High-speed elevator passenger comfort detection method and system based on electrocardiogram and skin conductivity

Abstract

A high-speed elevator passenger comfort detection method based on electrocardiogram and electrodermal conductivity, which simultaneously collects the accelerometer signal, electrocardiogram and electrodermal conductivity signals of the load-bearing platform where the passenger is located in time; classifies and processes the operation status of the load-bearing platform; classifies and marks the accelerometer signal; determines the start and end time of the accelerated operation state; determines the event response time window through the start time and the end time; extracts the features of the heart rate variability or skin conductivity of the passengers within the event response time window to obtain an accelerated state feature set; extracts the features of the electrocardiogram and electrodermal conductivity signals of the passengers outside the event response time window to obtain a baseline feature set; compares the accelerated state feature set with the baseline feature set; the greater the value difference of the comparison result, the lower the passenger's elevator ride comfort. And a high-speed elevator passenger ride comfort measurement system is provided. The present invention improves the accuracy and reliability of high-speed elevator ride comfort measurement.

Description

Technical Field

[0001] The present invention relates to the field of passenger comfort analysis and ergonomics of high-speed elevators, and in particular to a method for detecting human physiological (electrocardiogram and electrodermal) and behavioral dynamic information characteristics in a high-speed elevator translation acceleration environment. Background Art

[0002] In daily life, people often encounter passive acceleration, especially in translational transportation scenarios. A large number of studies have shown that the acceleration of high-speed elevators is closely related to people's emotions and peripheral physiological responses. Therefore, it is very important to develop a method that can sense the human body in passive acceleration events. When people are exposed to translational acceleration, the otolith organs play a role in the vestibular system to sense the passive translation of the body and trigger related human responses.

[0003] In practice, stress is a general term in psychology that refers to an emotional state that contains both negative valence and positive arousal. The experience of stress is paralleled by the activity of two major pathways, one involving the limbic system (called the hypothalamic-pituitary-adrenal axis) and the other involving the sympathetic component of the autonomic nervous system (ANS). Therefore, otolith stimulation consisting of passive translational acceleration can affect stress responses through the projection area of ​​the vestibular cortex to the limbic system, which is mainly involved in the regulation of emotions. In the ANS pathway, autonomic processes usually respond to stress by activating the sympathetic nervous system and simultaneously inhibiting the parasympathetic nervous system.

[0004] Stress-related psychological processes are largely involuntary. The valence of autonomic states associated with the presence of a stressor is highly time-dependent and may be triggered when acceleration occurs but disappear quickly when the stressor is withdrawn. Biosignal signatures mediated by the autonomic nervous system can serve as reliable biomarkers for analyzing such time-dependent psychological activities.

[0005] Electrodermal activity (EDA) is a measure of skin conductivity that reflects the activity of sweat glands. Sweat gland activity is completely controlled by the sympathetic nervous system (SNS), so EDA detection is an indicator of psychophysiological arousal. Skin conductance response (SCR) is a component of EDA. Earlier studies have demonstrated that the frequency of SCRs (SCRfre) increases under stressful situations. We also considered the complex dynamics of event-related SCR (ER-SCR) information and EDA signals, which helped to gain a deeper understanding of the EDA characteristics and stress assessment associated with a single acceleration stimulus. Summary of the invention

[0006] In order to overcome the deficiencies of the prior art, the purpose of the present invention is to provide a high-speed elevator passenger riding comfort detection method based on heart rate variability and skin conductivity, so as to improve the accuracy and reliability of high-speed elevator riding comfort detection.

