A method for monitoring vital signs of an intelligent arc-proof clothing

Abstract

The present invention relates to the technical field of data processing. More specifically, the present invention relates to a method for monitoring vital signs of an intelligent arc-proof clothing, and the method includes: determining the response duration and response degree of each dimension data to the change of the motion state according to the change of the vital sign data of each dimension when an experimental person wears the arc-proof clothing and conducts activities in different states, and further determining the prediction index of each dimension; collecting the real-time vital sign data of multiple dimensions when an operator wears the arc-proof clothing and conducts work; correcting the prediction index of the current dimension according to the change of the real-time vital sign data of each dimension whose response duration is less than that of the current dimension; predicting the vital sign data of each dimension at a future moment according to the corrected prediction index of each dimension, and conducting vital sign monitoring according to the prediction result. The present invention can improve the prediction and judgment accuracy of the health status of the operator and effectively improve the safety of the operator.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing. More specifically, the present invention relates to a method for monitoring vital signs of an intelligent arc-proof clothing. Background Art

[0002] As an important protective equipment for electric power operators, arc-proof clothing can prevent arc injuries to a certain extent, but there are still many deficiencies in dynamically monitoring the vital signs of operators and providing real-time warnings.

[0003] With the development of intelligent technologies, intelligent protective equipment combined with vital sign monitoring has gradually become an important tool for improving safety. By integrating sensors, intelligent arc-proof clothing can monitor the vital sign data of operators in real time, such as heart rate, blood oxygen, etc., and timely detect potential health risks. However, it is often difficult to achieve early warning by simply monitoring real-time data. Therefore, it is particularly important to predict the vital signs at future moments based on real-time vital sign data and issue early warnings based on the predicted values.

[0004] The exponential smoothing method is a data prediction method that can predict the vital sign values at future moments according to the changing trend of the vital sign data collected by the vital sign monitoring module integrated in the arc-proof clothing. However, the smoothing coefficient in the exponential smoothing method usually needs to be set manually. If the smoothing coefficient is set too large, the prediction model may overly focus on the latest data, thus ignoring the historical trend of the vital sign data, which will lead to inaccurate prediction of the vital sign data at future moments and even false alarms; on the contrary, if the smoothing coefficient is set too small, the prediction model will be relatively slow to respond to new data, making it difficult to capture sudden changes in the vital sign data in a timely manner, thereby reducing the prediction accuracy of the vital sign data and possibly resulting in missed alarms. Summary of the Invention

[0005] To solve the technical problem of inaccurate prediction of vital sign data caused by manually setting the smoothing coefficient of the exponential smoothing method, the present invention proposes a method for monitoring vital signs of an intelligent arc-proof clothing, which includes the following steps:

[0006] Collect experimental data, where the experimental data includes vital sign data in multiple dimensions when the experimental personnel wear arc-resistant clothing and perform activities in different states; according to the changes in the data of each dimension in the experimental data, determine the response duration and response degree of each dimension to the change in the motion state; determine the prediction index of each dimension according to the response duration and response degree; collect real-time vital sign data in multiple dimensions when the operator wears arc-resistant clothing and works; correct the prediction index of the current dimension according to the changes in the real-time vital sign data of each dimension with a response duration less than that of the current dimension; use the corrected prediction index of each dimension as the smoothing coefficient, and use the exponential smoothing method to predict the vital sign data of each dimension at a future moment; perform vital sign monitoring according to the prediction results of the vital sign data of each dimension at a future moment.

[0007] Through detailed analysis of the vital signs in each dimension of the experimental data, the present invention identifies the response characteristics of each dimension to the change in the motion state, determines the response duration and response degree of each dimension, and can improve the prediction and judgment accuracy of the health status of the operator; the working environment and the motion state of the operator are constantly changing. By collecting vital sign data in multiple dimensions and performing prediction and correction according to the response duration, response degree and data changes of each dimension, the present invention can ensure that the system effectively responds to the impact of different working states on vital signs in a dynamic environment; according to the changes in the real-time vital sign data of the dimension with a smaller response duration, the present invention corrects the prediction index of the dimension with a larger response duration, which can realize the dynamic adjustment of the prediction index, so that when using the exponential smoothing method to predict the vital sign data of each dimension at a future moment, the prediction result can not only reflect the historical trend of the vital sign data, but also capture the sudden changes of the vital sign data in time. Based on the prediction result for early warning, the safety of the operator can be improved.

