Power plant production area personnel violation monitoring and early warning method and system

Abstract

The invention discloses a power plant production area-based personnel violation monitoring and early warning method and system, and relates to the technical field of violation monitoring, and the method comprises the steps: obtaining a plurality of historical data of each production area through a database, and generating an importance assignment for each production area according to the plurality of historical data, the method comprises the following steps: comprehensively analyzing an equipment abnormal operation index and an unauthorized operation frequency through an abnormal analysis model, optimizing parameters of the abnormal analysis model through importance assignment of each production area, predicting whether a worker has a violation behavior, and generating a subsequent monitoring and early warning strategy of the worker based on a violation behavior abnormal division result. According to the early warning system, the detailed behaviors of the workers are monitored to predict whether the workers have the violation possibility, the monitoring strength of the workers with the violation behaviors is adjusted according to the importance of different production areas, and the monitoring and early warning effects and the monitoring resource utilization rate of the early warning system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of violation monitoring, and in particular to a method and system for early warning of violation monitoring of personnel in a production area of ​​a power plant. Background Art

[0002] A power plant is a high-risk working environment, involving a large number of mechanical equipment, high voltage electricity, chemicals, high temperatures and other factors. If the staff does not comply with the safe operating procedures, accidents can easily occur, which will not only threaten the lives of employees, but may also cause damage to production equipment, environmental pollution, and even affect the stability of power supply. Therefore, it is particularly important to monitor the personnel in the production area of ​​the power plant for violations.

[0003] The existing early warning system usually monitors whether the staff violates the rules by installing cameras in various areas of the power plant. This monitoring method has the following defects:

[0004] 1. Only by using cameras to monitor whether the staff has violated the rules, it can only monitor the surface violations of the staff (such as entering unauthorized areas or not wearing protective equipment), but cannot monitor some violations of the staff (such as illegal operation of equipment, etc.), thereby reducing the monitoring and warning effect and accuracy of the early warning system;

[0005] 2. Since different production areas have different importance relative to the power plant, adopting the same monitoring intensity for all production areas may easily lead to missed monitoring or erroneous monitoring (especially when people gather together), and will lead to waste of monitoring resources, thus reducing the monitoring effect;

[0006] Based on this, the present invention proposes a method and system for monitoring and early warning of violations of regulations by personnel in the production area of ​​a power plant. The method first predicts whether the staff is likely to violate regulations by monitoring their detailed behaviors, and adjusts the monitoring intensity of the staff who violate regulations according to the importance of different production areas, thereby improving the monitoring and early warning effect and monitoring resource utilization rate of the early warning system. Summary of the invention

[0007] The purpose of the present invention is to provide a method and system for monitoring and warning of violations of regulations by personnel in the production area of ​​a power plant, so as to overcome the deficiencies in the background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution: a method for early warning based on monitoring and early warning of personnel violations in the production area of ​​a power plant, the early warning method comprising the following steps:

[0009] Obtain the number of production areas in the power plant and obtain information about each production area, the production area information including the function of the production area, obtain multiple historical data of each production area based on a database, and generate importance values ​​for each production area based on the multiple historical data;

[0010] All production areas are sorted according to their importance values. During the operation of each production area, the abnormal operation index and unauthorized operation frequency of the staff are obtained in real time. The abnormal operation index and unauthorized operation frequency of the equipment are first comprehensively analyzed through the abnormal analysis model. Then, after the parameters of the abnormal analysis model are tuned by the importance value of each production area, it is predicted whether the staff has violated the rules.

[0011] According to the prediction results, the staff's illegal behaviors are divided into no abnormality, first-level abnormality and second-level abnormality, and the subsequent monitoring and early warning strategies for the staff are generated based on the abnormal classification results of illegal behaviors.

[0012] Further, multiple historical data of each production area are obtained based on the database, and importance values ​​are generated for each production area based on the multiple historical data, and all production areas are sorted according to the importance values, including the following steps:

[0013] Obtain multiple historical data of each production area based on the database, including accident frequency, operation and maintenance cost, power generation contribution rate and regional idle rate;

[0014] The importance of the production area is obtained by comprehensively calculating the accident frequency, operation and maintenance cost, power generation contribution rate and regional idle rate;

[0015] After obtaining the importance values ​​of the production areas, all production areas are sorted from large to small according to the importance values.

