CN111449652A - A construction safety monitoring method and device based on brain wave analysis - Google Patents

Abstract

The present disclosure provides a construction safety monitoring method and apparatus based on brain wave analysis, the method comprising: collecting brain wave signals of constructors; classifying by using a preset sparse representation classifier according to the brain wave signals, and obtaining the fatigue degree of the constructors according to a classification result; constructing a safety monitoring model according to the fatigue degree; inputting the acquired danger processing information into the safety monitoring model to obtain construction safety information; and judging whether the construction personnel have construction potential safety hazards or not according to the construction safety information. According to the method and the device, the fatigue degree of the constructors is judged through the brain wave signals of the constructors, then a safety monitoring model capable of reflecting the fatigue degree of the constructors is established, whether the constructors have potential safety hazards or not is monitored through the model, safety supervision is conducted on the behaviors of the constructors through the brain wave technology, and safety accidents can be avoided to the maximum degree.

Description

A construction safety monitoring method and device based on brain wave analysis

technical field

The present disclosure belongs to the technical field of construction safety monitoring, in particular to a construction safety monitoring method based on brain wave analysis and a construction safety monitoring device based on brain wave analysis.

Background technique

Based on the existing literature search and the actual conditions of the construction site, for construction safety management, the most current is to improve or supervise the construction equipment itself. For example, for tower cranes, traditional construction safety monitoring technologies include black box technology, hook positioning technology, etc. , the equipment ultimately requires human operation. Few studies take people as the research object, but human operation is crucial to the safety of hoisting operations. Safe operation requires the construction personnel to have clear cognitive ability and fast speed. Therefore, it is necessary to monitor the fatigue of construction personnel, such as operators such as towers.

SUMMARY OF THE INVENTION

The present disclosure aims to solve at least one of the technical problems existing in the prior art, and provides a construction safety monitoring method based on brain wave analysis and a construction safety monitoring device based on brain wave analysis.

One aspect of the present disclosure provides a construction safety monitoring method based on brain wave analysis, comprising:

Collect the brainwave signals of construction workers;

According to the brain wave signal, use a preset sparse representation classifier to classify, and obtain the fatigue level of the construction worker according to the classification result;

constructing a safety monitoring model according to the fatigue level;

Inputting the obtained hazard treatment information into the safety monitoring model to obtain construction safety information;

According to the construction safety information, it is determined whether the construction personnel have construction safety hazards.

Optionally, after collecting the brainwave signals of the construction personnel, the method further includes:

Perform segmental processing on the brainwave signal to obtain brainwave signals of multiple bands;

Fourier transform is performed on the multiple band brain wave signals and the corresponding power spectral density is calculated;

According to the frequency distribution and power spectral density of the brain wave signal, the energy characteristic values of the brain wave signals in the multiple bands are calculated respectively.

Optionally, the following relational formula is used to calculate the energy characteristic values of the brainwave signals of the multiple bands:

Among them, E _α is the energy characteristic value of the α-band brainwave signal; E _β is the energy characteristic value of the β-band brainwave signal; E _θ is the energy characteristic value of the θ-band brainwave signal; E _δ is the energy characteristic value of the δ-band brainwave signal. Energy eigenvalue; freq is the frequency, the unit is Hz; p _freq is the power spectral density of the brain wave in the frequency band freq.

Optionally, according to the brain wave signal, use a preset sparse representation classifier to perform classification, and obtain the fatigue level of the construction worker according to the classification result, including:

Obtaining the EEG feature matrix corresponding to different fatigue levels in advance, forming training samples, and using the training samples for training to obtain the sparse representation classifier;

The sparse representation classifier is used for classification according to the energy characteristic values of the brainwave signals of the multiple bands, and the fatigue level of the construction worker is obtained according to the classification result.

Optionally, the construction of a safety monitoring model according to the fatigue degree is specifically:

Among them, t _n is the reaction time of dangerous situations, R _n is the correct handling rate of dangerous situations, F _n is the degree of fatigue, a is the correlation coefficient between fatigue degree and safety, b is the correlation coefficient between reaction time and safety, and c is correct Correlation coefficient between processing rate and safety.

Optionally, the obtained hazard treatment information is input into the safety monitoring model to obtain construction safety information, including:

Obtain actual hazardous situation reaction time;

Obtain the correct handling rate of actual hazardous situations;

The acquired reaction time of the actual dangerous situation and the correct processing rate of the actual dangerous situation are input into the safety monitoring model to obtain the construction safety information.

