Coupling analysis method and device for downhole environment risk hidden danger and personnel vital signs

Abstract

The application relates to the technical field of mine risk analysis, in particular to an underground environment risk hidden danger and personnel vital sign coupling analysis method and equipment. The method comprises the following steps: acquiring vital sign information and environment information of underground personnel to determine a first abnormal time point sequence, thereby determining a related risk sequence, performing Fourier decomposition on the risk sequence and the first abnormal time point sequence, and determining a periodic abnormal event sequence and a non-periodic abnormal event sequence; the personnel vital sign information is collected through a wearable device; the environment information comprises gas concentration, temperature, humidity, ventilation volume, carbon monoxide concentration, dust concentration and carbon dioxide concentration. The application plays a role in improving the comprehensiveness of mine risk assessment, can avoid the one-sided problem of risk assessment results caused by single evaluation index, solves the problem of lack of periodic analysis in related mine risk assessment, and has the role of avoiding false positives or false negatives in mine risk prediction.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and in particular to a method and equipment for coupled analysis of underground environmental risks and personnel vital signs. Background Technology

[0002] In underground working environments such as coal mines and metal mines, workers face various environmental risks, such as gas explosions, toxic gas leaks, high temperatures and humidity, and poor ventilation. Meanwhile, vital signs (such as heart rate, body temperature, and blood oxygen saturation) reflect a person's health status and emergency response. Traditional underground safety monitoring systems typically separate environmental monitoring from personnel health monitoring: environmental sensors (such as gas sensors and temperature sensors) collect data independently, while vital signs are collected via wearable devices, but the two lack effective coupling analysis. This makes it impossible to accurately identify the correlation between environmental risks and personnel abnormalities; for example, it cannot distinguish whether an abnormal heart rate is caused by environmental factors (such as increased gas concentration) or personal health problems. Furthermore, existing methods struggle to handle periodic patterns in environmental risks (such as periodic ventilation system failures) and non-periodic events (such as sudden gas outbursts), limiting the accuracy and timeliness of risk assessment. Summary of the Invention

[0003] At least one aspect and advantage of this application will be set forth in part in the description which follows, or may be apparent from the description, or may be obtained by practicing the subject matter of this disclosure.

[0004] According to the first aspect of this application, a method for coupled analysis of downhole environmental risks and personnel vital signs is provided, including:

[0005] To obtain vital signs and environmental information of personnel underground;

[0006] The first abnormal time point sequence was determined based on the vital signs information of underground personnel and anomaly detection algorithms;

[0007] Risk sequences based on environmental information acquisition and environmental information association;

[0008] Based on the Fourier decomposition of the risk sequence associated with environmental information and the first anomalous time point sequence, the sequence of periodic and non-periodic anomalous events is determined.

[0009] The vital signs information of the personnel is collected through wearable devices;

[0010] The environmental information includes gas concentration, temperature, humidity, ventilation volume, carbon monoxide concentration, dust concentration, and carbon dioxide concentration.

[0011] According to one embodiment of this application, the first abnormal time point sequence is determined as follows:

[0012] The vital signs information of underground personnel is normalized based on the maximum and minimum values ​​of the vital signs information;

[0013] The vital signs information of personnel underground was sampled using the first sliding time window to obtain the first vital signs information sequence;

[0014] The first vital sign information sequence was detected using an outlier algorithm to obtain the first abnormal time point sequence.

[0015] According to one embodiment of this application, the environmental information is obtained based on the movement trajectory of underground personnel and corresponds to environmental parameters for each type, including at least sensor data collected in the roadway area where the user is located and adjacent areas connected by ventilation ducts.

[0016] According to one embodiment of this application, the method for obtaining the risk sequence associated with environmental information includes:

[0017] Based on the type of environmental parameter associated with the sensor, the upper and lower limits of the corresponding environmental parameter are determined, and the acquired environmental parameter is normalized based on the upper and lower limits of the environmental parameter to obtain the normalized environmental parameter.

[0018] The normalized environmental parameter information is fused and spliced ​​according to the environmental parameter type to obtain the feature vector corresponding to the time interval;

[0019] Input the feature vector corresponding to the time interval into the first preset model to obtain the risk value corresponding to the risk cycle sequence;

[0020] Risk sequences are obtained based on the output risk values ​​and their association with environmental information.