[0008] Preferably, determining the response duration and response degree of each dimension data to the change in the motion state includes: taking any one dimension as the target dimension; dividing the data of the target dimension into multiple segments according to the moment of the change in the motion state; determining the change degree of each data in each segment compared with the corresponding data in each period of the previous segment; forming a sequence with the change degrees of all the data in each segment, performing Otsu threshold segmentation on the sequence, and taking the difference between the moment corresponding to the first data in the second subsequence obtained by segmentation and the moment corresponding to the first data in this segment as the response duration of this segment; taking the mean value of the change degrees of all the data in the second subsequence as the response degree of this segment; taking the mean value of the response durations of all the segments and the mean value of the response degrees of all the segments as the response duration and response degree of the target dimension data to the change in the motion state respectively.

[0009] By calculating the degree of change of each segment of data relative to the previous segment, the dynamic changes of each stage can be quantified. By performing Otsu threshold segmentation on each segment, the response duration of each segment of data can be accurately identified. By calculating the mean value of the degree of change of each segment, the response degree of that segment can be obtained, which can provide a quantitative assessment of the overall reaction level of the change in the motion state and help accurately evaluate the adaptability and influence of different dimensions on the change in the motion state.

[0010] Preferably, determining the degree of change of each data in each segment compared to the corresponding data in each period of the previous segment includes: obtaining the period length of the data of the target dimension, dividing the data of the target dimension into multiple periods according to the period length; for each data in each segment, taking the position serial number of the data within its period as the first target serial number, obtaining the mean value of the differences between this data and the data with the first target serial number in each period of the previous segment, and taking the ratio of the mean value of the differences to the range of all data with the first target serial number in each period of the previous segment as the transformation degree of this data.

[0011] By calculating the mean value of the differences between each data and the data with the same position in each period of the previous segment, the volatility and change trend of the data between periods can be effectively evaluated, which helps to identify the potential laws and abnormal fluctuations of the data and is conducive to more accurately analyzing and predicting the trend changes of the target dimension.

[0012] Preferably, the method for obtaining the period length is: performing Fourier transform on the data of the target dimension, and taking the reciprocal of the frequency of the component with the largest amplitude after Fourier transform as the period length of the target dimension.

[0013] Preferably, determining the prediction index of each dimension includes: taking any one dimension as the target dimension, performing negative correlation normalization on the response duration of the target dimension data to the change in the motion state, performing positive correlation normalization on the response degree of the target dimension data to the change in the motion state, and taking the product of the result of negative correlation normalization of the response duration and the result of positive correlation normalization of the response degree as the prediction index of the target dimension.

[0014] In the present invention, when the response duration of the data of the target dimension to the change in the motion state is short and the response degree is large, it indicates that the sensitivity of this dimension is high. When predicting, more attention should be paid to the latest data to reduce the interference of historical data fluctuations on the prediction. By performing negative correlation normalization on the response duration and positive correlation normalization on the response degree, and then taking the product of the two as the prediction index, the data change characteristics of each dimension can be accurately reflected. Applying it to the exponential smoothing method to adjust the smoothing coefficient, when the prediction index is high, the larger the smoothing coefficient, the more the model will focus on the latest data changes, improving the accuracy and timeliness of the prediction.

[0015] Preferably, correcting the prediction index of the current dimension includes: sorting each dimension in ascending order of response duration, and the prediction index after correction of the th dimension satisfies the expression: , represents the prediction index of the th dimension; , respectively represent the response durations of the th dimension and the th dimension to the change in motion state; represents the change difference of the th data among the data before the current moment in the th dimension. The acquisition method is as follows: divide the real-time data of the th dimension into multiple periods according to the period length of the th dimension, record the serial number of the th data in its period as , and obtain the average difference between the th data and the th data in each period before its current period. Take the normalized result of the average difference as the change difference of the th data. th data.

[0016] By correcting the prediction index of the current dimension, the present invention can dynamically adjust the prediction index according to the response durations of different dimensions, thereby optimizing the accuracy of data prediction. Dimensions with shorter response durations react faster to changes in the motion state, so they can reflect changes in the motion state more promptly. For dimensions with longer response durations, their prediction indices are smaller, which helps to maintain the regularity of periodic data. When the motion state changes, by combining the change information of other dimensions to correct the prediction index, the predicted value of this dimension can be adjusted more effectively, enabling it to capture sudden changes in vital sign data in a timely manner.