Optionally, the obtaining the reaction time of the actual dangerous situation includes:

Obtain the time from the occurrence of multiple dangerous situations to the occurrence of the reaction within the preset time interval, and obtain the reaction time of multiple original dangerous situations;

The actual dangerous situation reaction time is obtained according to the plurality of original dangerous situation reaction times.

Optionally, the obtaining the correct handling rate of the actual dangerous situation includes:

Obtain the number of dangerous situations handled and the number of correct handling of dangerous situations within a preset time interval;

According to the number of times of handling the dangerous situation and the number of correct handling of the dangerous situation, the rate of obtaining the correct handling of the actual dangerous situation is obtained.

Optionally, judging whether the construction personnel have construction safety hazards according to the construction safety information includes:

If the construction safety information is less than or equal to a preset first threshold, it is determined that the construction personnel have potential construction safety hazards; otherwise, it is determined that the construction personnel do not have potential construction safety hazards.

Another aspect of the present disclosure provides a construction safety monitoring device based on brain wave analysis, comprising:

The acquisition module is used to collect the brainwave signals of construction workers;

an analysis module, configured to classify the brainwave signals with a preset sparse representation classifier, and obtain the fatigue level of the construction worker according to the classification result;

a model building module for building a safety monitoring model according to the fatigue degree;

a processing module, used for inputting the obtained hazard processing information into the safety monitoring model to obtain construction safety information;

The judgment module is used for judging whether the construction personnel have hidden dangers of construction safety according to the construction safety information.

In a construction safety monitoring method based on brain wave analysis and a construction safety monitoring device based on brain wave analysis according to the embodiments of the present disclosure, the degree of fatigue of the construction workers is judged by the brain wave signals of the construction workers, and then the construction can reflect the construction. The safety monitoring model of personnel fatigue level, and the use of the model to monitor whether there are potential safety hazards for construction personnel, and the use of brain wave technology to conduct safety supervision on human behavior, can greatly avoid the occurrence of safety accidents.

Description of drawings

FIG. 1 is a schematic block diagram of the composition of an electronic device according to the first embodiment of the disclosure;

2 is a schematic flowchart of a construction safety monitoring method based on brain wave analysis according to a second embodiment of the present disclosure;

3 is a schematic structural diagram of a construction safety monitoring device based on brain wave analysis according to a third embodiment of the present disclosure;

FIG. 4 is a schematic diagram of a brain wave signal processing flow according to a second embodiment of the present disclosure.

Detailed ways

In order to make those skilled in the art better understand the technical solutions of the present disclosure, the present disclosure will be further described in detail below with reference to the accompanying drawings and specific embodiments.

First, with reference to FIG. 1 , an example electronic device for implementing a brainwave analysis-based construction safety monitoring method and a brainwave analysis-based construction safety monitoring apparatus according to an embodiment of the present disclosure will be described.

As shown in FIG. 1 , the electronic device 200 includes one or more processors 210 , one or more storage devices 220 , one or more input devices 230 , one or more output devices 240 , etc., these components are connected through a bus system 250 and and/or other forms of interconnection. It should be noted that the components and structures of the electronic device shown in FIG. 1 are only exemplary and not restrictive, and the electronic device may also have other components and structures as required.

Processor 210 may be a central processing unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in electronic device 200 to perform desired functions.

Storage 220 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and/or cache memory, or the like. The non-volatile memory may include, for example, read only memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor may execute the program instructions to implement the client functions (implemented by the processor) in the embodiments of the present disclosure described below and / or other desired functionality. Various application programs and various data, for example, various data used and/or generated by the application program, etc. may also be stored in the computer-readable storage medium.

The input device 230 may be a device used by a user to input instructions, and may include one or more of a keyboard, a mouse, a microphone, a touch screen, and the like.

The output device 240 may output various information (eg, images or sounds) to the outside (eg, a user), and may include one or more of a display, a speaker, and the like.

Below, a construction safety monitoring method based on brain wave analysis according to an embodiment of the present disclosure will be described with reference to FIG. 2 .

As shown in Figure 2, a construction safety monitoring method S100 based on brain wave analysis includes:

S110: Collect the brain wave signals of the construction personnel.