[0021] According to one embodiment of this application, the first risk cycle sequence is obtained as follows:

[0022] Perform Fourier decomposition on the risk sequence to obtain the Fourier series representation of the risk sequence;

[0023] A second risk sequence aligned with the risk sequence is obtained based on the representation of Fourier series;

[0024] Based on outlier detection, the second time point sequence corresponding to the outlier values ​​in the second risk sequence is obtained;

[0025] A sequence of periodic abnormal events was obtained based on the second time point sequence;

[0026] A non-periodic abnormal event sequence was obtained based on the first time point sequence and the first abnormal time point sequence.

[0027] According to one embodiment of this application, before obtaining the second risk sequence, time-domain signals with periods greater than a first threshold in the Fourier series representation are removed.

[0028] According to one embodiment of this application, the risk sequence is subjected to the Dickey-Fuller test before Fourier decomposition.

[0029] According to one embodiment of this application, mutual information of environmental parameter information and downhole personnel vital signs information is determined based on anomalous events within a non-periodic anomaly event sequence.

[0030] According to a second aspect of this application, a device for coupled analysis of downhole environmental risks and personnel vital signs is provided, the device comprising:

[0031] The mine information acquisition module is used to acquire vital sign information of underground personnel and environmental information;

[0032] The time series determination module is used to determine the first abnormal time point sequence based on the vital signs information of downhole personnel and anomaly detection algorithms.

[0033] The risk sequence determination module is used to obtain and associate risk sequences based on environmental information.

[0034] The abnormal event determination module is used to determine the sequence of periodic and non-periodic abnormal events based on the Fourier decomposition of the risk sequence associated with environmental information and the sequence of the first abnormal time point.

[0035] The vital signs information of the personnel is collected through wearable devices;

[0036] The environmental information includes gas concentration, temperature, humidity, ventilation volume, carbon monoxide concentration, dust concentration, and carbon dioxide concentration.

[0037] According to a third aspect of the present invention, an electronic device is provided, comprising a memory and a processor, the memory being coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the steps of the method described above.

[0038] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the above-described method.

[0039] This application embodiment obtains the vital signs information of underground personnel and environmental information, and determines the first abnormal time point sequence based on the vital signs information of underground personnel and anomaly detection algorithms. Then, it obtains the risk sequence associated with the environmental information. This method of comprehensively evaluating environmental information and the vital signs of underground personnel through risk sequence plays a comprehensive role in mine risk assessment, avoiding the problem of one-sided risk assessment results caused by a single assessment indicator. On the other hand, it solves the problem of the lack of periodic analysis in relevant mine risk assessments, and has the function of avoiding false alarms or omissions in mine risk prediction. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below.

[0041] Figure 1 A flowchart illustrating a method for coupled analysis of downhole environmental risks and personnel vital signs, provided in one embodiment of this application;

[0042] Figure 2 This is a block diagram of a device for coupling analysis of downhole environmental risks and personnel vital signs, provided in one embodiment of this application. Detailed Implementation

[0043] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0044] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used herein are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0045] It should be understood that although this application may use the terms first, second, third, etc., to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0046] According to one embodiment of this application, a method for coupled analysis of downhole environmental risks and hazard tracing with personnel vital signs is provided, such as... Figure 1 As shown, the method includes:

[0047] Step S101: Obtain vital signs information and environmental information of personnel underground; vital signs information is collected through wearable devices; the environmental information includes gas concentration, temperature, humidity, ventilation volume, carbon monoxide concentration, dust concentration and carbon dioxide concentration.

[0048] Specifically, vital signs information includes heart rate, body temperature, blood oxygen saturation, etc., and wearable devices such as smart bracelets and smart helmets have built-in biosensors.

[0049] Specifically, environmental information can be collected by a network of environmental sensors pre-deployed underground.

[0050] Specifically, vital signs and environmental information can be transmitted to a central server or cloud platform on the ground via an underground industrial ring network or wireless mesh network and stored in a time-series database for subsequent analysis.

[0051] Step S102: Determine the first abnormal time point sequence based on the vital signs information of the personnel downhole and the abnormal detection algorithm.

[0052] The first anomaly sequence in this embodiment refers to the list of times when the vital signs of personnel underground became abnormal.

[0053] In practice, the vital signs information can be preprocessed by cleaning and noise reduction.

[0054] Specifically, statistical or machine learning methods, such as isolation forest, local favorite factor, ARIMA, LSTM and other anomaly detection algorithms, can be used for processing.

[0055] Step S103: Risk sequence based on environmental information acquisition and environmental information association.