[0017] Preferably, predicting the vital sign data of each dimension at a future moment includes: using the data sequence collected in real time for each dimension as a data sample, and performing exponential smoothing on the data sample according to a smoothing coefficient to obtain the prediction results of the vital sign data of each dimension at the future moment.

[0018] Preferably, predicting the vital sign data of each dimension at a future moment includes: taking any one dimension as the target dimension and using the data sequence collected in real time for the target dimension as the first data sample; dividing the data in real time for the target dimension into multiple cycles according to the cycle length of the target dimension. If the position serial number of the data at the current moment within its cycle is less than the cycle length of the target dimension, adding 1 to the position serial number of the data at the current moment within its cycle as the second target serial number; otherwise, taking 1 as the second target serial number, and forming a sequence of the data with the position serial number being the second target serial number in all cycles as the second data sample; performing exponential smoothing on the first data sample and the second data sample respectively according to the smoothing coefficient to obtain the first prediction value and the second prediction value; performing weighted summation on the first prediction value and the second prediction value to obtain the prediction result of the vital sign data of the target dimension at the future moment.

[0019] Preferably, when performing weighted summation on the first prediction value and the second prediction value, the weight of the first prediction value is and the weight of the second prediction value is where is the corrected prediction index for the target dimension.

[0020] The present invention effectively combines the periodic characteristics and real-time changes of vital sign data, improving the accuracy and reliability of vital sign data prediction. When the corrected prediction index of the target dimension is small, it indicates that the state of the operator is stable, and the prediction result depends more on the periodic changes of the target dimension. Therefore, by increasing the weight of the second prediction value, the periodic characteristics of the prediction are enhanced; while when the corrected prediction index is large, it indicates that the state of the operator has changed, and the prediction result focuses more on the real-time data changes. Therefore, by increasing the weight of the first prediction value, the prediction can better reflect the influence of the state change.

[0021] Preferably, performing vital sign monitoring according to the prediction results of the vital sign data of each dimension at a future moment includes: in response to the prediction result of a dimension exceeding the normal value range, or the actual value of the data of this dimension exceeding the normal value range, or the difference between the prediction result and the actual value of the data of this dimension exceeding the preset difference threshold, it indicates that the vital sign is abnormal.

[0022] The present invention has the following beneficial effects:

[0023] The prediction result of the vital sign data of each dimension at a future moment of the present invention can not only reflect the historical trend of the vital sign data but also capture the sudden changes of the vital sign data in a timely manner, improving the prediction and judgment accuracy of the health status of the operator. Based on the prediction result for early warning, it can effectively improve the safety of the operator. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1It is the flowchart of the steps of a method for monitoring vital signs of an intelligent arc-proof clothing according to the present invention.

[0025] Figure 2 It is the flowchart of step S2 of a method for monitoring vital signs of an intelligent arc-proof clothing according to the present invention.

[0026] Figure 3 It is a schematic diagram of a carbon dioxide concentration curve. Specific embodiments

[0027] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0028] In order to monitor the vital signs of operators, a carbon dioxide sensor and an oxygen sensor are installed inside the arc-proof clothing, and a heart rate sensor and a blood oxygen sensor are installed inside the cuffs of the arc-proof clothing. After the experimental personnel or operators wear the arc-proof clothing, the heart rate sensor and the blood oxygen sensor can closely contact the wrists of the experimental personnel or operators to collect the heart rate and blood oxygen of the experimental personnel or operators in real time.

[0029] Next, the specific embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0030] Please refer to Figure 1 , which shows the flowchart of the steps of a method for monitoring vital signs of an intelligent arc-proof clothing provided by the present invention. The method includes the following steps:

[0031] S1. Collect experimental data, where the experimental data includes vital sign data in multiple dimensions when experimental personnel wear arc-proof clothing and perform activities in different states.

[0032] The experimental personnel wear arc-proof clothing and perform activities in different motion states, such as standing, sitting, walking, running, etc., and record the moments when the motion states change. Collect the vital sign data of the experimental personnel during the experiment, such as the carbon dioxide concentration, oxygen concentration, heart rate, and blood oxygen in the arc-proof clothing. The carbon dioxide concentration and oxygen concentration in the arc-proof clothing are collected by the carbon dioxide sensor and oxygen sensor inside the arc-proof clothing, and the heart rate and blood oxygen of the experimental personnel are collected by the heart rate sensor and blood oxygen sensor inside the cuffs of the arc-proof clothing. The collection frequency is set by the implementer according to the actual implementation situation, such as 1 time / second.