Specifically, in this step, the brainwave information of the construction personnel is collected according to actual requirements, for example, one or more of alpha brainwaves, beta brainwaves, theta brainwaves, and gamma brainwaves are collected. In this step, the construction personnel include personnel performing construction operations. Exemplarily, if the construction equipment is a tower crane, the construction personnel are tower crane drivers.

Specifically, in this step, a specific device can be used to collect brain wave information. Exemplarily, Emotiv Epoc+ wireless portable EEG monitor and the supporting EmotivPRO software can be used as the EEG signal acquisition device to monitor the construction personnel's EEG information. The signal is collected in real time and transmitted to the PC terminal through the USB receiver for signal analysis. In addition, other devices can also be used to collect brain wave signals, which can be determined according to actual needs, which is not limited in the embodiments of the present disclosure.

S120: According to the brain wave signal, use a preset sparse representation classifier to classify, and obtain the fatigue level of the construction worker according to the classification result.

Specifically, in this step, the brainwave signal is input into the sparse representation classifier as a test sample, and the training samples corresponding to the test samples are obtained by performing residual analysis with the training samples in the sparse representation classifier. The training samples get the fatigue level of the test samples. The preset sparse representation classifier may be obtained through experience, and may also be specifically set according to different actual construction conditions, for example, a sparse representation classifier for classifying the fatigue level of the hoisting tower may be set.

S130: Build a safety monitoring model according to the fatigue degree.

Specifically, in this step, the parameters of the safety monitoring model are set according to the fatigue degree, and different safety monitoring models under different fatigue degrees are obtained. The safety monitoring model may use a safety monitoring model in the prior art, for example, a construction safety model related to construction duration may be constructed, which may be determined according to actual needs, which is not limited in the embodiments of the present disclosure.

S140: Input the obtained hazard treatment information into the safety monitoring model to obtain construction safety information.

Specifically, in this step, the acquired risk handling information includes information related to the handling operation of construction workers by the construction personnel detected by the detection device on the construction site, which may be the construction detected by the camera device installed on the construction site. The operation image of the personnel or the moving image of the construction equipment can also be the motion information of the construction personnel or the motion information of the construction equipment detected by the sensing device, for example, it can be the hoisting tower detected by the camera. The operating image of the company or the moving image of the tower can be determined according to actual needs, which is not limited in this embodiment of the present disclosure.

Further, in this step, the obtained risk handling information is input into the safety monitoring model, the safety monitoring model is solved, and construction safety information is obtained.

S150: Determine, according to the construction safety information, whether the construction personnel have construction safety hazards.

Specifically, in this step, according to the preset judgment method, according to the construction safety information, it is judged whether the construction personnel have potential construction safety hazards. The preset judgment method can be determined according to actual needs, for example, a threshold judgment method can be used. , the embodiments of the present disclosure do not limit this. Further, in this step, if it is determined that there is a potential construction safety hazard, an alarm is performed. Specifically, an alarm device installed on the construction site can be used to alarm, such as a horn, or an alarm device worn by the construction personnel can be used to alarm. For example, wearable alarms.

According to an embodiment of the present disclosure, a construction safety monitoring method based on brainwave analysis is used to determine the fatigue level of the construction workers by detecting the brainwave signals of the construction workers, build a construction safety monitoring model based on the fatigue level, and pass the safety monitoring model. To monitor whether there are hidden safety hazards in the construction personnel, and combine the working status of the construction personnel to monitor the hidden safety hazards, it solves the traditional technology that can only judge the hidden safety hazards by comparing the correctness of the operation of the construction personnel or construction equipment, and cannot realize the prediction technology. It realizes safety monitoring that can prejudge potential safety hazards and improves the accuracy of safety monitoring.

In order to improve the accuracy of obtaining the fatigue level of the construction workers according to the brain wave signals, it is necessary to perform necessary processing on the collected brain wave signals, and at the same time, it is necessary to ensure the classification accuracy of the preset sparse representation classifier. The process of preprocessing the brain wave signal and the process of constructing a sparse representation classifier, but the embodiment of the present disclosure is not limited thereto.

Exemplarily, with reference to FIG. 4 , after step S110, it further includes:

S111: Perform denoising processing on the brain wave signal.

