Thermal power plant personnel safety early warning method and system based on image recognition

Abstract

The invention provides a thermal power plant personnel safety early warning method and system based on image recognition, and the method comprises the steps: calculating the safety score of a worker through the basic information of the worker, the historical skill training data, the violation frequency and the accident frequency through a personnel scoring module, building an image danger recognition model through an image recognition building module, and carrying out the early warning of the safety of the worker. According to the method, an identification model is established, the identification model is trained, a personnel early warning module divides behavior danger levels according to image label information identified by the identification model, the number of illegal behaviors of workers, working duration and safety scores, and an environment early warning module divides equipment safety levels according to the number of abnormal types of each equipment by obtaining equipment operation parameters. The method comprises the steps of obtaining historical environment data in each area of a power plant, dividing environment danger levels, establishing a danger identification model through an early warning and prediction module, predicting dangerous accidents according to behavior danger levels, equipment safety levels and environment danger levels, and performing early warning according to prediction results.

Description

Technical Field

[0001] The present invention relates to the technical field, and in particular to a personnel safety early warning method and system for a thermal power plant based on image recognition. Background Art

[0002] During the operation of thermal power plants, personnel safety management is a challenging task. Traditional safety management methods mainly rely on manual monitoring and written records, which is not only inefficient but also prone to omissions of safety hazards due to human factors. Therefore, there is an urgent need for a system that can automatically identify dangerous factors and provide real-time warnings to improve the efficiency and effectiveness of safety management.

[0003] In the prior art, the publication number CN109614946B discloses a method and system for protecting personnel in the coal transportation system of a thermal power plant based on image intelligent recognition technology. The invention uses a deep convolutional neural network model to analyze the image to be detected in the working area, monitors in real time and intelligently evaluates whether a person falls on the coal conveyor pulley in the coal conveyor device. After detecting the target, it feeds back to the PLC control unit to control the emergency braking of the coal conveyor belt, thereby ensuring the personal safety of the staff. However, the invention is only applicable to the safety protection of personnel in the coal transportation system of a thermal power plant. In fact, a thermal power plant also has personnel in the boiler system, turbine system and generator system. Since there are too many types of positions for personnel who need safety warnings, it is also necessary to consider multiple factors for safety warnings, especially the mutual influence between different factors and dangerous accidents. At the same time, the accuracy and timeliness of the warning are also particularly important.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide a thermal power plant personnel safety early warning method and system based on image recognition to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: A personnel safety early warning method for a thermal power plant based on image recognition, the specific steps comprising: Step 1: Distribute unique identification number plates to power plant workers to be warned, match the identification number plates with the workers' identities one by one, obtain each worker's basic information and historical skill training data, number of violations, number of accidents, and calculate the worker's safety score; Step 2: Obtain historical images of the thermal power plant containing types of violations by staff, types of accidents, and types of equipment abnormalities to form an image dataset. Select the types of violations, types of accidents, identification number plates, and types of equipment abnormalities in the historical images, mark the label data, and establish an image hazard recognition model. Use the image dataset as the input of the model and the label as the output to train the model. Step 3: Obtain real-time images as input to the trained image hazard recognition model, output the recognized image label information through the recognition model, calculate the behavior hazard coefficient according to the number of violations, working hours and safety scores of the staff during the daily working period, and classify the behavior hazard level and formulate early warning strategies to directly warn of the accident type; Step 4: By obtaining the equipment operating parameters, the equipment safety valuation is calculated according to the number of abnormal types of each equipment, and the equipment safety level is divided. The power plant is divided into regions, and the historical environmental data in each region of the power plant is obtained. The regional environmental risk coefficient is calculated based on the environmental data, and the environmental risk level is divided according to the environmental risk coefficient, and an early warning is issued; Step 5: Obtain the historical accident types in each area, establish a hazard identification model through Bayesian theorem, and form a factor data set based on the staff identification plate number, behavioral hazard level, equipment safety level, and environmental hazard level in each area to predict the type of future dangerous accidents and issue warnings based on the prediction results.

[0007] Furthermore, the basic information includes the post area, working years, identification plate number; The post areas include boiler area, steam turbine area, and power generation area; The skill training data includes the skill training duration, the number of skill training times, and the assessment score of each training.

[0008] Furthermore, the specific calculation steps for calculating the safety score of the staff are: Calculate the staff's business skill level. The specific calculation formula is:

[0009] in, For the staff's business skills level, The number of skill training sessions, For the Length of skill training, For the Training assessment scores, , is a positive integer; Calculate the safety score of the staff. The specific calculation formula is:

[0010] in, Score the safety of the staff, is the influence coefficient of the number of violations on the safety score, is the influence coefficient of the number of accidents on the safety score, is the number of violations, The number of accidents.

