Virtual on-duty system oriented to electric power new energy AI model and voice recognition

Abstract

The invention discloses an AI model and voice recognition-oriented virtual on-duty system for electric power new energy, and relates to the technical field of electric power new energy, and the system comprises a data collection module which collects the operation data of electric power equipment in real time through a sensor network; the data processing and analyzing module is used for identifying the running state of the equipment and predicting a fault; the intelligent scheduling module is used for automatically generating an optimized scheduling scheme based on a data analysis result; the alarm notification module monitors the state of the equipment in real time and gives an alarm to related personnel when a fault and an abnormality occur; and the system management module is used for user management. The operation state of equipment is monitored in real time through the data acquisition module and a sensor network, the accuracy and timeliness of data are ensured, the data processing and analysis module adopts an advanced algorithm to deeply analyze the acquired data, the state of the equipment can be identified, potential faults can be predicted, and the safety of the equipment is improved. Therefore, the downtime and the maintenance cost of equipment are reduced.

Description

Technical Field

[0001] The present invention relates to the field of electric power and new energy technologies, and in particular to an electric power and new energy AI model and voice recognition virtual duty system. Background Art

[0002] With the transformation of the global energy structure, the application of new energy sources is becoming more and more extensive, especially in the fields of smart grid and renewable energy management. Traditional power monitoring and dispatching systems often face challenges such as insufficient data processing capabilities, delayed response time and inaccurate fault prediction. For this reason, a virtual duty system combining artificial intelligence and voice recognition technology has emerged to improve the operating efficiency and safety of power equipment.

[0003] The system uses the data acquisition module and the sensor network to monitor the equipment operating status in real time to ensure the accuracy and timeliness of the data. The data processing and analysis module uses advanced algorithms to conduct in-depth analysis of the collected data, which can not only identify the equipment status, but also predict potential failures, thereby reducing equipment downtime and maintenance costs. The intelligent scheduling module automatically generates optimized scheduling plans based on the analysis results to improve resource utilization. Summary of the invention

[0004] In order to solve the above technical problems, a virtual duty system for electric power new energy AI model and voice recognition is provided. This technical solution solves the above problems.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A virtual duty system for electric power and new energy AI model and voice recognition, including:

[0007] Data acquisition module: The data acquisition module is used to collect the operation data of the power equipment in real time through the sensor network;

[0008] Data processing and analysis module: The data processing and analysis module is electrically connected to the data acquisition module, and is used to pre-process and analyze the collected data, identify the equipment operation status, and predict faults;

[0009] Intelligent scheduling module: The intelligent scheduling module is electrically connected to the data processing and analysis module, and the intelligent scheduling module is used to automatically generate an optimized scheduling plan based on the data analysis results;

[0010] Alarm notification module: The alarm notification module is electrically connected to the intelligent scheduling module. The alarm notification module is used to monitor the equipment status in real time and send an alarm to relevant personnel when a fault or abnormality occurs;

[0011] System management module: The system management module is electrically connected to the alarm notification module, and is used for user management, authority control and system maintenance.

[0012] Preferably, the data acquisition module specifically includes:

[0013] Data preprocessing unit: Use filtering technology to remove noise from the data, handle missing data through interpolation, scale the data to the same range based on Z-score data standardization, and extract features from the original data;

[0014] Data analysis unit: Based on the decision tree algorithm, classify the equipment status, monitor the dashboard in real time, build a visual interface, display key performance indicators and equipment operation status, draw time series graphs, and analyze the change trend of equipment operation data;

[0015] Fault prediction unit: Build a fault prediction model, predict the probability of equipment failure, and identify potential faults.

[0016] Preferably, the data analysis unit specifically includes:

[0017] Divide the data set into a training set and a test set, using 80% of the data as the training set and 20% of the data as the test set;

[0018] Use the CART algorithm to build a decision tree, calculate the Gini index, and select the best split feature based on the Gini index;

[0019] The calculation formula of the Gini index is:

[0020]

[0021] In the formula, G(D) represents the Gini index of the data set D, D represents a specific data set, and C represents the total number of different categories in the data set. represents the probability of category i;

[0022] Select the best feature for node splitting, recursively split the data until the stopping condition is reached, and output the device classification status.

[0023] Preferably, the fault prediction unit specifically includes:

[0024] Based on the equipment operation status data, a fault prediction model is established using the logistic regression formula, where the fault prediction model expression is:

[0025]

[0026] In the formula, P is the probability of event Y occurring when feature X is given, Y is the dependent variable, X1X2 is the feature, and X nis the nth feature, β0 is the intercept term, β1β2 is the regression coefficient, β n is the regression coefficient of the nth feature;

[0027] Use the trained model to predict the failure probability of new equipment data, adjust the fault prediction threshold, identify equipment with a high failure probability, and output an alarm.

