Artificial intelligence-based power engineering site personnel supervision system and method

Abstract

The application relates to the technical field of personnel supervision of artificial intelligence, and particularly discloses a power engineering site personnel supervision system and method based on artificial intelligence, which is characterized in that, according to the electromagnetic environment characteristics of a power engineering site, an electromagnetic shielding room is built, the electromagnetic interference condition is simulated, the response data of an intelligent safety helmet are tested, and the stability of the intelligent safety helmet in a high electromagnetic interference environment is evaluated; the working frequency abnormality index and the signal strength abnormality index of the intelligent safety helmet are calculated by using algorithms such as fast Fourier transform and wavelet transform, so that the communication ability of the intelligent safety helmet is evaluated; based on the test results of the intelligent safety helmet, the intelligent safety helmet is divided into qualified and unqualified intelligent safety helmets, so that only qualified equipment is used to supervise construction personnel; by monitoring the position, health condition and environmental change data of workers in real time, a risk evaluation model is established by using a gradient boosting tree algorithm, the risk coefficient of a construction site is calculated, and corresponding personnel supervision and early warning response are implemented according to the risk level.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of personnel supervision based on artificial intelligence, and particularly relates to a power engineering site personnel supervision system and method based on artificial intelligence. BACKGROUND

[0002] With the continuous progress of Internet of Things technology, sensor technology and artificial intelligence technology, traditional personnel supervision methods are gradually replaced by modern intelligent supervision systems. Intelligent supervision systems can obtain real-time location information, health status and environmental conditions of construction personnel by integrating location tracking, health monitoring, environmental change monitoring and other sensors, providing important data support for safety management of construction sites. However, in high-risk environments such as substations and high-voltage power lines, the stability and reliability of intelligent devices are often affected by electromagnetic interference, leading to unstable signal transmission and affecting the accuracy of real-time monitoring and the timeliness of emergency response.

[0003] The prior art has the following disadvantages:

[0004] The existing intelligent safety helmet has the problem of insufficient electromagnetic compatibility in the application of power engineering site, specifically, the existing intelligent safety helmet often fails to fully consider the complex and high-intensity electromagnetic interference in the power engineering environment, which may cause the device to have microprocessor operation errors, unstable wireless communication module connection or data transmission interruption and other faults in actual use, thereby affecting the effectiveness of worker safety monitoring and personal protection functions. To make up for this deficiency, the electromagnetic environment under actual working conditions is accurately simulated, and the electromagnetic compatibility test and performance evaluation of the intelligent safety helmet are strictly carried out to ensure that it can maintain stable and reliable operation under strong electromagnetic radiation conditions, thereby improving the safety management level and work efficiency of the power engineering site. SUMMARY

[0005] The purpose of the present application is to provide a power engineering site personnel supervision system and method based on artificial intelligence to solve the problems in the background.

[0006] The purpose of the present application can be achieved by the following technical solutions:

[0007] The power engineering site personnel supervision method based on artificial intelligence comprises the following steps:

[0008] S1: According to the electromagnetic environment characteristics of the power engineering site, determine the electromagnetic frequency range and electromagnetic intensity level for testing to simulate actual electromagnetic interference conditions;

[0009] Design an electromagnetic shielding chamber to ensure that the electromagnetic interference conditions are adjustable;

[0010] S2: Placing the intelligent safety helmet in an electromagnetic shielding room, gradually increasing the electromagnetic field intensity, recording the response data of the intelligent safety helmet in real time, analyzing the real-time response data, and evaluating the stability of data transmission of the intelligent safety helmet;

[0011] The response data includes: working frequency and signal strength, and the signal strength is the strength of the intelligent safety helmet receiving or sending wireless signals;

[0012] S3: According to the evaluation result, the intelligent safety helmet is divided into qualified intelligent safety helmet and unqualified intelligent safety helmet, and the qualified safety helmet is used to supervise the power engineering site personnel, the position, health condition and environmental change of the worker are monitored in real time, and whether there is risk in the power engineering site is predicted;

[0013] S4: According to the prediction result, the construction risk level of the power engineering site is divided, the site personnel is supervised according to the risk level, and a warning response mechanism is adopted to make corresponding warning for different risk levels.

[0014] As a further scheme of the application: the analysis of the real-time response data specifically includes:

[0015] The intelligent safety helmet is placed in an electromagnetic shielding room, the electromagnetic field intensity is gradually increased, and the response data of the intelligent safety helmet is recorded in real time, including working frequency and signal strength;

[0016] The working frequency of the intelligent safety helmet is obtained according to the electromagnetic field intensity level, the working frequency abnormality index is calculated according to the fluctuation of the working frequency, and the frequency stability of the intelligent safety helmet under electromagnetic interference is evaluated according to the working frequency abnormality index;

[0017] The signal strength of the intelligent safety helmet is obtained according to the electromagnetic field intensity level, the signal strength abnormality index is calculated according to the fluctuation of the signal strength, and the signal stability of the intelligent safety helmet under electromagnetic interference is evaluated according to the signal strength abnormality index.