[0011] Furthermore, the types of violations include protection violations, production violations, and maintenance violations; The types of accidents include electric shock accidents, mechanical accidents, and scalding accidents; The equipment abnormality types include equipment displacement, loose connection, pipeline leakage, and line sparks; The tag data includes violation type, incident type, equipment anomaly type, and identification plate number.

[0012] Furthermore, the mathematical calculation formula for establishing the image hazard recognition model is: The hazard identification model is based on a CNN neural network, which specifically includes a convolutional layer, an activation layer, a pooling layer, and an output layer; Convolutional layer: extracts features from the bounding box and label of the input image through convolution operation, and the calculation formula is:

[0013] in, is the input image matrix, is the convolution kernel, are the coordinates of the output matrix, The convolution kernel is Row and The value of the column; The activation layer is calculated as:

[0014] in, The coordinates of the output matrix of the convolutional layer output; The calculation formula of the pooling layer is:

[0015] in, is the input matrix, is the maximum pooling output; The calculation formula of the output layer is:

[0016] in, is the output of the pooling layer, is the result of image recognition, is the weight, is the bias parameter.

[0017] Furthermore, the calculation formula of the behavior risk coefficient is:

[0018] in, is the behavioral risk factor, Score the safety of the staff, For working hours, The number of violations during each working day; The method for classifying behavior risk levels and formulating early warning strategies is as follows: when When the behavior is judged to be at level 1, no warning is issued; when When the behavior is judged to be at level 2, a warning is issued; when When the behavior is judged to be at level 3, a direct warning is issued and the person is asked to leave the job; in, , are the thresholds for different behavior risk levels. .

[0019] Furthermore, the equipment operation parameters include operating life, design service life, number of historical failures, and time of failure; The calculation formula for the equipment safety valuation is:

[0020] in, To provide equipment safety valuation, Design service life of the equipment. is the equipment operating life, For the The moment a failure occurs, For working hours, The number of each equipment abnormality type during each working period; The specific method for dividing the equipment security level is: when When the equipment is judged to be at level 1, no warning is issued; when When the equipment is judged to be at level 2, a warning is issued; when When the equipment is judged to be at level 3, an immediate warning is issued and the worker is asked to leave the work station; in, , They are the thresholds for different equipment security levels. .

[0021] Further, the environmental data includes coal dust particle concentration, temperature, humidity and noise; The calculation formula of the environmental risk factor is:

[0022] in, is the environmental risk factor, is the concentration of coal dust particles, is the temperature, For humidity, For noise, , , , are the weights of coal dust particle concentration, temperature, humidity and noise respectively. ; The specific method for classifying environmental hazard levels is as follows: when When the environmental danger level is judged to be level 1, no warning is issued; when When the environmental danger level is judged to be level 2, a warning is issued; when When the environmental danger level is judged to be level 3, an immediate warning is issued and the worker is asked to leave the work station; in, , They are the thresholds for different environmental hazard levels. .

[0023] Furthermore, the mathematical calculation formula of the factor data set is:

[0024] in, Identify the number plate number for the staff, The behavior risk level is is the device safety level, is the environmental hazard level; The specific steps of establishing the Bayesian-based comprehensive recognition model are: According to the regional location of dangerous events in historical data, the probability of each accident type is calculated, that is, the prior probability of each accident type:

[0025] in, For each accident type The prior probability of is the number of times the accident type occurred in historical data, is the indicative function, For the historical data Type of accident, , is the accident type in the historical data, Indicates an electric shock accident. Represents a mechanical accident. Represents a scalding accident. is the smoothing coefficient; The formula of the indicative function is:

[0026] Calculate the likelihood probability of the device feature set in each safety state:

[0027] in, For a given accident type The following influencing factor set is observed The probability of For a given accident type The following observation Factors that influence The probability of is the number of influencing factors, is a positive integer; Calculate the posterior probability of each accident type according to Bayes' theorem:

[0028] in, For accident type The posterior probability of is a normalizing constant; Establish a decision model for accident type occurrence:

[0029] in, The type of accident that was finally identified.