[0028] Preferably, the intelligent scheduling module specifically includes:

[0029] Data receiving unit: receives processed data from the data processing and analysis module, including the equipment's operating status, fault prediction results, task priority, and resource availability;

[0030] Requirements Analysis and Identification Unit: Evaluate the priority and urgency of the tasks to be scheduled, determine the resources required for each task, determine the number and type of available resources, identify resource constraints, and identify the start and end time constraints of tasks;

[0031] Optimization model building unit: builds a scheduling optimization model based on task requirements and constraints, defines optimization objectives, optimizes the model based on the linear programming algorithm, and generates a scheduling plan;

[0032] Scheduling plan generation unit: Based on the solution results of the optimization model, it generates a specific scheduling plan, allocates corresponding resources, determines the start and end time of the task, and applies the optimized scheduling plan to actual operations.

[0033] Preferably, the construction of a scheduling optimization model according to task requirements and constraints, definition of optimization objectives, optimization of the model according to a linear programming algorithm, and generation of a scheduling solution specifically include:

[0034] Construct the objective function, determine the optimization goal, minimize the total completion time, define constraints, and ensure that each task is assigned only once. The linear programming formula is:

[0035]

[0036] In the formula, MC max is the maximum completion time in the schedule, i represents the index of the task, C i is the completion time of task i, x i is the decision variable of task i;

[0037] Arrange the objective function and constraints into a standard linear programming form;

[0038] Use mathematical software to solve the model and obtain the optimal solution. Analyze task allocation and resource utilization based on the solution results and generate a scheduling plan.

[0039] Preferably, the alarm notification module specifically includes:

[0040] Condition monitoring unit: collects and monitors the operation data and status information of the equipment in real time;

[0041] Fault detection unit: determines whether the equipment is faulty or abnormal through the set threshold and algorithm;

[0042] Alarm generation unit: once a fault or anomaly is detected, it generates an alarm message including the fault type and severity;

[0043] Information transmission unit: sends alarm information to relevant personnel;

[0044] Record storage: record and archive fault and alarm information;

[0045] Status recovery monitoring: After the alarm, continue to monitor the equipment status, determine whether the fault has been repaired, and notify relevant personnel of the recovery status.

[0046] Preferably, judging whether a device fails or is abnormal by using a set threshold and algorithm specifically includes:

[0047] Obtain equipment operating data in real time, including temperature, pressure, current and vibration;

[0048] According to the normal operating range of the equipment, the threshold is set, and the fault or abnormality is judged based on the condition monitoring algorithm. The condition monitoring algorithm formula is:

[0049]

[0050] Where J is the value of the root mean square error, N is the total number of data samples, and x i is the i-th sample value, is the sample mean.

[0051] Preferably, the system management module specifically includes:

[0052] User management unit: add and store user information, verify user identity, ensure security, update and delete user information;

[0053] Permission control unit: set access rights according to user roles, regularly check and update user permissions to ensure compliance with security policies;

[0054] System maintenance unit: regularly back up system data to prevent data loss, install system updates, and ensure software security and functionality;

[0055] Log management unit: record user activities and system events, and check logs regularly.

[0056] Preferably, the authority control unit specifically includes:

[0057] Identify different user roles in the system and define the scope of authority for each role, bind authority to roles, set the system modules and functions that different roles can access, allow users to be assigned to specific roles, manage the relationship between users and roles, and provide the ability to modify and update user roles.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] The present invention proposes to use the sensor network to monitor the equipment operation status in real time through the data acquisition module to ensure the accuracy and timeliness of the data. The data processing and analysis module uses advanced algorithms to conduct in-depth analysis of the collected data, which can not only identify the equipment status, but also predict potential faults, thereby reducing equipment downtime and maintenance costs. The intelligent scheduling module automatically generates optimized scheduling plans based on the analysis results to improve resource utilization. The alarm notification module can respond quickly when a fault occurs and issue an alarm to relevant personnel in a timely manner to ensure the efficiency of fault handling. In addition, the system management module is responsible for user management and authority control to ensure system security and stability. Through the collaborative work of these modules, the AI ​​model and voice recognition virtual duty system for electric power and new energy have promoted the sustainable development of the power industry while improving the automation and intelligence level of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a system framework diagram of the present invention. DETAILED DESCRIPTION

[0061] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0062] Reference Figure 1 As shown, a virtual duty system for electric power new energy AI model and voice recognition includes:

[0063] Data acquisition module: The data acquisition module is used to collect the operation data of the power equipment in real time through the sensor network;

[0064] Data processing and analysis module: The data processing and analysis module is electrically connected to the data acquisition module, and is used to pre-process and analyze the collected data, identify the equipment operation status, and predict faults;

[0065] Intelligent scheduling module: The intelligent scheduling module is electrically connected to the data processing and analysis module, and the intelligent scheduling module is used to automatically generate an optimized scheduling plan based on the data analysis results;

[0066] Alarm notification module: The alarm notification module is electrically connected to the intelligent scheduling module. The alarm notification module is used to monitor the equipment status in real time and send an alarm to relevant personnel when a fault or abnormality occurs;

[0067] System management module: The system management module is electrically connected to the alarm notification module, and is used for user management, authority control and system maintenance.

[0068] The data acquisition module specifically includes:

[0069] Data preprocessing unit: Use filtering technology to remove noise from the data, handle missing data through interpolation, scale the data to the same range based on Z-score data standardization, and extract features from the original data;

[0070] Data analysis unit: Based on the decision tree algorithm, classify the equipment status, monitor the dashboard in real time, build a visual interface, display key performance indicators and equipment operation status, draw time series graphs, and analyze the change trend of equipment operation data;

[0071] Fault prediction unit: Build a fault prediction model, predict the probability of equipment failure, and identify potential faults.

[0072] The data analysis unit specifically includes:

[0073] Divide the data set into a training set and a test set, using 80% of the data as the training set and 20% of the data as the test set;

[0074] Use the CART algorithm to build a decision tree, calculate the Gini index, and select the best split feature based on the Gini index;

[0075] The calculation formula of the Gini index is:

[0076]

[0077] In the formula, G(D) represents the Gini index of the data set D, D represents a specific data set, and C represents the total number of different categories in the data set. represents the probability of category i;

[0078] Select the best feature for node splitting, recursively split the data until the stopping condition is reached, and output the device classification status.

[0079] The fault prediction unit specifically includes:

[0080] Based on the equipment operation status data, a fault prediction model is established using the logistic regression formula, where the fault prediction model expression is:

[0081]

[0082] In the formula, P is the probability of event Y occurring when feature X is given, Y is the dependent variable, X1X2 is the feature, and X n is the nth feature, β0 is the intercept term, β1β2 is the regression coefficient, β n is the regression coefficient of the nth feature;

[0083] Use the trained model to predict the failure probability of new equipment data, adjust the fault prediction threshold, identify equipment with a high failure probability, and output an alarm.

[0084] The intelligent scheduling module specifically includes:

[0085] Data receiving unit: receives processed data from the data processing and analysis module, including the equipment's operating status, fault prediction results, task priority, and resource availability;

[0086] Requirements Analysis and Identification Unit: Evaluate the priority and urgency of the tasks to be scheduled, determine the resources required for each task, determine the number and type of available resources, identify resource constraints, and identify the start and end time constraints of tasks;

[0087] Optimization model building unit: builds a scheduling optimization model based on task requirements and constraints, defines optimization goals, optimizes the model based on linear programming algorithms, and generates a scheduling plan;

[0088] Scheduling plan generation unit: Based on the solution results of the optimization model, it generates a specific scheduling plan, allocates corresponding resources, determines the start and end time of the task, and applies the optimized scheduling plan to actual operations.

[0089] The scheduling optimization model is constructed according to the task requirements and constraints, the optimization target is defined, the model is optimized according to the linear programming algorithm, and the scheduling scheme is generated, which specifically includes:

[0090] Construct the objective function, determine the optimization goal, minimize the total completion time, define constraints, and ensure that each task is assigned only once. The linear programming formula is:

[0091]

[0092] In the formula, MC max is the maximum completion time in the schedule, i represents the index of the task, C i is the completion time of task i, x i is the decision variable of task i;

[0093] Arrange the objective function and constraints into a standard linear programming form;

[0094] Use mathematical software to solve the model and obtain the optimal solution. Analyze task allocation and resource utilization based on the solution results and generate a scheduling plan.

[0095] The alarm notification module specifically includes:

[0096] Condition monitoring unit: collects and monitors the operation data and status information of the equipment in real time;

[0097] Fault detection unit: determines whether the equipment is faulty or abnormal through the set threshold and algorithm;

[0098] Alarm generation unit: once a fault or anomaly is detected, it generates an alarm message including the fault type and severity;

[0099] Information transmission unit: sends alarm information to relevant personnel;

[0100] Record storage: record and archive fault and alarm information;

[0101] Status recovery monitoring: After the alarm, continue to monitor the equipment status, determine whether the fault has been repaired, and notify relevant personnel of the recovery status.

