0036] The transmission line temperature threshold is set, and the impact index of the transmission line environment data on the power business is the impact index of the transmission line temperature on the power business. The process of calculating the impact index of the transmission line temperature on the power business using the transmission line temperature threshold is as follows:

[0037]

[0038] Among them, R is the impact index of transmission line temperature on power business, is the transmission line temperature, is the transmission line temperature threshold.

[0039] A further improvement of the technical solution of the present invention is that in step 5, the process of constructing the power business diagnosis and monitoring model includes:

[0040] A neural network model is constructed, and the power business diagnosis data and its impact index on the power business are used as data sets, which are divided into a training set and a test set in a ratio of 7:3. MLP is selected as the neural network structure. The input layer includes four neurons, which receive the power business diagnosis data. The hidden layer is configured with the MSE function. The output layer includes four neurons, which outputs the impact index of the power business diagnosis data on the power business. The input layer input data specifically includes the transmission line temperature, the stator voltage of the generator, the stator current of the generator, and the output frequency of the generator. The output layer output data specifically includes the impact index of the transmission line temperature, the stator voltage of the generator, the stator current of the generator, and the output frequency of the generator on the power business respectively.

[0041] Input the training set data into the neural network model, set the learning rate to 0.01, and the number of iterative training times to 1000. The training process includes forward propagation and back propagation, wherein the forward propagation is used to calculate the predicted output data, and the back propagation is used to update the weights and biases of the model. Through repeated iterative training, learn the nonlinear relationship between the transmission line temperature and the transmission line temperature on the power business impact index, the nonlinear relationship between the stator voltage of the generator and the stator voltage of the generator on the power business impact index, the nonlinear relationship between the stator current of the generator and the stator current of the generator on the power business impact index, and the nonlinear relationship between the output frequency of the generator and the output frequency of the generator on the power business impact index, until the set number of iterative training times is reached, and obtain the trained neural network model;

[0042] The test set data is input into the trained neural network model, and the MSE function is used to evaluate the error between the output value of the neural network model and the actual value. The parameters of the neural network model are adjusted according to the evaluation results, the performance of the neural network model is optimized, and the power business diagnosis and monitoring model is obtained.

[0043] A further improvement of the technical solution of the present invention is that in step 6, the process of intelligently diagnosing key power services in combination with the power service diagnosis and monitoring model includes:

[0044] Combined with the power business diagnosis monitoring model, the power business diagnosis data is analyzed. When the transmission line temperature impact index on the power business is lower than 0.3, the transmission line temperature has a low impact on the power business; when the transmission line temperature impact index on the power business is between 0.3 and 0.6, the transmission line temperature has a medium impact on the power business; when the transmission line temperature impact index on the power business is higher than 0.6, the transmission line temperature has a high impact on the power business;

[0045] When the impact index of the generator's stator voltage on the power business is lower than 0.4, the generator's stator voltage has a low impact on the power business; when the impact index of the generator's stator voltage on the power business is between 0.4 and 0.6, the generator's stator voltage has a medium impact on the power business; when the impact index of the generator's stator voltage on the power business is higher than 0.6, the generator's stator voltage has a high impact on the power business;

[0046] When the impact index of the generator's stator current on the power business is lower than 0.4, the generator's stator current has a low impact on the power business; when the impact index of the generator's stator current on the power business is between 0.4 and 0.6, the generator's stator current has a medium impact on the power business; when the impact index of the generator's stator current on the power business is higher than 0.6, the generator's stator current has a high impact on the power business;

[0047] When the impact index of the generator's output frequency on the power business is lower than 0.2, the generator's output frequency has a low impact on the power business; when the impact index of the generator's output frequency on the power business is between 0.2 and 0.5, the generator's output frequency has a medium impact on the power business; when the impact index of the generator's output frequency on the power business is higher than 0.5, the generator's output frequency has a high impact on the power business.

