Intelligent wearable vital sign detection method and system for power grid hot-line work

Abstract

The invention discloses an intelligent wearable vital sign detection method and system for power grid hot-line work. The method relates to the technical field of intelligent wearable vital sign detection, and comprises the following steps: acquiring environmental noise information of different placement positions on an intelligent wearable device located in a working environment of an operator in the same time period, and obtaining original noise signal data; performing noise intensity analysis and spectrum analysis on the environment noise information to obtain noise characteristics of different placement positions; calculating a noise balance score according to the noise characteristics, and determining an optimal vital sign acquisition position based on the noise balance score; detecting the vital signs of the operating personnel at the optimal vital sign acquisition position, and comparing the vital sign acquisition effect obtained at the optimal placement position with the vital sign acquisition effect measured by the operating personnel in the non-operating environment. According to the invention, the interference degree of different positions of the intelligent wearable device is researched, so that the problem of low monitoring precision of the existing power operation safety guarantee means is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of high-altitude strong electromagnetic environment monitoring, and in particular to an intelligent wearable vital sign detection method and system for live grid operations. Background Art

[0002] With the rapid development of power engineering, especially the construction of high-voltage power grids, smart grids and large-scale power facilities, live grid working has become a common operation method. Live working refers to the workers carrying out inspection, maintenance and installation of power grid equipment without cutting off the power supply. Since live working involves high voltage current and complex working environment, the life safety of workers is facing great risks.

[0003] The particularity of live grid operations means that traditional safety assurance measures cannot fully meet the needs of workers in complex and high-risk environments. By developing intelligent wearable vital signs detection technology, it is possible to monitor the health of workers in real time, detect abnormal situations in a timely manner, and issue warnings through early warning systems to avoid accidents. This technology can not only effectively reduce accidental injuries in power operations, but also improve the work efficiency of workers, reduce damage to grid equipment caused by accidents, and ensure the stable operation of the power system.

[0004] For example, the invention patent with announcement number: CN107492833B announces a rescue terminal device for a live-working robot, including a live-working robot that can be hung on a cable and walk, and also includes a rescue towing arm, one side of the rescue towing arm is detachably connected to the live-working robot, and the other side is extended with a towing support arm, and an opening is provided on the towing support arm, and a towing boom is movably connected to the towing support arm through a driving assembly, and the towing boom is provided with a towing hook that can form a closed towing cavity with the opening; the whole process does not require manual labor to be connected, and tasks that are difficult to complete by manual operation are completed, which can effectively make up for the limitations of manual operation, and live-working can avoid the impact of power outages on power grid operation and economic losses.

[0005] For example, the invention patent with announcement number: CN 217696567 U discloses a wearable vital sign monitoring device for live-line workers, which includes a wearable device and a monitoring terminal. The wearable device includes a detection module and an adjustment strap, the detection module is arranged on the adjustment strap, and the detection module is worn on the wrist or arm of the worker with the adjustment strap. A wireless communication module is arranged on the circuit board, and the wireless communication module is wirelessly connected to the monitoring terminal through a Bluetooth signal. The advantages of the utility model are as follows: the detection module is worn on the wrist or arm of the worker by adjusting the strap, and since the entire monitoring device is a fixed structure that can be worn, the monitoring device can be prevented from falling off during operation, and the data collected by the temperature sensor and the vital sign sensor are received by the main control module, so the operator's body temperature, heart rate, blood pressure, and blood oxygen data can be obtained in real time, and the Bluetooth signal transmission is stable, which can ensure that the monitoring data can be accurately and quickly transmitted to the monitoring terminal.

[0006] The vital signs monitoring systems of existing equipment are usually used in high-intensity working environments. The signals may be interfered by factors such as noise and movement. The location where the noise information is collected directly affects the operator's work environment assessment. Different locations (such as head, chest, wrist, etc.) will be affected by different environmental noises, which may affect the accuracy of subsequent vital signs. Excessive noise will interfere with the signals of vital signs detection equipment. Too low noise levels may make it impossible to effectively distinguish between environmental noise and equipment working signals, affecting equipment response and data processing. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a smart wearable vital signs detection method and system for live grid operations, which solves the problem of low monitoring accuracy of existing power operation safety assurance means by studying the interference degree of different positions of the smart wearable.

