Multi-channel brain-computer interface data acquisition and circulation system and method for manned space station

Abstract

The invention discloses a multi-channel brain-computer interface data acquisition and circulation system and method for a manned space station. The system comprises a multi-channel brain-computer interface sensor module, a data preprocessing module, a feature extraction module, a data circulation module and a decision feedback module. The multi-channel brain-computer interface sensor module is used for acquiring a multi-channel electroencephalogram signal of a space station operator; the data preprocessing module is used for preprocessing the multi-channel electroencephalogram signals to obtain a preprocessed signal set; the feature extraction module is connected with the data preprocessing module to obtain a feature signal set; the data circulation module is connected with the feature extraction module and is used for gathering the feature signals and sending the feature signals to each receiving end in the manned space station; and the decision feedback module is used for performing evaluation processing on the received signals received by each receiving end in the manned space station and the characteristic signal set to generate a feedback information set.

Description

Technical Field

[0001] The present invention relates to the fields of communications and brain-computer interface technology, and in particular to a multi-channel brain-computer interface data acquisition and circulation system and method for a manned space station. Background Art

[0002] With the continuous development of aerospace technology, space stations are playing an increasingly important role in communication, navigation, remote sensing and other fields. At the same time, brain-computer interface technology, as an emerging human-computer interaction method, has also shown great potential in the fields of medical treatment, rehabilitation, entertainment, etc. However, the application of brain-computer interface technology to the space station faces many challenges.

[0003] In the space station environment, due to factors such as limited space, limited resources, and signal transmission delays, traditional data acquisition and processing methods are difficult to meet the needs of brain-computer interfaces. In addition, data on the space station needs to be efficiently circulated and processed to ensure timely response and decision-making. Therefore, it is necessary to develop a multi-channel brain-computer interface data acquisition and intelligent flow processing method and system specifically suitable for the space station to improve the intelligence level and mission execution capability of the space station. Summary of the invention

[0004] The present invention discloses a multi-channel brain-computer interface data acquisition and circulation system and method for a manned space station, so as to improve the intelligence level and mission execution capability of the space station.

[0005] In a first aspect of an embodiment of the present invention, a multi-channel brain-computer interface data acquisition and circulation system for a manned space station is disclosed, comprising: a multi-channel brain-computer interface sensor module, a data preprocessing module, a feature extraction module, and a data circulation module;

[0006] The multi-channel brain-computer interface sensor module is used to collect multi-channel EEG signals of space station operators;

[0007] The data preprocessing module is connected to the multi-channel brain-computer interface sensor module and is used to preprocess the multi-channel EEG signals to obtain a preprocessed signal set;

[0008] The feature extraction module is connected to the data preprocessing module and is used to perform feature extraction processing on the preprocessing signal set to obtain a feature signal set;

[0009] The data transfer module is connected to the feature extraction module and is used to send the feature signal set to each receiving end inside the manned space station;

[0010] The data preprocessing module preprocesses the multi-channel EEG signal to obtain a preprocessed signal set, including:

[0011] The data preprocessing module performs data cleaning processing on the multi-channel EEG signals to obtain a first signal set;

[0012] Performing time registration processing on the first signal set to obtain a second signal set;

[0013] Normalizing the second signal set to obtain a third signal set;

[0014] Perform spatial feature filtering on the third signal set to obtain a preprocessed signal set.

[0015] The feature extraction module performs feature extraction processing on the preprocessed signal set to obtain a feature signal set, including:

[0016] The feature extraction module constructs a preprocessed signal matrix using the preprocessed signal set; a row vector of the preprocessed signal matrix is ​​each signal of the preprocessed signal set;

[0017] Performing deviation eigenvalue calculation processing on the preprocessed signal matrix to obtain a deviation amount sequence;

[0018] Performing high-order cumulants calculation processing on the preprocessed signal set to obtain a high-order cumulants set;

[0019] Performing high-order feature calculation processing on the high-order cumulant set to obtain a high-order feature sequence;

[0020] A characteristic signal set is constructed by using the deviation sequence and the high-order characteristic sequence.