[0016] Furthermore, predicting whether the staff has violated the rules includes the following steps:

[0017] The abnormal analysis model obtains the abnormal operation index and unauthorized operation frequency of the staff in real time, normalizes the abnormal operation index and the unauthorized operation frequency, maps the value range of the abnormal operation index and the unauthorized operation frequency to [0,1], obtains the normalized value of the abnormal operation index and the normalized value of the unauthorized operation frequency, and sums the normalized value of the abnormal operation index and the normalized value of the unauthorized operation frequency to obtain the staff abnormality coefficient;

[0018] After adjusting the first abnormality threshold and the second abnormality threshold set in the abnormality analysis model by assigning importance to each production area, the personnel abnormality coefficient is compared with the adjusted first abnormality threshold and the second abnormality threshold. If the personnel abnormality coefficient is less than or equal to the adjusted first abnormality threshold, it is predicted that the staff has no illegal behavior. If the personnel abnormality coefficient is greater than the adjusted first abnormality threshold and less than or equal to the adjusted second abnormality threshold, it is predicted that the staff has minor illegal behavior. If the personnel abnormality coefficient is greater than the adjusted second abnormality threshold, it is predicted that the staff has serious illegal behavior.

[0019] Further, adjusting the first abnormality threshold and the second abnormality threshold set in the abnormality analysis model by assigning importance to each production area includes the following steps:

[0020] Obtain the importance value of each production area. The larger the importance value, the smaller the first abnormal threshold and the second abnormal threshold of the production area need to be adjusted, so as to increase the monitoring of the staff in the production area with high importance. The adjustment algorithm is: In the formula, is the adjusted first abnormal threshold, is the adjusted second abnormal threshold, is the first abnormal threshold before adjustment, is the second abnormal threshold before adjustment, Z important Assign a value to importance.

[0021] Furthermore, the logic for obtaining the equipment abnormal operation index is as follows: before the staff operates the equipment, the staff needs to be identified. The identification information includes the staff's face and work number information. After the staff is successfully identified, the staff's real-time parameter setting information is recorded. After recording whether the setting value of each parameter is within the stable range, the abnormal deviation of each parameter is calculated. The expression is: Where C is the abnormal deviation, cs min ~cs max is the parameter stability range, cs z The real-time parameters input by the staff are used to comprehensively calculate the equipment abnormal operation index based on the abnormal deviation. The expression is: In the formula, SY is the equipment abnormal operation index, n is the number of real-time parameters input by the staff, C i is the abnormal deviation of the i-th real-time parameter.

[0022] Furthermore, the logic for obtaining the accident frequency is as follows: obtain the number of historical accidents in the production area, and divide the number of historical accidents by the total operating time of the power plant to obtain the accident frequency;

[0023] The logic for obtaining the operation and maintenance cost is as follows: obtain the labor cost, maintenance cost, energy cost, material cost, and construction cost of the production area, and sum up the labor cost, maintenance cost, energy cost, material cost, and construction cost to obtain the operation and maintenance cost;

[0024] The logic for obtaining the power generation contribution rate is as follows: obtain the power generation of the production area, and divide the power generation of the production area by the total power generation of the power plant to obtain the power generation contribution rate;

[0025] The logic for obtaining the regional idle rate is as follows: obtain the number of devices in the production area, divide the total idle time of each device by the total operating time of the power plant to obtain the device idle rate, and sum up the idle rates of all devices in the production area to obtain the regional idle rate.

[0026] Furthermore, a subsequent monitoring and early warning strategy for staff is generated based on the abnormal classification results of illegal behaviors, including the following steps:

[0027] No abnormality indicates that the staff has not violated any regulations. Level 2 abnormality indicates that the staff has committed serious violations, and the early warning system directly issues an early warning to the staff. Level 1 abnormality indicates that the staff has committed minor violations, and it is necessary to increase monitoring of the staff in the production area.