[0056] It should be noted that the risk series refers to a time series composed of risk values ​​of the quantitative comprehensive risk level sorted by time, where the risk value is a value obtained by fusing data from multiple environmental parameters.

[0057] In practice, the risk value can be obtained by using a preset data fusion algorithm, such as a weighted linear fusion algorithm, or a network model such as a random forest or gradient boosting tree.

[0058] Step S104: Based on the Fourier decomposition of the risk sequence associated with environmental information and the first anomalous time point sequence, determine the periodic anomalous event sequence and the non-periodic anomalous event sequence.

[0059] The periodic abnormal event sequence in this application refers to recurring abnormal events, which are time series corresponding to periodic risk events extracted through Fourier decomposition.

[0060] The non-periodic abnormal event sequence of this application is obtained by comparing a first abnormal time point sequence and a periodic sequence, specifically by calculating the difference between the first abnormal time point sequence and the periodic abnormal event sequence.

[0061] It should be noted that Fourier decomposition converts the risk sequence into frequency components, each represented by amplitude and phase. Frequency components with larger amplitudes correspond to periodic patterns with greater risk impact, while those with smaller amplitudes may be random noise. Therefore, the periodic anomalous event sequence is filtered through a preset amplitude threshold to obtain a reconstructed periodic risk sequence, from which anomalous time points are identified. Removing the periodic anomalous event sequence from the first anomalous time point sequence yields the non-periodic anomalous event sequence.

[0062] This application embodiment obtains the vital signs information of underground personnel and environmental information, and determines the first abnormal time point sequence based on the vital signs information of underground personnel and anomaly detection algorithms. Then, it obtains the risk sequence associated with the environmental information. This method of comprehensively evaluating environmental information and the vital signs of underground personnel through risk sequence plays a comprehensive role in mine risk assessment, avoiding the problem of one-sided risk assessment results caused by a single assessment indicator. On the other hand, it solves the problem of the lack of periodic analysis in relevant mine risk assessments, and has the function of avoiding false alarms or omissions in mine risk prediction.

[0063] According to one embodiment of this application, the first abnormal time point sequence is determined as follows:

[0064] The vital signs information of underground personnel is normalized based on the maximum and minimum values ​​of the vital signs information;

[0065] The vital signs information of personnel underground was sampled using the first sliding time window to obtain the first vital signs information sequence;

[0066] The first vital sign information sequence was detected using an outlier algorithm to obtain the first abnormal time point sequence.

[0067] It should be noted that this embodiment is generally configured with a personnel feature database, which includes the identifiers of different underground personnel and their corresponding extreme values ​​(maximum and minimum values). The maximum and minimum values ​​of a specified underground personnel are obtained by searching in the personnel feature database using the identifier of the underground personnel (such as the device identifier of a wearable device).

[0068] In practical implementation, the following formula can be used for normalization:

[0069] ;in, This is the normalized vital signs information of underground personnel. For the vital signs information of personnel underground. and These represent the maximum and minimum values ​​of vital signs information, respectively.

[0070] In practice, sampling can be performed using an overlapping sliding window method, such as assuming a window size of 5 minutes and a fixed step size of 4 minutes. This method can ensure that the sampling results have a high overlap rate, so that even if anomalies occur at the window boundaries, they can still be captured.

[0071] In practical implementation, multiple work scenarios can be pre-set, each corresponding to a different sliding window sampling method. Each work scenario can include various information items, such as work group, work type, work shift, and even the physical condition of the workers and the duration of continuous work. During application, the appropriate sliding window sampling method is determined based on the selected information items. For example, if the underground workers are working on a night shift, the sliding window sampling method would be a non-overlapping sliding window for the first time period and an overlapping sliding window for the second time period. This multi-scenario sliding window sampling method achieves dynamic adjustability of the sliding window sampling method.

[0072] According to one embodiment of this application, the environmental information is obtained based on the movement trajectory of underground personnel and corresponds to environmental parameters for each type, including at least sensor data collected in the roadway area where the user is located and adjacent areas connected by ventilation ducts.

[0073] It should be noted that the adjacent area connected by the ventilation duct refers to the upstream or downstream area directly connected to the area where personnel are located. This can be determined by the pre-configured mine ventilation network and the area where underground personnel are located.

[0074] In this embodiment, the environmental information consists of data collected by various environmental sensors in the area where underground personnel are located and related areas. The location of underground personnel can be determined using coordinates or the roadway markers. By acquiring environmental information about the area where underground personnel are located and related areas, not only is it possible to correlate personnel with locations where risks occur, achieving the goal of accurate risk assessment analysis, but it also serves as an early warning system for risk assessment, providing data for risk tracing.