[0048] A further improvement of the technical solution of the present invention is that in step seven, the process of sending a corresponding signal according to the intelligent diagnosis result includes:

[0049] A green signal is set to indicate that the power business is in a normal state, a yellow signal to indicate that the power business is in a warning state, and a red signal to indicate that the power business is in an emergency state. The power business diagnostic data that causes the power business abnormality is sent out in the form of text displayed on the display screen;

[0050] When the transmission line temperature has a low impact on the power business, the key power business operates normally and a normal transmission line temperature signal is issued; when the transmission line temperature has a medium impact on the power business, the key power business is affected by the transmission line temperature, a transmission line temperature warning signal is issued, and the display screen displays the transmission line temperature; when the transmission line temperature has a high impact on the power business, the transmission line temperature causes a power business failure, a transmission line temperature emergency signal is issued, and the display screen displays the transmission line temperature;

[0051] When the generator stator voltage has a low impact on the power business, the key power business operates normally and a normal generator stator voltage signal is issued; when the generator stator voltage has a medium impact on the power business, the key power business is affected by the generator stator voltage, a generator stator voltage warning signal is issued, and the display screen displays the generator stator voltage; when the generator stator voltage has a high impact on the power business, the generator stator voltage causes a power business failure, a generator stator voltage emergency signal is issued, and the display screen displays the generator stator voltage;

[0052] When the generator stator current has a low impact on the power business, the key power business operates normally and a normal generator stator current signal is issued; when the generator stator current has a medium impact on the power business, the key power business is affected by the generator stator current, a generator stator current warning signal is issued, and the display screen displays the generator stator current; when the generator stator current has a high impact on the power business, the generator stator current causes a power business failure, a generator stator current emergency signal is issued, and the display screen displays the generator stator current;

[0053] When the generator output frequency has a low impact on the power business, the key power business operates normally and a normal generator output frequency signal is issued; when the generator output frequency has a medium impact on the power business, the key power business is affected by the generator output frequency, a generator output frequency warning signal is issued, and the display screen displays the generator output frequency; when the generator output frequency has a high impact on the power business, the generator output frequency triggers a power business failure, a generator output frequency emergency signal is issued, and the display screen displays the generator output frequency.

[0054] The beneficial effects of the present invention are as follows: a full-link intelligent diagnosis method for key power services in the present invention, compared with the traditional full-link intelligent diagnosis method for key power services, the fiber Bragg grating temperature sensor technology, the Hall voltage sensor technology, the Hall current sensor technology and the neural network algorithm technology in the method of the present invention are closely combined with modern information technology, accurately capture the temperature of the transmission line, the stator voltage, the stator current and the output frequency of the generator, obtain the impact index of the power service diagnosis data on the power service, and achieve real-time and comprehensive monitoring of multiple links of the power service. By constructing a power service diagnosis and monitoring model, the problem that the existing technology cannot combine the data of multiple links in the full-link intelligent diagnosis process of the power service, resulting in the inability to accurately locate the power service fault, the troubleshooting time is prolonged, and the normal operation of the full link of the power service is affected is solved, ensuring that the method in the present invention can refine the dynamic monitoring standard of a full-link intelligent diagnosis method for key power services within a more precise range, so that the monitored data becomes a more accurate indicator under the same conditions. The research and development and application of this method significantly enhance the degree of intelligence in the full-link intelligent diagnosis process of key power services. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0056] Figure 1 The present invention is a flow chart of a full-link intelligent diagnosis method for key power services. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0058] like Figure 1 As shown, the present invention provides a full-link intelligent diagnosis method for key power services, comprising the following steps:

[0059] Step 1: Obtain power business diagnostic data through acquisition equipment, where the power business diagnostic data includes transmission line environment data and power generation data, providing data support for full-link intelligent diagnosis of key power businesses;

[0060] Step 2: pre-process the collected power business diagnostic data to obtain the power generation data weight, paving the way for the subsequent acquisition of the impact index of the power generation data on the power business;

[0061] Step 3: Using the power generation data weight, obtain the impact index of power generation data on power business;

[0062] Step 4: Using the transmission line environment data, obtain the impact index of the transmission line environment data on the power business;

[0063] Step 5: Use the neural network algorithm to build a power business diagnosis and monitoring model, which provides a solution to the problem that traditional methods cannot combine multi-link data to accurately locate power business faults;

[0064] Step 6: Combine the power business diagnosis and monitoring model to conduct intelligent diagnosis of key power businesses;

[0065] Step 7: Send out corresponding signals according to the intelligent diagnosis results.

