Fatigue monitoring safety helmet

Abstract

The invention discloses a fatigue monitoring safety helmet which comprises a helmet body which can be worn on the head of a user and provide safety protection. The signal acquisition unit is integrated in the cap body, is used for acquiring electroencephalogram signals of a user, and at least comprises a brain wave sensor; and the control processor is arranged in the helmet body, is in communication connection with the signal acquisition unit, and is used for receiving the electric signals fed back by the sensor, performing processing, feature extraction and result comparison on the electric signals and performing fatigue state judgment. The ICA algorithm is adopted to carry out real-time source separation on original electroencephalogram signals, motion artifacts and physiological interference can be effectively stripped, and the monitoring reliability is remarkably improved; the device is simple in structure, stable and comfortable to wear, integrates physiological fatigue monitoring, environmental risk perception and active intervention, constructs a complete safety closed loop of perception-analysis-early warning-execution, and changes passive protection into active early warning; the system integration degree is high, and cooperative work of multifunctional modules is achieved through hardware integration and software algorithm optimization.

Description

TECHNICAL FIELD

[0001] The present application relates to a safety helmet, in particular to a fatigue monitoring safety helmet. BACKGROUND

[0002] The safety helmet is a labor protection product, which can absorb most of the impact energy by elastic deformation and plastic deformation when impacted or extruded by external objects, so as to protect the head of the worker; with the progress of science and technology, part of the safety helmet has communication function, but in high-risk scenes such as tunnel construction, power inspection and mine operation, the risk of accidents caused by fatigue, heat stroke and distraction of workers in high-risk operation scenes (such as tunnel construction, power inspection and mine operation) is extremely high, the safety helmet can only provide passive protection, lacks active early warning capability and cannot identify the state of the worker. SUMMARY

[0003] The present application aims to provide a fatigue monitoring safety helmet to solve the problems in the background art.

[0004] To achieve the above-mentioned purpose, the present application provides the following technical solutions: A fatigue monitoring safety helmet for detecting the fatigue state of a user, comprising: A helmet body for the user to wear on the head and provide safety protection; A signal acquisition unit integrated in the helmet body for acquiring the electroencephalogram signal of the user, comprising at least one electroencephalogram sensor; the electroencephalogram sensor is connected to the inner wall of the helmet body through a connecting bracket, a floating joint is provided on the connecting bracket, and a mounting hole for mounting the electrode of the electroencephalogram sensor is provided on the floating joint; A control processor provided in the helmet body and in communication connection with the signal acquisition unit, for receiving the electrical signal fed back by the sensor, processing the electrical signal, extracting features and comparing results, and making a fatigue state determination; An alarm in communication connection with the control processor and issuing an alarm according to the fatigue state determination result; A power supply for providing energy for the signal acquisition unit, the control processor and the alarm.

[0005] Further, the sensor uses a TGAM electroencephalogram sensor with a frequency range of 3-125 Hz and a baud rate of 57600; the reference electrode is provided in the safety helmet at a position corresponding to the forehead of the wearer.

[0006] Further, the helmet body is provided with a lighting device electrically connected to the control processor, and is equipped with a light sensor in communication connection with the control processor.

[0007] Further, the helmet body is provided with a harmful gas sensor in communication connection with the control processor.

[0008] Further, a ventilation hole is formed on the cap.

[0009] Further, the application also provides a fatigue detection method using the above device, including the following steps: S1, collecting the electrical signals generated by the brain neurons of the user; S2, obtaining the purified signal after filtering, deartifacting and segmenting the original electrical signal: S3, extracting the features of the purified signal, and determining the threshold of the extracted feature value, and outputting the fatigue state; S4, executing the early warning operation according to the fatigue state.