[0033] S2. Determine the response duration and response degree of each dimension of data to the change in motion state according to the changes in each dimension of data in the experimental data.

[0034] It should be noted that the change in the motion state will cause the data in each dimension to change. For example, when the experimenter changes from a standing posture to walking, the experimenter's breathing rate increases, heart rate increases, body temperature increases, oxygen consumption increases, resulting in a decrease in blood oxygen, a decrease in the oxygen concentration inside the arc-proof suit, and an increase in the exhaled carbon dioxide, which causes an increase in the carbon dioxide concentration inside the arc-proof suit. However, the response time and response degree of the data in each dimension to the change in the motion state are different. For example, when the experimenter changes from a standing posture to walking, the muscles are constantly moving, consuming oxygen and energy, metabolizing to produce carbon dioxide, and discharging carbon dioxide out of the body. Therefore, the oxygen concentration inside the arc-proof suit is first affected by the change in the motion state, and the carbon dioxide concentration is affected later by the change in the motion state. Therefore, the response duration of the oxygen concentration to the change in the motion state is shorter than that of the carbon dioxide concentration to the change in the motion state. When the experimenter changes from a standing posture to walking, the heart rate increases to 1.5 to 2 times that before, while the degree of decrease in blood oxygen is limited, usually not exceeding 5%. Therefore, the response degree of the heart rate to the change in the motion state is greater than that of the blood oxygen to the change in the motion state. The present invention determines the response duration and response degree of the data in each dimension to the change in the motion state according to the changes in the data in each dimension in the experimental data.

[0035] Please refer to Figure 2 , which shows a flowchart of step S2 of a method for monitoring vital signs of an intelligent arc-proof suit according to the present invention, including step S201-step S202, specifically:

[0036] S201. Divide the data in each dimension into multiple segments according to the moment of the change in the motion state, and determine the change degree of each data in each segment compared with the corresponding data in each period of the previous segment.

[0037] It should be noted that during inhalation, the expansion and pressure change of the chest affect the blood return of the heart, causing the heart rate to accelerate slightly. Oxygen enters the lungs and diffuses into the blood through the alveoli, and the blood oxygen usually rises. During exhalation, the heart rate slows down slightly, carbon dioxide in the body is discharged, and the blood oxygen will drop slightly. Therefore, both the heart rate and blood oxygen change with the respiratory cycle. During one breathing process of the experimenter, the experimenter inhales oxygen and exhales carbon dioxide, which causes an increase in the carbon dioxide concentration inside the arc-proof suit and a decrease in the oxygen concentration. Since the arc-proof suit is designed with ventilation openings, the outside air enters the arc-proof suit through the ventilation openings, and the gas inside the arc-proof suit leaves through the ventilation openings, resulting in a decrease in the carbon dioxide concentration and an increase in the oxygen concentration inside the arc-proof suit. As the experimenter continues to breathe, the above process repeats, causing the carbon dioxide concentration and oxygen concentration to also show the characteristic of periodic fluctuation. Therefore, the present invention obtains the change degree of each data according to the law of periodic change of the data in each dimension, and uses the change degree to reflect the degree of influence of the data on the change in the motion state.

[0038] Specifically, take any dimension as the target dimension, perform Fourier transform on the data of the target dimension, and obtain the reciprocal of the frequency of the component with the largest amplitude after Fourier transform as the period length of the target dimension. Divide the data of the target dimension into multiple periods according to the period length.

[0039] Divide the data of the target dimension into multiple segments according to the moments when the motion state changes. The first data in each segment is the data of the target dimension corresponding to the moment when the motion state changes, and the last data in each segment is the data of the target dimension at the moment before the next moment when the motion state changes.

[0040] For each data in each segment, take the position serial number of the data within its period as the first target serial number, obtain the average value of the differences between this data and the data with the first target serial number in each period of the previous segment, and take the ratio of the average value of the differences to the range of all data with the first target serial number in each period of the previous segment as the transformation degree of this data.

[0041] It should be noted that the data with the first target serial number in each period of the previous segment are the data at the same position in each period under the previous motion state. Under the periodic law, these data are the same or similar. The current data is also the data at the same position within the period. If the difference between the current data and the data with the first target serial number in each period of the previous segment is greater, it means that the change of the current data compared with the previous data is greater, and the current data is more affected by the change of the motion state. On the contrary, if the difference between the current data and the data with the first target serial number in each period of the previous segment is smaller, it means that the change of the current data compared with the previous data is smaller, and the current data is less affected by the change of the motion state.