In order to reduce the noise in the brain wave signal, reduce the external interference of the brain wave signal, and improve the accuracy of the later signal processing, it is necessary to denoise the brain wave signal. Specifically, in this step, the denoising processing is performed by filtering, the linear filter is used for filtering, and the denoising processing of the EEG signal is performed in combination with the method of wavelet threshold decomposition. Of course, in addition to this, those skilled in the art can also select some other manners to perform denoising processing according to actual needs, which is not limited in the embodiments of the present disclosure.

S112: Perform segmentation processing on the brain wave signal to obtain brain wave signals of multiple bands.

Specifically, in this step, the brainwave signals are segmented according to preset frequency intervals to obtain brainwave signals of multiple bands. The preset frequency intervals may be equal intervals or unequal intervals, or Segmentation can be performed according to a specific frequency distribution according to actual needs. For example, for example, the bands can be divided according to the different frequencies of four brain waves α, β, γ, and θ. By segmenting the brain wave signal, the calculation amount of the later signal processing is reduced, and it is convenient to quickly obtain the brain wave of the target band.

S113: Perform Fourier transform on the brainwave signals of the multiple bands and calculate the corresponding power spectral density.

Specifically, in this step, the power spectral densities corresponding to the brainwave signals of multiple bands are calculated by the following relationship:

为波段freq在采样点n傅里叶变换后的功率，n为脑电信号采样点，N为脑电信号采样频率。Among them, freq represents the frequency, that is, the band at the frequency freq, p _freq (n) is the power spectral density of the brainwave in the band of the frequency freq, F _freq (n) is the original power of the band freq at the sampling point n,

is the power of the band freq after Fourier transform at the sampling point n, n is the sampling point of the EEG signal, and N is the sampling frequency of the EEG signal.

S114: According to the frequency distribution and power spectral density of the brainwave signal, respectively calculate the energy characteristic values of the brainwave signals in the multiple bands.

Specifically, in this step, the following relational formula is used to calculate the energy characteristic values of the brainwave signals of the multiple bands:

Among them, freq is the frequency, the unit is Hz; p _freq is the power spectral density of the brain wave in the frequency freq band; E _α is the energy characteristic value of the α-band brain wave signal, that is, the frequency of the brain wave signal in the frequency range of 8 ~ 13Hz. Energy eigenvalue; E _β is the energy eigenvalue of the β-band brainwave signal, that is, the energy eigenvalue of the brainwave signal with a frequency of 14-30 Hz; E _θ is the energy eigenvalue of the θ-band brainwave signal, that is, the frequency is 4- The energy characteristic value of the brain wave signal at 7 Hz; E _δ is the energy characteristic value of the brain wave signal in the delta band, that is, the energy characteristic value of the brain wave signal with a frequency of 0.5 to 3 Hz.

Exemplarily, step S120 includes:

S121: Pre-acquire EEG feature matrices corresponding to different degrees of fatigue, form training samples, and perform training by using the training samples to obtain the sparse representation classifier.

Specifically, in this step, an EEG feature matrix that can reflect five types of fatigue levels is constructed according to the collected empirical data, and corresponding feature matrices are constructed for the five types of fatigue levels, which are five energy eigenvalue feature matrices, that is, The five training samples corresponding to the five types of fatigue degrees are exemplarily, the five types of fatigue degrees in this embodiment may be 1, 3, 5, 7, and 9.

S122: Perform classification by using the sparse representation classifier according to the energy characteristic values of the brainwave signals of the multiple bands, and obtain the fatigue level of the construction worker according to the classification result.

Specifically, in this step, the energy characteristic value of the brainwave signal is input into the sparse representation classifier as a test sample, the test sample and five training samples are respectively put into the sparse representation classifier, and the test sample is The samples are respectively subjected to residual analysis with five training samples, and the training sample with the highest correlation with the test sample is obtained, then the fatigue degree corresponding to the test sample and the training sample is the same, and the classification result is obtained, that is, the brain The fatigue level of the radio signal.

A construction safety monitoring method based on brain wave analysis according to an embodiment of the present disclosure improves the accuracy of the brain wave signal by performing preprocessing such as denoising on the brain wave signal; uses the energy characteristic value as the test sample to input the sparse representation classification The residual analysis is carried out by the device; by constructing the brain wave feature matrix of multiple fatigue degrees, the classification results of the fatigue degree are refined, and the accuracy of the classification of the fatigue degree is improved by the above method, thereby improving the accuracy of safety monitoring.