[0066] Preferably, in step 1, the process of obtaining power business diagnostic data includes:

[0067] The acquisition equipment includes a fiber Bragg grating temperature sensor, a Hall voltage sensor, a Hall current sensor and an oscilloscope. The transmission line environmental data is the transmission line temperature. The power generation data includes the stator voltage, stator current and output frequency of the generator.

[0068] Preferably, in step 1, the process of obtaining the transmission line environment data includes:

[0069] The fiber Bragg grating temperature sensor is installed at the line clamp of the transmission line, and the temperature of the transmission line is collected by utilizing the temperature sensitivity of the fiber Bragg grating.

[0070] Preferably, in step 1, the process of obtaining power generation data includes:

[0071] The Hall voltage sensor is connected in parallel with the generator to obtain the stator voltage of the generator based on the Hall effect;

[0072] The Hall current sensor is connected in series with the generator, and the stator current of the generator is obtained by utilizing the Hall effect;

[0073] The output electrical signal of the generator is input into an oscilloscope to obtain the waveform of the generator electrical signal, and the period of the generator electrical signal waveform in the horizontal direction is measured. According to the inverse relationship between the frequency and the period, the output frequency of the generator is calculated and obtained.

[0074] Preferably, in step 2, the process of preprocessing the collected power business diagnosis data and obtaining the power generation data weight includes:

[0075] Clean the power business diagnosis data, remove abnormal values ​​and duplicate values ​​in the power business diagnosis data, and fill in the missing values ​​in the power business diagnosis data;

[0076] According to the impact of power generation data on power business, ten questionnaire questions are set, and questionnaire answers are set for the stator voltage, stator current and output frequency of the generator respectively. The questionnaire answers are set as important, general and unimportant. Questionnaire questions are distributed through the online questionnaire platform to obtain questionnaire results;

[0077] Assign 9 points, 6 points and 3 points to important, general and unimportant questionnaire answers respectively, convert the questionnaire results into data form, obtain the total score of the questionnaire results according to the number of questionnaire questions, and obtain the questionnaire data of the stator voltage, stator current and output frequency of the generator according to the assigned questionnaire answer scores. The calculation process of obtaining the weights of the stator voltage, stator current and output frequency of the generator is as follows:

[0078]

[0079]

[0080]

[0081] in, , and are the weights of the generator’s stator voltage, stator current and output frequency, respectively. is the total score of the questionnaire results, , and They are the questionnaire data of the stator voltage, stator current and output frequency of the generator respectively.

[0082] Preferably, in step 3, the process of obtaining the impact index of power generation data on power business by using the power generation data weight includes:

[0083] Using the weights of the generator's stator voltage, stator current and output frequency, the impact index of power generation data on the power business is the impact index of the generator's stator voltage, stator current and output frequency on the electronic business respectively. The process of calculating the impact index of the generator's stator voltage, stator current and output frequency on the electronic business respectively is as follows:

[0084]

[0085]

[0086]

[0087] in, , and are the influence indexes of the generator’s stator voltage, stator current and output frequency on the electronic business, , and are the weights of the generator’s stator voltage, stator current and output frequency, respectively. , and are the stator voltage, stator current and output frequency of the generator respectively.

[0088] Preferably, in step 4, the process of using the transmission line environment data to obtain the impact index of the transmission line environment data on the power business includes:

[0089] The transmission line temperature threshold is set, and the impact index of the transmission line environment data on the power business is the impact index of the transmission line temperature on the power business. The process of calculating the impact index of the transmission line temperature on the power business using the transmission line temperature threshold is as follows:

[0090]

[0091] Among them, R is the impact index of transmission line temperature on power business, is the transmission line temperature, is the transmission line temperature threshold.