[0028] A monitoring and early warning system for personnel violations in the production area of ​​a power plant, comprising a regional importance ranking module, a behavior prediction module, and an early warning strategy generation module;

[0029] Regional importance ranking module: obtain the number of production areas in the power plant and obtain the information of each production area, including the function of the production area, obtain multiple historical data of each production area based on the database, generate importance values ​​for each production area based on multiple historical data, and sort all production areas according to the importance values;

[0030] Behavior prediction module: During the operation of each production area, the abnormal operation index of the equipment and the frequency of unauthorized operation of the staff are obtained in real time. The abnormal operation index and the frequency of unauthorized operation of the equipment are comprehensively analyzed through the abnormal analysis model. Then, after the parameters of the abnormal analysis model are adjusted by assigning importance to each production area, it is predicted whether the staff has violated the rules.

[0031] Early warning strategy generation module: According to the prediction results, the staff's illegal behaviors are divided into no abnormality, first-level abnormality and second-level abnormality, and the subsequent monitoring and early warning strategies for the staff are generated based on the abnormal classification results of illegal behaviors.

[0032] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0033] The present invention obtains multiple historical data of each production area through a database, and generates importance assignments for each production area based on multiple historical data, sorts all production areas according to the importance assignments, obtains the abnormal operation index of the equipment and the frequency of unauthorized operation of the staff in real time during the operation of each production area, first comprehensively analyzes the abnormal operation index of the equipment and the frequency of unauthorized operation through an abnormal analysis model, and then optimizes the parameters of the abnormal analysis model through the importance assignment of each production area, predicts whether the staff has illegal behavior, and divides the illegal behavior of the staff into no abnormality, primary abnormality and secondary abnormality according to the prediction results, and generates subsequent monitoring and early warning strategies for the staff based on the abnormal classification results of illegal behavior. The early warning system first predicts whether the staff has the possibility of illegal behavior by monitoring the detailed behavior of the staff, and adjusts the monitoring intensity of the staff with illegal behavior according to the importance of different production areas, so as to improve the monitoring and early warning effect and monitoring resource utilization rate of the early warning system. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] 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.

[0035] Figure 1 is a flow chart of the method of the present invention;

[0036] Figure 2 It is a system structure diagram of the present invention. DETAILED DESCRIPTION

[0037] 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.

[0038] See also Figure 1 As shown, the present embodiment describes a method for early warning based on monitoring and early warning of personnel violations in the production area of ​​a power plant, and the early warning method comprises the following steps:

[0039] The early warning system obtains the number of production areas in the power plant and the information of each production area, the production area information includes the function of the production area, obtains multiple historical data of each production area based on the database, and generates importance values ​​for each production area based on the multiple historical data; sorts all production areas according to the importance values; in the operation process of each production area, obtains the equipment abnormal operation index and unauthorized operation frequency of the staff in real time, first comprehensively analyzes the equipment abnormal operation index and unauthorized operation frequency through the abnormal analysis model, and then optimizes the abnormal analysis model parameters through the importance assignment of each production area, predicts whether the staff has any illegal behavior, and divides the illegal behavior of the staff into no abnormality, first-level abnormality and second-level abnormality according to the prediction results, and generates subsequent monitoring and early warning strategies for the staff based on the abnormal classification results of illegal behavior.

[0040] Among them, no abnormality indicates that the staff has not violated the rules, the second-level abnormality indicates that the staff's violation is serious, and the early warning system directly issues an early warning to the staff member, and the first-level abnormality indicates that the staff's violation is minor, and it is necessary to increase the monitoring of the staff member in the production area.

