A method, system and device for analyzing the comfort of high-speed elevator passengers based on electroencephalogram

Abstract

The present invention provides a method, system and device for analyzing the comfort level of passengers in high-speed elevators based on electroencephalogram (EEG). The invention simultaneously collects and stores the acceleration data of the elevator car and the EEG data of the passengers; intercepts the EEG data and acceleration data according to the operating state of the elevator; preprocesses the above data; forms operation indexes and EEG indexes based on the feature extraction of the above data; finally, by recording the above indexes, forms operation index curves and EEG index curves, providing a tool for correlation analysis between elevator operation and passenger feelings, making the evaluation of the comfort level of passengers in high-speed elevators more objective and accurate. Through the collection, preprocessing, feature extraction and analysis of operation signals and EEG signals, the present invention provides a new objective analysis tool for the evaluation of the comfort level of passengers in high-speed elevators and the optimization design of elevator operation curves, avoiding the evaluation deviation caused by the uncertainty of subjective evaluation in the evaluation of the comfort level of passengers in the current transportation system.

Description

Technical Field

[0001] The present invention relates to the fields of high-speed elevator passenger comfort analysis and neuroscience, and specifically relates to a method, system, and device for analyzing the comfort of passengers based on human electroencephalogram during the operation of a high-speed elevator. Background Art

[0002] As a key vertical transportation vehicle, elevators have become an important part of modern urban infrastructure. Passenger comfort is an important indicator for evaluating the performance of high-speed elevators and is used to evaluate the riding experience of elevator passengers. Currently, the measurement of passenger comfort mainly relies on subjective scale methods, which quantify the operation data of the car through acceleration sensors and construct a comfort evaluation system. Existing methods generally have evaluation biases due to factors such as differences in perception among different people and memory errors. Summary of the Invention

[0003] In order to overcome the deficiencies of the prior art, the present invention provides a method, system, and device for analyzing the comfort of passengers based on human electroencephalogram during the operation of a high-speed elevator, aiming to provide a new objective analysis tool, thereby avoiding the evaluation biases caused by the uncertainties in the subjective evaluation of passenger comfort in current transportation systems and improving the reliability and effectiveness of passenger comfort analysis.

[0004] To achieve the above objective, the present invention provides a method for analyzing the comfort of passengers in a high-speed elevator based on electroencephalogram, including the following steps:

[0005] S1: Simultaneously collect and store the human electroencephalogram signals of passengers when riding a high-speed elevator and the car operation signals of the high-speed elevator;

[0006] S2: Based on the car operation signals, judge the changes in the operation state of the high-speed elevator; intercept the human electroencephalogram signals and car operation signals during the change of the operation state to obtain human electroencephalogram data and car operation data;

[0007] S3: Preprocess the human electroencephalogram data and car operation data;

[0008] S4: Extract features from the human electroencephalogram data and car operation data, and form human electroencephalogram indicators and car operation indicators after analysis; among them, the steps of feature analysis of the human electroencephalogram data include: performing power spectrum analysis on the intercepted electroencephalogram signals and performing effective connectivity analysis on the electroencephalogram signals;

[0009] S5: By recording and storing the human electroencephalogram indicators and car operation indicators, form a human electroencephalogram indicator curve and a car operation indicator curve; among them, the indicator curve is a quantitative trajectory of a single indicator mapped in a two-dimensional Cartesian coordinate system.

[0010] Preferably, the steps of preprocessing include:

[0011] A filter is used to remove the noise in the human EEG data and the car operation data;

[0012] Resample the human EEG data and the car operation data;

[0013] An independent component analysis algorithm is used to remove the interference signals in the human EEG data.

[0014] Preferably, in step S4, the steps of performing power spectrum analysis on the intercepted EEG signals include: calculating the power spectral density of each data segment in different EEG frequency bands using the Welch algorithm as an EEG power spectrum index.

[0015] Preferably, in step S4, the specific steps of performing effective connectivity analysis on the EEG signals include: obtaining the direct directed transfer function matrix of each data segment; calculating the superimposed average of the direct directed transfer function matrices of all data segments, and after dividing them into frequency bands, obtaining the mean value of the direct directed transfer function in different connection directions in each frequency band as an EEG effective connectivity index.