[0018] As a further scheme of the application: the working frequency abnormality index is obtained by:

[0019] The working frequency data of the intelligent safety helmet is collected in real time The working frequency data is subjected to Fourier transform, and the expression is:

[0020] ;

[0021] In the formula, Indicates the time point of working frequency data collection, Indicates the frequency in the frequency domain, Indicates the number of collection points, Indicates the total number of collection points, Represents the imaginary unit. Represents the base-logarithm of natural numbers. Represents frequency The corresponding complex amplitude value, The time-domain signal representation of the first Operating frequency of each collection point ;

[0022] Obtain the frequency with the largest amplitude in the spectrum, which is the operating frequency of the smart safety helmet, denoted as . ;

[0023] Obtain the bandwidth of the spectrum. ;

[0024] The formula for calculating harmonic energy is as follows:

[0025] ;

[0026] In the formula, Represents harmonic energy. Represents frequency The corresponding amplitude value, Indicates the order of harmonics. Indicates the maximum harmonic order;

[0027] The degree of deviation from the operating frequency is calculated and denoted as frequency deviation. The calculation expression is:

[0028] ;

[0029] In the formula, Indicates a point in time Frequency deviation on Indicates a point in time The actual operating frequency on This indicates the ideal operating frequency under conditions of no electromagnetic interference.

[0030] The standard deviation of the frequency deviation is calculated using the standard deviation calculation formula, and denoted as . ;

[0031] The bandwidth difference between the bandwidths under the maximum electromagnetic field strength and the bandwidths under the maximum electromagnetic field strength is calculated to obtain the bandwidth range, denoted as . ;

[0032] Harmonic energy Standard deviation of frequency deviation and bandwidth range Standardization processing is performed to calculate the working frequency anomaly index. .

[0033] As a further scheme of the present application, the signal strength anomaly index is obtained by:

[0034] The wireless signal strength data received or transmitted by the intelligent safety helmet is collected, denoted as ;

[0035] The signal strength data is converted from the time domain to the time-frequency domain by wavelet transform, and the calculation expression is:

[0036] ;

[0037] In the formula, represents the signal strength data The local features at the scale and the position , is a wavelet function, representing the result of the mother wavelet at the scale and the position , the scale parameter, represents the position parameter;

[0038] The standard deviation of the wavelet transform coefficient is calculated to reflect the fluctuation degree of the signal strength data. The weighted average calculation is performed on the fluctuation degree of the signal strength data at each scale, i.e. the standard deviation of the wavelet transform coefficient , to obtain the comprehensive standard deviation of the wavelet transform coefficient;

[0039] The expected deviation of the electromagnetic shielding efficiency is calculated by: calculating the difference between the signal strength without electromagnetic interference and the signal strength under electromagnetic interference to obtain the expected deviation of the electromagnetic shielding efficiency;

[0040] The comprehensive standard deviation and the expected deviation of the electromagnetic shielding efficiency are summed to obtain the signal strength anomaly index .

[0041] As a further scheme of the present application, the evaluation of the data transmission stability of the intelligent safety helmet specifically includes:

[0042] The frequency stability of the intelligent safety helmet under electromagnetic interference and the signal stability of the intelligent safety helmet under electromagnetic interference are comprehensively analyzed, a comprehensive coefficient is calculated, and the data transmission stability of the intelligent safety helmet is determined according to the comprehensive coefficient.

[0043] As a further scheme of the present application, the intelligent safety helmet is divided into qualified intelligent safety helmets and unqualified intelligent safety helmets according to the evaluation results, specifically including:

[0044] The working frequency anomaly index and the signal strength anomaly index The normalization processing is performed, and a comprehensive coefficient is calculated;

[0045] It is judged whether the comprehensive coefficient of each intelligent safety helmet is greater than or equal to a preset threshold value, if yes, it is recorded as an unqualified safety helmet, and if no, it is recorded as a qualified safety helmet.

[0046] As a further scheme of the application: the qualified safety helmet is used to supervise the electric power engineering site personnel, the position, health status and environmental change of the worker are monitored in real time, whether there is a risk in the electric power engineering site is predicted, and specifically includes:

[0047] The position data of the worker is acquired;

[0048] The health status data of the worker includes heart rate and body temperature;

[0049] The environmental change data of the worker includes environmental temperature and environmental humidity;

[0050] The position data, health status data and environmental change data of the worker are constructed into a feature vector, and all the feature vectors are constructed into a feature matrix ;

[0051] The position data, health status data and environmental change data of the historical normal worker are acquired as training data;

[0052] The training data is preprocessed, a gradient boosting tree is selected to construct a risk assessment model, and a risk coefficient is calculated;

[0053] The real-time position data, health status data and environmental change data of the worker are taken as input features, and the risk coefficient of the electric power engineering is taken as an output item of the model;