[0021] The data transfer module sends the characteristic signal set to each receiving end inside the manned space station, including:

[0022] The data flow module generates a channel detection signal; the channel detection signal is a carrier signal of a single frequency;

[0023] The channel detection signal is respectively sent to each receiving end in the manned space station, and each receiving end obtains a receiving signal corresponding to the channel detection signal; each receiving end pre-stores the channel detection signal;

[0024] Each receiving end compares the received signal corresponding to the channel detection signal with the pre-stored channel detection signal to extract the carrier deviation value and the phase deviation value;

[0025] The channel coding matrix is ​​constructed by using the carrier deviation values ​​and phase deviation values ​​of all receiving ends;

[0026] Using the channel coding matrix, encoding the characteristic signal set to obtain a sequence to be sent;

[0027] The sequence to be sent is sent to each receiving end inside the manned space station.

[0028] In a second aspect of an embodiment of the present invention, a multi-channel brain-computer interface data acquisition and circulation method for a manned space station is disclosed, which is implemented by using the multi-channel brain-computer interface data acquisition and circulation system for a manned space station, and includes:

[0029] S1, using the multi-channel brain-computer interface sensor module to collect multi-channel EEG signals of the space station operator;

[0030] S2, using the data preprocessing module to preprocess the multi-channel EEG signal to obtain a preprocessed signal set;

[0031] S3, using the feature extraction module to perform feature extraction processing on the preprocessed signal set to obtain a feature signal set;

[0032] S4, using the data transfer module to send the characteristic signal set to each receiving end inside the manned space station.

[0033] The preprocessing of the multi-channel EEG signals to obtain a preprocessed signal set includes:

[0034] Performing data cleaning processing on the multi-channel EEG signals to obtain a first signal set;

[0035] Performing time registration processing on the first signal set to obtain a second signal set;

[0036] Normalizing the second signal set to obtain a third signal set;

[0037] Perform spatial feature filtering on the third signal set to obtain a preprocessed signal set.

[0038] The step of performing feature extraction processing on the preprocessed signal set to obtain a feature signal set includes:

[0039] Using the preprocessed signal set, a preprocessed signal matrix is ​​constructed; a row vector of the preprocessed signal matrix is ​​each signal of the preprocessed signal set;

[0040] Performing deviation eigenvalue calculation processing on the preprocessed signal matrix to obtain a deviation amount sequence;

[0041] Performing high-order cumulants calculation processing on the preprocessed signal set to obtain a high-order cumulants set;

[0042] Performing high-order feature calculation processing on the high-order cumulant set to obtain a high-order feature sequence;

[0043] A characteristic signal set is constructed by using the deviation sequence and the high-order characteristic sequence.

[0044] The step of sending the characteristic signal set to each receiving end inside the manned space station includes:

[0045] Generate a channel detection signal; the channel detection signal is a carrier signal of a single frequency;

[0046] The channel detection signal is respectively sent to each receiving end in the manned space station, and each receiving end obtains a receiving signal corresponding to the channel detection signal; each receiving end pre-stores the channel detection signal;

[0047] Each receiving end compares the received signal corresponding to the channel detection signal with the pre-stored channel detection signal to extract the carrier deviation value and the phase deviation value;

[0048] The channel coding matrix is ​​constructed by using the carrier deviation values ​​and phase deviation values ​​of all receiving ends;

[0049] Using the channel coding matrix, encoding the characteristic signal set to obtain a sequence to be sent;

[0050] The sequence to be sent is sent to each receiving end inside the manned space station.

[0051] The expression of the spatial feature filtering process is:

[0052]

[0053] Among them, s(k) is the kth element of the signal in the third signal set, NS is the length of the signal, y1(z,x) is the element of the zth row and xth column of the matrix corresponding to the transformed data information obtained by the spatial feature filtering process, p1() is the transformation function corresponding to the spatial feature filtering process, p1(kT1-zT1) is the value of p1() at kT1-zT1, T1 and F1 are the time domain transformation length and frequency domain transformation length of the spatial feature filtering process respectively.