[0042] For example Figure 3 is a schematic diagram of the carbon dioxide concentration curve. Figure 3 A in Figure 3 are two moments when the motion state changes. B1 and B2 in

[0043] S202. Determine the response duration and response degree of each dimension to the change of the motion state according to the transformation degree of each data in each segment.

[0044] Specifically, form a sequence with the transformation degrees of all data in each segment, and perform Otsu threshold segmentation on this sequence to divide it into two subsequences.

[0045] It should be noted that the degree of change of the data in the first subsequence obtained by segmentation is relatively small, and at this time, the influence of the change in the motion state on the data in this dimension has not yet emerged. The degree of change of the data in the second subsequence obtained by segmentation is relatively large, that is, the influence of the change in the motion state on the data in this dimension begins to emerge. The moment corresponding to the first data in this segment is the moment when the motion state changes. Therefore, the difference between the moment corresponding to the first data in the second subsequence and the moment corresponding to the first data in this segment reflects the delay time of the influence of the change in the motion state on this segment, and the degree of change of the data in the second subsequence reflects the degree of influence of the change in the motion state on this segment. Therefore, the present invention obtains the response duration and response degree of this segment according to the delay time of the influence of the change in the motion state on this segment and the degree of influence of the change in the motion state on this segment.

[0046] Specifically, the difference between the moment corresponding to the first data in the second subsequence and the moment corresponding to the first data in this segment is used as the response duration of this segment. The average value of the degrees of change of all the data in the second subsequence is used as the response degree of this segment.

[0047] The average value of the response durations of all segments of the target dimension is used as the response duration of the target dimension data to the change in the motion state, and the average value of the response degrees of all segments of the target dimension is used as the response degree of the target dimension data to the change in the motion state.

[0048] Similarly, the response duration and response degree of the data in each dimension to the change in the motion state are obtained.

[0049] S3. Determine the prediction index of each dimension according to the response duration and response degree of the data in each dimension to the change in the motion state.

[0050] It should be noted that for any dimension, when the response duration of the data in this dimension to the change in the motion state is shorter and the response degree to the change in the motion state is larger, the data in this dimension is more sensitive to the change in the motion state. When performing data prediction later, less attention is paid to the previous data, avoiding the influence of the fluctuation law of the previous data on the accuracy of the predicted data, and more attention is paid to the latest generated data, so that the predicted data can reflect the data change brought about by the change in the motion state. In the present invention, the exponential smoothing method is used to predict data later. The larger the smoothing coefficient of the exponential smoothing method, the more attention is paid to the latest generated data, and the smaller the smoothing coefficient, the more attention is paid to the previous data. Therefore, the present invention determines the prediction index of each dimension according to the response duration and response degree of the data in each dimension to the change in the motion state, and obtains the smoothing coefficient by using the prediction index. When the response duration of the data in each dimension to the change in the motion state is shorter and the response degree to the change in the motion state is larger, the prediction index of this dimension is larger, and more attention is paid to the latest generated data when performing data prediction later.

[0051] Specifically, perform negative correlation normalization on the response duration of the target dimension data to the change in the motion state, perform positive correlation normalization on the response degree of the target dimension data to the change in the motion state, and use the product of the result of negative correlation normalization of the response duration and the result of positive correlation normalization of the response degree as the prediction index of the target dimension.

[0052] Further, the method adopted by the present invention for performing negative correlation normalization on the response duration is: , where is the result after performing negative correlation normalization on the response duration of the target dimension data to the change in the motion state, is the response duration of the target dimension data to the change in the motion state, is the cycle length of the target dimension, is the exponential function with the natural constant as the base.

[0053] The function adopted by the present invention for performing positive correlation normalization on the response degree is the hyperbolic tangent function. In other embodiments, the implementer can select the methods of negative correlation normalization and positive correlation normalization according to the actual implementation situation.

[0054] Similarly, obtain the prediction indices of each dimension.

[0055] S4. Collect the real-time vital sign data of multiple dimensions when the operator wears the arc-proof suit to work.

[0056] Specifically, when the operator wears the arc-proof suit to work, collect the real-time vital sign data of the operator during the work process, such as the carbon dioxide concentration, oxygen concentration, heart rate, blood oxygen, etc. inside the arc-proof suit. The carbon dioxide concentration and oxygen concentration inside the arc-proof suit are collected by the carbon dioxide sensor and oxygen sensor on the inner side of the arc-proof suit, and the heart rate and blood oxygen of the operator are collected by the heart rate sensor and blood oxygen sensor on the inner side of the cuff of the arc-proof suit. The collection frequency is the same as the collection frequency of the experimental data.