[0054] An initial model is set, and mean initialization is performed;

[0055] For the first tree, the residual error of each training set is calculated;

[0056] A new tree is trained to fit the residual error;

[0057] Multiple trees are trained by iteration until the maximum number of trees is reached;

[0058] The final output of the model is the risk coefficient;

[0059] The calculation expression of the risk coefficient is:

[0060] ;

[0061] In the formula, represents the final predicted risk coefficient, represents an initial prediction value, representing the output of a tree, representing a learning rate. As a further scheme of the present application: the construction risk level of the power engineering site is divided according to the prediction result, and specifically includes:

[0062] If the risk coefficient is greater than or equal to the preset threshold, it means that the corresponding power engineering worker has a high risk level, which is recorded as high risk, and if not, it means that the corresponding power engineering worker has a low risk level, which is recorded as low risk.

[0063] The power engineering site personnel supervision system based on artificial intelligence comprises:

[0064] The electromagnetic environment simulation and test module determines the electromagnetic frequency range and intensity level that need to be tested by simulating the electromagnetic environment of the power engineering site; designs and builds an electromagnetic shielding room to ensure adjustable electromagnetic interference and provide a standardized environment for electromagnetic compatibility testing of the intelligent safety helmet;

[0065] The intelligent safety helmet response data acquisition and analysis module gradually increases the interference under different electromagnetic field intensities by placing the intelligent safety helmet in the electromagnetic shielding room, and real-time acquires the response data of the intelligent safety helmet; by analyzing the response data of the intelligent safety helmet, the data transmission stability of the intelligent safety helmet under electromagnetic interference is evaluated;

[0066] The intelligent safety helmet evaluation and personnel supervision module divides the intelligent safety helmet into qualified safety helmets and unqualified safety helmets, and for qualified safety helmets, personnel supervision is applied in the power engineering site, including real-time monitoring of the position, health status and environmental changes of the worker, and predicting whether there is a potential risk in the power engineering site based on data analysis;

[0067] The risk prediction and early warning response module divides the construction risk level of the power engineering site; according to the different risk levels, corresponding personnel supervision measures are taken, and risk warning and management are carried out through the early warning response mechanism.

[0068] The beneficial effects of the present application are:

[0069]

[0070] ​(1) The electromagnetic interference test of the intelligent safety helmet is carried out in the electromagnetic shielding chamber, the electromagnetic field environment with adjustable height is used to accurately simulate the electromagnetic interference that may be encountered in the actual power engineering site; the working frequency and signal strength of the intelligent safety helmet under different electromagnetic field intensities are monitored in real time, and advanced technologies such as Fourier transform and spectrum analysis are combined to analyze the frequency fluctuation and signal strength change, and the working frequency abnormality index and signal strength abnormality index are calculated; these indexes can comprehensively reflect the anti-interference ability and data transmission stability of the intelligent safety helmet under high electromagnetic interference, thereby providing a scientific basis for the electromagnetic compatibility of the intelligent safety helmet; in a complex electromagnetic environment, the intelligent safety helmet needs to maintain efficient and stable communication and data transmission capability, which is crucial for ensuring the safety of personnel in the power engineering site; the present application accurately calculates and compares the abnormality degree of working frequency and signal strength, ensures that the intelligent safety helmet can effectively suppress external electromagnetic interference in the actual construction process, and ensures the real-time transmission and processing of key data such as worker position and health status; in this way, not only the technical stability of the intelligent safety helmet is improved, but also strong technical support is provided for the safety of personnel in the power engineering site, the anti-interference and reliability of the equipment are enhanced, and the safety protection level of the entire power construction site is improved;

[0071] (2) The present application comprehensively monitors the position, health status and environmental changes of workers in the power engineering site in real time, uses gradient boosting tree algorithm to deeply analyze multi-dimensional data, and calculates accurate risk coefficients; this method not only can capture the changes of the environment where the workers are in real time, but also can establish an efficient risk assessment model combined with historical data, dynamically predict the risk level in the construction process according to different working environment and worker health status; through accurate risk prediction, the present application realizes the comprehensive control of the construction site risk, and provides a scientific basis for subsequent safety decision; with the help of this accurate risk assessment system, the present application can automatically identify high risk level, and dynamically adjust personnel supervision strategy according to risk coefficient to formulate corresponding safety management scheme; when the system detects potential danger or abnormal worker health, it can immediately trigger the early warning response mechanism to ensure that timely and effective emergency measures are taken to minimize the possibility of accidents. BRIEF DESCRIPTION OF DRAWINGS

[0072] The present application will be further described below in conjunction with the drawings.