[0054] The deviation characteristic value calculation process includes:

[0055] Performing feature transformation on the preprocessed signal matrix to obtain a feature domain signal matrix;

[0056] For the feature domain signal matrix and the preprocessing signal matrix, respectively calculating a cross-correlation matrix and a cross-covariance matrix;

[0057] The mutual correlation matrix and the mutual covariance matrix are fused and calculated to obtain a fused feature matrix; the expression of the fusion calculation process is:

[0058]

[0059] Among them, M is the fusion feature matrix, S XX is the cross-correlation matrix of the preprocessed signal matrix, S XY is the cross-covariance matrix of the feature domain signal matrix and the preprocessed signal matrix, S YY is the cross-correlation matrix of the feature domain signal matrix;

[0060] Performing eigenvalue decomposition processing on the fused feature matrix to obtain an eigenvalue sequence;

[0061] The eigenvalue sequence is determined to be a deviation sequence.

[0062] The beneficial effects of the present invention are:

[0063] The present invention discloses a multi-channel brain-computer interface data acquisition and circulation system and method for a manned space station, so as to improve the intelligence level and mission execution capability of the space station.

[0064] In the multi-channel brain-computer interface data acquisition and circulation system and method for the manned space station constructed by the present invention, a data preprocessing module is established to realize filtering and standardization of the collected signals, filter out irrelevant variables, and ensure the accuracy of feature extraction.

[0065] In the multi-channel brain-computer interface data acquisition and circulation system and method for the manned space station constructed by the present invention, the extraction of abnormal features of the collected EEG signals is realized through the feature extraction module. By analyzing the signals in the statistical domain and the high-order domain, the signal features of the two domains are extracted, ensuring the comprehensiveness and completeness of the signal feature extraction, while also reducing the pressure of subsequent data transmission.

[0066] In the multi-channel brain-computer interface data acquisition and circulation system and method for the manned space station constructed by the present invention, a data circulation module is established. Before data transmission, the channel of each terminal is firstly modeled and a channel matrix is ​​constructed to eliminate the influence of the non-ideal characteristics of various channels and ensure the stability and reliability of communication transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 1 is a flow chart for implementing the method of the present invention;

[0068] Figure 2 It is a composition diagram of the device of the present invention. DETAILED DESCRIPTION

[0069] In order to better understand the content of the present invention, an embodiment is given here.

[0070] Figure 1 is a flow chart for implementing the method of the present invention, Figure 2 It is a composition diagram of the device of the present invention.

[0071] In a first aspect of an embodiment of the present invention, a multi-channel brain-computer interface data acquisition and circulation system for a manned space station is disclosed, comprising: a multi-channel brain-computer interface sensor module, a data preprocessing module, a feature extraction module, and a data circulation module;

[0072] The multi-channel brain-computer interface sensor module is used to collect multi-channel EEG signals of space station operators;

[0073] The data preprocessing module is connected to the multi-channel brain-computer interface sensor module and is used to preprocess the multi-channel EEG signals to obtain a preprocessed signal set;

[0074] The feature extraction module is connected to the data preprocessing module and is used to perform feature extraction processing on the preprocessing signal set to obtain a feature signal set;

[0075] The data transfer module is connected to the feature extraction module and is used to send the feature signal set to each receiving end inside the manned space station;

[0076] Specifically, the device of the present invention also includes a decision feedback module, which is connected to the data flow module and the feature extraction module, and is used to evaluate and process the received signals and feature signal sets received by each receiving end inside the manned space station to generate a feedback information set.