[0008] To achieve the above object, the present invention provides the following technical solutions: A smart wearable vital sign detection method for live grid operation comprises the following steps: obtaining environmental noise information of different placement positions of a smart wearable located in an operator's working environment in the same time period to obtain original noise signal data; performing noise intensity analysis and spectrum analysis on the environmental noise information to obtain noise characteristics of different placement positions; calculating a noise balance score according to the noise characteristics, and determining an optimal vital sign collection position based on the noise balance score; detecting the vital signs of the operator at the optimal vital sign collection position, comparing the vital sign collection effect obtained at the optimal placement position with the vital sign collection effect measured by the operator in a non-operating environment, and verifying the detection accuracy of the optimal position.

[0009] In a preferred embodiment, the noise intensity analysis is performed as follows: data preprocessing is performed on the original noise signal data, and the processed noise signal data is combined with the sound pressure level calculation formula to obtain noise intensity; weighted filtering is applied to adjust noise signal data of different intensities to obtain an equivalent continuous sound level; based on the noise intensity and the equivalent continuous sound level, the noise intensity at different locations is spatially analyzed to obtain the noise attenuation rate.

[0010] In a preferred embodiment, the spectrum analysis process is as follows: the processed noise signal data is converted into a time domain signal, and the time domain signal is discrete Fourier transformed to obtain a spectrum diagram corresponding to each placement position; the power spectrum is extracted from the spectrum diagram, and the power spectrum density is calculated, and the power spectrum density is combined with the Euclidean matrix to obtain the noise spectrum morphology similarity of noise signals at different positions.

[0011] In a preferred embodiment, the noise intensity at different positions is spatially analyzed to obtain the noise attenuation rate, specifically as follows: the noise intensity and the equivalent continuous sound level value are obtained to establish a two-dimensional coordinate axis; in the two-dimensional coordinate axis, the peak-to-valley fluctuation segment of the first noise signal is obtained according to the fluctuation trend of the data; a smooth curve is obtained by curve fitting in each peak-to-valley fluctuation segment to obtain the peak value on the smooth curve; for any peak point, two extreme value large points adjacent to the peak point on the left and right of the smooth curve are obtained; the interval between adjacent maximum value points adjacent to the left and right, the peak fluctuation segment width, is calculated using the attenuation model to obtain the noise attenuation rate.

[0012] In a preferred embodiment, the power spectrum is extracted from the spectrum diagram as follows: performing an inverse Fourier transform on the spectrum to obtain a time domain waveform of the signal; performing a square operation on the time domain waveform to obtain an energy density spectrum of the signal; dividing the energy density spectrum by the number of sampling points to obtain an average power at each frequency point; and normalizing the power spectrum to obtain the integral over the entire spectrum range as the power spectrum.

[0013] In a preferred embodiment, the power spectral density is combined with the Euclidean matrix to obtain the noise spectrum morphology similarity of noise signals at different positions, which specifically includes: organizing the power spectral density into a matrix form, and treating the power spectral density of each signal at different frequencies as a vector; calculating the Euclidean distance metric between any two positions, and obtaining a similarity matrix by traversing and calculating the Euclidean distance between all positions; calculating the rank of the similarity matrix to obtain the noise spectrum morphology similarity of noise signals at different positions.

[0014] In a preferred embodiment, the system of the intelligent wearable vital signs detection method for live grid operation is characterized by comprising an environmental noise data acquisition module, a noise feature analysis module, a noise balance scoring module, and a vital signs detection effect verification module: the environmental noise data acquisition module is used to obtain environmental noise information of different placement positions on the intelligent wearable located in the working environment of the operator in the same time period to obtain original noise signal data; the noise feature analysis module is used to perform noise intensity analysis and spectrum analysis on the environmental noise information to obtain noise features of different placement positions; the noise balance scoring module is used to calculate the noise balance score according to the noise features, and determine the optimal vital signs collection position based on the noise balance score; the vital signs detection effect verification module is used to detect the vital signs of the operator at the optimal vital signs collection position, compare the vital signs collection effect obtained at the optimal placement position with the vital signs collection effect measured by the operator in a non-operating environment, and verify the detection accuracy of the optimal position.