[0073] Figure 1 is the specific step flow chart of the power engineering site personnel supervision method based on artificial intelligence of the present application;

[0074] Figure 2 is the process flow chart of the power engineering site personnel supervision system based on artificial intelligence in the present application. DETAILED DESCRIPTION

[0075] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0076] Please refer to Figure 1 The present application is a power engineering site personnel supervision method based on artificial intelligence, which comprises the following steps:

[0077] S1: According to the electromagnetic environment characteristics of the power engineering site, the electromagnetic frequency range and electromagnetic intensity level of the test are determined to simulate the actual electromagnetic interference situation;

[0078] Design an electromagnetic shielding room to ensure that the electromagnetic interference situation is adjustable;

[0079] S2: Place the intelligent safety helmet in the electromagnetic shielding room, gradually increase the electromagnetic field intensity, record the response data of the intelligent safety helmet in real time, analyze the real-time response data, and evaluate the stability of the data transmission of the intelligent safety helmet;

[0080] The response data includes: working frequency and signal strength;

[0081] S3: According to the evaluation results, the intelligent safety helmet is divided into qualified intelligent safety helmet and unqualified intelligent safety helmet, and the qualified safety helmet is used to supervise the power engineering site personnel, including: by real-time monitoring of the position, health status and environmental changes of the worker, predicting whether there is risk in the power engineering site;

[0082] S4: According to the prediction result, the construction risk level of the power engineering site is divided, according to the risk level, the on-site personnel are supervised, and the early warning response mechanism is adopted to correspond to the early warning of different risk levels.

[0083] In S1, according to the electromagnetic environment characteristics of the power engineering site, the electromagnetic frequency range and electromagnetic intensity level of the test are determined to simulate the actual electromagnetic interference situation, which specifically includes:

[0084] According to the actual electromagnetic environment characteristics of the power engineering site, the main interference sources and their frequency range (such as 50Hz to 3GHz) and electromagnetic field intensity level (such as 1V / m to 200V / m) are determined, an electromagnetic shielding room with high shielding efficiency is designed and built, high-conductivity metal materials and wave-absorbing materials are used to construct the shielding structure to ensure the shielding of external interference, and an adjustable electromagnetic interference generation system is built inside to generate multi-frequency and multi-mode electromagnetic fields through a signal generator and a radiation antenna, and a high-precision electromagnetic field detector and a central control system are used to monitor and adjust the test environment in real time, thereby providing accurate and reliable simulation conditions for electromagnetic compatibility testing of the intelligent safety helmet under various actual working conditions.

[0085] In S2, the intelligent safety helmet is placed in the electromagnetic shielding room, the electromagnetic field intensity is gradually increased, and the response data of the intelligent safety helmet is recorded in real time. The real-time response data is analyzed to evaluate the stability of data transmission of the intelligent safety helmet, including:

[0086] The intelligent safety helmet is placed in the electromagnetic shielding room, the electromagnetic field intensity is gradually increased, and the response data of the intelligent safety helmet is recorded in real time, including the working frequency and signal strength;

[0087] According to the electromagnetic field intensity level, the working frequency of the intelligent safety helmet is obtained, the working frequency abnormality index is calculated according to the fluctuation of the working frequency, and the frequency stability of the intelligent safety helmet under electromagnetic interference is evaluated according to the working frequency abnormality index;

[0088] According to the electromagnetic field intensity level, the signal strength of the intelligent safety helmet is obtained, the signal strength abnormality index is calculated according to the fluctuation of the signal strength, and the signal stability of the intelligent safety helmet under electromagnetic interference is evaluated according to the signal strength abnormality index;

[0089] Wherein, the signal strength is the strength of the wireless signal received or transmitted by the intelligent safety helmet;

[0090] The frequency stability of the intelligent safety helmet under electromagnetic interference and the signal stability of the intelligent safety helmet under electromagnetic interference are comprehensively analyzed, a comprehensive coefficient is calculated, and the stability of data transmission of the intelligent safety helmet is judged according to the comprehensive coefficient;

[0091] Wherein, the working frequency abnormality index is obtained by:

[0092] Real-time acquisition of working frequency data of the intelligent safety helmet The working frequency data is subjected to Fourier transform, and the expression is:

[0093] ;

[0094] In the formula, represents the time point of working frequency data acquisition, represents a frequency in a frequency domain, represents a number of acquisition points, represents a total number of acquisition points, represents an imaginary unit, represents a natural number base logarithm, represents a frequency corresponding amplitude value, is a working frequency of the th acquisition point in a time domain signal representation ;

[0095] Obtain the frequency with the largest amplitude in the frequency spectrum, that is, the working frequency of the intelligent safety helmet, denoted as ;

[0096] Obtain the bandwidth of the spectrum in the frequency spectrum ;

[0097] Calculate the harmonic energy, and the calculation expression is:

[0098] ;

[0099] In the formula, represents the harmonic energy, represents a frequency corresponding amplitude value, represents the order of the harmonic, represents the maximum harmonic order;

[0100] Calculate the degree of deviation of the working frequency, denoted as the frequency deviation, and the calculation expression is:

[0101] ;