[0016] The present invention also provides an analysis system for the comfort of high-speed elevator passengers based on EEG, which includes:

[0017] An acquisition module for acquiring the human EEG signals of the passengers and the car operation signals of the high-speed elevator;

[0018] A trigger module, coupled to the car operation data acquisition module, configured to judge the change in the operation state of the high-speed elevator car based on the car operation signal and output an activation signal to the data analysis module during the change in the operation state;

[0019] A data analysis module configured to receive the activation signal, the human EEG signal, and the car operation signal; intercept and record the human EEG signal and the car operation signal according to the activation signal to obtain human EEG data and car operation data; perform time synchronization, data preprocessing, and feature extraction analysis on the human EEG data and the car operation data, and output EEG indexes and car operation indexes; wherein, when performing feature analysis on the human EEG data, perform power spectrum analysis on the intercepted EEG signals through the Welch algorithm to obtain the power spectrum index of the EEG data, and perform effective connectivity analysis on the EEG signals through the direct directed transfer function to obtain the effective connectivity index of the EEG data.

[0020] Preferably, when the trigger module judges the change in the operation state of the high-speed elevator car, the process is as follows:

[0021] Set a threshold according to the historical data of the car operation signal, determine whether the car operation signal exceeds the threshold range. When the judgment result is yes, output an activation signal; when the judgment result is no, stop outputting the activation signal.

[0022] Preferably, the car operation signal includes an acceleration signal, a speed signal and an attitude signal; the car operation index includes the time-domain feature, frequency-domain feature and information entropy of the operation data; the electroencephalogram index includes the time-domain feature, frequency-domain feature, information entropy and effective connection of the electroencephalogram data.

[0023] The present invention also provides an analysis device for the comfort of high-speed elevator passengers based on electroencephalogram, which performs analysis by applying the analysis method for the comfort of high-speed elevator passengers based on electroencephalogram, including:

[0024] An electroencephalogram sensor, an operation sensor, an intelligent terminal, an uninterruptible power supply, a toolbox and a mobile acquisition trolley; the electroencephalogram sensor includes the electroencephalogram electrode cap and an electroencephalogram signal amplifier; the operation sensor includes an acceleration sensor and an operation sensor host; the mobile acquisition trolley includes, from top to bottom: an equipment layer, a tool layer and an operation layer, and the layers are rigidly connected by four groups of fixed rods; the equipment layer includes a placement chassis and universal wheels connected to the bottom of the placement chassis for placing the uninterruptible power supply; the tool layer is used for placing the acceleration sensor, the electroencephalogram electrode cap and the toolbox; the operation layer includes an operation console, and a handrail is arranged on one side of the operation console, and the electroencephalogram signal amplifier and the operation sensor host are detachably connected to one side of the bottom surface of the operation console; the operation layer is used for placing the intelligent terminal; the electroencephalogram sensor, the operation sensor, the uninterruptible power supply and the intelligent terminal are electrically connected to each other;

[0025] When performing analysis, collect human electroencephalogram data through the electroencephalogram sensor and collect car operation data through the operation sensor; input the collected data into the intelligent terminal for judging the change of the operation state of the elevator car, preprocessing the human electroencephalogram data and the car operation data, and performing feature extraction and analysis, and finally outputting human electroencephalogram indexes and car operation indexes.

[0026] The present invention also provides an intelligent terminal, which includes:

[0027] At least one processor, and a machine-readable storage medium communicatively connected to the at least one processor; wherein, the machine-readable storage medium has computer instructions executed by the at least one processor; the computer instructions are used to implement the analysis method and system for the comfort of high-speed elevator passengers based on electroencephalogram.