[0077] The data preprocessing module preprocesses the multi-channel EEG signal to obtain a preprocessed signal set, including:

[0078] The data preprocessing module performs data cleaning processing on the multi-channel EEG signals to obtain a first signal set;

[0079] Performing time registration processing on the first signal set to obtain a second signal set;

[0080] Normalizing the second signal set to obtain a third signal set;

[0081] Performing spatial feature filtering processing on the third signal set to obtain a preprocessed signal set;

[0082] The expression of the spatial feature filtering process is:

[0083]

[0084] Wherein, s(k) is the kth element of the signal in the third signal set, NS is the length of the signal, y1(z,x) is the element of the zth row and xth column of the matrix corresponding to the transformed data information obtained by the spatial feature filtering process, p1() is the transformation function corresponding to the spatial feature filtering process, p1(kT1-zT1) is the value of p1() at kT1-zT1, and T1 and F1 are respectively the time domain transformation length and frequency domain transformation length of the spatial feature filtering process;

[0085] After obtaining the matrix corresponding to the transformed data information, all row vectors of the matrix corresponding to the transformed data information are concatenated to obtain a preprocessed signal; and a preprocessed signal set is constructed using all preprocessed signals. p1() may use a Gaussian function.

[0086] The time registration process is to unify different types of data to the same time reference; the time registration process can adopt the internal push / extrapolation method, the Lagrange three-point interpolation method, etc.;

[0087] The normalization process is to map data in different value ranges to a specified value range, and its mathematical expression is:

[0088]

[0089] Among them, t is a data value in the data set, t max is the maximum value of all data in the data set, t min is the minimum value of all data in the data set, t 归一化 is the value of data t after normalization;

[0090] The feature extraction module performs feature extraction processing on the preprocessed signal set to obtain a feature signal set, including:

[0091] The feature extraction module constructs a preprocessed signal matrix using the preprocessed signal set; a row vector of the preprocessed signal matrix is ​​each signal of the preprocessed signal set;

[0092] Performing deviation eigenvalue calculation processing on the preprocessed signal matrix to obtain a deviation amount sequence;

[0093] The deviation characteristic value calculation process includes:

[0094] Performing feature transformation on the preprocessed signal matrix to obtain a feature domain signal matrix; the feature transformation may be a Fourier transform or a wavelet transform; performing feature transformation on the preprocessed signal matrix is ​​to perform feature transformation on each row vector of the preprocessed signal matrix to obtain a feature domain vector; using all the feature domain vectors, constructing a feature domain signal matrix;

[0095] For the feature domain signal matrix and the preprocessing signal matrix, a cross-correlation matrix and a cross-covariance matrix are calculated respectively; in the process of calculating the cross-correlation matrix and the cross-covariance matrix, the row vectors of the feature domain signal matrix and the preprocessing signal matrix are used as samples;

[0096] The mutual correlation matrix and the mutual covariance matrix are fused and calculated to obtain a fused feature matrix; the expression of the fusion calculation process is:

[0097]

[0098] Among them, M is the fusion feature matrix, S XX is the cross-correlation matrix of the preprocessed signal matrix, S XY is the cross-covariance matrix of the feature domain signal matrix and the preprocessed signal matrix, S YY is the cross-correlation matrix of the feature domain signal matrix;

[0099] Performing eigenvalue decomposition processing on the fused feature matrix to obtain an eigenvalue sequence;

[0100] Determine the eigenvalue sequence as a deviation sequence;

[0101] Performing high-order cumulants calculation processing on the preprocessed signal set to obtain a high-order cumulants set;

[0102] Performing high-order feature calculation processing on the high-order cumulant set to obtain a high-order feature sequence;

[0103] Using the deviation sequence and the high-order characteristic sequence, a characteristic signal set is constructed;

[0104] The expression for the high-order cumulative amount calculation process is:

[0105]

[0106] Wherein, x(n) is the nth item of the mean signal obtained by averaging all preprocessed signals of the preprocessed signal set, y(n) is the nth item of the frequency domain signal corresponding to the mean signal, RX4, RX6, RX8 are the fourth-order cumulant, sixth-order cumulant and eighth-order cumulant of the mean signal respectively, RY3, RY5, RY7 are the third-order cumulant, fifth-order cumulant and seventh-order cumulant of the frequency domain signal respectively, RXY 34 RXY 56 RXY 78 They are the third and fourth order joint cumulants, the fifth and sixth order joint cumulants, and the seventh and eighth order joint cumulants, N is the length of the preprocessed signal, and FFT represents fast Fourier transform processing.