[0007] To achieve the above object, the present invention adopts a high-speed elevator passenger comfort detection method based on electrocardiogram and skin electricity, comprising the following steps:

[0008] Step 1. Collect the accelerometer signal of the load platform of the high-speed elevator where the passenger is located over time, and simultaneously collect the electrocardiogram and skin conduction signals of the passenger over time;

[0009] Step 2. Classify the operating state of the load-bearing platform, wherein the classification includes a braking stop / constant speed operating state and an accelerated operating state;

[0010] Step 3. Marking the accelerometer signal with the category;

[0011] Step 4. Determine the start time and end time of the acceleration running state in the acceleration signal;

[0012] Step 5. Determine the event response time window of the electrocardiogram and skin electricity associated with the accelerated running state through the start time and the end time;

[0013] Step 6. Extract features of the passenger's electrocardiogram and electrocutaneous signal within the event response time window to obtain at least one feature extraction result, and use the result as the acceleration state feature set of the at least one electrocardiogram and electrocutaneous signal;

[0014] Step 7. Perform the feature extraction on the electrocardiogram and skin electricity of the passenger outside the event response time window to obtain at least one feature extraction result, and use it as a baseline feature set of the electrocardiogram and skin electricity;

[0015] Step 8. Compare the acceleration state feature set in step 6 with the baseline feature set in step 7 to obtain a comparison result;

[0016] Step 9. The greater the difference in the values ​​of the comparison results of step 8, the lower the comfort of the passenger. Meanwhile, the smaller the difference in the values ​​of the comparison results of step 8, the higher the comfort of the passenger.

[0017] Preferably, the accelerometer is placed on the carrying platform and the accelerometer signal includes an acceleration signal in at least one spatial direction.

[0018] Preferably, the operating status of the load-bearing platform is classified and processed, wherein the classification processing includes the following sub-steps:

[0019] Step 2.1. Determine the upper threshold and the lower threshold of the accelerometer signal when the carrier platform is in the braking stop state;

[0020] Step 2.2. Classify the accelerometer signal that is greater than the upper threshold or less than the lower threshold as an accelerated operating state.

[0021] Preferably, the upper threshold and the lower threshold are determined by the following method: collecting the accelerometer signal when the supporting platform is in the braking stop state in step 1; performing a hypothesis test on the acceleration signal in the same spatial direction; given a significance level, determining the acceptance domain of the acceleration signal in the same spatial direction; determining the upper critical value of the acceptance domain as the upper threshold and determining the lower critical value of the acceptance domain as the lower threshold.

[0022] Preferably, the hypothesis test is a two-tailed test and the significance level is 0.05.

[0023] Preferably, in step 4, the start time is the time corresponding to the first data point of the continuous acceleration data marked as the accelerated running state, and the end time is the time corresponding to the last data point of the acceleration data marked as the accelerated running state continuous with the start time.

[0024] Preferably, the event response time window of the electrocutaneous signal is within at most 15 seconds from the start time of the accelerated running state to the end time of the accelerated running state; the event response time window of the electrocardiogram signal is within at most 300 seconds from the start time of the accelerated running state to the end time of the accelerated running state.

[0025] Preferably, in step 6, the feature extraction results include time domain features, frequency domain features, and information entropy features of the electrocardiogram and electrodermal conductivity.

[0026] Preferably, in step 8, the comparison result includes the mean absolute difference, median absolute difference, p value determined by statistical knowledge, and expected mean of the root mean square value between the acceleration state feature set and the baseline feature set.

[0027] Preferably, the time domain features of the ECG and EEG include the root mean square of the difference between consecutive RR intervals of the ECG, the standard deviation of the NN interval of the ECG, the heart rate of the ECG, the skin conductance response frequency of the EEG, the average peak value of the skin conductance response of the EEG, the average delay of the skin conductance response of the EEG and the rising time of the skin conductance response of the EEG;

[0028] The frequency domain features of the ECG and EEG include the absolute power of the ECG's extremely low frequency band, the absolute power of the ECG's low frequency band, the absolute power of the ECG's low frequency band, and the ratio of the absolute power of the ECG's low frequency band to the absolute power of the low frequency band;

[0029] The information entropy characteristics of the electrocardiogram and electroskin electricity include the Shannon entropy of the electrocardiogram and electroskin electricity, the cross entropy of the electrocardiogram and electroskin electricity, the Renyi entropy of the electrocardiogram and electroskin electricity, and the Tsallis entropy of the electrocardiogram and electroskin electricity.

[0030] Preferably, the very low frequency band is 0.0033 to 0.04 Hz, the low frequency band is 0.04 to 0.15 Hz, and the high frequency band is 0.15 to 0.4 Hz.