[0028] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0029] Based on brain science, the present invention realizes an analysis method that does not rely on the subjective feedback of the occupant, avoiding the influence brought by oral communication. The present invention uses electroencephalogram (EEG) signals to analyze the ride comfort of the occupant. Compared with the peripheral electrophysiological analysis techniques such as electrocardiogram (ECG) and electrodermal activity (EDA), EEG signals have higher temporal resolution and are suitable for capturing neural events and cognitive events in a short time in high-speed elevators. In addition, EEG signals are directly related to high-level cognitive functions such as comfort, while peripheral physiology such as ECG and EDA is only indirectly related to high-level neural activities. Based on this, analyzing the comfort of elevator occupants through EEG signals has higher objectivity and reliability. Description of the Drawings

[0030] Figure 1 It is a flowchart of a method for analyzing the comfort of high-speed elevator occupants based on EEG provided by the present invention;

[0031] Figure 2 It is a framework diagram of a system for analyzing the comfort of high-speed elevator occupants based on EEG provided by the present invention;

[0032] Figure 3 It is a flowchart of a system for analyzing the comfort of high-speed elevator occupants based on EEG provided by the present invention;

[0033] Figure 4 It is a schematic diagram of the connection positions of human brain electrodes;

[0034] Figure 5 It is a graph of the running acceleration of a high-speed elevator going up and down;

[0035] Figure 6 It is a schematic structural diagram of a device for analyzing the comfort of high-speed elevator occupants based on EEG provided by the present invention;

[0036] Figure 7 It is a schematic diagram of the use of a device for analyzing the comfort of high-speed elevator occupants based on EEG provided by the present invention. Detailed Embodiments

[0037] The following specific examples illustrate the embodiments of the present invention. Those skilled in the art can easily understand the other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0038] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner. Therefore, only the components related to the present invention are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The types, quantities, and proportions of the components in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0039] Occupant comfort originates from human perception, and the nervous system plays a major regulatory role. The neural pathways of this system are widely distributed in the brainstem, cerebellum, and cerebral cortex regions, triggering physiological responses by integrating perceptual information. Based on this, by detecting the electrophysiological signals of relevant brain regions and the parameters of the signals, the analysis of the comfort of high-speed elevator occupants can be achieved.

[0040] As Figures 1 - 7 shown, a method for analyzing the comfort of high-speed elevator occupants based on electroencephalogram provided by the present invention includes the following steps:

[0041] S1: Simultaneously collect and store the human electroencephalogram signal of the occupant when taking the high-speed elevator and the car operation signal of the high-speed elevator;

[0042] S2: Based on the car operation signal, judge the change in the operation state of the high-speed elevator; intercept the human electroencephalogram signal and the car operation signal during the change in the operation state to obtain human electroencephalogram data and car operation data;

[0043] S3: Preprocess the human electroencephalogram data and the car operation data;

[0044] S4: Extract features from the human electroencephalogram data and the car operation data, and form human electroencephalogram indicators and car operation indicators after analysis; among them, the steps for feature analysis of the human electroencephalogram data include: performing power spectrum analysis on the intercepted electroencephalogram signal and performing effective connectivity analysis on the electroencephalogram signal;

[0045] S5: By recording and storing the human electroencephalogram indicators and the car operation indicators, form a human electroencephalogram indicator curve and a car operation indicator curve; among them, the indicator curve is a quantitative trajectory of a single indicator mapped in a two-dimensional Cartesian coordinate system.

[0046] First, the experimenter placed the accelerometer at the center of the high-speed elevator car to collect the acceleration signal of the high-speed elevator. The sampling rate of the accelerometer is 1 kHz and the resolution is 0.0005 g / LSB. The experimenter placed the 32-lead EEG electrode cap on the occupant's head. The sampling rate of the EEG acquisition system was 1 kHz. The electrode distribution followed the 10-10 international standard lead system. The Cz electrode was set as the reference electrode and the Fpz electrode was set as the ground electrode. The occupant was required to clean his hair and inject conductive paste at the electrode position to ensure that the electrode impedance was less than 5k ohms during the EEG recording process. The experiment sent synchronized timestamps to the EEG acquisition system and accelerometer through serial communication. The timestamps were sent every 30 seconds.

[0047] Under the guidance of the experimenter, the passenger enters the elevator and stands near the center of the elevator car with his eyes closed. First, the acceleration signal of the elevator in a stationary state and the resting EEG signal of the passenger in the elevator in a stationary state are collected. The three-axis acceleration signal of the elevator is extracted, and its Euclidean norm is taken as the elevator acceleration data. The acceleration data is transmitted to the trigger module, which first calculates the confidence interval of the acceleration data of the elevator in a stationary state. The calculation formula is:

[0048]

[0049] in, At a 95% confidence level Value, approximately equal to 1.96; is the sample mean of vertical acceleration; is the standard deviation; is the number of samples, is the limit of the confidence interval. The acceptance domain of the data is calculated by the above formula.