[0030] The present invention also provides a thermal power plant personnel safety warning system based on image recognition, the thermal power plant personnel safety warning system based on image recognition is used to execute the thermal power plant personnel safety warning method based on image recognition, comprising: A personnel scoring module is used to distribute unique identification number plates to the power plant staff to be warned, match the identification number plates with the workers' identities one by one, obtain the basic information and historical skill training data, number of violations, number of accidents of each staff member, and calculate the safety score of the staff member; An image recognition building module, which is used to obtain historical images containing types of violations by staff, types of accidents, and types of equipment abnormalities in a thermal power plant, form an image data set, select the types of violations, types of accidents, identification number plates, and types of equipment abnormalities in the historical images, mark label data, establish an image hazard recognition model, and use the image data set as the input of the model and the label as the output to train the model; A personnel warning module is used to obtain real-time images as input to a trained image hazard recognition model, output the recognized image label information through the recognition model, calculate the behavior hazard coefficient according to the number of violations, working hours and safety scores of the staff during the daily working period, and classify the behavior hazard level and formulate a warning strategy to directly warn of the accident type; An environmental early warning module is used to obtain equipment operating parameters, calculate equipment safety estimates according to the number of abnormal types of each equipment, and classify equipment safety levels, divide the power plant into regions, obtain historical environmental data in each region of the power plant, calculate regional environmental risk factors according to the environmental data, classify environmental risk levels according to the environmental risk factors, and issue early warnings; The early warning prediction module is used to obtain the historical accident types in each area, establish a hazard identification model through Bayesian theorem, form a factor data set based on the staff identification plate number, behavior hazard level, equipment safety level, and environmental hazard level in each area, predict the type of future dangerous accidents, and issue an early warning based on the prediction results.

[0031] Compared with the prior art, the present invention has the following beneficial effects: the present invention calculates the safety score of the staff through the basic information and historical skill training data, number of violations, and number of accidents of the staff in the personnel scoring module, establishes an image hazard recognition model through the image recognition construction module, and trains the recognition model; the personnel early warning module divides the behavior hazard level according to the image label information recognized by the recognition model, the number of violations of the staff, the working hours and the safety score; the environmental early warning module divides the equipment safety level according to the number of abnormal types of each equipment by obtaining the equipment operating parameters; divides the environmental hazard level by obtaining the historical environmental data in each area of ​​the power plant; establishes a hazard recognition model through the early warning prediction module, predicts dangerous accidents according to the behavior hazard level, equipment safety level and environmental hazard level, and issues an early warning based on the prediction results; The present invention conducts quantitative scoring and risk assessment of staff violations, and comprehensively analyzes possible safety hazards by combining equipment operating parameters and environmental historical data. The hazard identification model created by multi-dimensional analysis and early warning prediction modules can more accurately predict potential accidents and issue early warnings before danger occurs. This method not only greatly improves the accuracy and timeliness of early warnings, but also effectively reduces safety hazards caused by human factors and management omissions; The present invention establishes a hazard identification model through Bayesian theorem, which can take into account the mutual influence between different factors and dangerous accidents. Through this information fusion, the actual risks in the power plant can be evaluated more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of the overall method flow of the present invention; Figure 2 It is a schematic diagram of the overall system structure of the present invention. DETAILED DESCRIPTION

[0033] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0034] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0035] Example:

[0036] See also Figure 1 , the present invention provides a technical solution: A personnel safety early warning method for a thermal power plant based on image recognition, the specific steps comprising: Step 1: Distribute unique identification number plates to power plant workers who are to be warned, match the identification number plates with the workers' identities one by one, obtain each worker's basic information and historical skill training data, number of violations, number of accidents, and calculate the worker's safety score.

[0037] Each worker is issued a unique identification number plate to ensure that everyone can be accurately identified. This allows the system to clearly associate data and events with specific workers during monitoring and analysis. The identification number plate is tied to the worker's identity information, basic information, and historical records. This means that any monitored behavioral data can be instantly associated with the person's comprehensive history for personalized analysis and early warning.

[0038] In this embodiment, the basic information includes job area, years of service, and identification plate number; The post areas include boiler area, steam turbine area, and power generation area; The skill training data includes the skill training duration, the number of skill training times, and the assessment score of each training.

[0039] Workers in different areas face different safety issues. For example, high temperature, high pressure and mechanical operation areas are generally considered to have higher risks. Another example is that workers in the boiler area go to the turbine area. Due to the different equipment, workers in the boiler area cannot operate the equipment in the turbine area skillfully, which is dangerous to both personnel and equipment.

[0040] A staff member's longer working tenure usually reflects rich experience, which helps to more effectively identify and avoid potential safety risks, and thus has a higher hazard avoidance ability. A longer training period generally leads to better mastery of safety skills and improved ability to identify and avoid hazards. Multiple training opportunities help consolidate safety awareness and skill operations. Higher training assessment scores indicate a good grasp of safety knowledge and execution capabilities, which will positively affect the score.

[0041] Multiple violation records may reflect that the worker has weak safety awareness or inadequate implementation of safety regulations within the power plant, increasing the probability of dangerous accidents. Multiple accident records may indicate that the worker has a higher risk tendency and is more likely to have dangerous accidents.