[0010] Compared with the prior art, the application has the beneficial effects that: The ICA algorithm is used to perform real-time source separation on the original brain electrical signals, which can effectively strip the motion artifacts and physiological interference, and significantly improve the monitoring reliability; it is stable, comfortable to wear, and integrates physiological fatigue monitoring, environmental risk perception and active intervention, and builds a complete safety closed loop of "perception-analysis-warning-execution", which changes passive protection to active early warning; the system has high integration, and through hardware integration and software algorithm optimization, the collaborative work of multiple functional modules is realized. BRIEF DESCRIPTION OF DRAWINGS

[0011] Fig. 1 is a schematic diagram of the overall structure of the application; Fig. 2 is a schematic diagram of the working process of the application.

[0012] In the figure: 1, cap; 2, signal acquisition unit; 3, control processor; 4, warning device; 5, power supply; 6, lighting device; 7, light sensor; 8, harmful gas sensor; 9, ventilation hole. DETAILED DESCRIPTION

[0013] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only a part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the application.

[0014] Please refer to Figs. 1-2 The application provides a technical solution: a fatigue monitoring safety cap for detecting the fatigue state of a user, comprising: Cap 1, which can be worn on the head of the user and provides safety protection; A signal acquisition unit 2 is integrated in the cap 1 and used to acquire the brain electrical signals of the user, and at least includes one brain wave sensor; the brain wave sensor is connected with the inner wall of the cap 1 through a connecting support, a floating joint is arranged on the connecting support, and a mounting hole for mounting the electrode of the brain wave sensor is arranged on the floating joint; A control processor 3 is arranged in the cap 1 and is in communication connection with the signal acquisition unit 2, used to receive the electrical signals fed back by the sensor, process the electrical signals, extract features and compare results, and make a fatigue state determination; An alarm 4 is in communication connection with the control processor 3 and issues an alarm according to the fatigue state determination result; A power supply 5 is used to provide energy for the signal acquisition unit 2, the control processor 3 and the alarm 4; Further, the sensor adopts a TGAM brain wave sensor, the frequency range is 3-125 Hz, and the baud rate is 57600; and the reference electrode is arranged in the safety cap at a position corresponding to the forehead of the wearer.

[0015] Further, the cap 1 is provided with a lighting device 6 electrically connected with the control processor 3, and is provided with a light sensor 7 in communication connection with the control processor 3.

[0016] Further, the cap 1 is provided with a harmful gas sensor 8 in communication connection with the control processor 3.

[0017] Further, the cap 1 is provided with a ventilation hole 9.

[0018] A fatigue detection method applied to the device according to any one of claims 1-5, characterized in that the method comprises the following steps: S1, collecting the electrical signals generated by the brain neuron activities of the user; S2, obtaining a purified signal after filtering, de-artifacting and segmenting the original electrical signals: A one-dimensional brain wave signal model can be expressed as: n(k) = f(k) + εe(k) k = 0, 1, …, n-1 (1) In the formula, n(k) is a signal containing noise; f(k) is an original brain wave signal; e(k) is noise; and ε is the standard deviation of the noise coefficient.