[0092] Preferably, in step 5, the process of constructing the power business diagnosis and monitoring model includes:

[0093] A neural network model is constructed, and the power business diagnosis data and its impact index on the power business are used as data sets, which are divided into a training set and a test set in a ratio of 7:3. MLP is selected as the neural network structure. The input layer includes four neurons, which receive the power business diagnosis data. The hidden layer is configured with the MSE function. The output layer includes four neurons, which outputs the impact index of the power business diagnosis data on the power business. The input layer input data specifically includes the transmission line temperature, the stator voltage of the generator, the stator current of the generator, and the output frequency of the generator. The output layer output data specifically includes the impact index of the transmission line temperature, the stator voltage of the generator, the stator current of the generator, and the output frequency of the generator on the power business respectively.

[0094] Input the training set data into the neural network model, set the learning rate to 0.01, and the number of iterative training times to 1000. The training process includes forward propagation and back propagation, wherein the forward propagation is used to calculate the predicted output data, and the back propagation is used to update the weights and biases of the model. Through repeated iterative training, learn the nonlinear relationship between the transmission line temperature and the transmission line temperature on the power business impact index, the nonlinear relationship between the stator voltage of the generator and the stator voltage of the generator on the power business impact index, the nonlinear relationship between the stator current of the generator and the stator current of the generator on the power business impact index, and the nonlinear relationship between the output frequency of the generator and the output frequency of the generator on the power business impact index, until the set number of iterative training times is reached, and obtain the trained neural network model;

[0095] The test set data is input into the trained neural network model, and the MSE function is used to evaluate the error between the output value of the neural network model and the actual value. The parameters of the neural network model are adjusted according to the evaluation results, the performance of the neural network model is optimized, and the power business diagnosis and monitoring model is obtained.

[0096] Preferably, in step 6, the process of performing intelligent diagnosis on key power services in combination with the power service diagnosis and monitoring model includes:

[0097] Combined with the power business diagnosis monitoring model, the power business diagnosis data is analyzed. When the transmission line temperature impact index on the power business is lower than 0.3, the transmission line temperature has a low impact on the power business; when the transmission line temperature impact index on the power business is between 0.3 and 0.6, the transmission line temperature has a medium impact on the power business; when the transmission line temperature impact index on the power business is higher than 0.6, the transmission line temperature has a high impact on the power business;

[0098] When the impact index of the generator's stator voltage on the power business is lower than 0.4, the generator's stator voltage has a low impact on the power business; when the impact index of the generator's stator voltage on the power business is between 0.4 and 0.6, the generator's stator voltage has a medium impact on the power business; when the impact index of the generator's stator voltage on the power business is higher than 0.6, the generator's stator voltage has a high impact on the power business;

[0099] When the impact index of the generator's stator current on the power business is lower than 0.4, the generator's stator current has a low impact on the power business; when the impact index of the generator's stator current on the power business is between 0.4 and 0.6, the generator's stator current has a medium impact on the power business; when the impact index of the generator's stator current on the power business is higher than 0.6, the generator's stator current has a high impact on the power business;

[0100] When the impact index of the generator's output frequency on the power business is lower than 0.2, the generator's output frequency has a low impact on the power business; when the impact index of the generator's output frequency on the power business is between 0.2 and 0.5, the generator's output frequency has a medium impact on the power business; when the impact index of the generator's output frequency on the power business is higher than 0.5, the generator's output frequency has a high impact on the power business.