[0107] The high-order feature calculation process includes:

[0108] H1=-|RX6 / RX4|log2|RX8 / RX4|,

[0109]

[0110] Among them, H1, H2, and H3 represent the first, second, and third items of the high-order feature sequence, respectively.

[0111] The data transfer module sends the characteristic signal set to each receiving end inside the manned space station, including:

[0112] The data flow module generates a channel detection signal; the channel detection signal is a carrier signal of a single frequency;

[0113] The channel detection signal is respectively sent to each receiving end in the manned space station, and each receiving end obtains a receiving signal corresponding to the channel detection signal; each receiving end pre-stores the channel detection signal;

[0114] Each receiving end compares the received signal corresponding to the channel detection signal with the pre-stored channel detection signal to extract the carrier deviation value and the phase deviation value;

[0115] The channel coding matrix is ​​constructed by using the carrier deviation values ​​and phase deviation values ​​of all receiving ends;

[0116] Using the channel coding matrix, encoding the characteristic signal set to obtain a sequence to be sent;

[0117] The sequence to be sent is sent to each receiving end inside the manned space station.

[0118] The channel coding matrix is ​​constructed by using the carrier deviation values ​​and phase deviation values ​​of all receiving ends;

[0119] The carrier deviation value and phase deviation value of the i-th receiving end are represented as f i and Set the number of sampling points to M;

[0120] The elements of the i-th row and j-th column of the constructed channel coding matrix are Where T s is the sampling time;

[0121] The method of using the channel coding matrix to encode the characteristic signal set to obtain the sequence to be sent is to convert the characteristic signal set into a row vector that matches the dimension of the channel coding matrix, and multiply the row vector by the channel coding matrix to obtain the sequence to be sent.

[0122] The comparison process is performed to extract the carrier deviation value and the phase deviation value. The carrier deviation value can be estimated using a carrier frequency deviation algorithm; and the phase deviation value can be estimated using a phase-locked loop.

[0123] Specifically, the multi-channel brain-computer interface sensor module can adopt BLueBrain-40 from Xi'an Blue Brain. The performance comparison chart between this sensor and other sensors on the market is as follows.

[0124] Figure 1. Comparison of EEG sensor performance

[0125]

[0126] As can be seen from Table 1, the main performance indicators of this sensor are higher than those of other existing sensors.

[0127] A second aspect of an embodiment of the present invention discloses a multi-channel brain-computer interface data acquisition and circulation method for a manned space station, comprising:

[0128] Using the multi-channel brain-computer interface sensor module, multi-channel EEG signals of space station operators are collected;

[0129] Using the data preprocessing module, preprocessing the multi-channel EEG signal to obtain a preprocessed signal set;

[0130] Using the feature extraction module, performing feature extraction processing on the preprocessed signal set to obtain a feature signal set;

[0131] Using the data transfer module, the characteristic signal set is sent to each receiving end inside the manned space station;

[0132] The decision feedback module is used to evaluate and process the received signals and characteristic signal sets received by each receiving end inside the manned space station to generate a feedback information set.

[0133] The preprocessing of the multi-channel EEG signals to obtain a preprocessed signal set includes:

[0134] Performing data cleaning processing on the multi-channel EEG signals to obtain a first signal set;

[0135] Performing time registration processing on the first signal set to obtain a second signal set;

[0136] Normalizing the second signal set to obtain a third signal set;

[0137] Performing spatial feature filtering processing on the third signal set to obtain a preprocessed signal set;

[0138] The expression of the spatial feature filtering process is:

[0139]

[0140] Wherein, s(k) is the kth element of the signal in the third signal set, NS is the length of the signal, y1(z,x) is the element of the zth row and xth column of the matrix corresponding to the transformed data information obtained by the spatial feature filtering process, p1() is the transformation function corresponding to the spatial feature filtering process, p1(kT1-zT1) is the value of p1() at kT1-zT1, and T1 and F1 are respectively the time domain transformation length and frequency domain transformation length of the spatial feature filtering process;