[0042] In this embodiment, the specific calculation steps for calculating the safety score of the staff member are: Calculate the staff's business skill level. The specific calculation formula is:

[0043] in, For the staff's business skills level, The number of skill training sessions, For the Length of skill training, For the Training assessment scores, , is a positive integer; Calculate the safety score of the staff. The specific calculation formula is:

[0044] in, Score the safety of the staff, is the influence coefficient of the number of violations on the safety score, is the influence coefficient of the number of accidents on the safety score, is the number of violations, The number of accidents.

[0045] The safety score reflects the worker's safety awareness and the ability to respond to and avoid danger. A high score may indicate that the worker has received adequate training, has few violations and accident records, has a high safety awareness, and has a high ability to respond to and avoid danger. On the contrary, the safety awareness is not strong and dangerous accidents cannot be effectively handled. The safety score is not just a static value, but a dynamic indicator that changes with time and events. This helps to record and reflect the changing trends of workers' safety awareness and ability to respond to danger in a specific period of time.

[0046] Step 2: Obtain historical images of the thermal power plant that contain types of staff violations, accident types, and equipment abnormalities to form an image dataset. Select the types of violations, accident types, identification number plates, and equipment abnormalities in the historical images, mark the label data, and establish an image hazard recognition model. Use the image dataset as the input of the model and the label as the output to train the model.

[0047] In this embodiment, the types of violation behaviors include protection violation, production violation, and maintenance violation; The types of accidents include electric shock accidents, mechanical accidents, and scalding accidents; The equipment abnormality types include equipment displacement, loose connection, pipeline leakage, and line sparks; The tag data includes violation type, incident type, equipment anomaly type, and identification plate number.

[0048] Protection violations refer to workers' failure to correctly wear or use necessary protective equipment, or failure to comply with the rules of the protection area, such as failure to wear safety helmets, goggles, protective gloves, and failure to wear prescribed protective clothing in areas with high temperature, high pressure or electrical hazards. Production violations refer to workers' violation of regulations in actual production operations, which may directly threaten equipment and personal safety, such as failure to operate key equipment such as high-pressure boilers and turbines in accordance with regulations. Maintenance violations refer to workers' failure to comply with safety regulations during equipment maintenance and overhaul, such as failure to set up warning signs during the overhaul process to prevent others from accidentally touching them.

[0049] Obtain historical images containing types of staff violation behaviors, accident types, and equipment abnormality types in thermal power plants to form an image dataset. That is, a historical image contains one or more of these features, such as types of staff violation behaviors, accident types, and equipment abnormality types. Use historical images as the input of the image hazard recognition model and labels as output. Train the model to identify these features in images through real-time images.

[0050] The image hazard recognition model based on CNN neural network is established because CNN neural network has powerful feature extraction ability, efficient multi-label classification ability and robustness in adapting to complex environments when processing image data. The environment of thermal power plants is complex, and there may be dynamic lighting changes, background interference (such as equipment operation, smoke) and various types of dangerous behaviors. CNN neural network can capture local spatial features through convolution layers, reduce background interference through pooling layers, and abstract key features layer by layer to adapt to these complex environments.

[0051] For the application scenario of personnel safety warning in thermal power plants, the CNN neural network can efficiently identify violations, accident types and equipment anomalies, help achieve automated and real-time safety monitoring, and provide important guarantees for accident prevention and production safety.

[0052] In this embodiment, the mathematical calculation formula for establishing the image hazard recognition model is: The hazard identification model is based on a CNN neural network, which specifically includes a convolutional layer, an activation layer, a pooling layer, and an output layer; Convolutional layer: extracts features from the bounding box and label of the input image through convolution operation, and the calculation formula is:

[0053] in, is the input image matrix, is the convolution kernel, are the coordinates of the output matrix, The convolution kernel is Row and The value of the column; The activation layer is calculated as:

[0054] in, The coordinates of the output matrix of the convolutional layer output; The calculation formula of the pooling layer is:

[0055] in, is the input matrix, is the maximum pooling output; The calculation formula of the output layer is:

[0056] in, is the output of the pooling layer, is the result of image recognition, is the weight, is the bias parameter.

[0057] Step 3: Obtain real-time images as input to the trained image hazard recognition model. Output the recognized image label information through the recognition model. Calculate the behavior hazard coefficient based on the number of violations, working hours and safety scores of the staff during daily work. Classify the behavior hazard level and formulate an early warning strategy to directly warn of the accident type.

[0058] The frequency of violations is an important indicator to measure the safety awareness and actual operation norms of staff. People who violate the rules often have higher potential safety hazards in their operations. By counting the number of violations, it can directly reflect the safety operation performance of staff in a specific time period. A high number of violations can trigger a higher level of behavioral danger, which requires special attention to avoid further expansion of hidden dangers.