[0015] Technical effects and advantages of the intelligent wearable vital signs detection method and system for live grid operation of the present invention: 1. By analyzing the characteristics of environmental noise and selecting the best location for collecting vital signs, the accuracy of vital sign monitoring of operators can be improved, and the interference of the noise environment on vital sign detection can be reduced, thereby effectively reducing the impact of noise on monitoring signals, and effectively solving the problem of low monitoring accuracy of existing power operation safety assurance means in the prior art.

[0016] 2. By detecting the noise interference at different placement positions of the smart wearable device, the sensor placement position is determined, thereby reducing the signal interference received by the sensor when monitoring the safety of the operator.

[0017] 3. By combining power spectral density and Euclidean matrix, the similarity of noise signals at different locations in the frequency domain can be effectively measured, thereby achieving accurate analysis of the spectral characteristics of the signal.

[0018] 4. By calculating the noise balance score, it is possible to evaluate whether the noise characteristics of different environmental locations are balanced, thereby helping to select the best detection location in a changing operating environment. Areas with high noise balance will reduce unnecessary interference, making vital sign data more accurate and reliable. BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 A flow chart of a smart wearable vital signs detection method for live grid operations provided in an embodiment of the present application; Figure 2 A schematic diagram of the system structure of a smart wearable vital signs detection method for live grid operations provided in an embodiment of the present application; DETAILED DESCRIPTION The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0020] Embodiment 1, Figure 1 The present invention provides an intelligent wearable vital sign detection method for live grid operation, comprising the following steps: Obtain environmental noise information at different placement positions of the smart wearable device in the working environment of the operator in the same time period to obtain original noise signal data; Performing noise intensity analysis and spectrum analysis on the environmental noise information to obtain noise characteristics at different placement positions; Calculating a noise balance score according to the noise characteristics, and determining an optimal vital sign collection position based on the noise balance score; The vital signs of the operator are detected at the optimal vital signs collection position, and the vital signs collection effect obtained at the optimal placement position is compared with the vital signs collection effect measured by the operator in a non-operating environment to verify the detection accuracy of the optimal position.

[0021] The original noise signal data includes the number of sampling points, sampling frequency, sampling time, instantaneous sound pressure level within the sampling time, and the distance between the sampling point and the noise source.

[0022] The different placement positions are set to be head position, chest position, and wrist position; The different time periods include working hours and non-working days, cloudy and sunny weather periods and rainy and snowy weather periods.

[0023] Noise signals are random and non-stationary, so efficient noise processing techniques (such as filtering, denoising, frequency division, etc.) are needed to ensure the accuracy of spectrum analysis results.

[0024] The noise intensity analysis process is as follows: Performing data preprocessing on the original noise signal data, and combining the processed noise signal data with a sound pressure level calculation formula to obtain noise intensity; Apply weighted filtering to adjust noise signal data of different intensities to obtain equivalent continuous sound levels; Based on the noise intensity and equivalent continuous sound level, the noise intensity at different locations is spatially analyzed to obtain the noise attenuation rate.

[0025] The spectrum analysis process is as follows: Converting the processed noise signal data into a time domain signal, performing a discrete Fourier transform on the time domain signal, and obtaining a frequency spectrum corresponding to each placement position; The power spectrum is extracted from the spectrum diagram, the power spectrum density is calculated, and the power spectrum density is combined with the Euclidean matrix to obtain the noise spectrum morphology similarity of noise signals at different positions.

[0026] The purpose of data preprocessing is to remove background noise, improve data quality, and provide a more reliable basis for subsequent data analysis and modeling. The specific goals of data preprocessing include: ‌Redundant data removal‌: Reduce the size of the data set by identifying and removing duplicate data, and improve data abstraction and data mining efficiency; ‌Handling missing values‌: filling or deleting missing data to ensure data integrity; ‌Noise Smoothing‌: Reduce noise and outliers in the data through smoothing techniques to improve data accuracy; ‌Normalize data‌: convert, standardize, and normalize data to adapt it to specific data analysis and model requirements; ‌Feature Selection and Feature Engineering‌: Select features relevant to the problem and create new features to improve the accuracy of data analysis results.

[0027] Sound pressure level is a physical quantity that describes the intensity of sound. It is measured in decibels (dB) and represents the difference between the minimum audible sound intensity and the sound intensity that can cause pain.