[0057] S5. Modify the prediction index of the current dimension according to the changes in the real-time vital sign data of each dimension whose response duration is less than that of the current dimension.

[0058] It should be noted that the data of the dimension with a long response duration responds slowly to the change in the motion state, and its prediction index is small. If the motion state has not changed, the small prediction index can make the predicted value of this dimension better reflect the periodic change law of the data. If the motion state changes, the prediction index needs to be increased so that the predicted value of this dimension can reflect the change brought about by the change in the motion state. Therefore, the present invention determines whether the motion state has changed according to the changes in the real-time vital sign data of the dimension with a short response duration, and thus adjusts the prediction index of the dimension with a long response duration.

[0059] Specifically, each dimension is sorted in ascending order of response duration.

[0060] The predicted index after correction for the th dimension satisfies the expression:

[0061] ;

[0062] where represents the predicted index of the th dimension; , respectively represent the response durations of the th dimension and the th dimension to the change in motion state; represents the change difference of the th data among the data before the current moment in the th dimension. The acquisition method is as follows: According to the period length of the th dimension, the real-time data of the th dimension is divided into multiple periods. Denote the period where the th data is located as . When , it is stipulated that . Otherwise, denote the serial number of the th data in its period as . Obtain the average difference between the th data and the th data in the previous periods. Take the normalized result of the average difference as the change difference of the th data.

[0063] If the change difference of the th data among the data before the current moment in the th dimension is larger, it indicates that the motion state of the operator may have changed within the th dimension before the current moment. At this time, it is necessary to increase the predicted index of the th dimension, so that when predicting the data of the th dimension later, more attention is paid to the latest generated data, enabling the predicted data to reflect the data changes brought about by the change in motion state. On the contrary, if the change difference of the th data among the data before the current moment in the The prediction indices of each dimension should be kept as constant as possible so that when predicting the data of the th dimension later, more attention is paid to the previous data, enabling the predicted data to reflect the overall pattern of the data in that dimension.

[0064] It should be noted that when occurs, there are no other dimensions before the th dimension. Therefore, it is stipulated that when occurs, the corrected prediction index of the th dimension is equal to the prediction index before correction .

[0065] Thus, the correction of the prediction indices of each dimension is achieved.

[0066] S6. Use the corrected prediction indices of each dimension as smoothing coefficients to predict the vital sign data of each dimension at future times.

[0067] In the first embodiment, the data sequence collected in real time for the target dimension is used as the data sample, and the corrected prediction index of the target dimension is used as the smoothing coefficient to perform exponential smoothing on the data sample to obtain the prediction result of the vital sign data of the target dimension at future times.

[0068] In the second embodiment, the data sequence collected in real time for the target dimension is used as the first data sample, and the corrected prediction index of the target dimension is used as the smoothing coefficient to perform exponential smoothing on the first data sample to obtain the first predicted value of the vital sign data of the target dimension at future times.

[0069] The real-time data of the target dimension is divided into multiple cycles according to the cycle length of the target dimension. If the position serial number of the data at the current time within its cycle is less than the cycle length of the target dimension, add 1 to the position serial number of the data at the current time within its cycle as the second target serial number; otherwise, use 1 as the second target serial number. The data with the position serial number of the second target serial number in all cycles forms a sequence as the second data sample, and the corrected prediction index of the target dimension is used as the smoothing coefficient to perform exponential smoothing on the second data sample to obtain the second predicted value of the vital sign data of the target dimension at future times.

[0070] Perform weighted summation on the first predicted value and the second predicted value of the vital sign data of the target dimension at future times to obtain the prediction result of the vital sign data of the target dimension at future times. Among them, when performing weighted summation on the first predicted value and the second predicted value of the vital sign data of the target dimension at future times, the weights of the first predicted value and the second predicted value are both 0.5.

[0071] It should be noted that since the vital sign data in each dimension changes periodically, if only the real-time data sequence is used for prediction, there may be certain deviations in the results. Therefore, in the second embodiment, the periodic change characteristics of the data are also considered, and the data at the same position in the period as the data at the future moment is used to predict the data at the future moment. Compared with only predicting based on the real-time data sequence, the result is more accurate.