[0031] A high-speed elevator passenger comfort detection system based on electrocardiogram and skin electricity, the system comprising:

[0032] An electrocardiogram and electrodermal signal acquisition device, used to acquire electrocardiogram and electrodermal signal data of the passenger;

[0033] An acceleration acquisition device, used to acquire the accelerometer signal data of the load-bearing platform of the high-speed elevator where the passenger is located over time;

[0034] A data time synchronization module, used to unify the sampling rates of the electrocardiogram and electrocutaneous signal data of the electrocardiogram and electrocutaneous signal acquisition device and the accelerometer signal data of the acceleration acquisition device, and to align the data frames in time;

[0035] The passenger comfort analysis module is used to preprocess the ECG and galvanic skin signal data and the accelerometer signal data, extract the time domain features, frequency domain features or information entropy features of the ECG and galvanic skin data and form the baseline feature set and the acceleration state feature set, and analyze the passenger comfort through the comparison results of the feature sets.

[0036] Preferably, in the passenger comfort analysis module, the preprocessing includes: performing noise reduction processing on the accelerometer signal data and the electrocardiogram and electrodermal signal data.

[0037] According to the upper threshold and the lower threshold of the accelerometer signal data, the acceleration signal data is divided into the stop / uniform speed running state and the accelerated running state.

[0038] The event response time window of the electrocardiogram and electrocutaneous signal data is determined according to the category label of the data time synchronization module and the acceleration signal data; and the electrocardiogram and electrocutaneous signal data are divided into the event response window and the event response window.

[0039] Preferably, the acceleration acquisition device includes an accelerometer or a posture sensor.

[0040] Preferably, the electrocardiogram and electrodermal collection device comprises an electrode sheet, a finger clip, a wristwatch or a glove.

[0041] Preferably, the noise reduction process includes Kalman filtering, high-pass filtering, low-pass filtering or band-pass filtering.

[0042] The beneficial effects of the present invention are as follows: since the human physiological characteristic response needs to reach millisecond to second level accuracy in time resolution, which is difficult to achieve with conventional detection methods, the proposed high-speed elevator passenger comfort detection method can effectively solve this problem; in addition, based on the accuracy of this time resolution, the present method innovatively provides heart rate variability and skin conductivity characteristics that can effectively reflect the human comfort feeling. The present method can improve the accuracy and reliability of passenger comfort detection in high-speed elevators. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 The figure is a flow chart of a high-speed elevator passenger comfort detection method based on electrocardiogram and skin conductivity.

[0044] Figure 2 This is a downward acceleration diagram of a high-speed elevator car captured using this detection method when it is accelerating upward.

[0045] Figure 3 This is a downward acceleration diagram of a high-speed elevator car captured using this detection method when it is accelerating downward.

[0046] Figure 4 This is a statistical comparison of the SCR frequency of the EDA signal under baseline and acceleration conditions.

[0047] Figure 5 This is a statistical method to compare the differences in the RMSSD parameters of the HRV signal under baseline and acceleration conditions.

[0048] Figure 6 This is a statistical comparison of the differences in LF parameters of HRV signals under baseline and acceleration conditions.

[0049] Figure 7 This is a structural diagram of a high-speed elevator passenger comfort detection system based on electrocardiogram and skin conductivity.

[0050] Figure 8 This is a schematic diagram of the human body electrode connection positions of the skin electrode collection device.

[0051] Fig. 9 This is a schematic diagram of the human body electrode connection positions of the ECG acquisition device.

[0052] Fig.10 This is a schematic diagram of the placement of the acceleration acquisition device at the bottom of the elevator car. DETAILED DESCRIPTION

[0053] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, but the present invention is not limited to these embodiments. The present invention covers any substitution, modification, equivalent method and scheme made within the spirit and scope of the present invention.

[0054] In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without these detailed descriptions.