In order to ensure the accuracy of safety monitoring, in addition to improving the accuracy of brain wave signal detection and classification, it is also necessary to ensure the accuracy of the safety monitoring model constructed according to the fatigue level of construction workers. The process of constructing the security monitoring model and the process of performing security monitoring according to the security monitoring model, but the embodiments of the present disclosure are not limited thereto.

Exemplarily, step S130 further includes:

The construction of a safety monitoring model according to the fatigue degree is specifically:

Among them, t _n is the reaction time of dangerous situations, R _n is the correct handling rate of dangerous situations, F _n is the degree of fatigue, a is the correlation coefficient between fatigue degree and safety, b is the correlation coefficient between reaction time and safety, and c is correct Correlation coefficient between processing rate and safety.

Specifically, in this step, a safety monitoring model is constructed according to the dangerous situation reaction time, the correct risk handling rate and the degree of fatigue as input parameters, and the output _Sn of the safety monitoring model is construction safety information. Wherein, the fatigue level _Fn is obtained from the fatigue level of the construction worker obtained from the brain wave signal, and may be any one of 1, 3, 5, 7, and 9.

Specifically, in this step, the correlation coefficient a between the degree of fatigue and safety, the correlation coefficient b between the reaction time and safety, and the correlation coefficient c between the correct processing rate and safety can be set according to actual usage conditions. , the coefficient a can be set to 5, the coefficient b can be set to 0.14, and c can be set to 1.67, in addition, those skilled in the art can also set other coefficient values according to actual needs, which is not limited in the embodiments of the present disclosure .

Further, further improvements can be made to the above-mentioned fatigue degree building safety monitoring model, specifically:

The improved model adds the first constant coefficient d and the second constant coefficient e on the basis of the above-mentioned model, which improves the flexibility of using the model in the specific use process. Likewise, the first constant coefficient d and the second constant coefficient e can be set according to actual usage conditions. Exemplarily, in the improved model, the coefficient a can be set to 7.592, the coefficient b can be set to 0.5, c can be set to 0.5, the first constant coefficient d can be set to 105.11, the second constant coefficient e can be set to 120, In addition to this, those skilled in the art can also set other coefficient values according to actual needs, which are not limited in the embodiments of the present disclosure.

The construction process of the safety monitoring model is described above, and the following will describe the process of obtaining construction safety information according to the hazard processing information and the constructed safety monitoring model.

Exemplarily, the construction safety information in step S140 includes the reaction time of the actual dangerous situation and the correct processing rate for obtaining the actual dangerous situation, and the step S140 further includes:

S141: Obtain the actual dangerous situation reaction time.

Specifically, in this step, the actual dangerous situation reaction time is the actual reaction time of the construction personnel when facing the dangerous situation, and the obtaining the actual dangerous situation reaction time can be obtained from the occurrence of the dangerous situation to the construction personnel facing the dangerous situation. The time when the dangerous situation starts to operate can also be obtained from the occurrence of the dangerous situation to the time when the construction equipment starts to operate.

Further, in this step, the device installed on the construction site can be used to obtain the reaction time of the actual dangerous situation. For example, a camera device can be used to detect the image of the construction site, to detect the moment when a dangerous situation occurs on the construction site, to detect the moment when the construction personnel start to react and operate, or to detect the moment when the construction equipment starts to perform risk avoidance actions. The difference is used to obtain the actual dangerous situation reaction time. In addition, those skilled in the art can also select other methods such as sensors to obtain the actual dangerous situation response time according to actual needs, which is not limited in the embodiments of the present disclosure.

Exemplarily, step S141 further includes:

Obtain the time from the occurrence of multiple dangerous situations to the occurrence of the reaction within the preset time interval, and obtain the reaction time of multiple original dangerous situations. Specifically, in this step, the preset time interval is a time period set according to the actual situation, which can be exemplarily 30 minutes. The obtaining of a plurality of original dangerous situation reaction times is to obtain the reaction times for all dangerous situations within the preset time interval. Exemplarily, if a total of 5 dangerous situations have occurred within the preset time interval of 30 minutes , it is to obtain the original dangerous situation reaction time of these five dangerous situations.

The actual dangerous situation reaction time is obtained according to the plurality of original dangerous situation reaction times. Specifically, in this step, the actual dangerous situation reaction time is obtained by averaging the multiple original dangerous situation reaction times.

S142: Obtain the correct handling rate of the actual dangerous situation.