[0075] According to one embodiment of this application, the method for obtaining the risk sequence associated with environmental information includes:

[0076] Based on the type of environmental parameter associated with the sensor, the upper and lower limits of the corresponding environmental parameter are determined, and the acquired environmental parameter is normalized based on the upper and lower limits of the environmental parameter to obtain the normalized environmental parameter.

[0077] The normalized environmental parameter information is fused and spliced ​​according to the environmental parameter type to obtain the feature vector corresponding to the time interval;

[0078] Input the feature vector corresponding to the time interval into the first preset model to obtain the risk value corresponding to the risk cycle sequence;

[0079] Risk sequences are obtained based on the output risk values ​​and their association with environmental information.

[0080] In this embodiment, the feature vector refers to a high-dimensional array containing information about the risk context, specifically including the normalized environmental parameters of the local area, the previous area, and the narrow area where the personnel are located.

[0081] It should be noted that the first preset model is a risk value calculation model trained using historical feature vectors. In specific applications, the first preset model can be selected from random forest, convolutional neural network (CNN), support vector machine, etc., which will not be listed here.

[0082] According to one embodiment of this application, the periodic abnormal event sequence and the non-periodic abnormal event sequence are obtained as follows:

[0083] Perform Fourier decomposition on the risk sequence to obtain the Fourier series representation of the risk sequence;

[0084] A second risk sequence aligned with the risk sequence is obtained based on the representation of Fourier series;

[0085] Based on outlier detection, the second time point sequence corresponding to the outlier values ​​in the second risk sequence is obtained;

[0086] A sequence of periodic abnormal events was obtained based on the second time point sequence;

[0087] A non-periodic abnormal event sequence was obtained based on the first time point sequence and the first abnormal time point sequence.

[0088] This embodiment represents the risk sequence in the frequency domain through Fourier transform, that is, converts the time series into frequency components, and then performs an inverse Fourier transform on the frequency components with larger amplitudes to obtain the second risk sequence.

[0089] The second time point series in this embodiment includes points that significantly deviate from the overall or local normal fluctuation range of the second risk series. In specific implementation, methods such as Z-score, IQR, and isolated forest can be used for determination. For example, the Z-score is used to calculate the mean and standard deviation of the series, the risk value of each time point is converted into a Z-score, and compared with a set score threshold. If Z > 2.5 (score threshold), it is determined to be an outlier.

[0090] In practice, the periodic abnormal event sequence can be obtained by mapping the second time point sequence, that is, the second time point sequence is defined as the periodic abnormal event sequence.

[0091] According to one embodiment of this application, before obtaining the second risk sequence, time-domain signals with periods greater than a first threshold in the Fourier series representation are removed.

[0092] Because the risk sequence may contain upward trends with long fluctuation periods, such as the overall increase in geothermal temperature with increasing mining depth, Fourier decomposition interprets this as a sine wave with a large amplitude and a long period. The resulting second risk sequence may be predicted as high-risk, affecting the accuracy of risk assessment. Therefore, removing unimportant long-period components can simplify the reconstructed second risk sequence and improve the accuracy of subsequent outlier detection.

[0093] Specifically, the first threshold can be determined based on the mine's operation and management requirements.

[0094] According to one embodiment of this application, the risk sequence is subjected to a Dickey-Fuller test before Fourier decomposition. The Dickey-Fuller test ensures that the risk sequence is stationary, thus guaranteeing the reliability of subsequent periodic analysis results and avoiding errors in the periodic anomaly sequence caused by unreliable periodic conclusions.

[0095] According to one embodiment of this application, mutual information of environmental parameter information and downhole personnel vital signs information is determined based on anomalous events within a non-periodic anomaly event sequence.

[0096] In this embodiment, mutual information refers to the dependency and correlation between environmental parameter information and the vital signs of personnel underground under sudden abnormal situations. Based on quantified mutual information values, the importance of different environmental parameter information can be compared, and complex dependencies that cannot be detected by correlation coefficients can be captured, thereby prioritizing the treatment of the environmental risk factors with the strongest correlation.