[0050] Then, under the operation of the experimenter, each passenger experienced "up-down-up-down", a total of 4 elevator runs. During the elevator operation, the elevator acceleration signal and the passenger's EEG signal were recorded. The start and end time of the acceleration data segment exceeding the upper confidence limit and below the lower confidence limit were taken as the elevator acceleration event window.

[0051] Preprocess the EEG signals.

[0052] First, a band-pass filter with a frequency range of 0.5 - 45 Hz is used to filter the EEG data, and the sampling signal is reduced to 250 Hz to remove the baseline drift and power frequency interference of the signal. Then, the reference point of the EEG signal is adjusted to the average reference. The pseudo-shadow subspace reconstruction algorithm is used to remove the bad data segments in the signal. The human EEG data and the car operation data are resampled. The independent component analysis algorithm is used to remove the eye movement and EMG interference in the EEG data. The EEG and acceleration data are time-synchronized according to the synchronous timestamps of each sensor. Finally, the elevator acceleration event window is used to intercept the EEG data.

[0053] Perform power spectrum analysis on the intercepted EEG signal.

[0054] The Welch algorithm is used to calculate the power spectral density of each data segment in different EEG frequency bands. Among them, the Delta band is in the range of 1 - 4 Hz; the Theta band is in the range of 4 - 8 Hz; the Alpha band is in the range of 8 - 13 Hz; the Beta band is in the range of 13 - 30 Hz; the Gamma band is in the range of 30 - 45 Hz. Among them, Welch selects the Hanning window, calculates the power spectral density for each data segment of the EEG sample, and calculates the average value of each port. Extract the effective connectivity features of the EEG data in the frontal brain region, and use the direct directed transfer function to calculate the effective connectivity values between each EEG port; then calculate the average value of the effective connectivity values within each brain region and the average value of the effective connectivity values between brain regions as the effective connectivity features.

[0055] Perform effective connectivity analysis on the EEG signal.

[0056] The calculation of the effective connectivity value parameters is performed using the direct directed transfer function based on Granger causality. First, a time-varying window analysis is used to establish a multivariate autoregressive model of the sliding window. A rectangular window is selected, with a duration of 0.4 seconds and a step of 0.03 seconds.

[0057] The multivariate autoregressive model is defined as:

[0058]

[0059] In the formula, is the 32-channel EEG time series, is the 32×32 coefficient matrix, is the white noise remainder, is the order of the multivariate autoregressive model determined by the Hannan-Quinn information criterion.

[0060] Use the fast Fourier transform to transform the above formula into the frequency domain, that is:

[0061]

[0062] Among them, is the transfer matrix of the system, is the frequency, is a complex number. The direct directional transfer function is defined as:

[0063]

[0064] where, is the full-frequency directional transfer function; are the row and column numbers of the matrix respectively.

[0065]

[0066] In the formula represents the number of channels, is the full-frequency directional transfer function of the column number.

[0067] is the partial coherence function, defined as:

[0068]

[0069] Its expression is:

[0070] ,

[0071] where, is the power spectral function.

[0072] After obtaining the direct directional transfer function matrix of each data segment in this way, first calculate the superimposed average of the direct directional transfer function matrices of all data segments. Then, after dividing it into frequency bands, calculate the average value of the direct directional transfer function in different connection directions under each frequency band, as an index to describe the effective connection strength of EEG.

[0073] Finally, statistical analysis is carried out on the characteristics of the human EEG data in the resting state and the EEG data characteristics intercepted in the acceleration event window of the elevator. The analysis results show that under the influence of the high-speed elevator acceleration, the absolute power of the whole-brain Theta band of the human body increases from 0.45±0.022 μV² / Hz at the baseline to 0.726±0.197 μV² / Hz.

[0074] Table 1 shows the EEG characteristic parameters (mean ± standard deviation) in the baseline state and the acceleration state, as well as the corresponding results of the p-value of the comparison between the two.

[0075]

[0076] Table 1

[0077] Based on the above analysis, compared with the prior art, the present invention realizes the acquisition and analysis of human EEG data of passengers in a high-speed elevator environment, and uses this as the basis for comfort analysis.