[0041] This application obtains multiple historical data of each production area through the database, and generates importance values ​​for each production area based on multiple historical data, sorts all production areas according to the importance values, obtains the abnormal operation index of the equipment and the frequency of unauthorized operation of the staff in real time during the operation of each production area, first comprehensively analyzes the abnormal operation index of the equipment and the frequency of unauthorized operation through the abnormal analysis model, and then optimizes the parameters of the abnormal analysis model through the importance value of each production area, predicts whether the staff has violated the rules, and divides the staff's violations into no abnormalities, first-level abnormalities and second-level abnormalities based on the prediction results, and generates subsequent monitoring and early warning strategies for the staff based on the abnormal division results of violations. The early warning system first predicts whether the staff may violate the rules by monitoring the detailed behavior of the staff, and adjusts the monitoring intensity of the staff with illegal behavior according to the importance of different production areas, so as to improve the monitoring and early warning effect and monitoring resource utilization of the early warning system.

[0042] The early warning system obtains the number of production areas in the power plant and obtains information about each production area, the production area information including the function of the production area, including the following steps:

[0043] The power plant production areas and functions mentioned in this application include:

[0044] 1. Boiler-House

[0045] Boiler body: includes combustion equipment, furnace, superheater, reheater, etc., used to burn fuel and heat water to generate steam.

[0046] Auxiliary equipment: such as blowers, induced draft fans, fuel delivery systems, etc., to ensure the normal operation of the boiler.

[0047] 2. Turbine-Hall

[0048] Steam turbine: Converts the thermal energy of high-pressure steam into mechanical energy to drive a generator.

[0049] Generator: Converts the mechanical energy of the turbine into electrical energy.

[0050] Condenser: Cools the steam to condense it into water, which then returns to the boiler for recycling.

[0051] 3. Fuel-Handling-Area

[0052] Fuel storage: coal bunkers, oil tanks, natural gas tanks, etc., used to store fuel for power generation.

[0053] Fuel delivery system: including coal conveyor belts, oil pumps, gas delivery pipelines, etc., to ensure a stable supply of fuel.

[0054] 4. Electrical Equipment Area

[0055] Transformer: used to increase or decrease voltage to meet different power transmission and usage requirements.

[0056] Switching station: controls the distribution and transmission of electricity and protects the safe operation of the power system.

[0057] Control room: monitors and controls the operation of the entire power plant.

[0058] 5. Water-Treatment-Area

[0059] Raw water treatment: Treat water from external sources to meet boiler water standards.

[0060] Circulating water system: used to cool the steam discharged from the turbine.

[0061] Wastewater treatment: Treat the wastewater generated during the power generation process to meet the discharge standards.

[0062] 6. Chemical Treatment Area

[0063] Water chemical treatment: Control the chemical composition of boiler water and circulating water to prevent corrosion and scaling.

[0064] Waste gas treatment: Treat the waste gas produced by combustion, remove harmful components and reduce pollutant emissions.

[0065] 7. Auxiliary-Facilities-Area

[0066] Maintenance workshop: used for equipment maintenance and repair.

[0067] Warehouse: storage of spare parts and consumables.

[0068] Emergency facilities: such as fire-fighting equipment, first aid equipment, etc.

[0069] 8. Switchyard-or-Substation-Area

[0070] Transmission lines: carry the electricity generated by generators to the grid.

[0071] Power distribution equipment: such as circuit breakers, disconnectors, etc., to ensure safe distribution and transmission of electricity.

[0072] 9. Ash-Handling-Area

[0073] Ash storage: storage of fly ash and bottom ash generated by coal-fired boilers.

[0074] Ash conveying system: transports ash from the boiler room to the ash storage or processing device.

[0075] 10. Environmental-Control-Area

[0076] Desulfurization device: removes sulfur dioxide from combustion exhaust gas.

[0077] Denitrification device: reduces the emission of nitrogen oxides.

[0078] Dust removal equipment: captures and removes particulate matter from flue gas.