[0102] In the formula, represents the frequency deviation at the time point , represents the actual working frequency at the time point , represents the ideal working frequency without electromagnetic interference;

[0103] Calculate the standard deviation of the frequency deviation by the standard deviation calculation formula, denoted as ;

[0104] Calculate the difference between the bandwidth at the maximum electromagnetic field strength and the bandwidth at the maximum electromagnetic field strength to obtain the bandwidth range value, denoted as ;

[0105] Standardize the harmonic energy , the standard deviation of the frequency deviation , and the bandwidth range value to calculate the working frequency abnormality index , the calculation expression is:

[0106] ;

[0107] In the formula, represents the working frequency abnormality index, , and is a preset proportional coefficient, and , and are all greater than 0;

[0108] The working frequency abnormality index is compared with a preset threshold value;

[0109] If the working frequency abnormality index is greater than or equal to the preset threshold value, it indicates that the corresponding intelligent safety helmet is greatly affected by electromagnetic interference, and the corresponding working frequency is abnormal;

[0110] If the working frequency abnormality index is less than the preset threshold value, it indicates that the corresponding intelligent safety helmet is less affected by electromagnetic interference, and the corresponding working frequency is normal;

[0111] It should be noted that by applying Fourier transform to analyze the working frequency of the intelligent safety helmet, the deviation degree, bandwidth change and harmonic energy distribution of the working frequency are calculated, and finally the working frequency abnormality index is generated. The greater the value of the working frequency abnormality index, the higher the degree of influence of the corresponding intelligent safety helmet affected by electromagnetic interference.

[0112] The signal strength abnormality index is obtained by:

[0113] The wireless signal strength data received or transmitted by the intelligent safety helmet is collected, denoted as ;

[0114] The signal strength data is converted from the time domain to the time-frequency domain by wavelet transform, and the calculation expression is:

[0115] ;

[0116] In the formula, represents the local features of the signal strength data at the scale and the position , is a wavelet function, representing the result of the mother wavelet at the scale and the position , the scale parameter, the position parameter;

[0117] The coefficient a standard deviation of the signal intensity data, for reflecting a fluctuation degree of the signal intensity data, the fluctuation degree of the signal intensity data at each scale, i.e., a coefficient of the wavelet transform a standard deviation of the signal intensity data, for reflecting a fluctuation degree of the signal intensity data, the fluctuation degree of the signal intensity data at each scale, i.e., a coefficient of the wavelet transform

[0118] calculating an expected deviation of the electromagnetic shielding efficiency, including: calculating a difference between the signal intensity without electromagnetic interference and the signal intensity under electromagnetic interference, to obtain the expected deviation of the electromagnetic shielding efficiency;

[0119] summing the comprehensive standard deviation and the expected deviation of the electromagnetic shielding efficiency, to obtain a signal intensity anomaly index

[0120] comparing the signal intensity anomaly index with a preset threshold value;

[0121] if the signal intensity anomaly index is greater than or equal to the preset threshold value, it indicates that the wireless signal transmission capability of the intelligent safety helmet under electromagnetic interference is low;

[0122] if the signal intensity anomaly index is less than the preset threshold value, it indicates that the wireless signal transmission capability of the intelligent safety helmet under electromagnetic interference is high;

[0123] It should be noted that the signal intensity anomaly index reflects the wireless signal transmission capability of the intelligent safety helmet under electromagnetic interference, and the greater the value of the signal intensity anomaly index, the weaker the corresponding wireless signal transmission capability.

[0124] wherein, the comprehensive coefficient is obtained by:

[0125] normalizing the work frequency anomaly index and the signal intensity anomaly index to obtain a comprehensive coefficient, and the calculation expression is:

[0126]

[0127] In the formula, the comprehensive coefficient is represented by and and represent a preset proportion coefficient;

[0128] It should be noted that the comprehensive coefficient is used to reflect whether the intelligent safety helmet meets the use of power engineering site, and the smaller the value of the comprehensive coefficient, the higher the protection level of the intelligent safety helmet against electromagnetic interference.

[0129] In S3, according to the evaluation result, the intelligent safety helmet is divided into qualified intelligent safety helmet and unqualified intelligent safety helmet, specifically including:

[0130] ​​Determine whether the comprehensive coefficient of each intelligent safety helmet is greater than or equal to a preset threshold, if yes, record as an unqualified safety helmet, if no, record as a qualified safety helmet;

[0131] By monitoring the position, health status and environmental changes of the workers in real time, calculating the risk coefficient, and predicting whether there is a risk in the power engineering site according to the risk coefficient, specifically including:

[0132] Obtain the position data of the workers;

[0133] Obtaining the health status data of the workers includes heart rate and body temperature;

[0134] Obtaining the environmental change data of the workers, including environmental temperature and environmental humidity;

[0135] The position data, health status data and environmental change data of the workers are used to construct a feature vector, and all feature vectors are used to establish a feature matrix ;