[0028] The sound pressure level calculation formula has the following effects: Assessing environmental noise: Sound pressure level is widely used in environmental noise monitoring. By measuring the sound pressure level, the impact of sound on human hearing can be determined and its impact on the environment can be assessed; Quantifying sound intensity: The sound pressure level calculation formula takes the common logarithm of the ratio of the sound pressure to the reference sound pressure and multiplies it by 20. The result is in decibels, which can quantify the intensity of the sound. This method allows the intensity of the sound to be expressed on a logarithmic scale, which is convenient for practical application and comparison.

[0029] The sound pressure level calculation formula is defined as follows:

[0030] Where: represents the sound pressure level calculation formula, p is the instantaneous sound pressure level within the sampling time, As the reference sound pressure, 20 μPa is taken.

[0031] The equivalent continuous sound level is calculated as follows:

[0032] Where: is the equivalent continuous sound level, in db; T is the sampling time; is the value of the sound pressure level calculation formula within the sampling time.

[0033] It should be noted that the equivalent continuous sound level (Leq) is used to represent the average noise intensity over a period of time. The equivalent continuous sound level represents a continuous equivalent noise level in a period of time in which the sound pressure level is equal to the noise power in this period of time.

[0034] The noise attenuation rate refers to the degree to which the noise intensity decreases with increasing distance. It is usually expressed by the attenuation coefficient n. The value of the attenuation coefficient n determines the speed of attenuation. When the value of n is large, the noise intensity decays faster with increasing distance; when the value of n is small, the noise intensity decays slower.

[0035] The noise intensity at different locations is spatially analyzed to obtain the noise attenuation rate, which is specifically: Obtain noise intensity and equivalent continuous sound level values ​​and establish a two-dimensional coordinate axis; Obtaining the peak-to-valley value fluctuation segment of the first noise signal according to the fluctuation trend of the data in the two-dimensional coordinate axis; A smooth curve is obtained by curve fitting in each peak-to-valley fluctuation segment, and a peak value on the smooth curve is obtained; For any peak point, obtain two extreme value large points adjacent to the peak point on the left and right sides of the smooth curve; The noise attenuation rate is calculated by using the attenuation model to calculate the interval between the adjacent maximum points on the left and right and the peak fluctuation segment width.

[0036] The noise attenuation rate is calculated by the following formula:

[0037] Where: S is the noise attenuation rate, As the reference sound pressure, take 20 micropascals. is the adjacent maximum point to the left, is the adjacent maximum point to the right, is the attenuation coefficient, which indicates the speed of attenuation.

[0038] The power spectrum represents the signal power within a unit frequency band and is defined as the signal power within a unit frequency band. It shows how the signal power changes with frequency, that is, the distribution of the signal power in the frequency domain. The power spectrum is often used to describe and analyze power signals (as distinct from energy signals). Its curve (i.e., the power spectrum curve) generally has the frequency as the horizontal axis and the power as the vertical axis, and is often used to describe and analyze power signals.

[0039] Power spectral density (PSD) is a signal represented in the form of a wave in physics, indicating the power carried by the wave per unit frequency. It is usually used in random vibration analysis, and continuous transient responses can only be described by probability distribution functions. Mathematically, the area under the curve of the relationship between power spectral density value and frequency value is the variance, that is, the square value of the standard deviation of the response. The unit of power spectral density is usually expressed in watts per hertz (W / Hz).

[0040] The extracting of the power spectrum from the frequency spectrum diagram is specifically as follows: Perform inverse Fourier transform on the spectrum to obtain the time domain waveform of the signal; Perform a square operation on the time domain waveform to obtain the energy density spectrum of the signal; Divide the energy density spectrum by the number of sampling points to get the average power at each frequency point; The power spectrum is normalized and the integral over the entire spectrum is obtained as the power spectrum.

[0041] The power spectrum is calculated as follows:

[0042] Where: is the power spectrum, is the frequency domain signal after Fourier transform, is the frequency, is the period of the time domain waveform.

[0043] The power spectrum is normalized as follows:

[0044] Where: is the normalized power spectrum, is the average power at each frequency point, is the unnormalized power spectrum, N is the number of sampling points, is the frequency domain signal after Fourier transform, is the sampling frequency within the sampling time.

[0045] The power spectrum density is calculated by the following formula:

[0046] Where: is the power spectral density, and T is the sampling time.