[0078] As Figure 3 shown, the present invention also provides a high-speed elevator occupant comfort analysis system based on electroencephalogram (EEG), which includes: a collection module, a trigger module, and a data analysis module. The collection module is used to collect the human EEG signals of the occupant and the car operation signals of the high-speed elevator. The trigger module is coupled with the car operation data collection module, and is configured to judge the change of the operation state of the high-speed elevator car based on the car operation signals, and output an activation signal to the data analysis module during the change of the operation state. The data analysis module is configured to receive the activation signal, the human EEG signals, and the car operation signals; intercept and record the human EEG signals and the car operation signals according to the activation signal to obtain human EEG data and car operation data; perform time synchronization, data preprocessing, and feature extraction analysis on the human EEG data and the car operation data, and output EEG indexes and car operation indexes. Among them, the collection module includes a human EEG data collection module for collecting the human EEG signals of the occupant; a car operation data collection module for collecting the car operation signals of the high-speed elevator;

[0079] Among them, when the trigger module judges the change of the operation state of the high-speed elevator car, specifically: set a threshold according to the historical data of the car operation signals; judge whether the car operation signals exceed the threshold range; when the judgment result is "yes", output an activation signal; when the judgment result is "no", stop outputting the activation signal; wherein, the threshold is set to the 95% confidence interval of the statistical distribution of the historical data.

[0080] Among them, when the collection module collects human EEG data, it is collected by an EEG sensor; the EEG sensor is set on the head of the occupant by an EEG electrode cap; according to the relevant regulations in GB / T 24474.1-2020 "Elevator - Part 1: Measurement of ride quality", when the collection module collects car operation data, it is collected by an operation sensor; the operation sensor is an acceleration sensor set at the center position of the bottom of the high-speed elevator car.

[0081] Among them, the operation indexes include the time-domain characteristics, frequency-domain characteristics, and information entropy of the operation data; the EEG indexes include the time-domain characteristics, frequency-domain characteristics, information entropy, and effective connectivity of the EEG data.

[0082] The present invention also provides an intelligent terminal, including: at least one processor; and a machine-readable storage medium communicatively connected with the at least one processor; wherein, the machine-readable storage medium has computer instructions executed by the at least one processor; the computer instructions are used to implement the high-speed elevator occupant comfort analysis system based on EEG.

[0083] As Figures 6 - 7 shown, the present invention also provides a high-speed elevator occupant comfort analysis device based on EEG, which includes:

[0084] It includes an electroencephalogram (EEG) sensor, an operation sensor, a smart terminal, an uninterruptible power supply, a toolbox, and a mobile acquisition trolley; the EEG sensor includes an EEG electrode cap and an EEG signal amplifier; the operation sensor includes an acceleration sensor and an operation sensor host; the mobile acquisition trolley includes an equipment layer, a tool layer, and an operation layer; the equipment layer and the tool layer are rigidly connected by four groups of fixed rods; the tool layer and the operation layer are rigidly connected by four groups of fixed rods; the equipment layer includes a placement chassis and universal wheels connected to the bottom of the placement chassis for placing the uninterruptible power supply; the tool layer is used for placing the acceleration sensor, the EEG electrode cap, and the toolbox; the operation layer includes an operation console, and at least one side of the operation console is provided with a handrail, and one side of the bottom surface of the operation console is detachably connected with the EEG signal amplifier and the operation sensor host; the operation layer is used for placing the smart terminal; the EEG sensor, the operation sensor, the uninterruptible power supply, and the smart terminal are electrically connected to each other.

[0085] When analyzing, the human EEG data is collected through the EEG sensor, and the car operation data is collected through the operation sensor; the collected data is input into the smart terminal, and the smart terminal analyzes and judges the collected data, and finally outputs the human EEG index and the car operation index. Among them, the specific analysis and judgment process of the smart terminal for the collected data is the same as the process in the method for analyzing the comfort of high-speed elevator passengers based on EEG, and will not be repeated here.