[0055] Reference Figure 1 to Figure 10 A method for detecting the riding comfort of high-speed elevator passengers based on skin electricity and electrocardiogram includes the following steps:

[0056] Step 1. Collect the accelerometer signal of the load platform of the high-speed elevator where the passenger is located over time, and simultaneously collect the passenger's electrocardiogram and skin electricity over time;

[0057] The accelerometer is placed on the carrying platform and the accelerometer signal includes an acceleration signal in at least one spatial direction;

[0058] The event response time window of the skin conductivity signal is within 15 seconds from the start time of the accelerated running state to the end time of the accelerated running state;

[0059] The heart rate variability signal event response time window is within 300 seconds from the start time of the accelerated running state to the end time of the accelerated running state.

[0060] Step 2. Classify the running status of the load-bearing platform, wherein the classification processing categories include brake stop / constant speed running status and acceleration running status;

[0061] The classification process consists of the following sub-steps:

[0062] Step 2.1. Determine the maximum and minimum values ​​of the accelerometer signal when the carrier platform is in a braking stop state; the maximum and minimum values ​​are determined by the following method: collect the accelerometer signal when the carrier platform is in a braking stop state in step 1; perform hypothesis testing on the acceleration signal in the same spatial direction; given a significance level, determine the receiving domain of the acceleration signal in the same spatial direction; determine the maximum critical value of the receiving domain as the maximum value and the minimum critical value of the receiving domain as the minimum value; the hypothesis test is a two-tailed test; the significance level is 0.05;

[0063] Step 2.2. Classify the accelerometer signal that is greater than the maximum value or less than the minimum value as an accelerated running state.

[0064] Step 3: Label the accelerometer signal into categories.

[0065] Step 4. Determine the start time and end time of the accelerated running state in the acceleration signal; the start time is the time corresponding to the first data point of the continuous acceleration data marked as the accelerated running state, and the end time is the time corresponding to the last data point of the acceleration data marked as the accelerated running state that is continuous with the start time.

[0066] Step 5. Determine an event response time window of at least one electrocardiogram and skin electrical signal associated with the accelerated running state through the start time and the end time;

[0067] The event response time window of the human behavior signal is within 5 seconds from the start time of the accelerated running state to the end time of the accelerated running state;

[0068] The event response time window of the eye movement signal is within 5 seconds at most from the start time of the accelerated running state to the end time of the accelerated running state.

[0069] Step 6. Extract features of the ECG and EGG signals of passengers within the event response time window to obtain at least one feature extraction result, and use it as the acceleration state feature set of the ECG and EGG signals; the feature extraction results include time domain features, frequency domain features, and information entropy features of the ECG and EGG signals;

[0070] The time domain characteristics of ECG and EEG include the root mean square of the difference of consecutive RR intervals of heart rate variability, the standard deviation of NN intervals of heart rate variability, the heart rate of heart rate variability, the skin conductance response frequency of skin conductivity, the average peak value of skin conductance response of skin conductivity, the average delay of skin conductance response of skin conductivity and the rise time of skin conductance response of skin conductivity;

[0071] The frequency domain characteristics of ECG and EEG include the absolute power of the very low frequency band of heart rate variability, the absolute power of the low frequency band of heart rate variability, the absolute power of the high frequency band of heart rate variability and the ratio of the absolute power of the low frequency band to the high frequency band of heart rate variability;

[0072] The information entropy characteristics of ECG and EG include Shannon entropy of ECG and EG, cross entropy of ECG and EG, Renyi entropy of ECG and EG, and Tsallis entropy of ECG and EG.

[0073] Step 7. Perform feature extraction on an electrocardiogram and electrocutaneous signal of a passenger outside the event response time window to obtain at least one feature extraction result, and use it as a baseline feature set of the electrocardiogram and electrocutaneous signal.

[0074] Step 8. Compare the accelerated state feature set of step 6 with the baseline feature set of step 7 to obtain a comparison result; the comparison result includes the average absolute difference, median absolute difference, p value determined by statistical knowledge or expected mean of the root mean square value between the accelerated state feature set and the baseline feature set.

[0075] Step 9. The greater the value difference of the comparison result of step 8, the lower the passenger's high-speed elevator riding comfort. At the same time, the smaller the value difference of the comparison result of step 8, the higher the passenger's high-speed elevator riding comfort.