[0141] The feature extraction module performs feature extraction processing on the preprocessed signal set to obtain a feature signal set, including:

[0142] The feature extraction module constructs a preprocessed signal matrix using the preprocessed signal set; a row vector of the preprocessed signal matrix is ​​each signal of the preprocessed signal set;

[0143] Performing deviation eigenvalue calculation processing on the preprocessed signal matrix to obtain a deviation amount sequence;

[0144] The deviation characteristic value calculation process includes:

[0145] Performing feature transformation on the preprocessed signal matrix to obtain a feature domain signal matrix; the feature transformation may be a Fourier transform or a wavelet transform; performing feature transformation on the preprocessed signal matrix is ​​to perform feature transformation on each row vector of the preprocessed signal matrix to obtain a feature domain vector; using all the feature domain vectors, constructing a feature domain signal matrix;

[0146] For the feature domain signal matrix and the preprocessing signal matrix, respectively calculating a cross-correlation matrix and a cross-covariance matrix;

[0147] The mutual correlation matrix and the mutual covariance matrix are fused and calculated to obtain a fused feature matrix; the expression of the fusion calculation process is:

[0148]

[0149] Among them, M is the fusion feature matrix, S XX is the cross-correlation matrix of the preprocessed signal matrix, S XY is the cross-covariance matrix of the feature domain signal matrix and the preprocessed signal matrix, S YY is the cross-correlation matrix of the feature domain signal matrix;

[0150] Performing eigenvalue decomposition processing on the fused feature matrix to obtain an eigenvalue sequence;

[0151] Determine the eigenvalue sequence as a deviation sequence;

[0152] Performing high-order cumulants calculation processing on the preprocessed signal set to obtain a high-order cumulants set;

[0153] Performing high-order feature calculation processing on the high-order cumulant set to obtain a high-order feature sequence;

[0154] Using the deviation sequence and the high-order characteristic sequence, a characteristic signal set is constructed;

[0155] The data transfer module sends the characteristic signal set to each receiving end inside the manned space station, including:

[0156] The data flow module generates a channel detection signal; the channel detection signal is a carrier signal of a single frequency;

[0157] Sending the channel detection signal to each receiving end in the manned space station, each receiving end pre-stores the channel detection signal;

[0158] Each receiving end compares the received signal of the channel detection signal with the pre-stored channel detection signal to extract the carrier deviation value and the phase deviation value;

[0159] The channel coding matrix is ​​constructed by using the carrier deviation values ​​and phase deviation values ​​of all receiving ends;

[0160] Using the channel coding matrix, encoding the characteristic signal set to obtain a sequence to be sent;

[0161] The sequence to be sent is sent to each receiving end inside the manned space station.

[0162] The decision feedback module is connected to the data flow module and the feature extraction module, and is used to evaluate and process the received signals and feature signal sets received by each receiving end inside the manned space station to generate a feedback information set;

[0163] The eigenvalue decomposition process can be implemented by using an eigenvalue decomposition algorithm of a matrix.

[0164] The expression for the high-order cumulative amount calculation process is:

[0165]

[0166] Wherein, x(n) is the nth item of the mean signal obtained by averaging all preprocessed signals of the preprocessed signal set, y(n) is the nth item of the frequency domain signal corresponding to the mean signal, RX4, RX6, RX8 are the fourth-order cumulant, sixth-order cumulant and eighth-order cumulant of the mean signal respectively, RY3, RY5, RY7 are the third-order cumulant, fifth-order cumulant and seventh-order cumulant of the frequency domain signal respectively, RXY 34 RXY 56 RXY 78 They are the third and fourth order joint cumulants, the fifth and sixth order joint cumulants, and the seventh and eighth order joint cumulants, N is the length of the preprocessed signal, and FFT represents fast Fourier transform processing.