[0102] The method of determining whether a device fails or is abnormal by using the set threshold and algorithm specifically includes:

[0103] Obtain equipment operating data in real time, including temperature, pressure, current and vibration;

[0104] According to the normal operating range of the equipment, the threshold is set, and the fault or abnormality is judged based on the condition monitoring algorithm. The condition monitoring algorithm formula is:

[0105]

[0106] Where J is the value of the root mean square error, N is the total number of data samples, and x i is the i-th sample value, is the sample mean.

[0107] The system management module specifically includes:

[0108] User management unit: add and store user information, verify user identity, ensure security, update and delete user information;

[0109] Permission control unit: set access rights according to user roles, regularly check and update user permissions to ensure compliance with security policies;

[0110] System maintenance unit: regularly back up system data to prevent data loss, install system updates, and ensure software security and functionality;

[0111] Log management unit: record user activities and system events, and check logs regularly.

[0112] The authority control unit specifically includes:

[0113] Identify different user roles in the system and define the scope of authority for each role, bind authority to roles, set the system modules and functions that different roles can access, allow users to be assigned to specific roles, manage the relationship between users and roles, and provide the ability to modify and update user roles.

[0114] In summary, the advantages of the present invention are:

[0115] Improve operating efficiency. Through real-time data collection and analysis, the system can quickly identify the operating status and potential failures of the equipment, thereby optimizing the operating efficiency of the equipment and reducing downtime;

[0116] Fault prediction and prevention: Using advanced fault prediction algorithms, the system can identify the risk of equipment failure in advance, reduce the probability of unexpected equipment downtime, and improve equipment reliability;

[0117] Intelligent scheduling optimization: Through the intelligent scheduling module, the system can automatically generate the optimal scheduling plan based on real-time data and task priority to ensure efficient use of resources and timely completion of tasks;

[0118] Rapid response mechanism, the alarm notification module monitors the equipment status in real time and issues an alarm immediately when a fault or abnormality occurs, ensuring that relevant personnel can respond and handle the problem quickly to reduce accident losses;

[0119] System security: The system management module provides user management and authority control functions to ensure the security and stability of the system and avoid unauthorized access and operation;

[0120] Data visualization: The data analysis module displays key performance indicators through a visual interface, which makes it easier for operators to monitor the equipment operation status in real time and improve the accuracy and efficiency of decision-making;

[0121] Continuous monitoring and maintenance: The system can continuously track the status of equipment after a failure through the status recovery monitoring function, ensuring that the failure is repaired in time and normal operation is restored, further enhancing the reliability of the system;

[0122] Flexible permission management: the system supports setting different access rights based on user roles to ensure information security and data integrity in compliance with corporate security policies.

[0123] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A virtual duty system for electric power new energy AI model and voice recognition, characterized in that: include: Data acquisition module: The data acquisition module is used to collect the operation data of the power equipment in real time through the sensor network; Data processing and analysis module: The data processing and analysis module is electrically connected to the data acquisition module, and is used to pre-process and analyze the collected data, identify the equipment operation status, and predict faults; Intelligent scheduling module: The intelligent scheduling module is electrically connected to the data processing and analysis module, and the intelligent scheduling module is used to automatically generate an optimized scheduling plan based on the data analysis results; Alarm notification module: The alarm notification module is electrically connected to the intelligent scheduling module. The alarm notification module is used to monitor the equipment status in real time and send an alarm to relevant personnel when a fault or abnormality occurs; System management module: The system management module is electrically connected to the alarm notification module, and is used for user management, authority control and system maintenance.

2. According to claim 1, a virtual duty system for electric power and new energy AI model and voice recognition is characterized in that: The data acquisition module specifically includes: Data preprocessing unit: Use filtering technology to remove noise from the data, handle missing data through interpolation, scale the data to the same range based on Z-score data standardization, and extract features from the original data; Data analysis unit: Based on the decision tree algorithm, classify the equipment status, monitor the dashboard in real time, build a visual interface, display key performance indicators and equipment operation status, draw time series graphs, and analyze the change trend of equipment operation data; Fault prediction unit: Build a fault prediction model, predict the probability of equipment failure, and identify potential faults.