[0079] Based on the database, multiple historical data of each production area are obtained, and importance values ​​are generated for each production area according to the multiple historical data, and all production areas are sorted according to the importance values, including the following steps:

[0080] Obtain multiple historical data of each production area based on the database, including accident frequency, operation and maintenance cost, power generation contribution rate and regional idle rate;

[0081] The accident frequency, operation and maintenance cost, power generation contribution rate and regional idle rate are calculated comprehensively to obtain the importance value of the production area. The expression is: In the formula, Z importantis the importance assignment, μ is the accident frequency, Operation and maintenance cost, τ is the contribution rate of power generation, σ is the regional idle rate, β, γ, δ, α are the proportional coefficients of accident frequency, operation and maintenance cost, contribution rate of power generation and regional idle rate, and β, γ, δ, α are all greater than 0;

[0082] The larger the importance value is, the more important the production area is in the power plant. Therefore, after obtaining the importance value of the production area, all production areas are sorted from large to small according to the importance value.

[0083] The logic for obtaining the accident frequency is as follows: obtain the number of historical accidents in the production area, and divide the number of historical accidents by the total operating time of the power plant to obtain the accident frequency. The greater the accident frequency, the more accidents occur in the production area during the operation of the power plant. Therefore, it is necessary to increase the monitoring of production areas with high accident frequencies.

[0084] The logic for obtaining the operation and maintenance cost is as follows: obtain the labor cost, maintenance cost, energy cost, material cost and construction cost of the production area, and then sum up the labor cost, maintenance cost, energy cost, material cost and construction cost to obtain the operation and maintenance cost. The larger the operation and maintenance cost, the more funds the production area has invested in the operation of the power plant, and the more priority attention it needs.

[0085] The logic for obtaining the power generation contribution rate is: obtain the power generation of the production area, and divide the power generation of the production area by the total power generation of the power plant to obtain the power generation contribution rate. The larger the power generation contribution rate, the greater the proportion of the production area in the total power generation of the power plant, and the more priority attention it needs.

[0086] The logic for obtaining the regional idle rate is as follows: obtain the number of equipment in the production area, divide the total idle time of each equipment by the total operating time of the power plant to obtain the equipment idle rate, and sum up the idle rates of all equipment in the production area to obtain the regional idle rate. The larger the regional idle rate, the less important the production area is relative to other areas.

[0087] During the operation of each production area, the abnormal operation index of the equipment and the frequency of unauthorized operation of the staff are obtained in real time, including the following steps:

[0088] The logic for obtaining the equipment abnormal operation index is as follows: before the staff operates the equipment, the staff needs to be identified. The identification information usually includes the staff's face and work number information. After the staff is successfully identified, the staff's real-time parameter setting information is recorded, and after recording whether the setting value of each parameter is within the stable range, the abnormal deviation of each parameter is calculated. The expression is: Where C is the abnormal deviation, cs min ~cs maxis the parameter stability range, cs z The real-time parameters input by the staff are used to comprehensively calculate the equipment abnormal operation index based on the abnormal deviation. The expression is: In the formula, SY is the equipment abnormal operation index, n is the number of real-time parameters input by the staff, C i is the abnormal deviation of the i-th real-time parameter;

[0089] Record the real-time parameter setting information of the staff. The real-time parameter setting information is the parameters input for controlling the operation of the equipment. For example, if the input real-time parameter is the input power of the equipment, then the corresponding input power has a corresponding input power stability range. In this application, the parameter stability range is given by the equipment manufacturer in the equipment manual and entered into the early warning system by the technician.

[0090] The larger the equipment abnormal operation index is, the more likely it is that the staff will violate regulations or engage in abnormal behavior when operating the equipment;

[0091] The logic for obtaining the frequency of unauthorized operations is as follows: within a period of time, when the device is in operation, the detection device set at the device detects whether the RFID card of the staff matches the device. When the RFID card of the staff does not match the device or no matching RFID card is detected, the number of times the staff operates the device without authorization is recorded, and the number of times the staff operates the device without authorization is divided by the monitoring time to obtain the frequency of unauthorized operations;

[0092] In actual applications, if there is an abnormality in the staff itself, the following situation may occur: the authorized staff encounters an emergency problem during the operation of the equipment and temporarily leaves without locking the equipment, and then the illegal personnel perform abnormal operations on the equipment. This application performs device matching detection on the staff's RFID card for such special situations.