[0086] Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Claims

1. A method for analyzing the comfort of occupants in a high-speed elevator based on electroencephalogram, characterized in that, It includes the following steps: S1: Simultaneously collect and store the human electroencephalogram signal of the occupant when taking a high-speed elevator and the car operation signal of the high-speed elevator; S2: Based on the car operation signal, judge the change of the operation state of the high-speed elevator; intercept the human electroencephalogram signal and the car operation signal during the change of the operation state to obtain human electroencephalogram data and car operation data; The steps of intercepting human electroencephalogram data and elevator operation data include: Collect the acceleration signal of the elevator in the stationary state and the resting electroencephalogram signal of the occupant in the stationary state of the elevator; extract the three-axis acceleration signal of the elevator and take its Euclidean norm as the elevator acceleration data; Calculate the confidence interval of the elevator acceleration data in the stationary state; Operate the elevator and record the acceleration signal of the elevator car and the electroencephalogram signal of the occupant; Take the start and end times of the acceleration data segments that exceed the upper confidence limit and are lower than the lower confidence limit as the elevator acceleration event window; S3: Preprocess the human electroencephalogram data and the car operation data; The steps of the preprocessing include: Filter the electroencephalogram data with a filter of 0.5~45 Hz, and reduce the sampling signal to 250 Hz to remove the noise in the human electroencephalogram data; Adopt the pseudo-shadow space reconstruction algorithm to remove the bad data segments in the human electroencephalogram data; Adopt the independent component analysis algorithm to remove the interference signals in the human electroencephalogram data; Synchronize the electroencephalogram and acceleration data according to the synchronous timestamp; Adopt the elevator acceleration event window to intercept the electroencephalogram data; S4: Extract features from the human electroencephalogram data and the car operation data, and form human electroencephalogram indicators and car operation indicators after analysis; among them, the steps of feature analysis of the human electroencephalogram data include: performing power spectrum analysis on the intercepted electroencephalogram signal and performing effective connectivity analysis on the electroencephalogram signal; The steps of performing power spectrum analysis on the intercepted electroencephalogram signal include: calculating the power spectral density of each data segment in different electroencephalogram frequency bands by using the Welch algorithm as an EEG power spectrum index; among them, the electroencephalogram frequency bands include: Delta band, Theta band, Alpha band, Beta band and Gamma band; the Welch algorithm uses a Hanning window to calculate the power spectral density of each data segment of the EEG sample and find the average value of each electroencephalogram signal port; extract the effective connectivity features of the electroencephalogram data, and calculate the effective connectivity values between each electroencephalogram port by using the direct directed transfer function based on Granger causality; calculate the average value of the effective connectivity values within each brain region and the average value of the effective connectivity values between brain regions as the effective connectivity features; S5: By recording and storing the human electroencephalogram indicators and car operation indicators, form a human electroencephalogram indicator curve and a car operation indicator curve; among them, the indicator curve is the quantization trajectory of a single indicator mapped in a two-dimensional Cartesian coordinate system.

2. The method for analyzing the comfort of high-speed elevator passengers based on electroencephalogram according to claim 1, wherein In the step S4, the specific steps for effective connectivity analysis of EEG signals include: obtaining the direct directed transfer function matrix of each data segment; calculating the superposition average of the direct directed transfer function matrices of all data segments, and after dividing them into frequency bands, obtaining the mean value of the direct directed transfer function in different connection directions in each frequency band as an EEG effective connectivity index.