[0136] Obtain the position data, health status data and environmental change data of the workers as training data;

[0137] Preprocess the training data, select a gradient boosting tree to construct a risk assessment model, and calculate the risk coefficient;

[0138] The real-time position data, health status data and environmental change data of the workers are used as input features, and the risk coefficient of the power engineering is used as the output item of the model;

[0139] Set an initial model and initialize by mean value;

[0140] For the mth tree, calculate the residual of each training set;

[0141] Train a new tree to fit the residual;

[0142] Iteratively train multiple trees until the maximum number of trees is reached;

[0143] The final output of the model is the risk coefficient;

[0144] Through the trained gradient boosting tree model, each worker and construction site is monitored in real time, and the risk coefficient is calculated according to the real-time input features (such as position, health status, environmental change, etc.), and the calculation expression is:

[0145] ;

[0146] In the formula, represents the final predicted risk coefficient, represents the initial prediction value, represents the mth tree, The output of the tree, Indicate the learning rate;

[0147] Compare the risk coefficient with the preset threshold value;

[0148] If the risk coefficient is greater than or equal to the preset threshold value, it means that the corresponding electric power engineering worker has a high risk level;

[0149] If the risk coefficient is less than the preset threshold value, it means that the corresponding electric power engineering worker has a low risk level.

[0150] In S4, according to the prediction result, the construction risk level of the electric power engineering site is divided, the on-site personnel are supervised according to the risk level, and the early warning response mechanism is adopted to correspond to the early warning of different risk levels, which specifically includes:

[0151] According to different risk levels, the on-site personnel are dynamically supervised;

[0152] For low-risk areas, the monitoring system can perform routine checks and data collection to ensure personnel safety;

[0153] For high-risk areas, the system needs to strengthen the close monitoring of on-site personnel, real-time tracking of their activities and health status, and ensure the adoption of emergency measures;

[0154] According to different risk levels, the system will start the corresponding early warning response mechanism

[0155] When the risk level is low, the system performs routine reminders and reports;

[0156] When the risk level is high, the system immediately issues a strong alarm and automatically activates the emergency response mechanism to notify all relevant personnel to evacuate quickly or take emergency safety measures;

[0157] Finally, the implementation of the early warning response mechanism includes real-time location tracking, health monitoring and environmental data feedback, so as to timely identify and handle abnormal behavior or unsafe conditions;

[0158] The system will also automatically trigger alarms and transmit information to the on-site command center based on real-time data of the worker's area and health status, so as to ensure that the safety management of the construction site reaches the most efficient and safest standard.

[0159] Please refer to Figure 2 The AI-based electric power engineering site personnel supervision system, as shown in the figure, includes:

[0160] An electromagnetic environment simulation and test module determines the electromagnetic frequency range and intensity level that needs to be tested by simulating the electromagnetic environment of a power engineering site; designs and builds an electromagnetic shielding room to ensure adjustable electromagnetic interference and provide a standardized environment for electromagnetic compatibility testing of intelligent safety helmets;

[0161] An intelligent safety helmet response data acquisition and analysis module places the intelligent safety helmet in the electromagnetic shielding room, gradually increases the interference under different electromagnetic field intensities, and acquires the response data of the intelligent safety helmet in real time; by analyzing the response data of the intelligent safety helmet, the data transmission stability of the intelligent safety helmet under electromagnetic interference is evaluated;

[0162] An intelligent safety helmet evaluation and personnel supervision module divides the intelligent safety helmet into qualified safety helmets and unqualified safety helmets; for qualified safety helmets, personnel supervision is applied in the power engineering site, including real-time monitoring of the position, health status and environmental changes of workers, and predicting whether there is a potential risk in the power engineering site based on data analysis;

[0163] A risk prediction and early warning response module divides the construction risk level of the power engineering site; according to the different risk levels, corresponding personnel supervision measures are taken, and risk warning and management are carried out through the early warning response mechanism.

[0164] The working principle of the present application is as follows: by simulating the electromagnetic environment characteristics of the power engineering site, designing and building an electromagnetic shielding room, accurately regulating the electromagnetic frequency range and intensity level, and truly reproducing the electromagnetic interference of facilities such as substations, reliable simulation conditions are provided for electromagnetic compatibility testing of intelligent safety helmets; the intelligent safety helmet is placed in the shielding room, the electromagnetic field intensity is gradually increased, the response data such as working frequency and signal strength are acquired in real time, the stability of the intelligent safety helmet under electromagnetic interference is evaluated through the calculation of frequency anomaly index and signal strength anomaly index, and the comprehensive coefficient is obtained through comprehensive analysis to evaluate the data transmission stability of the intelligent safety helmet; according to the evaluation results, the intelligent safety helmet is divided into qualified and unqualified categories, the position, health status and environmental changes of workers are monitored in real time, the risk coefficient is calculated by using the gradient boosting tree model to predict the construction risk of the power engineering site; according to the predicted risk coefficient, the risk level is divided, the on-site personnel are dynamically supervised, the safety control of high-risk areas is strengthened, the corresponding early warning response mechanism is started, and accurate safety measures are taken under different risk levels; the present application can improve the safety of the power engineering construction site through intelligent supervision, timely predict and respond to potential risks, minimize safety hazards, and protect the safety of workers.