[0076] A high-speed elevator passenger comfort detection system based on electrocardiogram and skin electricity, the system includes:

[0077] ECG and galvanic skin signal collection device, used to collect ECG and galvanic skin signal data of passengers;

[0078] An acceleration acquisition device for acquiring accelerometer signal data over time of the load-bearing platform of the high-speed elevator where the passengers are located;

[0079] A data time synchronization module is used to unify the sampling rates of the ECG and EGD signal data of the ECG and EGD acquisition device and the accelerometer signal data of the acceleration acquisition device, and to align the data frames in time;

[0080] The passenger comfort analysis module is used to preprocess the ECG and skin electrical signal data and the accelerometer signal data, extract the time domain features, frequency domain features or information entropy features of the ECG and skin electrical data, and form a baseline feature set and an acceleration state feature set, and analyze the passenger comfort through the comparison results of the feature sets.

[0081] In the passenger comfort analysis module, preprocessing includes: noise reduction processing of accelerometer signal data and electrocardiogram and skin conductance signal data.

[0082] According to the upper threshold and the lower threshold of the accelerometer signal data, the acceleration signal data is divided into a stop / uniform speed running state and an accelerated running state.

[0083] Determine the event response time window of the ECG and galvanic skin signal data according to the category label of the data time synchronization module and the acceleration signal data; divide the ECG and galvanic skin signal data into the event response window and the event response window; wherein the acceleration acquisition device includes an accelerometer or a posture sensor; the ECG and galvanic skin acquisition device includes an electrode sheet, a finger clip, a watch or a glove; the noise reduction processing includes Kalman filtering, high-pass filtering, low-pass filtering or band-pass filtering.

[0084] Example 1: Using a posture sensor to obtain the three-axis acceleration of the center position of a high-speed elevator car, such as Fig.10The sensor is placed at the center of the high-speed elevator car platform. The acceleration signal is converted to 16-bit analog-to-digital with a sampling frequency of 2 kHz and then downsampled to 250 Hz. The acceleration data is then converted to horizontal-vertical coordinates using the gyro signal in the attitude sensor and a trigonometric coordinate transformation is applied.

[0085] The maximum strength of the positive half-sine wave of the acceleration curve of the high-speed elevator is measured to be 1.06g, and the maximum strength of the negative half-sine wave is 0.93g. Figure 2 , 3 .

[0086] In order to distinguish the acceleration and non-acceleration states of a high-speed elevator and extract the duration of the vertical translation acceleration, a pilot experiment was conducted. In the pilot experiment, the acceleration data of the high-speed elevator in operation were collected three times continuously for about 1 min, and the acceleration data were collected when the high-speed elevator was stationary. A single-sample t-test (two-tailed, α=0.05, t=0) was performed on the 1-minute vertical acceleration data in the stationary state to obtain the maximum and minimum values ​​of the receiving domain. The duration of the positive / negative half-sine wave is determined by the vertical acceleration data outside the rejection domain. The vertical acceleration data of the moving high-speed elevator was analyzed to obtain the average duration of the positive and negative half-sine waves, see Figure 2 , 3 .

[0087] EDA was collected with a sampling rate of 1 kHz. Two electrodes were connected to the distal phalanges of the index and middle fingers of the non-dominant hand to detect EDA, such as Figure 8 The original EDA data was preprocessed using a low-pass filter with a cutoff frequency of 35 Hz, and then downsampled to 250 Hz. A 0.5 Hz high-pass filter was used, and 0.05 μS was used as the minimum threshold amplitude of the preprocessed EDA signal. The number of SCR signals was obtained from the preprocessed EDA data and divided by the time value. In other words, the number of SCRs in the preprocessed EDA signal greater than 0.05 μS is the SCR signal frequency (SCR fre ), the unit is nSCR / s. By calculating the SCR within 8s from the occurrence of the acceleration event to the end of the acceleration event fre , analyze the high-speed elevator ride comfort of passengers in the high-speed elevator car. The above data set is the acceleration state data set of EDA.