[0059] Working for a long time will lead to accumulated fatigue and increase the risk of negligence and misoperation. Introducing working hours as a calculation factor can dynamically reflect the impact of fatigue on safety risks.

[0060] By comprehensively considering the number of violations, working hours and safety scores, the calculation of the behavioral risk coefficient is more comprehensive and scientific, avoiding the one-sidedness of single-factor assessment. This method can dynamically reflect the safety risks of employees under different working conditions and improve the accuracy of risk assessment.

[0061] In this embodiment, the calculation formula of the behavior risk coefficient is:

[0062] in, is the behavioral risk factor, Score the safety of the staff, For working hours, The number of violations during each working day; The method for classifying behavior risk levels and formulating early warning strategies is as follows: when When the behavior is judged to be at level 1, no warning is issued; when When the behavior is judged to be at level 2, a warning is issued; when When the behavior is judged to be at level 3, a direct warning is issued and the person is asked to leave the job; in, , are the thresholds for different behavior risk levels. .

[0063] Step 4: By obtaining the equipment operating parameters, calculate the equipment safety valuation according to the number of abnormal types of each equipment, and divide the equipment safety level, divide the power plant into areas, obtain the historical environmental data in each area of ​​the power plant, calculate the regional environmental hazard factor based on the environmental data, divide the environmental hazard level according to the environmental hazard factor, and issue an early warning.

[0064] In this embodiment, the equipment operation parameters include operating life, design service life, number of historical failures, and time of failure; The calculation formula for the equipment safety valuation is:

[0065] in, To provide equipment safety valuation, Design service life of the equipment. is the equipment operating life, For the The moment a failure occurs, For working hours, The number of each device exception type during each working period.

[0066] The equipment safety valuation reflects the current safety status of the equipment. The higher the equipment safety valuation, the safer the operating status, and the lower the side, the more warning is needed. As the equipment's operating life increases, the physical wear and aging of the equipment increases, the performance of key components (such as pipes, bearings, and circuits) may decline, and the probability of failure increases. The failure of aging equipment may cause fire, explosion, or electrical hazards, directly threatening the life safety of workers. The comparison between the designed service life and the actual operating life can predict the future risks of the equipment. Equipment with frequent failures may have potential systemic defects or fatigue damage, which, if not repaired in time, will lead to more serious accidents. Equipment with frequent failures may be unstable, increase the uncertainty of the operating environment, and pose a threat to personnel working near the equipment.

[0067] The specific method for dividing the equipment security level is: when When the equipment is judged to be at level 1, no warning is issued; when When the equipment is judged to be at level 2, a warning is issued; when When the equipment is judged to be at level 3, an immediate warning is issued and the worker is asked to leave the work station; in, , They are the thresholds for different equipment security levels. .

[0068] In this embodiment, the environmental data includes coal dust particle concentration, temperature, humidity and noise.

[0069] The calculation formula of the environmental risk factor is:

[0070] in, is the environmental risk factor, is the concentration of coal dust particles, is the temperature, For humidity, For noise, , , , are the weights of coal dust particle concentration, temperature, humidity and noise respectively. .

[0071] Coal dust is a common risk factor in thermal power plants. Long-term exposure to high-concentration coal dust may lead to serious health problems such as respiratory diseases (such as pneumoconiosis) and lung cancer. In addition, the tiny particles of coal dust can deeply penetrate the lungs, increasing the risk of chronic respiratory diseases. When coal dust is in a high-concentration environment and encounters a fire source (such as electrical equipment failure, heat source, etc.), it may explode. Coal dust explosions can cause equipment damage and serious casualties.

[0072] The temperature inside a thermal power plant is usually high, especially in the boiler room, unit equipment and other areas. High temperature environment can easily cause heat stress reactions such as heat stroke and heat exhaustion, especially when personnel are exposed for a long time. High temperature can also cause safety accidents such as equipment overheating and fire.

[0073] An environment with excessive humidity (especially in humid climates or near equipment) can cause electrical equipment to short-circuit or corrode, leading to fire or electric shock. In addition, excessive humidity can also increase discomfort and increase health problems such as heat stroke and eczema.

[0074] The noise inside a thermal power plant usually comes from steam units, pumps, fans and other equipment. Being in a high-noise environment for a long time can easily lead to hearing damage (such as noise-induced hearing loss), fatigue and stress, and may even cause staff to make mistakes and increase the probability of accidents. Excessive noise also means that there are safety hazards in the equipment.

[0075] By real-time monitoring of hazardous factors such as coal dust concentration and temperature, measures can be taken before explosion, fire or overheating to prevent accidents. Temperature and humidity monitoring helps identify possible overload or short circuit risks of equipment, and timely maintenance measures can be taken to reduce equipment failure rate and the probability of danger.