Specifically, in this step, the correct handling of dangerous situations refers to that when an emergency occurs, the construction personnel make correct reflection measures to avoid on-site losses, and the wrong handling of dangerous situations refers to the illegal operation behavior of the construction personnel during the construction operation. . The rate of correct handling of the actual dangerous situation is the probability that the construction personnel will correctly handle the dangerous situation. Exemplarily, step S142 specifically includes:

Get the number of dangerous situations handled and the number of correct dangerous situations handled within a preset time interval. The actual number of times of dealing with dangerous situations is the number of times the construction personnel are dealing with dangerous situations, which can be the number of times the construction personnel have performed operations or the number of times the construction equipment has moved; The number of correct handling in the face of dangerous situations can be the number of correct operations performed by construction personnel or the number of correct movements of construction equipment.

Specifically, in this step, the preset time interval is a time period set according to the actual situation, which can be exemplarily 30 minutes. Obtaining the number of times of handling dangerous situations and the number of correct handling of dangerous situations within the preset time interval is to obtain the number of times of handling and correct handling of all dangerous situations within the preset time interval. Exemplary, if preset If a total of 5 dangerous situations have occurred within 30 minutes, and the operator has handled 4 times and handled 1 time correctly, the number of handling 4 dangerous situations and the number of correct handling 1 dangerous situation within 30 minutes is obtained.

Further, the actual number of times of dealing with dangerous situations includes the number of times the construction personnel did not handle the dangerous situation. Exemplarily, if a total of 5 dangerous situations occurred within a preset time interval of 30 minutes, and the operator handled the situation. 4 times and 1 correct handling, then the number of handling 5 dangerous situations and 1 correct handling of dangerous situations within 30 minutes is obtained.

Further, in this step, the device installed on the construction site can be used to obtain the number of times of handling dangerous situations and the number of times of correct handling of dangerous situations. For example, a camera device can be used to detect the image of the construction site, and the image of the construction personnel operating in the face of dangerous situations can be detected, and the number of operations performed by the construction personnel and the number of correct operations performed by the construction personnel can be obtained through image recognition and image analysis; The device detects the image of the construction equipment moving in the face of dangerous situations, and obtains the number of movements of the construction equipment in order to avoid the danger and the correct number of movements of the construction equipment through image recognition and image analysis. In addition, those skilled in the art can also select other methods, such as sensors, to obtain the reaction time of actual dangerous situations according to actual needs, which is not limited in the embodiment of the present disclosure.

According to the number of times of handling the dangerous situation and the number of correct handling of the dangerous situation, the rate of obtaining the correct handling of the actual dangerous situation is obtained, as shown in the following relation:

In addition, those skilled in the art can also select other methods to obtain the correct handling rate of the actual dangerous situation according to actual needs, which is not limited by the embodiments of the present disclosure.

S143: Input the acquired reaction time of the actual dangerous situation and the correct processing rate of the actual dangerous situation into the safety monitoring model to obtain the construction safety information.

Specifically, in this step, the acquired reaction time of the actual dangerous situation and the correct processing rate of the actual dangerous situation are input into the safety monitoring model as t _n and R _n respectively, and the construction safety information Sn _is calculated.

The above content describes the process of obtaining construction safety information according to the hazard processing information and the constructed safety monitoring model, and the following further describes the process of judging whether there is a potential safety hazard based on the construction safety information.

Exemplarily, step S150 specifically includes:

If the construction safety information is less than or equal to a preset first threshold, it is determined that the construction personnel have potential construction safety hazards; otherwise, it is determined that the construction personnel do not have potential construction safety hazards.

In this step, the preset first threshold is a debriefing set according to the actual situation, which can be set to 60 in an example.

In a construction safety monitoring method based on brain wave analysis according to an embodiment of the present disclosure, the construction safety information is obtained according to the reaction time of the actual dangerous situation and the correct processing rate of the actual dangerous situation, and whether there is a potential safety hazard is judged according to the construction safety information, that is, in addition to passing the The degree of fatigue obtained by the brain wave signal collects the specific operation conditions of the construction personnel when they are facing danger to monitor the safety risk, which improves the accuracy and reliability of the safety monitoring.