[0167] The high-order feature calculation process includes:

[0168] H1=-|RX6 / RX4|log2|RX8 / RX4|,

[0169] Among them, H1, H2, and H3 represent the first, second, and third items of the high-order feature sequence, respectively.

[0170] The channel coding matrix is ​​constructed by using the carrier deviation values ​​and phase deviation values ​​of all receiving ends;

[0171] The carrier deviation value and phase deviation value of the i-th receiving end are represented as f i and Set the number of sampling points to M;

[0172] The elements of the i-th row and j-th column of the constructed channel coding matrix are Where T s is the sampling time;

[0173] The method of using the channel coding matrix to encode the characteristic signal set to obtain the sequence to be sent is to convert the characteristic signal set into a row vector that matches the dimension of the channel coding matrix, and multiply the row vector by the channel coding matrix to obtain the sequence to be sent.

[0174] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A multi-channel brain-computer interface data acquisition and circulation system for a manned space station, characterized in that: include: Multi-channel brain-computer interface sensor module, data preprocessing module, feature extraction module, data flow module and decision feedback module; The multi-channel brain-computer interface sensor module is used to collect multi-channel EEG signals of space station operators; The data preprocessing module is connected to the multi-channel brain-computer interface sensor module and is used to preprocess the multi-channel EEG signals to obtain a preprocessed signal set; The feature extraction module is connected to the data preprocessing module and is used to perform feature extraction processing on the preprocessing signal set to obtain a feature signal set; The data transfer module is connected to the feature extraction module and is used to send the feature signal set to each receiving end inside the manned space station.

2. A multi-channel brain-computer interface data acquisition and circulation system for a manned space station as claimed in claim 1, characterized in that: The data preprocessing module preprocesses the multi-channel EEG signal to obtain a preprocessed signal set, including: The data preprocessing module performs data cleaning processing on the multi-channel EEG signals to obtain a first signal set; Performing time registration processing on the first signal set to obtain a second signal set; Normalizing the second signal set to obtain a third signal set; Perform spatial feature filtering on the third signal set to obtain a preprocessed signal set.

3. A multi-channel brain-computer interface data acquisition and circulation system for a manned space station as claimed in claim 1, characterized in that: The feature extraction module performs feature extraction processing on the preprocessed signal set to obtain a feature signal set, including: The feature extraction module constructs a preprocessed signal matrix using the preprocessed signal set; a row vector of the preprocessed signal matrix is ​​each signal of the preprocessed signal set; Performing deviation eigenvalue calculation processing on the preprocessed signal matrix to obtain a deviation amount sequence; Performing high-order cumulants calculation processing on the preprocessed signal set to obtain a high-order cumulants set; Performing high-order feature calculation processing on the high-order cumulant set to obtain a high-order feature sequence; A characteristic signal set is constructed by using the deviation sequence and the high-order characteristic sequence.

4. A multi-channel brain-computer interface data acquisition and circulation system for a manned space station as claimed in claim 1, characterized in that: The data transfer module sends the characteristic signal set to each receiving end inside the manned space station, including: The data flow module generates a channel detection signal; the channel detection signal is a carrier signal of a single frequency; The channel detection signal is respectively sent to each receiving end in the manned space station, and each receiving end obtains a receiving signal corresponding to the channel detection signal; each receiving end pre-stores the channel detection signal; Each receiving end compares the received signal corresponding to the channel detection signal with the pre-stored channel detection signal to extract the carrier deviation value and the phase deviation value; The channel coding matrix is ​​constructed by using the carrier deviation values ​​and phase deviation values ​​of all receiving ends; Using the channel coding matrix, encoding the characteristic signal set to obtain a sequence to be sent; The sequence to be sent is sent to each receiving end inside the manned space station.