[0076] The specific method for classifying environmental hazard levels is as follows: when When the environmental danger level is judged to be level 1, no warning is issued; when When the environmental danger level is judged to be level 2, a warning is issued; when When the environmental danger level is judged to be level 3, an immediate warning is issued and the worker is asked to leave the work station; in, , They are the thresholds for different environmental hazard levels. .

[0077] Step 5: Obtain the historical accident types in each area, establish a hazard identification model through Bayesian theorem, and form a factor data set based on the staff identification plate number, behavioral hazard level, equipment safety level, and environmental hazard level in each area to predict the type of future dangerous accidents and issue warnings based on the prediction results.

[0078] In this embodiment, the mathematical calculation formula of the factor data set is:

[0079] in, Identify the number plate number for the staff, The behavior risk level is is the device safety level, Environmental hazard level.

[0080] Factors such as worker identification number plate number, behavioral hazard level, equipment safety level, and environmental hazard level do not exist independently, but are interrelated and influence each other. For example, poor environmental conditions will increase the risk of equipment failure, requiring workers to perform more manual intervention, which increases the possibility of accidents caused by human error. At the same time, people who are not in the post area and break into the post area will increase the risk of accidents. The accumulation of multiple factors may lead to a higher overall risk level. For example, although an employee scores high in safety behavior, if he works near a piece of equipment that keeps malfunctioning and the surrounding environment is also bad, the overall risk is still high.

[0081] Through the quantitative assessment of these factors, high-risk areas and operations can be identified in advance, specific safety countermeasures can be formulated, and accidents can be reduced by providing early warning to personnel.

[0082] Bayesian models are based on probability theory and can effectively handle uncertainty and incomplete data, which is a core capability for making predictions in complex environments. The prediction of accidents is based on known probabilities rather than deterministic events, which makes the predictions more flexible and adaptable.

[0083] Bayesian theorem is well suited to incorporate historical accident data as prior knowledge and to update it based on new observations. This dynamic updating capability helps maintain the accuracy and relevance of predictions as the environment changes.

[0084] In thermal power plants, accidents are often affected by a variety of factors, including human behavior, equipment status, environmental conditions, etc. The Bayesian model can integrate these different types of variables to provide a comprehensive risk assessment. By comprehensively considering multiple influencing factors and their interrelationships, the Bayesian model can reduce the false alarm rate and missed alarm rate and improve the reliability of safety warnings. It effectively improves the accuracy of predictions, reduces the possibility of accidents, and ensures the safety of personnel and equipment.

[0085] The specific steps of establishing the Bayesian-based comprehensive recognition model are: According to the regional location of dangerous events in historical data, the probability of each accident type is calculated, that is, the prior probability of each accident type:

[0086] in, For each accident type The prior probability of is the number of times the accident type occurred in historical data, is the indicative function, For the historical data Type of accident, , is the accident type in the historical data, Indicates an electric shock accident. Represents a mechanical accident. Represents a scalding accident. is the smoothing coefficient; The formula of the indicative function is: ; Calculate the likelihood probability of the device feature set in each safety state:

[0087] in, For a given accident type The following influencing factor set is observed The probability of For a given accident type The following observation Factors that influence The probability of is the number of influencing factors, is a positive integer; Calculate the posterior probability of each accident type according to Bayes' theorem:

[0088] in, For accident type The posterior probability of is a normalizing constant; Establish a decision model for accident type occurrence:

[0089] in, The type of accident that was finally identified.

[0090] The present invention also provides a thermal power plant personnel safety warning system based on image recognition, the thermal power plant personnel safety warning system based on image recognition is used to execute the thermal power plant personnel safety warning method based on image recognition, comprising: A personnel scoring module is used to distribute unique identification number plates to the power plant staff to be warned, match the identification number plates with the workers' identities one by one, obtain the basic information and historical skill training data, number of violations, number of accidents of each staff member, and calculate the safety score of the staff member; An image recognition building module, which is used to obtain historical images containing types of violations by staff, types of accidents, and types of equipment abnormalities in a thermal power plant, form an image data set, select the types of violations, types of accidents, identification number plates, and types of equipment abnormalities in the historical images, mark label data, establish an image hazard recognition model, and use the image data set as the input of the model and the label as the output to train the model; A personnel warning module is used to obtain real-time images as input to a trained image hazard recognition model, output the recognized image label information through the recognition model, calculate the behavior hazard coefficient according to the number of violations, working hours and safety scores of the staff during the daily working period, and classify the behavior hazard level and formulate a warning strategy to directly warn of the accident type; An environmental early warning module is used to obtain equipment operating parameters, calculate equipment safety estimates according to the number of abnormal types of each equipment, and classify equipment safety levels, divide the power plant into regions, obtain historical environmental data in each region of the power plant, calculate regional environmental risk factors according to the environmental data, classify environmental risk levels according to the environmental risk factors, and issue early warnings; The early warning prediction module is used to obtain the historical accident types in each area, establish a hazard identification model through Bayesian theorem, form a factor data set based on the staff identification plate number, behavior hazard level, equipment safety level, and environmental hazard level in each area, predict the type of future dangerous accidents, and issue an early warning based on the prediction results.