Next, a construction safety monitoring device 100 based on brain wave analysis according to another embodiment of the present disclosure will be described below with reference to FIG. 3 . The device can be applied to the construction safety monitoring method based on brain wave analysis described above. For details, please refer to the above-mentioned related recorded, and will not be repeated here. The device includes a collection module 110, an analysis module 120, a model construction module 130, a processing module 140 and a judgment module 150, specifically:

The collection module 110 is used to collect the brain wave signals of construction workers;

An analysis module 120, configured to classify the brainwave signal with a preset sparse representation classifier, and obtain the fatigue level of the construction worker according to the classification result;

a model building module 130, configured to build a safety monitoring model according to the fatigue degree;

The processing module 140 is configured to input the obtained hazard treatment information into the safety monitoring model to obtain construction safety information;

The judging module 150 is used for judging whether the construction personnel have hidden dangers in construction safety according to the construction safety information.

According to an embodiment of the present disclosure, a construction safety monitoring device based on brainwave analysis determines the fatigue level of the construction workers by detecting the brainwave signals of the construction workers, constructs a construction safety monitoring model based on the fatigue level, and uses the safety monitoring model To monitor whether there are hidden safety hazards in the construction personnel, and combine the working status of the construction personnel to monitor the hidden safety hazards, it solves the traditional technology that can only judge the hidden safety hazards by comparing the correctness of the operation of the construction personnel or construction equipment, and cannot realize the prediction technology. It realizes safety monitoring that can prejudge potential safety hazards and improves the accuracy of safety monitoring.

Further, the device further includes a brain wave processing module 111 for denoising the brain wave signal; for segmenting the brain wave signal to obtain brain wave signals of multiple bands; for Fourier transform is performed on the brainwave signals of the multiple bands and the corresponding power spectral density is calculated; for calculating the energy of the brainwave signals of the multiple bands respectively according to the frequency distribution and power spectral density of the brainwave signals Eigenvalues.

Further, the analysis module 120 further includes a classifier construction sub-module and a classification sub-module.

The classifier construction sub-module is used to obtain the EEG feature matrix corresponding to different fatigue levels in advance, form training samples, and use the training samples for training to obtain the sparse representation classifier; The energy characteristic values of the brainwave signals of multiple bands are classified by the sparse representation classifier, and the fatigue level of the construction worker is obtained according to the classification result.

Further, the processing module 140 further includes an acquisition sub-module and an operation sub-module.

The obtaining sub-module is used to obtain the reaction time of the actual dangerous situation and the correct processing rate of the actual dangerous situation, and is specifically to obtain the time from the occurrence of multiple dangerous situations to the occurrence of the reaction within the preset time interval, and obtain a plurality of original dangerous situation reaction times, The actual dangerous situation reaction time is obtained according to the multiple original dangerous situation reaction times; the number of dangerous situation processing times and the number of correct dangerous situation processing times within a preset time interval are taken, and the number of dangerous situation processing times and the number of correct dangerous situation processing times are obtained. The said obtaining the correct processing rate of the actual dangerous situation.

The operation sub-module is configured to input the acquired reaction time of the actual dangerous situation and the correct processing rate of the actual dangerous situation into the safety monitoring model to obtain the construction safety information.

A construction safety monitoring device based on brain wave analysis according to an embodiment of the present disclosure can monitor safety risks in combination with fatigue degree, reaction time of actual dangerous situations, and correct handling rate of actual dangerous situations, thereby improving the accuracy and reliability of safety monitoring .

Further, an electronic device is also disclosed in this embodiment, including:

one or more processors;

A storage unit for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors can implement the aforementioned brain wave-based analysis construction safety monitoring method.

Further, this embodiment also discloses a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the aforementioned method for monitoring construction safety based on brain wave analysis can be implemented.

The computer-readable medium may be included in the apparatus, device, or system of the present disclosure, or may exist independently.

Wherein, the computer-readable storage medium can be any tangible medium that contains or stores a program, which can be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device. More specific examples include, but are not limited to: having one or more Electrical connection of multiple wires, portable computer disks, hard disks, optical fibers, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), portable compact disk read only memory ( CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

The computer-readable storage medium may also include data signals in baseband or as part of a carrier wave, carrying computer-readable program codes, specific examples of which include, but are not limited to, electromagnetic signals, optical signals, or any suitable The combination.

It should be understood that the above embodiments are merely exemplary embodiments adopted to illustrate the principles of the present disclosure, but the present disclosure is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and essence of the present disclosure, and these modifications and improvements are also regarded as the protection scope of the present disclosure.