[0165] The above formulas are all dimensionless values calculated, the formulas are obtained by collecting a large amount of data to simulate a formula of the most recent real situation, and preset parameters in the formulas are set by a person skilled in the art according to actual conditions.

[0166] The above embodiments can be implemented wholly or partially by software, hardware, firmware, or any other combination. When implemented by software, the above embodiments can be implemented wholly or partially in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0167] It should be understood that the term "and / or" herein merely describes the association relationship of the associated objects, and means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In addition, the character " / " herein generally represents that the front and rear associated objects are in an "or" relationship, but can also represent an "and / or" relationship, which can be understood according to the context.

[0168] It should be understood that in various embodiments of the present application, the size of the sequence number of the above processes does not mean the order of execution, and the execution order of the processes should be determined according to their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0169] The above describes one embodiment of the present application in detail, but the content described is only the preferred embodiment of the present application and cannot be considered as limiting the scope of the implementation of the present application. Any equivalent changes and improvements made within the scope of the present application should still belong to the patent coverage of the present application.

Claims

1. An AI-based power engineering site personnel supervision method, characterized by, The method comprises the following steps: S1: According to the electromagnetic environment characteristics of the power engineering site, determine the electromagnetic frequency range and electromagnetic intensity level of the test to simulate the actual electromagnetic interference situation; Design an electromagnetic shielding room to ensure that the electromagnetic interference situation is adjustable; S2: Place the intelligent safety helmet in the electromagnetic shielding room, gradually increase the electromagnetic field intensity, and record the response data of the intelligent safety helmet in real time, analyze the real-time response data, and evaluate the stability of data transmission of the intelligent safety helmet; Wherein, the response data includes: working frequency and signal strength, signal strength is the strength of the intelligent safety helmet receiving or sending wireless signal; S3: According to the evaluation result, the intelligent safety helmet is divided into qualified intelligent safety helmet and unqualified intelligent safety helmet, and the qualified safety helmet is used to supervise the power engineering site personnel, and through real-time monitoring of the position, health status and environmental changes of the workers, it is predicted whether there is risk in the power engineering site; S4: According to the prediction result, the construction risk level of the power engineering site is divided, the on-site personnel is supervised according to the risk level, and the early warning response mechanism is adopted to make corresponding early warning for different risk levels; The analysis of the real-time response data specifically includes: Place the intelligent safety helmet in the electromagnetic shielding room, gradually increase the electromagnetic field intensity, and record the response data of the intelligent safety helmet in real time, including working frequency and signal strength; According to the working frequency, the working frequency abnormal index is calculated according to the fluctuation of the working frequency, and the frequency stability of the intelligent safety helmet under electromagnetic interference is evaluated according to the working frequency abnormal index; According to the signal strength, the signal strength abnormal index is calculated according to the fluctuation of the signal strength, and the signal stability of the intelligent safety helmet under electromagnetic interference is evaluated according to the signal strength abnormal index; The qualified safety helmet is used to supervise the power engineering site personnel, and through real-time monitoring of the position, health status and environmental changes of the workers, it is predicted whether there is risk in the power engineering site, specifically including: Obtain the position data of the workers; Obtain the health status data of the workers, including heart rate and body temperature; Obtain the environmental change data of the workers, including environmental temperature and environmental humidity; The position data of the worker, the health state data and the environment change data are constructed into a feature vector, and all the feature vectors are established into a feature matrix ; Obtain the historical normal position data, health status data and environmental change data of the workers as training data; Preprocess the training data, select gradient boosting tree to construct risk assessment model, and calculate risk coefficient; Take the real-time position data, health status data and environmental change data of the workers as input features, and take the risk coefficient of the power engineering as the output item of the model; Set the initial model through mean initialization; For the first tree, compute the residuals for each training set; Train a new tree to fit the residual; Through iterative training of multiple trees, until the maximum number of trees is reached; The final output of the model is the risk coefficient; Wherein, the calculation expression of the risk coefficient is: ； wherein, represents the risk coefficient of the final prediction, represents the initial prediction value, represents the output of the tree, represents the learning rate. 2.The AI-based electric power engineering site personnel supervision method of claim 1, wherein The working frequency abnormal index is obtained by: Real-time acquisition of working frequency data of intelligent safety helmet The working frequency data is subjected to Fourier transform, and the expression is calculated as ； In the formula, denotes the time point of the data acquisition of the operating frequency, denotes the frequency in the frequency domain, denotes the number of acquisition points, denotes