[0088] At the same time, the EDA data of passengers in the high-speed elevator in the stopped state is collected, and the data is intercepted with equal length according to the duration of the above EDA data, and the features are calculated using the same feature algorithm. The features are used as the baseline feature data of the passengers.

[0089] SCR of passengers in baseline condition freThe average value is 0.12±0.03 nSCR / s, and the SCR of passengers under acceleration fre The average value was 0.2±0.08 nSCR / s, see Table 1. Independent sample t test was used to perform statistical analysis on baseline characteristic data and acceleration state data set, see Figure 4 The results showed that the SCR signal frequency under acceleration was significantly greater than the baseline (p<0.05).

[0090] Table 1 shows the skin electrodermal characteristic parameters (mean ± standard deviation) in the baseline state and acceleration state, as well as the corresponding results of the p value for the comparison between the two.

[0091] Skin electrical characteristic parameters Baseline status Acceleration status p-value SCRfre, nSCR / s 0.12±0.03 0.2±0.08 Less than 0.05

[0092] Table 1

[0093] Example 2: Using a posture sensor to obtain the three-axis acceleration of the center position of a high-speed elevator car, such as Fig.10 The sensor is placed at the center of the high-speed elevator car platform. The acceleration signal is converted to 16-bit analog-to-digital with a sampling frequency of 2 kHz and then downsampled to 250 Hz. The acceleration data is then converted to horizontal-vertical coordinates using the gyro signal in the attitude sensor and a trigonometric coordinate transformation is applied.

[0094] The maximum strength of the positive half-sine wave of the acceleration curve of the high-speed elevator is measured to be 1.06g, and the maximum strength of the negative half-sine wave is 0.93g. Figure 2 , 3 .

[0095] In order to distinguish the acceleration and non-acceleration states of the high-speed elevator and extract the duration of the vertical translation acceleration, a pilot experiment was conducted. In the pilot experiment, the acceleration data of the high-speed elevator operation were collected three times continuously for about 1 min, and the acceleration data were collected when the high-speed elevator was stationary. A single-sample t-test (two-tailed, α=0.05, t=0) was performed on the 1-minute vertical acceleration data in the stationary state, and the maximum and minimum values ​​of the acceptance domain were accepted. The duration of the positive / negative half-sine wave is determined by the vertical acceleration data outside the rejection domain. The vertical acceleration data of the moving high-speed elevator were analyzed to obtain the average duration of the positive and negative half-sine waves, see Figure 2 , 3 .

[0096] Record the electrocardiogram with a sampling rate of 1 kHz, where the positive electrode is placed on the left upper limb, the negative electrode is placed on the right upper limb, and the ground electrode is placed on the left lower limb. Fig. 9. The ECG signal is processed by a 0.5 ~ 40 Hz bandpass filter. HRV is calculated based on the RR interval extracted from the ECG signal. Fast Fourier transform is used to perform frequency domain analysis on HRV. HRV parameters include the root mean square (RMSSD) of the continuous difference of normal heartbeats and the low-frequency power. The above parameters are used as the characteristics of HRV, and the data set they constitute is the acceleration state data set. The HRV collection data segment is within 180 seconds from the acceleration event to the end of the acceleration event. At the same time, the HRV data of passengers in the high-speed elevator in the stopped state is collected, and the data is intercepted with equal length according to the duration of the above-mentioned HRV data, and the features are calculated using the same feature algorithm. This feature is used as the baseline feature data of the passenger.

[0097] The mean RMSSD of the passengers in the baseline condition was 24.66±7.71 ms, and the mean RMSSD of the passengers in the acceleration condition was 20.22±6.06 ms, see Table 2. The mean LF of the passengers in the baseline condition was 329.62±75.87 ms 2 The average LF of passengers in the acceleration state is 227.31±78.75 ms 2 , see Table 2. The baseline characteristic data and the accelerated state data set were statistically analyzed using the t test, and the results are shown in Figure 5 , 6 The results showed that the RMSSD in the acceleration state was significantly smaller than that in the baseline (p<0.05), and the LF in the acceleration state was also significantly smaller than that in the baseline (p<0.05).