[0093] First, the abnormal operation index of the equipment and the frequency of unauthorized operation are comprehensively analyzed through the abnormal analysis model. Then, after tuning the parameters of the abnormal analysis model by assigning importance to each production area, it is predicted whether the staff has violated the rules, including the following steps:

[0094] The abnormal analysis model obtains the abnormal operation index and unauthorized operation frequency of the staff in real time, normalizes the abnormal operation index and the unauthorized operation frequency, maps the value range of the abnormal operation index and the unauthorized operation frequency to [0,1], obtains the normalized value of the abnormal operation index and the normalized value of the unauthorized operation frequency, and sums the normalized value of the abnormal operation index and the normalized value of the unauthorized operation frequency to obtain the staff abnormality coefficient;

[0095] After adjusting the first abnormality threshold and the second abnormality threshold set in the abnormality analysis model by assigning importance to each production area, the personnel abnormality coefficient is compared with the adjusted first abnormality threshold and the second abnormality threshold. If the personnel abnormality coefficient is less than or equal to the adjusted first abnormality threshold, it is predicted that the staff has no illegal behavior. If the personnel abnormality coefficient is greater than the adjusted first abnormality threshold and less than or equal to the adjusted second abnormality threshold, it is predicted that the staff has minor illegal behavior. If the personnel abnormality coefficient is greater than the adjusted second abnormality threshold, it is predicted that the staff has serious illegal behavior.

[0096] Initial settings of the first anomaly threshold and the second anomaly threshold:

[0097] The first abnormality threshold and the second abnormality threshold are set according to the personnel abnormality coefficient, and each personnel abnormality set is similarly classified. The first abnormality threshold and the second abnormality threshold can be set according to the percentile method, and the personnel abnormality coefficients are arranged from small to large to form a personnel abnormality coefficient data set, and N% is set as a screening condition. The first abnormality threshold and the second abnormality threshold are set for the personnel abnormality coefficient data set with the N% screening condition. For example, 40% is used as the screening condition, and the personnel abnormality coefficients exceeding 40% of the data in the personnel abnormality coefficient data set are used as the second abnormality threshold, and 80% of the second abnormality threshold is taken as the first abnormality threshold.

[0098] Adjusting the first abnormality threshold and the second abnormality threshold set in the abnormality analysis model by assigning importance to each production area includes the following steps:

[0099] Obtain the importance value of each production area. The larger the importance value, the smaller the first abnormal threshold and the second abnormal threshold of the production area need to be adjusted, so as to increase the monitoring of the staff in the production area with high importance. The adjustment algorithm is: In the formula, is the adjusted first abnormal threshold, is the adjusted second abnormal threshold, is the first abnormal threshold before adjustment, is the second abnormal threshold before adjustment, Z important Assign a value to importance.

[0100] According to the prediction results, the staff's illegal behaviors are divided into no abnormality, first-level abnormality and second-level abnormality. Based on the abnormal classification results of illegal behaviors, the subsequent monitoring and early warning strategy of the staff is generated, including the following steps:

[0101] When it is predicted that the staff has no violation of regulations, the staff will be classified as normal; when it is predicted that the staff has a minor violation of regulations, the staff will be classified as a first-level abnormality; when it is predicted that the staff has a serious violation of regulations, the staff will be classified as a second-level abnormality. Normal camera monitoring will be carried out on the staff without abnormalities, and the monitoring of the first-level abnormal staff will be strengthened. For example, the movable camera in the production area will track and monitor the first-level abnormal staff based on face recognition technology. When the first-level abnormal staff has the following behaviors, an early warning signal will be issued:

[0102] Entering dangerous areas or unauthorized areas without authorization, violating special work regulations such as high-altitude work and safety lock-out procedures.

[0103] For second-level abnormal staff, early warning reminders will be issued directly.