the total number of acquisition points, denotes the imaginary unit, denotes the natural number base logarithm, denotes the frequency corresponding complex amplitude value, is the operating frequency of the time-domain signal at the first acquisition point. The frequency with the largest amplitude in the spectrum, i.e. the working frequency of the smart safety hat, is obtained, denoted as ; acquiring a bandwidth of a spectrum in the spectrum ; Calculate the harmonic energy, and the calculation expression is: ； wherein denotes the harmonic energy, denotes the frequency corresponding amplitude value, denotes the order of the harmonic, denotes the maximum harmonic order; Calculate the deviation degree of working frequency, recorded as frequency deviation, and the calculation expression is: ； wherein denotes the frequency deviation at the point in time denotes the actual operating frequency at the point in time denotes the ideal operating frequency in the absence of electromagnetic interference;​​ The standard deviation of the frequency deviation is calculated by the standard deviation calculation formula, and is denoted as ; The bandwidth difference value is obtained by subtracting the bandwidth at the maximum electromagnetic field strength from the bandwidth at the maximum electromagnetic field strength, denoted as ; harmonic energy , standard deviation of frequency deviation and bandwidth range standardized, calculate the operating frequency anomaly index . 3.The AI-based electric power engineering site personnel supervision method of claim 1, wherein, The signal strength abnormal index is obtained by: The wireless signal strength data received or sent by the intelligent safety helmet is collected and recorded as ; The signal intensity data is converted from time domain to time-frequency domain by wavelet transform, and the calculation expression is: ； wherein represents signal intensity data at scale and position , is a wavelet function, representing the mother wavelet at scale and position , scale parameter, denotes position parameter; by calculating the standard deviation of the coefficients of the wavelet transform for reflecting the fluctuation degree of the signal intensity data, the standard deviation of the coefficients of the wavelet transform for each scale, i.e. the coefficients of the wavelet transform, and performing a weighted average calculation to obtain a comprehensive standard deviation of the coefficients of the wavelet transform; The expected deviation of the electromagnetic shielding efficiency is calculated by subtracting the signal intensity without electromagnetic interference from the signal intensity under electromagnetic interference; Summing the standard deviation of the combined criteria with the expected deviation of the electromagnetic shielding efficiency results in the signal strength anomaly index . 4.The AI-based electric power engineering site personnel supervision method of claim 1, wherein The stability of data transmission of the intelligent safety helmet is evaluated, specifically including: The frequency stability of the intelligent safety helmet under electromagnetic interference is analyzed together with the signal stability of the intelligent safety helmet under electromagnetic interference, a comprehensive coefficient is calculated, and the stability of data transmission of the intelligent safety helmet is determined according to the comprehensive coefficient. 5.The AI-based electric power engineering site personnel supervision method of claim 1, wherein According to the evaluation result, the intelligent safety helmet is divided into qualified intelligent safety helmet and unqualified intelligent safety helmet, specifically including: calculating a working frequency abnormality index calculating a signal strength abnormality index normalizing and calculating a comprehensive coefficient If the comprehensive coefficient of each intelligent safety helmet is greater than or equal to the preset threshold, it is recorded as an unqualified safety helmet, otherwise, it is recorded as a qualified safety helmet. 6.The AI-based electric power engineering site personnel supervision method of claim 1, wherein, According to the prediction result, the construction risk level of the power engineering site is divided, specifically including: If the risk coefficient is greater than or equal to the preset threshold, it means that the corresponding power engineering worker has a high risk level, and is recorded as high risk, otherwise, it means that the corresponding power engineering worker has a low risk level, and is recorded as low risk.

7. An AI-based power engineering site personnel supervision system, characterized by, The method for monitoring power engineering site personnel based on artificial intelligence according to any one of claims 1-6, comprising: An electromagnetic environment simulation and test module, which determines the electromagnetic frequency range and intensity level to be tested by simulating the electromagnetic environment of the power engineering site, designs and builds an electromagnetic shielding room to ensure adjustable electromagnetic interference, and provides a standardized environment for electromagnetic compatibility testing of the intelligent safety helmet; An intelligent safety helmet response data acquisition and analysis module, which places the intelligent safety helmet in the electromagnetic shielding room, gradually increases the interference under different electromagnetic field intensities, and acquires the response data of the intelligent safety helmet in real time; by analyzing the response data of the intelligent safety helmet, the data transmission stability of the intelligent safety helmet under electromagnetic interference is evaluated; An intelligent safety helmet evaluation and personnel monitoring module, which divides the intelligent safety helmet into qualified and unqualified safety helmet categories, and applies the qualified safety helmet to personnel monitoring in the power engineering site, including real-time monitoring of the position, health status and environmental changes of the worker, and predicting whether there is a potential risk in the power engineering site based on data analysis; A risk prediction and early warning response module, which divides the construction risk level of the power engineering site; according to the different risk levels, corresponding personnel monitoring measures are taken, and risk warning and management are carried out through the early warning response mechanism.

Images