[0097] In practice, the process for determining mutual information is as follows:

[0098] (1) Data preparation, namely, extracting corresponding environmental parameter information from the sequence of non-periodic abnormal events. and vital signs data ,in , ;

[0099] (2) Discretization processing;

[0100] (3) Calculate mutual information according to the following formula:

[0101] ;in, For the first Information on environmental parameters (such as gas concentration, temperature, humidity, ventilation volume, carbon monoxide concentration, dust concentration, and carbon dioxide concentration). For the first underground personnel Individual vital signs information (such as heart rate, blood oxygen, etc.). and These are the number of bins for environmental parameter information and the number of bins for underground personnel vital signs information, respectively. For empirical joint probability, and It is the empirical marginal probability.

[0102] One embodiment of this application provides a device 20 for coupled analysis of downhole environmental risks and hazard analysis and personnel vital signs, such as... Figure 2 As shown, there are a mine information acquisition module 201, a time series determination module 202, a risk series determination module 203, and an abnormal event determination module 204.

[0103] The mine information acquisition module 201 is used to acquire vital sign information of underground personnel and environmental information;

[0104] The time series determination module 202 is used to determine the first abnormal time point sequence based on the vital signs information of underground personnel and anomaly detection algorithms;

[0105] Risk sequence determination module 203 is used to obtain and associate risk sequences based on environmental information.

[0106] The abnormal event determination module 204 is used to determine the periodic abnormal event sequence and the non-periodic abnormal event sequence based on the Fourier decomposition of the risk sequence associated with environmental information and the first abnormal time point sequence.

[0107] The vital signs information of the personnel is collected through wearable devices;

[0108] The environmental information includes gas concentration, temperature, humidity, ventilation volume, carbon monoxide concentration, dust concentration, and carbon dioxide concentration.

[0109] This application embodiment obtains the vital signs information of underground personnel and environmental information, and determines the first abnormal time point sequence based on the vital signs information of underground personnel and anomaly detection algorithms. Then, it obtains the risk sequence associated with the environmental information. This method of comprehensively evaluating environmental information and the vital signs of underground personnel through risk sequence plays a comprehensive role in mine risk assessment, avoiding the problem of one-sided risk assessment results caused by a single assessment indicator. On the other hand, it solves the problem of the lack of periodic analysis in relevant mine risk assessments, and has the function of avoiding false alarms or omissions in mine risk prediction.

[0110] Furthermore, the first abnormal time point sequence is determined as follows:

[0111] The vital signs information of underground personnel is normalized based on the maximum and minimum values ​​of the vital signs information;

[0112] The vital signs information of personnel underground was sampled using the first sliding time window to obtain the first vital signs information sequence;

[0113] The first vital sign information sequence was detected using an outlier algorithm to obtain the first abnormal time point sequence.

[0114] Furthermore, the environmental information is obtained based on the movement trajectory of underground personnel, and for each type of environmental parameter, it includes at least sensor data collected in the roadway area where the user is located and in adjacent areas connected by ventilation ducts.

[0115] Furthermore, the methods for obtaining the risk sequences associated with environmental information include:

[0116] Based on the type of environmental parameter associated with the sensor, the upper and lower limits of the corresponding environmental parameter are determined, and the acquired environmental parameter is normalized based on the upper and lower limits of the environmental parameter to obtain the normalized environmental parameter.

[0117] The normalized environmental parameter information is fused and spliced ​​according to the environmental parameter type to obtain the feature vector corresponding to the time interval;

[0118] Input the feature vector corresponding to the time interval into the first preset model to obtain the risk value corresponding to the risk cycle sequence;

[0119] Risk sequences are obtained based on the output risk values ​​and their association with environmental information.

[0120] Furthermore, the sequences of periodic and non-periodic anomalous events are obtained as follows:

[0121] Perform Fourier decomposition on the risk sequence to obtain the Fourier series representation of the risk sequence;

[0122] A second risk sequence aligned with the risk sequence is obtained based on the representation of Fourier series;

[0123] Based on outlier detection, the second time point sequence corresponding to the outlier values ​​in the second risk sequence is obtained;

[0124] A sequence of periodic abnormal events was obtained based on the second time point sequence;

[0125] A non-periodic abnormal event sequence was obtained based on the first time point sequence and the first abnormal time point sequence.

[0126] Furthermore, before obtaining the second risk sequence, time-domain signals with periods greater than the first threshold in the Fourier series representation are removed.

[0127] Furthermore, the risk series are subjected to the Dickey-Fuller test before Fourier decomposition.

[0128] Furthermore, mutual information between environmental parameter information and underground personnel vital signs information is determined based on anomalous events within a non-periodic anomaly event sequence.