[0072] In the third embodiment, the real-time data sequence collected in the target dimension is used as the first data sample, and the corrected prediction index in the target dimension is used as the smoothing coefficient to perform exponential smoothing on the first data sample to obtain the first predicted value of the vital sign data in the target dimension at the future moment.

[0073] According to the period length of the target dimension, the real-time data in the target dimension is divided into multiple periods. If the position serial number of the data at the current moment within its period is less than the period length of the target dimension, the position serial number of the data at the current moment within its period plus 1 is used as the second target serial number; otherwise, 1 is used as the second target serial number. The data with the position serial number being the second target serial number in all periods is formed into a sequence as the second data sample, and the corrected prediction index in the target dimension is used as the smoothing coefficient to perform exponential smoothing on the second data sample to obtain the second predicted value of the vital sign data in the target dimension at the future moment.

[0074] The first predicted value and the second predicted value of the vital sign data in the target dimension at the future moment are weighted and summed to obtain the prediction result of the vital sign data in the target dimension at the future moment. Among them, when the first predicted value and the second predicted value of the vital sign data in the target dimension at the future moment are weighted and summed, the weight of the first predicted value is and the weight of the second predicted value is where is the corrected prediction index in the target dimension.

[0075] It should be noted that in the third embodiment, when the corrected prediction index in the target dimension is smaller, it indicates that the movement state of the operator remains unchanged. At this time, a smaller weight is assigned to the first predicted value and a larger weight is assigned to the second predicted value, so that the result of the final predicted value depends more on the periodic change characteristics, and the final predicted value can better reflect the periodic change law of the target dimension. On the contrary, when the corrected prediction index in the target dimension is larger, it indicates that the movement state of the operator has changed. At this time, a larger weight is assigned to the first predicted value and a smaller weight is assigned to the second predicted value, so that the result of the final predicted value pays more attention to the real-time change of the sequence, and the final predicted value can better reflect the change brought by the change of the movement state.

[0076] S7. Perform vital sign monitoring according to the prediction results of the vital sign data in each dimension at the future moment.

[0077] It should be noted that when the predicted result exceeds the normal value range, it indicates that the change trend of the vital sign data of the operator is abnormal, and abnormalities such as arc flash, high temperature, and high pressure may have occurred. The vital signs of the operator will be abnormal at a future time. When the actual value exceeds the normal value range, it indicates that the vital signs of the operator have already been abnormal. When the difference between the predicted result and the actual value exceeds the difference threshold, it indicates that the change of the vital signs of the operator does not conform to the change law of the previous data, and at this time, abnormalities such as arc flash, high temperature, and high pressure may have occurred.

[0078] Specifically, in response to the predicted result of a dimension exceeding the normal value range, or the actual value of the data of this dimension exceeding the normal value range, or the difference between the predicted result and the actual value exceeding the preset difference threshold, it is considered that an abnormality has occurred. At this time, the monitoring personnel should immediately instruct the operator to stop working and check the physical condition of the operator.

[0079] Among them, the normal data range and difference threshold of each dimension are set by the implementer according to the actual implementation situation. For example, the normal value range of heart rate is 60 beats per minute - 110 beats per minute, and the difference threshold is 5 beats per minute; the normal value range of blood oxygen is 95% - 100%, and the difference threshold is 1%; the normal value range of carbon dioxide concentration is 0.04% - 0.1%, and the difference threshold is 0.005%; the normal value range of oxygen concentration is 19.5% to 23.5%, and the difference threshold is 0.01%.