[0091] 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.

[0092] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0093] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0094] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the 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.

Claims

1. A personnel safety early warning method for a thermal power plant based on image recognition, characterized in that: The specific steps include: Step 1: Distribute unique identification number plates to power plant workers to be warned, match the identification number plates with the workers' identities one by one, obtain each worker's basic information and historical skill training data, number of violations, number of accidents, and calculate the worker's safety score; Step 2: Obtain historical images of the thermal power plant containing types of violations by staff, types of accidents, and types of equipment abnormalities to form an image dataset. Select the types of violations, types of accidents, identification number plates, and types of equipment abnormalities in the historical images, mark the label data, and establish an image hazard recognition model. Use the image dataset as the input of the model and the label as the output to train the model. Step 3: Obtain real-time images as input to the trained image hazard recognition model, output the recognized image label information through the recognition model, calculate the behavior hazard coefficient according to the number of violations, working hours and safety scores of the staff during the daily working period, and classify the behavior hazard level and formulate early warning strategies to directly warn of the accident type; Step 4: By obtaining the equipment operating parameters, the equipment safety valuation is calculated according to the number of abnormal types of each equipment, and the equipment safety level is divided. The power plant is divided into regions, and the historical environmental data in each region of the power plant is obtained. The regional environmental risk coefficient is calculated based on the environmental data, and the environmental risk level is divided according to the environmental risk coefficient, and an early warning is issued; Step 5: Obtain the historical accident types in each area, establish a hazard identification model through Bayesian theorem, and form a factor data set based on the staff identification plate number, behavioral hazard level, equipment safety level, and environmental hazard level in each area to predict the type of future dangerous accidents and issue warnings based on the prediction results.

2. The method for early warning of personnel safety in a thermal power plant based on image recognition according to claim 1, characterized in that: The basic information includes job location, years of service, and identification plate number; The post areas include boiler area, steam turbine area, and power generation area; The skill training data includes the skill training duration, the number of skill training times, and the assessment score of each training.

3. The method for early warning of personnel safety in a thermal power plant based on image recognition according to claim 2 is characterized in that: The specific calculation steps for calculating the safety score of the staff member are: Calculate the staff's business skill level. The specific calculation formula is: ， in, For the staff's business skills level, The number of skill training sessions, For the Length of skill training, For the Training assessment scores, , is a positive integer; Calculate the safety score of the staff. The specific calculation formula is: ， in, Score the safety of the staff, is the influence coefficient of the number of violations on the safety score, is the influence coefficient of the number of accidents on the safety score, is the number of violations, The number of accidents.

4. The method for early warning of personnel safety in a thermal power plant based on image recognition according to claim 1, characterized in that: The types of violations include protection violations, production violations, and maintenance violations; The types of accidents include electric shock accidents, mechanical accidents, and scalding accidents; The equipment abnormality types include equipment displacement, loose connection, pipeline leakage, and line sparks; The tag data includes violation type, incident type, equipment anomaly type, and identification plate number.

5. The method for early warning of personnel safety in a thermal power plant based on image recognition according to claim 1, characterized in that: The mathematical calculation formula for establishing the image hazard recognition model is: The hazard identification model is based on a CNN neural network, which specifically includes a convolutional layer, an activation layer, a pooling layer, and an output layer; Convolutional layer: extracts features from the bounding box and label of the input image through convolution operation, and the calculation formula is: ， in, is the input image matrix, is the convolution kernel, are the coordinates of the output matrix, The convolution kernel is Row and The value of the column; The activation layer is calculated as: ， in, The coordinates of the output matrix of the convolutional layer output; The calculation formula of the pooling layer is: ， in, is the input matrix, is the maximum pooling output; The calculation formula of the output layer is: ， in, is the output of the pooling layer, is the result of image recognition, is the weight, is the bias parameter.