Claims (10)

1. a construction safety monitoring method based on brain wave analysis, is characterized in that, comprises: Collect the brainwave signals of construction workers; According to the brain wave signal, use a preset sparse representation classifier to classify, and obtain the fatigue level of the construction worker according to the classification result; constructing a safety monitoring model according to the fatigue level; Inputting the obtained hazard treatment information into the safety monitoring model to obtain construction safety information; According to the construction safety information, it is determined whether the construction personnel have construction safety hazards. 2. The method according to claim 1, characterized in that, after the collection of the brainwave signals of the construction personnel, the method further comprises: Perform segmental processing on the brainwave signal to obtain brainwave signals of multiple bands; Fourier transform is performed on the multiple band brain wave signals and the corresponding power spectral density is calculated; According to the frequency distribution and power spectral density of the brain wave signal, the energy characteristic values of the brain wave signals in the multiple bands are calculated respectively. 3. method according to claim 2, is characterized in that, adopts following relational formula to calculate the energy characteristic value of described multiple band brain wave signal:

Among them, E _α is the energy characteristic value of the α-band brainwave signal; E _β is the energy characteristic value of the β-band brainwave signal; E _θ is the energy characteristic value of the θ-band brainwave signal; E _δ is the energy characteristic value of the δ-band brainwave signal. Energy eigenvalue; freq is the frequency, the unit is Hz; p _freq is the power spectral density of the brain wave in the frequency band freq. 4. The method according to claim 2, wherein, according to the brain wave signal, the classification is performed with a preset sparse representation classifier, and the fatigue level of the construction worker is obtained according to the classification result, comprising: Obtaining the EEG feature matrix corresponding to different fatigue levels in advance, forming training samples, and using the training samples for training to obtain the sparse representation classifier; The sparse representation classifier is used for classification according to the energy characteristic values of the brainwave signals of the multiple bands, and the fatigue level of the construction worker is obtained according to the classification result. 5. The method according to any one of claims 1 to 4, wherein the building a safety monitoring model according to the fatigue degree is specifically:

Among them, t _n is the reaction time of dangerous situations, R _n is the correct handling rate of dangerous situations, F _n is the degree of fatigue, a is the correlation coefficient between fatigue degree and safety, b is the correlation coefficient between reaction time and safety, and c is correct Correlation coefficient between processing rate and safety. 6. The method according to any one of claims 1 to 4, wherein the inputting the obtained hazard treatment information into the safety monitoring model to obtain construction safety information, comprising: Obtain actual hazardous situation reaction time; Obtain the correct handling rate of actual hazardous situations; The acquired reaction time of the actual dangerous situation and the correct processing rate of the actual dangerous situation are input into the safety monitoring model to obtain the construction safety information. 7. The method according to claim 6, wherein the acquiring the actual dangerous situation reaction time comprises: Obtain the time from the occurrence of multiple dangerous situations to the occurrence of the reaction within the preset time interval, and obtain the reaction time of multiple original dangerous situations; The actual dangerous situation reaction time is obtained according to the plurality of original dangerous situation reaction times. 8. The method according to claim 6, wherein the obtaining the correct processing rate of the actual dangerous situation comprises: Obtain the number of dangerous situations handled and the number of correct handling of dangerous situations within a preset time interval; According to the number of times of handling the dangerous situation and the number of correct handling of the dangerous situation, the rate of obtaining the correct handling of the actual dangerous situation is obtained. 9. The method according to any one of claims 1 to 4, wherein the judging according to the construction safety information whether the construction personnel have hidden dangers in construction safety comprises: If the construction safety information is less than or equal to a preset first threshold, it is determined that the construction personnel have potential construction safety hazards; otherwise, it is determined that the construction personnel do not have potential construction safety hazards. 10. A construction safety monitoring device based on brain wave analysis, characterized in that, comprising: The acquisition module is used to collect the brainwave signals of construction workers; an analysis module, configured to classify the brainwave signals with a preset sparse representation classifier, and obtain the fatigue level of the construction worker according to the classification result; a model building module for building a safety monitoring model according to the fatigue degree; a processing module, used for inputting the obtained hazard processing information into the safety monitoring model to obtain construction safety information; The judgment module is used for judging whether the construction personnel have hidden dangers of construction safety according to the construction safety information.

Images