[0104] The aforementioned personnel violation monitoring and early warning system based on the production area of ​​a power plant includes a regional importance ranking module, a behavior prediction module, and an early warning strategy generation module;

[0105] Regional importance ranking module: obtain the number of production areas in the power plant and obtain the information of each production area, including the function of the production area, obtain multiple historical data of each production area based on the database, and generate importance values ​​for each production area based on multiple historical data, sort all production areas according to the importance values, and send the importance values ​​to the behavior prediction module;

[0106] Behavior prediction module: During the operation of each production area, the abnormal operation index and unauthorized operation frequency of the staff are obtained in real time. The abnormal operation index and unauthorized operation frequency of the equipment are first analyzed comprehensively through the abnormal analysis model. Then, after the parameters of the abnormal analysis model are tuned by assigning importance to each production area, it is predicted whether the staff has any illegal behavior, and the prediction results are sent to the early warning strategy generation module;

[0107] Early warning strategy generation module: According to the prediction results, the staff's illegal behaviors are divided into no abnormalities, level one abnormalities and level two abnormalities. Based on the abnormal classification results of illegal behaviors, the subsequent monitoring and early warning strategies for the staff are generated. Among them, no abnormalities indicate that the staff has no illegal behaviors, level two abnormalities indicate that the staff's illegal behaviors are serious, and an early warning is directly issued to the staff. Level one abnormalities indicate that the staff's illegal behaviors are minor, and it is necessary to increase the monitoring of the staff in the production area.

[0108] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0109] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0110] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for monitoring and early warning of personnel violations in the production area of ​​a power plant, characterized by: The early warning method comprises the following steps: Obtain the number of production areas in the power plant and obtain information about each production area, the production area information including the function of the production area, obtain multiple historical data of each production area based on a database, and generate importance values ​​for each production area based on the multiple historical data; All production areas are sorted according to their importance values. During the operation of each production area, the abnormal operation index and unauthorized operation frequency of the staff are obtained in real time. The abnormal operation index and unauthorized operation frequency of the equipment are first comprehensively analyzed through the abnormal analysis model. Then, after the parameters of the abnormal analysis model are tuned by the importance value of each production area, it is predicted whether the staff has violated the rules. According to the prediction results, the staff's illegal behaviors are divided into no abnormality, first-level abnormality and second-level abnormality, and the subsequent monitoring and early warning strategies for the staff are generated based on the abnormal classification results of illegal behaviors.

2. A method for monitoring and early warning of personnel violations in the production area of ​​a power plant according to claim 1, characterized in that: Based on the database, multiple historical data of each production area are obtained, and importance values ​​are generated for each production area according to the multiple historical data, and all production areas are sorted according to the importance values, including the following steps: Obtain multiple historical data of each production area based on the database, including accident frequency, operation and maintenance cost, power generation contribution rate and regional idle rate; The importance of the production area is obtained by comprehensively calculating the accident frequency, operation and maintenance cost, power generation contribution rate and regional idle rate; After obtaining the importance values ​​of the production areas, all production areas are sorted from large to small according to the importance values.

3. A method for monitoring and early warning of personnel violations in the production area of ​​a power plant according to claim 2, characterized in that: Predicting whether a worker has committed a violation includes the following steps: The abnormal analysis model obtains the abnormal operation index and unauthorized operation frequency of the staff in real time, normalizes the abnormal operation index and the unauthorized operation frequency, maps the value range of the abnormal operation index and the unauthorized operation frequency to [0,1], obtains the normalized value of the abnormal operation index and the normalized value of the unauthorized operation frequency, and sums the normalized value of the abnormal operation index and the normalized value of the unauthorized operation frequency to obtain the staff abnormality coefficient; After adjusting the first abnormality threshold and the second abnormality threshold set in the abnormality analysis model by assigning importance to each production area, the personnel abnormality coefficient is compared with the adjusted first abnormality threshold and the second abnormality threshold. If the personnel abnormality coefficient is less than or equal to the adjusted first abnormality threshold, it is predicted that the staff has no illegal behavior. If the personnel abnormality coefficient is greater than the adjusted first abnormality threshold and less than or equal to the adjusted second abnormality threshold, it is predicted that the staff has minor illegal behavior. If the personnel abnormality coefficient is greater than the adjusted second abnormality threshold, it is predicted that the staff has serious illegal behavior.