3. According to claim 2, a virtual duty system for electric power and new energy AI model and voice recognition is characterized in that: The data analysis unit specifically includes: Divide the data set into a training set and a test set, using 80% of the data as the training set and 20% of the data as the test set; Use the CART algorithm to build a decision tree, calculate the Gini index, and select the best split feature based on the Gini index; The calculation formula of the Gini index is: In the formula, G(D) represents the Gini index of the data set D, D represents a specific data set, and C represents the total number of different categories in the data set. represents the probability of category i; Select the best feature for node splitting, recursively split the data until the stopping condition is reached, and output the device classification status.

4. According to claim 3, a virtual duty system for electric power and new energy AI model and voice recognition is characterized in that: The fault prediction unit specifically includes: Based on the equipment operation status data, a fault prediction model is established using the logistic regression formula, where the fault prediction model expression is: In the formula, P is the probability of event Y occurring when feature X is given, Y is the dependent variable, X1X2 is the feature, and X n is the nth feature, β0 is the intercept term, β1β2 is the regression coefficient, β n is the regression coefficient of the nth feature; Use the trained model to predict the failure probability of new equipment data, adjust the fault prediction threshold, identify equipment with a high failure probability, and output an alarm.

5. According to claim 4, a virtual duty system for electric power new energy AI model and voice recognition is characterized in that: The intelligent scheduling module specifically includes: Data receiving unit: receives processed data from the data processing and analysis module, including the equipment's operating status, fault prediction results, task priority, and resource availability; Requirements Analysis and Identification Unit: Evaluate the priority and urgency of the tasks currently to be scheduled, determine the resources required for each task, determine the number and type of available resources, identify resource constraints, and identify the start and end time constraints of tasks; Optimization model building unit: builds a scheduling optimization model based on task requirements and constraints, defines optimization objectives, optimizes the model based on the linear programming algorithm, and generates a scheduling plan; Scheduling plan generation unit: Based on the solution results of the optimization model, it generates a specific scheduling plan, allocates corresponding resources, determines the start and end time of the task, and applies the optimized scheduling plan to actual operations.

6. The AI ​​model and voice recognition virtual duty system for electric power and new energy according to claim 5 is characterized in that: The scheduling optimization model is constructed according to the task requirements and constraints, the optimization target is defined, the model is optimized according to the linear programming algorithm, and the scheduling scheme is generated, which specifically includes: Construct the objective function, determine the optimization goal, minimize the total completion time, define constraints, and ensure that each task is assigned only once. The linear programming formula is: MC max =∑ i C i ·x i In the formula, MC max is the maximum completion time in the schedule, i represents the index of the task, C i is the completion time of task i, x i is the decision variable of task i; Arrange the objective function and constraints into a standard linear programming form; Use mathematical software to solve the model and obtain the optimal solution. Analyze task allocation and resource utilization based on the solution results and generate a scheduling plan.

7. The AI ​​model and voice recognition virtual duty system for electric power and new energy according to claim 6 is characterized in that: The alarm notification module specifically includes: Condition monitoring unit: collects and monitors the operation data and status information of the equipment in real time; Fault detection unit: determines whether the equipment is faulty or abnormal through the set threshold and algorithm; Alarm generation unit: once a fault or anomaly is detected, it generates an alarm message including the fault type and severity; Information transmission unit: sends alarm information to relevant personnel; Record storage: record and archive fault and alarm information; Status recovery monitoring: After the alarm, continue to monitor the equipment status, determine whether the fault has been repaired, and notify relevant personnel of the recovery status.

8. The AI ​​model and voice recognition virtual duty system for electric power and new energy according to claim 7 is characterized in that: The method of determining whether a device fails or is abnormal by using the set threshold and algorithm specifically includes: Obtain equipment operating data in real time, including temperature, pressure, current and vibration; According to the normal operating range of the equipment, the threshold is set, and the fault or abnormality is judged based on the condition monitoring algorithm. The condition monitoring algorithm formula is: Where J is the value of the root mean square error, N is the total number of data samples, and x i is the i-th sample value, is the sample mean.

9. The AI ​​model and voice recognition virtual duty system for electric power and new energy according to claim 8 is characterized in that: The system management module specifically includes: User management unit: add and store user information, verify user identity, ensure security, update and delete user information; Permission control unit: set access rights according to user roles, regularly check and update user permissions to ensure compliance with security policies; System maintenance unit: regularly back up system data to prevent data loss, install system updates, and ensure software security and functionality; Log management unit: record user activities and system events, and check logs regularly.

10. The virtual duty system for electric power new energy AI model and voice recognition according to claim 9 is characterized in that: The authority control unit specifically includes: Identify different user roles in the system and define the scope of authority for each role, bind authority to roles, set the system modules and functions that different roles can access, allow users to be assigned to specific roles, manage the relationship between users and roles, and provide the ability to modify and update user roles.

Images