[0047] The power spectrum density is combined with the Euclidean matrix to obtain the noise spectrum morphology similarity of noise signals at different positions, specifically including: Arrange the power spectrum density into a matrix form, and regard the power spectrum density of each signal at different frequencies as a vector; Calculate the Euclidean distance metric between any two positions, and obtain the similarity matrix by traversing and calculating the Euclidean distance between all positions; The rank of the similarity matrix is ​​calculated to obtain the noise spectrum morphology similarity of noise signals at different positions.

[0048] It should be noted that if the distance is small, it means that the spectra of the two are similar, otherwise the spectrum difference is large.

[0049] The noise characteristics of different placement positions specifically include: The sound pressure level and equivalent continuous sound level at each location can reflect the noise intensity level at that location; The noise attenuation rate analysis obtains the variation pattern of noise intensity at different locations with distance, revealing the propagation characteristics of the noise source; The noise spectrum morphology similarity of the noise signals at different positions is used to obtain the spectrum morphology difference of the noise at different positions, which helps to identify the frequency domain characteristics of the noise.

[0050] Noise characteristics are indicators used to describe the state of environmental noise. In order to make the noise characteristics comparable at the same scale, it is necessary to standardize the noise spectrum, noise intensity, waveform characteristics, noise source directionality, etc. The standardized characteristic value range can be unified between 0 and 1, indicating the degree of influence of noise on acquisition.

[0051] The noise balance score is used to measure whether the noise characteristics at a certain location are balanced. Balanced noise has lower intensity differences and a more uniform spectrum distribution. A higher noise balance score indicates a more uniform noise spectrum with smaller intensity differences.

[0052] The noise balance score is calculated according to the noise characteristics, specifically: Assign a weight to each noise feature and map the noise feature to the corresponding weight; Determine the upper and lower limits of the noise balance score by using a preset balance function, and calculate the proportion of each noise feature in the weighted sum of the noise features within the range of the noise balance score; The noise balance score is deduced based on machine learning by combining the proportion of each noise feature in the weighted sum of noise features.

[0053] The system of the intelligent wearable vital signs detection method for live grid operation is characterized by comprising an environmental noise data acquisition module, a noise feature analysis module, a noise balance scoring module, and a vital signs detection effect verification module: The environmental noise data acquisition module is used to obtain environmental noise information of different placement positions of the smart wearable device in the working environment of the operator in the same time period to obtain the original noise signal data; A noise feature analysis module, used to perform noise intensity analysis and spectrum analysis on the environmental noise information to obtain noise features at different placement locations; A noise balance scoring module, configured to calculate a noise balance score according to the noise characteristics, and determine an optimal vital sign collection position based on the noise balance score; The vital signs detection effect verification module is used to detect the vital signs of the operating personnel at the optimal vital signs collection position, compare the vital signs collection effect obtained at the optimal placement position with the vital signs collection effect measured by the operating personnel in a non-operating environment, and verify the detection accuracy of the optimal position.

[0054] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0055] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0056] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0057] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0058] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0059] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent wearable vital sign detection method for live grid operation, characterized in that: The following steps are involved: Obtain environmental noise information at different placement positions of the smart wearable device in the working environment of the operator in the same time period to obtain original noise signal data; Performing noise intensity analysis and spectrum analysis on the environmental noise information to obtain noise characteristics at different placement positions; Calculating a noise balance score according to the noise characteristics, and determining an optimal vital sign collection position based on the noise balance score; The vital signs of the operator are detected at the optimal vital signs collection position, and the vital signs collection effect obtained at the optimal placement position is compared with the vital signs collection effect measured by the operator in a non-operating environment to verify the detection accuracy of the optimal position.

2. The intelligent wearable vital sign detection method for live grid operation as claimed in claim 1, characterized in that: The noise intensity analysis process is as follows: Performing data preprocessing on the original noise signal data, and combining the processed noise signal data with a sound pressure level calculation formula to obtain noise intensity; Apply weighted filtering to adjust noise signal data of different intensities to obtain equivalent continuous sound levels; Based on the noise intensity and equivalent continuous sound level, the noise intensity at different locations is spatially analyzed to obtain the noise attenuation rate.