6. The method for early warning of personnel safety in a thermal power plant based on image recognition according to claim 1, characterized in that: The calculation formula of the behavior risk coefficient is: ， in, is the behavioral risk factor, Score the safety of the staff, For working hours, The number of violations during each working day; The method for classifying behavior risk levels and formulating early warning strategies is as follows: when When the behavior is judged to be at level 1, no warning is issued; when When the behavior is judged to be at level 2, a warning is issued; when When the behavior is judged to be at level 3, a warning will be issued immediately and the person will be removed from work. in, , are the thresholds for different behavior risk levels. .

7. The method for early warning of personnel safety in a thermal power plant based on image recognition according to claim 1, characterized in that: The equipment operation parameters include operating life, design service life, number of historical failures, and time of failure; The calculation formula for the equipment safety valuation is: ， in, To provide equipment safety valuation, Design service life of the equipment. is the equipment operating life, For the The moment a failure occurs, For working hours, The number of each equipment abnormality type during each working period; The specific method for dividing the equipment security level is: when When the equipment is judged to be at level 1, no warning is issued; when When the equipment is judged to be at level 2, a warning is issued; when When the equipment is judged to be at level 3, an immediate warning is issued and the worker is asked to leave the work station; in, , They are the thresholds for different equipment security levels. .

8. The method for early warning of personnel safety in a thermal power plant based on image recognition according to claim 1, characterized in that: The environmental data include coal dust particle concentration, temperature, humidity and noise; The calculation formula of the environmental risk factor is: ， in, is the environmental risk factor, is the concentration of coal dust particles, is the temperature, For humidity, For noise, , , , are the weights of coal dust particle concentration, temperature, humidity and noise respectively. ; The specific method for classifying environmental hazard levels is as follows: when When the environmental danger level is judged to be level 1, no warning is issued; when When the environmental danger level is judged to be level 2, a warning is issued; when When the environmental danger level is judged to be level 3, an immediate warning is issued and the worker is asked to leave the work station; in, , They are the thresholds for different environmental hazard levels. .

9. The method for early warning of personnel safety in a thermal power plant based on image recognition according to claim 1, characterized in that: The mathematical calculation formula of the factor data set is: ， in, Identify the number plate number for the staff, The behavior risk level is is the device safety level, is the environmental hazard level; The specific steps of establishing the Bayesian-based comprehensive recognition model are: According to the regional location of dangerous events in historical data, the probability of each accident type is calculated, that is, the prior probability of each accident type: ， in, For each accident type The prior probability of is the number of times the accident type occurred in historical data, is the indicative function, For the historical data Type of accident, , is the accident type in the historical data, Indicates an electric shock accident. Represents a mechanical accident. Represents a scalding accident. is the smoothing coefficient; The formula of the indicative function is: ； Calculate the likelihood probability of the device feature set in each safety state: ， in, For a given accident type The following influencing factor set is observed The probability of For a given accident type Next, observe Factors that influence The probability of is the number of influencing factors, is a positive integer; Calculate the posterior probability of each accident type according to Bayes' theorem: ， in, For accident type The posterior probability of is a normalizing constant; Establish a decision model for accident type occurrence: ， in, The type of accident that was finally identified.

10. A thermal power plant personnel safety warning system based on image recognition, characterized in that: The thermal power plant personnel safety warning system based on image recognition is used to execute the thermal power plant personnel safety warning method based on image recognition according to any one of claims 1 to 9, comprising: A personnel scoring module is used to distribute unique identification number plates to the power plant staff to be warned, match the identification number plates with the workers' identities one by one, obtain the basic information and historical skill training data, number of violations, number of accidents of each staff member, and calculate the safety score of the staff member; An image recognition building module, which is used to obtain historical images containing types of violations by staff, types of accidents, and types of equipment abnormalities in a thermal power plant, form an image data set, select the types of violations, types of accidents, identification number plates, and types of equipment abnormalities in the historical images, mark label data, establish an image hazard recognition model, and use the image data set as the input of the model and the label as the output to train the model; A personnel warning module is used to obtain real-time images as input to a trained image hazard recognition model, output the recognized image label information through the recognition model, calculate the behavior hazard coefficient according to the number of violations, working hours and safety scores of the staff during the daily working period, and classify the behavior hazard level and formulate a warning strategy to directly warn of the accident type; An environmental early warning module is used to obtain equipment operating parameters, calculate equipment safety estimates according to the number of abnormal types of each equipment, and classify equipment safety levels, divide the power plant into regions, obtain historical environmental data in each region of the power plant, calculate regional environmental risk factors according to the environmental data, classify environmental risk levels according to the environmental risk factors, and issue early warnings; The early warning prediction module is used to obtain the historical accident types in each area, establish a hazard identification model through Bayesian theorem, form a factor data set based on the staff identification plate number, behavior hazard level, equipment safety level, and environmental hazard level in each area, predict the type of future dangerous accidents, and issue an early warning based on the prediction results.

Images