[0101] Preferably, in step seven, the process of sending a corresponding signal according to the intelligent diagnosis result includes:

[0102] A green signal is set to indicate that the power business is in a normal state, a yellow signal to indicate that the power business is in a warning state, and a red signal to indicate that the power business is in an emergency state. The power business diagnostic data that causes the power business abnormality is sent out in the form of text displayed on the display screen;

[0103] When the transmission line temperature has a low impact on the power business, the key power business operates normally and a normal transmission line temperature signal is issued; when the transmission line temperature has a medium impact on the power business, the key power business is affected by the transmission line temperature, a transmission line temperature warning signal is issued, and the display screen displays the transmission line temperature; when the transmission line temperature has a high impact on the power business, the transmission line temperature causes a power business failure, a transmission line temperature emergency signal is issued, and the display screen displays the transmission line temperature;

[0104] When the generator stator voltage has a low impact on the power business, the key power business operates normally and a normal generator stator voltage signal is issued; when the generator stator voltage has a medium impact on the power business, the key power business is affected by the generator stator voltage, a generator stator voltage warning signal is issued, and the display screen displays the generator stator voltage; when the generator stator voltage has a high impact on the power business, the generator stator voltage causes a power business failure, a generator stator voltage emergency signal is issued, and the display screen displays the generator stator voltage;

[0105] When the generator stator current has a low impact on the power business, the key power business operates normally and a normal generator stator current signal is issued; when the generator stator current has a medium impact on the power business, the key power business is affected by the generator stator current, a generator stator current warning signal is issued, and the display screen displays the generator stator current; when the generator stator current has a high impact on the power business, the generator stator current causes a power business failure, a generator stator current emergency signal is issued, and the display screen displays the generator stator current;

[0106] When the generator output frequency has a low impact on the power business, the key power business operates normally and a normal generator output frequency signal is issued; when the generator output frequency has a medium impact on the power business, the key power business is affected by the generator output frequency, a generator output frequency warning signal is issued, and the display screen displays the generator output frequency; when the generator output frequency has a high impact on the power business, the generator output frequency triggers a power business failure, a generator output frequency emergency signal is issued, and the display screen displays the generator output frequency.

[0107] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A full-link intelligent diagnosis method for key power services, characterized in that: The following steps are involved: Step 1: Obtain power business diagnostic data through a collection device, wherein the power business diagnostic data includes transmission line environment data and power generation data; Step 2: pre-process the collected power business diagnosis data to obtain the power generation data weight; Step 3: Using the power generation data weight, obtain the impact index of power generation data on power business; Step 4: Using the transmission line environment data, obtain the impact index of the transmission line environment data on the power business; Step 5: Construct a power business diagnosis and monitoring model through a neural network algorithm; Step 6: Combine the power business diagnosis and monitoring model to conduct intelligent diagnosis of key power businesses; Step 7: Send out corresponding signals according to the intelligent diagnosis results.

2. According to claim 1, a full-link intelligent diagnosis method for key power services is characterized by: In step 1, the process of obtaining power business diagnostic data includes: The acquisition equipment includes a fiber grating temperature sensor, a Hall voltage sensor, a Hall current sensor and an oscilloscope. The power transmission line environmental data is the power transmission line temperature. The power generation data includes the stator voltage, stator current and output frequency of the generator.

3. According to claim 2, a full-link intelligent diagnosis method for key power services is characterized by: In the step 1, the process of obtaining the transmission line environment data includes: The fiber Bragg grating temperature sensor is installed at the line clamp of the transmission line, and the temperature of the transmission line is collected by utilizing the temperature sensitivity of the fiber Bragg grating.

4. The full-link intelligent diagnosis method for key power services according to claim 3 is characterized by: In step 1, the process of obtaining power generation data includes: The Hall voltage sensor is connected in parallel with the generator to obtain the stator voltage of the generator based on the Hall effect; The Hall current sensor is connected in series with the generator, and the stator current of the generator is obtained by utilizing the Hall effect; The output electrical signal of the generator is input into an oscilloscope to obtain the waveform of the generator electrical signal, and the period of the generator electrical signal waveform in the horizontal direction is measured. According to the inverse relationship between the frequency and the period, the output frequency of the generator is calculated and obtained.