3. A high-speed elevator passenger comfort analysis system based on electroencephalogram, characterized in that, Including: An acquisition module for acquiring the human EEG signals of the occupant and the car operation signals of the high-speed elevator; A trigger module coupled to the car operation signal acquisition module, configured to judge the change in the operation state of the high-speed elevator car based on the car operation signal, and output an activation signal to the data analysis module during the change in the operation state; A data analysis module configured to receive the activation signal, the human EEG signals, and the car operation signals; intercept and record the human EEG signals and the car operation signals according to the activation signal to obtain human EEG data and car operation data; The steps of intercepting EEG data include: Acquiring the acceleration signals in the elevator stationary state and the resting EEG signals of the occupant in the elevator stationary state; extracting the three-axis acceleration signals of the elevator and taking their Euclidean norm as the elevator acceleration data; Calculating the confidence interval of the elevator stationary state acceleration data; Operating the elevator and recording the acceleration signals of the elevator and the EEG signals of the occupant; Taking the start and end times of the acceleration data segments exceeding the confidence upper limit and lower than the confidence lower limit as the elevator acceleration event window; Performing time synchronization, data preprocessing, and feature extraction analysis on the human EEG data and the car operation data, and outputting EEG indexes and car operation indexes; The steps of the preprocessing include: Filtering the EEG data with a filter of 0.5~45 Hz and reducing the sampling signal to 250 Hz to remove the noise in the human EEG data; Adopting a pseudo-shadow subspace reconstruction algorithm to remove the bad data segments in the signals; Adopting an independent component analysis algorithm to remove the interference signals in the human EEG data; Performing time synchronization on the EEG and acceleration data according to the synchronization timestamps of each sensor; Intercepting the EEG data with the elevator acceleration event window; Wherein, when performing feature analysis on the human EEG data, performing power spectrum analysis on the intercepted EEG signals through the Welch algorithm to obtain the power spectrum index of the EEG data, and performing effective connectivity analysis on the EEG signals through the direct directed transfer function to obtain the effective connectivity index of the EEG data; The steps of performing power spectrum analysis on the intercepted EEG signals include: calculating the power spectral density of each data segment in different EEG frequency bands using the Welch algorithm as an EEG power spectrum index; where the EEG frequency bands include: Delta band, Theta band, Alpha band, Beta band, and Gamma band; the Welch algorithm uses a Hanning window to calculate the power spectral density of each data segment of the EEG samples and obtains the average value of each EEG signal port; extracting the effective connectivity features of the EEG data, and calculating the effective connectivity values between each EEG port using the direct transfer function based on Granger causality; calculating the average value of the effective connectivity values within each brain region and the average value of the effective connectivity values between brain regions as the effective connectivity features.

4. The EEG-based high-speed elevator passenger comfort analysis system according to claim 3, wherein When the trigger module determines the change in the operating state of the high-speed elevator car, the process is as follows: Setting a threshold according to the historical data of the car running signal, determining whether the car running signal exceeds the threshold range, when the determination result is yes, outputting an activation signal, and when the determination result is no, stopping outputting the activation signal.

5. The EEG-based high-speed elevator passenger comfort analysis system according to claim 3, characterized in that, The car running signals include acceleration signals, speed signals, and attitude signals; the car running indicators include the time-domain characteristics, frequency-domain characteristics, and information entropy of the running data; the EEG indicators include the time-domain characteristics, frequency-domain characteristics, information entropy, and effective connectivity of the EEG data.

6. An apparatus for analyzing the comfort of occupants in a high-speed elevator based on electroencephalogram, which analyzes by applying the method for analyzing the comfort of occupants in a high-speed elevator based on electroencephalogram according to any one of claims 1 to 2, characterized in that It includes: EEG sensors, running sensors, intelligent terminals, uninterruptible power supplies, toolboxes, and mobile acquisition trolleys; The EEG sensors include: an EEG electrode cap and an EEG signal amplifier; the running sensors include an acceleration sensor and a running sensor host; the mobile acquisition trolley includes, from top to bottom: an equipment layer, a tool layer, and an operation layer, and the layers are rigidly connected by four groups of fixed rods; the equipment layer includes a placement chassis and universal wheels connected to the bottom of the placement chassis for placing the uninterruptible power supply; the tool layer is used to place the acceleration sensor, the EEG electrode cap, and the toolbox; the operation layer includes an operation console, where a handrail is provided on one side of the operation console, and the EEG signal amplifier and the running sensor host are detachably connected to one side of the bottom surface of the operation console; the operation layer is used to place the intelligent terminal; the EEG sensors, the running sensors, the uninterruptible power supply, and the intelligent terminal are electrically connected to each other; When performing analysis, the human EEG data is collected through the EEG sensors, and the car running data is collected through the running sensors; the collected data is input into the intelligent terminal for judging the change in the operating state of the elevator car, preprocessing the human EEG data and the car running data, and extracting and analyzing features, and finally outputting the human EEG indicators and the car running indicators.

7. An intelligent terminal, characterized in that, It includes: At least one processor, and a machine-readable storage medium communicatively connected to at least one processor; wherein, the machine-readable storage medium has computer instructions executed by at least one processor; the computer instructions are used to implement the method for analyzing the comfort of high-speed elevator passengers based on EEG as described in any one of claims 1 to 2.

Images