[0019] In order to retain the signals of a specific frequency band and remove the noise, filtering is performed: Y(k) = ((x(k)-x(k-1))-(x(k-2)-x(k-3)) In order to eliminate the electro-oculogram and electromyogram interference, de-artifacting is performed: Assuming that the EEG signal is composed of a mixture of multiple original signals, then X=AS X represents the measured brain signal, A is the mixture matrix, and S represents the independent components. Estimate the mixture matrix A and its pseudo-inverse matrix pinv(A) using ICA. Find S = pinv(A)X Remove the artifact components from the original signal to obtain S The purified signal was obtained by reconstructing the data using X=AS; The signal is segmented for processing; S3. Extract features from the purification signal, determine the threshold of the extracted feature values, and output the fatigue state. For the processed signal, extract the time-domain features: mean and variance. Mean: variance: Frequency domain feature extraction: power spectral density, α / β / θ / δ wave energy, etc., achieved through Fourier transform. Calculate the Fourier transform of x(t): X(jw) Modulus: |X(jw)|, then square: |X(jw)|^2, then divide by the sample length: |X(jw)|^2 / T The power spectral density function of x(t) is obtained as: Gxx(w) = |X(jw)|^2 / T Nonlinear feature extraction: sample entropy, approximate entropy; extracting various types of features from EEG signals to comprehensively reflect brain activity in different states; Based on different frequencies, brain waves can be divided into delta waves (0.5~4 Hz), theta waves (4~8 Hz), alpha waves (8~13 Hz), and beta waves (14~30 Hz). Alpha waves can be further divided into slow alpha waves (8~9 Hz), intermediate alpha waves (9~12 Hz), and fast alpha waves (12~14 Hz). The correspondence between different brainwave signals and a person's mental state: Delta waves (0.5~4Hz) represent the mental state of a person in deep sleep or unconsciousness. Theta waves at 4~8Hz indicate a state of light sleep in humans who can be awakened by slight noises. Alpha waves (8-13Hz): A person's mental state is relaxed yet alert, with frequent thought processes. At this time, a person's stress and tension are relatively light. The mental state of a person with beta waves at 14~30Hz is usually one of fear, tension, or anger, with significant emotional fluctuations and the possibility of overreaction. The mind is highly alert, and the body is in a tense state. When people are tired, the brain activity will'slow down': high frequency beta waves weaken, and theta and delta waves, which represent drowsiness, increase; By final calculation comparison, it is determined whether the user is in a fatigue state; S4, a warning operation is performed according to the fatigue state, if it is determined that the user is tired, the alarm 4 voice prompts 'tired', and a light alarm is sent.

[0020] Working principle: when the present application is used, the user's hat body is worn on the head, the forehead reference electrode is in contact with the user's forehead, the forehead part is not covered by hair, can be used as a stable reference point, which helps to improve the accuracy of the signal; The signal acquisition unit transmits the collected electroencephalogram signal to the control processor, then the control processor filters, removes artifacts and segments the electroencephalogram signal to obtain a purified signal: then the purified signal is feature extracted, and the extracted feature value threshold is determined, and the fatigue state is output; if the result is determined as a fatigue state, the control processor controls the alarm to voice prompt 'tired', and sends a light alarm.

[0021] Although the embodiments of the present application have been shown and described, it can be understood by those skilled in the art that various changes, modifications, replacements and variations can be made to the embodiments without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A fatigue monitoring safety helmet for detecting a user's fatigue state, characterized in that, include: The hat body is designed for the user's head to wear and provide safety protection; A signal acquisition unit, integrated within the cap body, is used to acquire the user's electroencephalogram (EEG) signals and includes at least one EEG sensor. The EEG sensor is connected to the inner wall of the cap body via a connecting bracket, which is equipped with a floating connector and mounting holes for mounting the EEG sensor electrodes. A control processor, located inside the cap, is communicatively connected to the signal acquisition unit. It is used to receive electrical signals fed back by the sensor, process the electrical signals, extract features, compare results, and determine fatigue state. The alarm device communicates with the control processor and issues an alarm based on the fatigue status determination result; The power supply provides energy to the signal acquisition unit, control processor, and alarm.

2. The fatigue monitoring safety helmet according to claim 1, characterized in that, The sensor is a TGAM brainwave sensor with a frequency range of 3-125Hz and a baud rate of 57600; its reference electrode is set inside the helmet at the position corresponding to the wearer's forehead.

3. The fatigue monitoring safety helmet according to claim 1, characterized in that, The cap is equipped with a lighting device electrically connected to the control processor, and a light sensor communicatively connected to the control processor.

4. The fatigue monitoring safety helmet according to claim 1, characterized in that, The cap is equipped with a hazardous gas sensor that is in communication with the control processor.

5. A fatigue monitoring safety helmet according to claim 1, characterized in that, The cap has ventilation holes.

6. A fatigue detection method applied to the apparatus as described in any one of claims 1-5, characterized in that, Includes the following steps: S1. Collect electrical signals generated by the activity of neurons in the user's brain; S2. After filtering, artifact removal, and segmentation of the original electrical signal, the purified signal is obtained: S3. Extract features from the purification signal, determine the threshold of the extracted feature values, and output the fatigue state. S4. Execute early warning operations based on fatigue status.

Images