5. The full-link intelligent diagnosis method for key power services according to claim 4 is characterized in that: In step 2, the process of preprocessing the collected power business diagnosis data and obtaining the power generation data weight includes: Clean the power business diagnosis data, remove abnormal values ​​and duplicate values ​​in the power business diagnosis data, and fill in the missing values ​​in the power business diagnosis data; According to the impact of power generation data on power business, ten questionnaire questions are set, and questionnaire answers are set for the stator voltage, stator current and output frequency of the generator respectively. The questionnaire answers are set as important, general and unimportant. Questionnaire questions are distributed through the online questionnaire platform to obtain questionnaire results; Assign 9 points, 6 points and 3 points to important, general and unimportant questionnaire answers respectively, convert the questionnaire results into data form, obtain the total score of the questionnaire results according to the number of questionnaire questions, and obtain the questionnaire data of the stator voltage, stator current and output frequency of the generator according to the assigned questionnaire answer scores. The calculation process of obtaining the weights of the stator voltage, stator current and output frequency of the generator is as follows: ； ； ； in, , and are the weights of the generator’s stator voltage, stator current and output frequency, respectively. is the total score of the questionnaire results, , and They are the questionnaire data of the stator voltage, stator current and output frequency of the generator respectively.

6. A full-link intelligent diagnosis method for key power services according to claim 5, characterized in that: In step 3, the process of obtaining the impact index of power generation data on power business by using the power generation data weight includes: Using the weights of the generator's stator voltage, stator current and output frequency, the impact index of power generation data on the power business is the impact index of the generator's stator voltage, stator current and output frequency on the electronic business respectively. The process of calculating the impact index of the generator's stator voltage, stator current and output frequency on the electronic business respectively is as follows: ； ； ； in, , and are the influence indexes of the generator’s stator voltage, stator current and output frequency on the electronic business, , and are the weights of the generator’s stator voltage, stator current and output frequency, respectively. , and are the stator voltage, stator current and output frequency of the generator respectively.

7. A full-link intelligent diagnosis method for key power services according to claim 6, characterized in that: In the step 4, the process of using the transmission line environment data to obtain the impact index of the transmission line environment data on the power business includes: The transmission line temperature threshold is set, and the impact index of the transmission line environment data on the power business is the impact index of the transmission line temperature on the power business. The process of calculating the impact index of the transmission line temperature on the power business using the transmission line temperature threshold is as follows: ； Among them, R is the impact index of transmission line temperature on power business, is the transmission line temperature, is the transmission line temperature threshold.

8. The full-link intelligent diagnosis method for key power services according to claim 7 is characterized by: In step 5, the process of constructing the power business diagnosis and monitoring model includes: A neural network model is constructed, and the power business diagnosis data and its impact index on the power business are used as data sets, which are divided into a training set and a test set in a ratio of 7:

3. MLP is selected as the neural network structure. The input layer includes four neurons, which receive the power business diagnosis data. The hidden layer is configured with the MSE function. The output layer includes four neurons, which outputs the impact index of the power business diagnosis data on the power business. The input layer input data specifically includes the transmission line temperature, the stator voltage of the generator, the stator current of the generator, and the output frequency of the generator. The output layer output data specifically includes the impact index of the transmission line temperature, the stator voltage of the generator, the stator current of the generator, and the output frequency of the generator on the power business respectively. Input the training set data into the neural network model, set the learning rate to 0.01, and the number of iterative training times to 1000. The training process includes forward propagation and back propagation, wherein the forward propagation is used to calculate the predicted output data, and the back propagation is used to update the weights and biases of the model. Through repeated iterative training, learn the nonlinear relationship between the transmission line temperature and the transmission line temperature on the power business impact index, the nonlinear relationship between the stator voltage of the generator and the stator voltage of the generator on the power business impact index, the nonlinear relationship between the stator current of the generator and the stator current of the generator on the power business impact index, and the nonlinear relationship between the output frequency of the generator and the output frequency of the generator on the power business impact index, until the set number of iterative training times is reached, and obtain the trained neural network model; The test set data is input into the trained neural network model, and the MSE function is used to evaluate the error between the output value of the neural network model and the actual value. The parameters of the neural network model are adjusted according to the evaluation results, the performance of the neural network model is optimized, and the power business diagnosis and monitoring model is obtained.