[0098] Table 2 shows the ECG characteristic parameters (mean ± standard deviation) of the baseline state and the acceleration state, as well as the corresponding results of the p value for the comparison between the two.

[0099] ECG characteristic parameters Baseline status Acceleration status p-value RMSSD, ms 24.66±7.71 20.22±6.06 Less than 0.05 <![CDATA[LF, ms 2 ]]> 329.62±75.87 227.31±78.75 Less than 0.05

[0100] Table 2

[0101] A high-speed elevator passenger comfort detection system based on skin electricity and electrocardiogram, such as Figure 7As shown. The system includes an electrocardiogram and skin electricity acquisition device, an acceleration acquisition device, a data time synchronization module, and a passenger comfort analysis module. The electrocardiogram and skin electricity acquisition device is mainly used to collect the electrocardiogram and skin electricity signal data of the passenger. In this embodiment, the Ag / AgCl electrode sheet is non-invasively attached to the passenger's skin to obtain the electrical signal; the acceleration acquisition device is mainly used to collect the accelerometer signal data of the load platform of the high-speed elevator where the passenger is located in time. In this specific embodiment, the posture sensor is used to collect the acceleration signal of the elevator in the vertical direction; the data time synchronization module is mainly used to unify the sampling rate of the electrocardiogram and skin electricity signal data of the electrocardiogram and skin electricity acquisition device and the accelerometer signal data of the acceleration acquisition device, and to align the data frames in time; the passenger comfort analysis module is mainly used to pre-process the electrocardiogram and skin electricity signal data and the accelerometer signal data, extract the time domain characteristics, frequency domain characteristics or information entropy characteristics of the electrocardiogram and skin electricity data, and form a baseline feature set and an acceleration state feature set. Through the comparison results of the feature sets, the passenger comfort is analyzed. The comparison in this scheme adopts a program algorithm based on the independent sample t test.

[0102] The contents of the embodiments of this specification are merely an enumeration of the implementation forms of the inventive concept and are for illustrative purposes only. The protection scope of the present invention should not be considered to be limited to the specific forms described in this embodiment, and the protection scope of the present invention also extends to equivalent technical means that can be thought of by ordinary technicians in this field based on the inventive concept.

Claims

1. A high-speed elevator passenger comfort detection method based on electrocardiogram and skin electricity, characterized in that: The method comprises the following steps: Step 1: collecting the acceleration signal of the load platform of the high-speed elevator where the passenger is located over time, and simultaneously collecting the electrocardiogram and electrodermal signals of the passenger over time; Step 2, classifying the running state of the load-bearing platform, wherein the classification includes a braking stop / uniform speed running state and an accelerated running state; Step 3: marking the acceleration signal by category; Step 4: determining the start time and end time of the acceleration running state in the acceleration signal; Step 5: Determine the event response time window of the electrocardiogram and skin electricity associated with the accelerated running state through the start time and the end time; Step 6: extracting features from the passenger's electrocardiogram and electrodermal function within the event response time window to obtain at least one feature extraction result, and using the result as at least one acceleration state feature set of the electrocardiogram and electrodermal function; Step 7: extracting features from the electrocardiogram and skin electricity of passengers outside the event response time window to obtain at least one feature extraction result, and using the result as a baseline feature set of the electrocardiogram and skin electricity; Step 8, comparing the acceleration state feature set of step 6 with the baseline feature set of step 7 to obtain a comparison result; Step 9: The greater the value difference of the comparison result of step 8 is, the lower the comfort of the passenger is; meanwhile, the smaller the value difference of the comparison result of step 8 is, the higher the comfort of the passenger is.

2. The high-speed elevator passenger comfort detection method based on electrocardiogram and skin conduction according to claim 1 is characterized in that: In the step 1, the accelerometer is fixed to the supporting platform, and the acceleration signal includes an acceleration signal in at least one spatial direction.

3. The high-speed elevator passenger comfort detection method based on electrocardiogram and skin electricity according to claim 1 or 2, characterized in that: In the step 2, the operating status of the carrier platform is classified, wherein the classification includes the following sub-steps: Step 2.1, determining an upper threshold and a lower threshold of the acceleration signal when the bearing platform is in a braking stop state; Step 2.2: Classify the acceleration signal that is greater than the upper threshold or less than the lower threshold as an accelerated running state.