5. A multi-channel brain-computer interface data acquisition and circulation method for a manned space station, implemented by using the multi-channel brain-computer interface data acquisition and circulation system for a manned space station as described in any one of claims 1 to 4, characterized in that: include: S1, using the multi-channel brain-computer interface sensor module to collect multi-channel EEG signals of the space station operator; S2, using the data preprocessing module to preprocess the multi-channel EEG signal to obtain a preprocessed signal set; S3, using the feature extraction module to perform feature extraction processing on the preprocessed signal set to obtain a feature signal set; S4, using the data transfer module to send the characteristic signal set to each receiving end inside the manned space station.

6. A multi-channel brain-computer interface data acquisition and circulation method for a manned space station as claimed in claim 5, characterized in that: The preprocessing of the multi-channel EEG signals to obtain a preprocessed signal set includes: Performing data cleaning processing on the multi-channel EEG signals to obtain a first signal set; Performing time registration processing on the first signal set to obtain a second signal set; Normalizing the second signal set to obtain a third signal set; Perform spatial feature filtering on the third signal set to obtain a preprocessed signal set.

7. A multi-channel brain-computer interface data acquisition and circulation method for a manned space station as claimed in claim 5, characterized in that: The step of performing feature extraction processing on the preprocessed signal set to obtain a feature signal set includes: Using the preprocessed signal set, a preprocessed signal matrix is ​​constructed; a row vector of the preprocessed signal matrix is ​​each signal of the preprocessed signal set; Performing deviation eigenvalue calculation processing on the preprocessed signal matrix to obtain a deviation amount sequence; Performing high-order cumulants calculation processing on the preprocessed signal set to obtain a high-order cumulants set; Performing high-order feature calculation processing on the high-order cumulant set to obtain a high-order feature sequence; A characteristic signal set is constructed by using the deviation sequence and the high-order characteristic sequence.

8. A multi-channel brain-computer interface data acquisition and circulation method for a manned space station as claimed in claim 5, characterized in that: The step of sending the characteristic signal set to each receiving end inside the manned space station includes: Generate a channel detection signal; the channel detection signal is a carrier signal of a single frequency; The channel detection signal is respectively sent to each receiving end in the manned space station, and each receiving end obtains a receiving signal corresponding to the channel detection signal; each receiving end pre-stores the channel detection signal; Each receiving end compares the received signal corresponding to the channel detection signal with the pre-stored channel detection signal to extract the carrier deviation value and the phase deviation value; The channel coding matrix is ​​constructed by using the carrier deviation values ​​and phase deviation values ​​of all receiving ends; Using the channel coding matrix, encoding the characteristic signal set to obtain a sequence to be sent; The sequence to be sent is sent to each receiving end inside the manned space station.

9. The multi-channel brain-computer interface data acquisition and circulation method for a manned space station as claimed in claim 6, characterized in that: The expression of the spatial feature filtering process is: Among them, s(k) is the kth element of the signal in the third signal set, NS is the length of the signal, y1(z,x) is the element of the zth row and xth column of the matrix corresponding to the transformed data information obtained by the spatial feature filtering process, p1() is the transformation function corresponding to the spatial feature filtering process, p1(kT1-zT1) is the value of p1() at kT1-zT1, T1 and F1 are the time domain transformation length and frequency domain transformation length of the spatial feature filtering process respectively.

10. The multi-channel brain-computer interface data acquisition and circulation method for a manned space station as claimed in claim 7, characterized in that: The deviation characteristic value calculation process comprises: Performing feature transformation on the preprocessed signal matrix to obtain a feature domain signal matrix; For the feature domain signal matrix and the preprocessing signal matrix, respectively calculating a cross-correlation matrix and a cross-covariance matrix; The mutual correlation matrix and the mutual covariance matrix are fused and calculated to obtain a fused feature matrix; the expression of the fusion calculation process is: Among them, M is the fusion feature matrix, S XX is the cross-correlation matrix of the preprocessed signal matrix, S XY is the cross-covariance matrix of the feature domain signal matrix and the preprocessed signal matrix, S YY is the cross-correlation matrix of the feature domain signal matrix; Performing eigenvalue decomposition processing on the fused feature matrix to obtain an eigenvalue sequence; The eigenvalue sequence is determined to be a deviation sequence.

Images