[0080] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for monitoring vital signs of an intelligent arc-proof clothing, characterized in that, Including: Collecting experimental data, where the experimental data includes vital sign data in multiple dimensions when experimental personnel wear arc-proof clothing and perform activities in different states; According to the changes in the data of each dimension in the experimental data, determining the response duration and response degree of each dimension to the change in the motion state, including: taking any one dimension as the target dimension; dividing the data of the target dimension into multiple segments according to the moment of the change in the motion state; determining the change degree of each data in each segment compared with the corresponding data in each period of the previous segment; forming a sequence with the change degrees of all the data in each segment, performing Otsu threshold segmentation on the sequence to obtain two subsequences, the change degrees of the data in the first subsequence obtained by segmentation are smaller, and the change degrees of the data in the second subsequence are larger, taking the difference between the moment corresponding to the first data in the second subsequence obtained by segmentation and the moment corresponding to the first data in this segment as the response duration of this segment; taking the mean value of the change degrees of all the data in the second subsequence as the response degree of this segment; Taking the mean value of the response durations of all the segments and the mean value of the response degrees of all the segments as the response duration and response degree of the target dimension data to the change in the motion state respectively; determining the prediction index of each dimension according to the response duration and response degree; Collecting real-time vital sign data in multiple dimensions when operating personnel wear arc-proof clothing to work; Modify the prediction index of the current dimension, including: sorting each dimension in ascending order of response duration, and the prediction index of the th dimension after modification satisfies the expression: , represents the prediction index of the th dimension; , respectively represent the response durations of the th dimension and the th dimension to the change in motion state; represents the change difference of the th data among the data before the current moment in the th dimension. The acquisition method is: dividing the real-time data of the th dimension into multiple periods according to the period length of the th dimension, recording the serial number of the th data in its period as , obtaining the average difference between the th data and the th data in each period before its period, and taking the normalized result of the average difference as the change difference of the th data; th data; Taking the corrected prediction index of each dimension as the smoothing coefficient, and using the exponential smoothing method to predict the vital sign data of each dimension at a future moment; Performing vital sign monitoring according to the prediction results of the vital sign data of each dimension at a future moment.

2. The method for monitoring vital signs of an intelligent arc-proof clothing according to claim 1, characterized in that, Determining the change degree of each data in each segment compared with the corresponding data in each period of the previous segment, including: Obtaining the period length of the data of the target dimension, dividing the data of the target dimension into multiple periods according to the period length; for each data in each segment, taking the position serial number of this data in its period as the first target serial number, obtaining the mean value of the differences between this data and the data with the first target serial number in each period of the previous segment, and taking the ratio of the mean value of the differences to the range of all the data with the first target serial number in each period of the previous segment as the change degree of this data.

3. A method for monitoring vital signs of an intelligent arc-proof clothing according to claim 2, characterized in that, The method for obtaining the period length is: Performing Fourier transform on the data of the target dimension, and taking the reciprocal of the frequency of the component with the largest amplitude after Fourier transform as the period length of the target dimension.

4. A method for monitoring vital signs of an intelligent arc-proof clothing according to claim 1, characterized in that, Determining the prediction index of each dimension, including: Taking any one dimension as the target dimension, performing negative correlation normalization on the response duration of the target dimension data to the change in the motion state, performing positive correlation normalization on the response degree of the target dimension data to the change in the motion state, and taking the product of the result of negative correlation normalization of the response duration and the result of positive correlation normalization of the response degree as the prediction index of the target dimension.

5. A method for monitoring vital signs of an intelligent arc-proof clothing according to claim 1, characterized in that, Predicting the vital sign data of each dimension at a future moment, including: Taking the real-time collected data sequence of each dimension as the data sample, and performing exponential smoothing on the data sample according to the smoothing coefficient to obtain the prediction results of the vital sign data of each dimension at a future moment.

6. A method for monitoring vital signs of an intelligent arc-proof clothing according to claim 1, characterized in that, Predict the vital sign data of each dimension at a future moment, including: taking any dimension as the target dimension and using the data sequence collected in real time for the target dimension as the first data sample; dividing the real-time data of the target dimension into multiple periods according to the period length of the target dimension. If the position serial number of the data at the current moment within its period is less than the period length of the target dimension, adding 1 to the position serial number of the data at the current moment within its period as the second target serial number. Otherwise, taking 1 as the second target serial number, and forming a sequence of the data with the position serial number being the second target serial number in all periods as the second data sample; performing exponential smoothing on the first data sample and the second data sample respectively according to the smoothing coefficient to obtain the first predicted value and the second predicted value; performing weighted summation on the first predicted value and the second predicted value to obtain the prediction result of the vital sign data of the target dimension at the future moment.

7. A method for monitoring vital signs of an intelligent arc-proof clothing according to claim 6, characterized in that, When performing weighted summation on the first predicted value and the second predicted value, the weight of the first predicted value is , and the weight of the second predicted value is , where is the predicted index after target dimension correction.

8. A method for monitoring vital signs of an intelligent arc-proof clothing according to claim 1 or 5 or 6, characterized in that, Perform vital sign monitoring according to the prediction results of the vital sign data of each dimension at the future moment, including: In response to the prediction result of a dimension exceeding the normal value range, or the actual value of the data of this dimension exceeding the normal value range, or the difference between the prediction result and the actual value of the data of this dimension exceeding the preset difference threshold, the vital signs are abnormal.

Images