4. The high-speed elevator passenger comfort detection method based on electrocardiogram and skin electricity as claimed in claim 3 is characterized in that: In the step 2.1, the upper threshold and the lower threshold are determined by the following method: collecting the acceleration signal of the carrying platform in the braking stop state in the step 1; performing hypothesis testing on the acceleration signal in the same spatial direction; Given a significance level, determining a receptive domain of the acceleration signal in the same spatial direction; determining an upper critical value of the receptive domain as an upper threshold value and determining a lower critical value of the receptive domain as a lower threshold value.

5. The high-speed elevator passenger comfort detection method based on electrocardiogram and skin electricity according to claim 1 or 2, characterized in that: In step 4, the start time is the time corresponding to the first data point of the continuous acceleration data marked as the accelerated running state, and the end time is the time corresponding to the last data point of the acceleration data marked as the accelerated running state that is continuous with the start time.

6. The high-speed elevator passenger comfort detection method based on electrocardiogram and skin electricity as claimed in claim 2, characterized in that: In step 5, the event response time window of the electrocutaneous signal is within 15 seconds at most from the start time of the accelerated running state to the end time of the accelerated running state; the event response time window of the electrocardiogram signal is within 300 seconds at most from the start time of the accelerated running state to the end time of the accelerated running state.

7. The high-speed elevator passenger comfort detection method based on electrocardiogram and skin conduction as claimed in claim 1 or 2, characterized in that: In step 6, the feature extraction results include time domain features, frequency domain features, and information entropy features of the electrocardiogram and electrodermal conductivity.

8. The high-speed elevator passenger comfort detection method based on electrocardiogram and skin conduction as claimed in claim 1 or 2, characterized in that: In step 8, the comparison result includes the average absolute difference between the acceleration state feature set and the baseline feature set, the median absolute difference, the p value determined by statistical knowledge, and the expected mean of the root mean square value.

9. The high-speed elevator passenger comfort detection method based on electrocardiogram and skin conduction as claimed in claim 7, characterized in that: The time domain features of the ECG and EEG include the root mean square of the difference between the continuous RR intervals of the ECG, the standard deviation of the NN interval of the ECG, the heart rate of the ECG, the skin conductance response frequency of the EEG, the average peak value of the skin conductance response of the EEG, the average delay of the skin conductance response of the EEG and the rising time of the skin conductance response of the EEG; The frequency domain features of the ECG and EEG include the absolute power of the ECG's extremely low frequency band, the absolute power of the ECG's low frequency band, the absolute power of the ECG's high frequency band, and the ratio of the absolute power of the ECG's low frequency band to the absolute power of the high frequency band; The information entropy characteristics of the electrocardiogram and electroskin electricity include the Shannon entropy of the electrocardiogram and electroskin electricity, the cross entropy of the electrocardiogram and electroskin electricity, the Renyi entropy of the electrocardiogram and electroskin electricity, and the Tsallis entropy of the electrocardiogram and electroskin electricity.

10. A system for implementing the high-speed elevator passenger comfort detection method based on electrocardiogram and skin conduction as claimed in claim 7, characterized in that: The system comprises: An electrocardiogram and electrodermal signal acquisition device, used to acquire the electrocardiogram and electrodermal signal data of the passenger; An acceleration acquisition device, used to acquire acceleration signal data of the load-bearing platform of the high-speed elevator where the passenger is located over time; A data time synchronization module, used to unify the sampling rates of the electrocardiogram and electrocutaneous signal data of the electrocardiogram and electrocutaneous signal acquisition device and the acceleration signal data of the acceleration acquisition device, and to align the data frames in time; The passenger comfort analysis module is used to preprocess the ECG and electrocutaneous signal data and the acceleration signal data, extract the time domain features, frequency domain features or information entropy features of the ECG and electrocutaneous data and form the baseline feature set and the acceleration state feature set, and analyze the passenger comfort through the comparison results of the feature sets.

Images