9. A full-link intelligent diagnosis method for key power services according to claim 8, characterized in that: In step 6, the process of intelligently diagnosing key power services in combination with the power service diagnosis and monitoring model includes: Combined with the power business diagnosis monitoring model, the power business diagnosis data is analyzed. When the transmission line temperature impact index on the power business is lower than 0.3, the transmission line temperature has a low impact on the power business; when the transmission line temperature impact index on the power business is between 0.3 and 0.6, the transmission line temperature has a medium impact on the power business; when the transmission line temperature impact index on the power business is higher than 0.6, the transmission line temperature has a high impact on the power business; When the impact index of the generator's stator voltage on the power business is lower than 0.4, the generator's stator voltage has a low impact on the power business; when the impact index of the generator's stator voltage on the power business is between 0.4 and 0.6, the generator's stator voltage has a medium impact on the power business; when the impact index of the generator's stator voltage on the power business is higher than 0.6, the generator's stator voltage has a high impact on the power business; When the impact index of the generator's stator current on the power business is lower than 0.4, the generator's stator current has a low impact on the power business; when the impact index of the generator's stator current on the power business is between 0.4 and 0.6, the generator's stator current has a medium impact on the power business; when the impact index of the generator's stator current on the power business is higher than 0.6, the generator's stator current has a high impact on the power business; When the impact index of the generator's output frequency on the power business is lower than 0.2, the generator's output frequency has a low impact on the power business; when the impact index of the generator's output frequency on the power business is between 0.2 and 0.5, the generator's output frequency has a medium impact on the power business; when the impact index of the generator's output frequency on the power business is higher than 0.5, the generator's output frequency has a high impact on the power business.

10. A full-link intelligent diagnosis method for key power services according to claim 9, characterized in that: In step 7, the process of sending a corresponding signal according to the intelligent diagnosis result includes: A green signal is set to indicate that the power business is in a normal state, a yellow signal to indicate that the power business is in a warning state, and a red signal to indicate that the power business is in an emergency state. The power business diagnostic data that causes the power business abnormality is sent out in the form of text displayed on the display screen; When the transmission line temperature has a low impact on the power business, the key power business operates normally and a normal transmission line temperature signal is issued; when the transmission line temperature has a medium impact on the power business, the key power business is affected by the transmission line temperature, a transmission line temperature warning signal is issued, and the display screen displays the transmission line temperature; when the transmission line temperature has a high impact on the power business, the transmission line temperature causes a power business failure, a transmission line temperature emergency signal is issued, and the display screen displays the transmission line temperature; When the generator stator voltage has a low impact on the power business, the key power business operates normally and a normal generator stator voltage signal is issued; when the generator stator voltage has a medium impact on the power business, the key power business is affected by the generator stator voltage, a generator stator voltage warning signal is issued, and the display screen displays the generator stator voltage; when the generator stator voltage has a high impact on the power business, the generator stator voltage causes a power business failure, a generator stator voltage emergency signal is issued, and the display screen displays the generator stator voltage; When the generator stator current has a low impact on the power business, the key power business operates normally and a normal generator stator current signal is issued; when the generator stator current has a medium impact on the power business, the key power business is affected by the generator stator current, a generator stator current warning signal is issued, and the display screen displays the generator stator current; when the generator stator current has a high impact on the power business, the generator stator current causes a power business failure, a generator stator current emergency signal is issued, and the display screen displays the generator stator current; When the generator output frequency has a low impact on the power business, the key power business operates normally and a normal generator output frequency signal is issued; when the generator output frequency has a medium impact on the power business, the key power business is affected by the generator output frequency, a generator output frequency warning signal is issued, and the display screen displays the generator output frequency; when the generator output frequency has a high impact on the power business, the generator output frequency triggers a power business failure, a generator output frequency emergency signal is issued, and the display screen displays the generator output frequency.

Images