[0129] The downhole environmental risk and personnel vital signs coupling analysis device of this embodiment can execute the downhole environmental risk and personnel vital signs coupling analysis method shown in the embodiment of this application. Its implementation principle is similar and will not be described again here.

[0130] Another embodiment of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method.

[0131] Specifically, the processor can be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0132] Specifically, the processor connects to the memory via a bus, which may include a path for transmitting information. The bus can be a PCI bus or an EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc.

[0133] The memory may be ROM or other types of static storage devices that can store static information and instructions, RAM or other types of dynamic storage devices that can store information and instructions, or EEPROM, CD-ROM or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto.

[0134] Optionally, the memory stores the code of a computer program that executes the scheme of this application, and the execution is controlled by a processor. The processor executes the application code stored in the memory to implement the operation of the apparatus provided in the above embodiments.

[0135] Another embodiment of this application provides a computer-readable storage medium storing computer-executable instructions for performing the methods provided in the above embodiments.

[0136] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0137] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0138] The above is a detailed description of the preferred embodiments of this application. However, this application is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A method for coupled analysis of underground environmental risks and hazard with personnel vital signs, characterized in that, include: To obtain vital signs and environmental information of personnel underground; The first abnormal time point sequence was determined based on the vital signs information of underground personnel and anomaly detection algorithms; Risk sequences based on environmental information acquisition and environmental information association; Based on the Fourier decomposition of the risk sequence associated with environmental information and the first anomalous time point sequence, the sequence of periodic and non-periodic anomalous events is determined. The vital signs information of the personnel is collected through wearable devices; The environmental information includes gas concentration, temperature, humidity, ventilation volume, carbon monoxide concentration, dust concentration, and carbon dioxide concentration; The sequences of periodic and non-periodic anomalous events are obtained as follows: Perform Fourier decomposition on the risk sequence to obtain the Fourier series representation of the risk sequence; A second risk sequence aligned with the risk sequence is obtained based on the representation of Fourier series; Based on outlier detection, the second time point sequence corresponding to the outlier values ​​in the second risk sequence is obtained; A sequence of periodic abnormal events was obtained based on the second time point sequence; The non-periodic abnormal event sequence is calculated by the difference between the first abnormal time point sequence and the periodic abnormal event sequence; The first abnormal time point sequence was determined as follows: The vital signs information of underground personnel is normalized based on the maximum and minimum values ​​of the vital signs information; The vital signs information of personnel underground was sampled using the first sliding time window to obtain the first vital signs information sequence; The first vital sign information sequence was detected using an outlier algorithm to obtain the first abnormal time point sequence.

2. The method for coupled analysis of downhole environmental risks and personnel vital signs as described in claim 1, characterized in that, The environmental information is obtained based on the movement trajectory of underground personnel and corresponds to environmental parameters for each type, including at least sensor data collected in the roadway area where the user is located and in adjacent areas connected to ventilation ducts.

3. The method for coupled analysis of downhole environmental risks and personnel vital signs as described in claim 1, characterized in that, The methods for obtaining the risk sequences associated with environmental information include: Based on the type of environmental parameter associated with the sensor, the upper and lower limits of the corresponding environmental parameter are determined, and the acquired environmental parameter is normalized based on the upper and lower limits of the environmental parameter to obtain the normalized environmental parameter. The normalized environmental parameter information is fused and spliced ​​according to the environmental parameter type to obtain the feature vector corresponding to the time interval; Input the feature vector corresponding to the time interval into the first preset model to obtain the risk value corresponding to the risk cycle sequence; Risk sequences are obtained based on the output risk values ​​and their association with environmental information.

4. The method for coupled analysis of downhole environmental risks and personnel vital signs as described in claim 1, characterized in that, Before obtaining the second risk sequence, time-domain signals with periods greater than the first threshold in the Fourier series representation are removed.

5. The method for coupled analysis of downhole environmental risks and personnel vital signs as described in claim 1, characterized in that, Before performing Fourier decomposition, the risk series is subjected to the Dickey-Fuller test.

6. The method for coupled analysis of downhole environmental risks and personnel vital signs as described in claim 1, characterized in that, The mutual information between environmental parameter information and the vital signs information of downhole personnel is determined based on the abnormal events within the non-periodic abnormal event sequence.

7. An electronic device, characterized in that, The method includes a memory and a processor, wherein the memory is coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the method for coupled analysis of downhole environmental risks and personnel vital signs as described in any one of claims 1-6.

Images