4. A method for monitoring and early warning of personnel violations in the production area of ​​a power plant according to claim 3, characterized in that: Adjusting the first abnormality threshold and the second abnormality threshold set in the abnormality analysis model by assigning importance to each production area includes the following steps: Obtain the importance value of each production area. The larger the importance value, the smaller the first abnormal threshold and the second abnormal threshold of the production area need to be adjusted, so as to increase the monitoring of the staff in the production area with high importance. The adjustment algorithm is: In the formula, is the adjusted first abnormal threshold, is the adjusted second abnormal threshold, is the first abnormal threshold before adjustment, is the second abnormal threshold before adjustment, Z important Assign a value to importance.

5. A method for monitoring and early warning of personnel violations in the production area of ​​a power plant according to claim 4, characterized in that: The logic for obtaining the equipment abnormal operation index is as follows: before the staff operates the equipment, the staff needs to be identified. The identification information includes the staff's face and work number information. After the staff is successfully identified, the staff's real-time parameter setting information is recorded. After recording whether the setting value of each parameter is within the stable range, the abnormal deviation of each parameter is calculated. The expression is: Where C is the abnormal deviation, cs min ~cs max is the parameter stability range, cs Z The real-time parameters input by the staff are used to comprehensively calculate the equipment abnormal operation index based on the abnormal deviation. The expression is: In the formula, SY is the equipment abnormal operation index, n is the number of real-time parameters input by the staff, C i is the abnormal deviation of the i-th real-time parameter.

6. The method for monitoring and early warning of personnel violations in the production area of ​​a power plant according to claim 2 is characterized by: The logic for obtaining the accident frequency is as follows: obtain the number of accidents that occurred in the production area in history, and divide the number of accidents in history by the total operating time of the power plant to obtain the accident frequency; The logic for obtaining the operation and maintenance cost is as follows: obtain the labor cost, maintenance cost, energy cost, material cost, and construction cost of the production area, and sum up the labor cost, maintenance cost, energy cost, material cost, and construction cost to obtain the operation and maintenance cost; The logic for obtaining the power generation contribution rate is as follows: obtain the power generation of the production area, and divide the power generation of the production area by the total power generation of the power plant to obtain the power generation contribution rate; The logic for obtaining the regional idle rate is as follows: obtain the number of devices in the production area, divide the total idle time of each device by the total operating time of the power plant to obtain the device idle rate, and sum up the idle rates of all devices in the production area to obtain the regional idle rate.

7. The method for monitoring and early warning of personnel violations in the production area of ​​a power plant according to claim 1 is characterized by: The subsequent monitoring and early warning strategy for staff is generated based on the abnormal classification results of illegal behaviors, including the following steps: No abnormality indicates that the staff has not violated any regulations. Level 2 abnormality indicates that the staff has committed serious violations, and the early warning system directly issues an early warning to the staff. Level 1 abnormality indicates that the staff has committed minor violations, and it is necessary to increase monitoring of the staff in the production area.

8. A monitoring and early warning system for personnel violations in the production area of ​​a power plant, implemented by the early warning method according to any one of claims 1 to 7, characterized in that: It includes regional importance ranking module, behavior prediction module, and early warning strategy generation module; Regional importance ranking module: obtain the number of production areas in the power plant and obtain the information of each production area, including the function of the production area, obtain multiple historical data of each production area based on the database, generate importance values ​​for each production area based on multiple historical data, and sort all production areas according to the importance values; Behavior prediction module: During the operation of each production area, the abnormal operation index of the equipment and the frequency of unauthorized operation of the staff are obtained in real time. The abnormal operation index and the frequency of unauthorized operation of the equipment are comprehensively analyzed through the abnormal analysis model. Then, after the parameters of the abnormal analysis model are adjusted by assigning importance to each production area, it is predicted whether the staff has violated the rules. Early warning strategy generation module: According to the prediction results, the staff's illegal behaviors are divided into no abnormality, first-level abnormality and second-level abnormality, and the subsequent monitoring and early warning strategies for the staff are generated based on the abnormal classification results of illegal behaviors.

Images