3. The intelligent wearable vital signs detection method for live grid operation as claimed in claim 2, characterized in that: The spectrum analysis process is as follows: Converting the processed noise signal data into a time domain signal, performing a discrete Fourier transform on the time domain signal, and obtaining a frequency spectrum corresponding to each placement position; The power spectrum is extracted from the spectrum diagram, the power spectrum density is calculated, and the power spectrum density is combined with the Euclidean matrix to obtain the noise spectrum morphology similarity of noise signals at different positions.

4. The intelligent wearable vital signs detection method for live grid operation as claimed in claim 3, characterized in that: The noise intensity at different locations is spatially analyzed to obtain the noise attenuation rate, which is specifically: Obtain noise intensity and equivalent continuous sound level values ​​and establish a two-dimensional coordinate axis; Obtaining the peak-to-valley value fluctuation segment of the first noise signal according to the fluctuation trend of the data in the two-dimensional coordinate axis; A smooth curve is obtained by curve fitting in each peak-to-valley fluctuation segment, and a peak value on the smooth curve is obtained; For any peak point, obtain two extreme value large points adjacent to the peak point on the left and right sides of the smooth curve; The noise attenuation rate is calculated by using the attenuation model to calculate the interval between the adjacent maximum points on the left and right and the peak fluctuation segment width.

5. The intelligent wearable vital sign detection method for live grid operation as claimed in claim 4, characterized in that: The power spectrum is extracted from the spectrum diagram as follows: Perform inverse Fourier transform on the spectrum to obtain the time domain waveform of the signal; Perform a square operation on the time domain waveform to obtain the energy density spectrum of the signal; Divide the energy density spectrum by the number of sampling points to get the average power at each frequency point; The power spectrum is normalized and the integral over the entire frequency spectrum is obtained as the power spectrum.

6. The intelligent wearable vital sign detection method for live grid operation as claimed in claim 5, characterized in that: The power spectrum density is combined with the Euclidean matrix to obtain the noise spectrum morphology similarity of noise signals at different positions, specifically including: Arrange the power spectrum density into a matrix form, and regard the power spectrum density of each signal at different frequencies as a vector; Calculate the Euclidean distance metric between any two positions, and obtain the similarity matrix by traversing and calculating the Euclidean distance between all positions; The rank of the similarity matrix is ​​calculated to obtain the noise spectrum morphology similarity of noise signals at different positions.

7. The intelligent wearable vital sign detection method for live grid operation as claimed in claim 6, characterized in that: The equivalent continuous sound level is calculated as follows: Where: is the equivalent continuous sound level, in db; T is the sampling time; is the value of the sound pressure level calculation formula within the sampling time.

8. The intelligent wearable vital sign detection method for live grid operation as claimed in claim 7, characterized in that: The noise attenuation rate is calculated by the following formula: Where: S is the noise attenuation rate, The reference sound pressure is 20 micropascals by default. is the adjacent maximum point to the left, is the adjacent maximum point to the right, is the attenuation coefficient, which indicates the speed of attenuation.

9. The intelligent wearable vital sign detection method for live grid operation as claimed in claim 8, characterized in that: The power spectrum is normalized as follows: Where: is the normalized power spectrum, is the average power at each frequency point, is the unnormalized power spectrum, N is the number of sampling points, is the frequency domain signal after Fourier transform, is the sampling frequency within the sampling time.

10. A system using the smart wearable vital sign detection method for live grid operation as claimed in any one of claims 1 to 9, characterized in that: It includes environmental noise data acquisition module, noise feature analysis module, noise balance scoring module, and vital sign detection effect verification module: The environmental noise data acquisition module is used to obtain environmental noise information of different placement positions of the smart wearable device in the working environment of the operator in the same time period to obtain the original noise signal data; A noise feature analysis module, used to perform noise intensity analysis and spectrum analysis on the environmental noise information to obtain noise features at different placement locations; A noise balance scoring module, configured to calculate a noise balance score according to the noise characteristics, and determine an optimal vital sign collection position based on the noise balance score; The vital signs detection effect verification module is used to detect the vital signs of the operating personnel at the optimal vital signs collection position, compare the vital signs collection effect obtained at the optimal placement position with the vital signs collection effect measured by the operating personnel in a non-operating environment, and verify the detection accuracy of the optimal position.

Images