Data acquisition method and system based on Internet of Things equipment

Abstract

The invention relates to the technical field of data processing, in particular to a data acquisition method and system based on internet-of-things equipment, and the method comprises the steps: installing a smoke concentration sensor and a temperature sensor in a cargo area of a warehouse, and calculating the smoke concentration and temperature of the cargo area according to the deviation degrees and change rates of the smoke concentration and temperature at the current moment; determining a smoke concentration risk index and a temperature risk index, and determining a comprehensive risk index by combining the mutual information of the smoke concentration and the temperature; and determining a comprehensive value index according to the respective uncertainty of the historical smoke concentration sequence and the historical temperature sequence and the similarity between the historical smoke concentration sequence and the historical temperature sequence and the corresponding standard sequence, and adjusting the acquisition frequency of the sensor by using the comprehensive risk index and the comprehensive value index to realize a self-adaptive data acquisition strategy. According to the method, environmental changes can be responded in time, potential risks can be recognized in time, and generation of excessive redundant data can be avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing. Specifically, it relates to a data acquisition method and system based on Internet of Things devices. Background Art

[0002] With the wide application of Internet of Things technology, data acquisition systems based on multiple sensors have been applied in scenarios such as warehouse security, industrial monitoring, and environmental detection. In these application scenarios, temperature sensors and smoke concentration sensors, as core sensing devices in warehouse fire monitoring, are commonly used because of their simple mechanism and low deployment cost.

[0003] In the prior art, temperature sensors and smoke concentration sensors usually collect data at a fixed acquisition frequency, that is, periodically sample environmental data at set time intervals and trigger an alarm when the detected value exceeds the threshold.

[0004] However, in actual applications, the warehouse environment is highly dynamic, and the process of fire occurrence is sudden and non-linear. The fixed acquisition frequency cannot adapt to the rapid changes in the environmental state. Especially in the stage of rapid evolution of fire risk, if the set fixed acquisition frequency is low, the change rates of temperature and smoke concentration are much higher than the time scale that the fixed acquisition frequency can perceive, and problems such as lag in risk identification and untimely alarm response are likely to occur. If high-frequency continuous acquisition is set, a large amount of redundant data will be generated during periods of environmental stability or low risk, leading to problems such as data storage pressure, waste of computing resources, and increase in communication load.

[0005] Therefore, there is an urgent need for a method that can adjust the data acquisition strategy in real time according to the dynamic changes of the environmental state, which can not only respond to environmental changes in a timely manner, effectively identify potential risks, but also avoid the generation of excessive redundant data. Summary of the Invention

[0006] To solve the problems of data redundancy and risk lag caused by the fixed acquisition frequency in the prior art, the present invention proposes a data acquisition method and system based on Internet of Things devices.

[0007] In a first aspect, the present invention provides a data acquisition method based on Internet of Things devices, including: Install smoke concentration sensors and temperature sensors in the cargo area of the warehouse; Taking any moment as the current moment, determine the smoke concentration risk index and temperature risk index at the current moment according to the deviation degree of the smoke concentration and temperature at the current moment respectively, and the change rate of the smoke concentration and temperature at the current moment respectively; Determine the mutual information of the smoke concentration and temperature at the current moment based on the historical smoke concentration sequence and historical temperature sequence at the current moment, and combine the mutual information, the smoke concentration risk index, and the temperature risk index to determine the comprehensive risk index of the smoke concentration and temperature at the current moment; Determine the comprehensive value index of the smoke concentration and temperature at the current moment according to the uncertainties of the historical smoke concentration sequence and historical temperature sequence at the current moment and their similarities with the corresponding standard sequences; wherein, the uncertainty is determined based on the information entropy value; Use the comprehensive risk index and comprehensive value index to dynamically adjust the acquisition frequencies of the smoke concentration sensor and the temperature sensor to implement an adaptive data acquisition strategy.

[0008] This technical solution realizes real-time monitoring of environmental changes by arranging smoke concentration sensors and temperature sensors in the cargo area, providing accurate data support for data acquisition and subsequent risk identification. By analyzing the deviation degree and change rate of the smoke concentration, temperature at the current moment from the historical data, abnormal fluctuations and trends of the data can be identified, and then the corresponding risk index can be calculated to feedback the potential risks of the environment in real time. Considering the correlation between the smoke concentration and temperature comprehensively, the comprehensive risk index is further determined, thus improving the accuracy of risk assessment. In addition, information entropy is introduced to calculate the uncertainty of historical data, enabling the method to effectively reflect the stability or volatility of the data; combining the uncertainty of historical data and its similarity with the standard data, comprehensively evaluate the contribution degree of the real-time collected data to risk judgment. This comprehensive value index can help the system make more accurate adjustment decisions, thereby optimizing the data acquisition strategy. Finally, by adjusting the acquisition frequency in real time, the data acquisition strategy can respond to environmental changes in real time, avoiding the lag and redundant data caused by fixed-frequency acquisition, and ensuring the efficient operation of the system and the reasonable utilization of resources.

[0009] Furthermore, the dynamic adjustment of the acquisition frequencies of the smoke concentration sensor and the temperature sensor is based on the following formula:

[0010] In the formula, is the adjusted acquisition frequency of the smoke concentration sensor or the temperature sensor, is the initial acquisition frequency of the smoke concentration sensor or the temperature sensor, is the comprehensive risk index of the temperature and smoke concentration at the moment of is the sign function, is the comprehensive value index of the temperature and smoke concentration at the moment of is The theoretical intermediate value; and correspond to the smoke concentration sensor or the temperature sensor simultaneously.

[0011] This technical solution closely links the acquisition frequencies of the smoke concentration sensor and the temperature sensor with the current environmental risk and data value, ensuring that the data acquisition frequency is increased when the risk is high to promptly capture environmental changes, and decreased when the risk is low to avoid generating redundant data. By combining the comprehensive risk index and the value index, and using the sign function to control the direction of frequency adjustment, the system can flexibly respond to environmental changes, improve the response ability, and optimize resources simultaneously.

[0012] Furthermore, dynamically adjusting the acquisition frequencies of the smoke concentration sensor and the temperature sensor also includes adding boundary restrictions to the adjusted acquisition frequencies of the smoke concentration sensor and the temperature sensor respectively, including: obtaining the maximum acquisition frequency and the minimum acquisition frequency of each according to the respective hardware parameters of the smoke concentration sensor and the temperature sensor; if the adjusted acquisition frequency of the smoke concentration sensor or the temperature sensor is less than its respective minimum acquisition frequency, setting the adjusted acquisition frequency to its respective minimum acquisition frequency; if the adjusted acquisition frequency of the smoke concentration sensor or the temperature sensor is greater than its respective maximum acquisition frequency, setting the adjusted acquisition frequency to its respective maximum acquisition frequency.

[0013] This technical solution sets hardware-level maximum and minimum boundary restrictions for the acquisition frequencies of the smoke concentration sensor and the temperature sensor, ensuring that the acquisition frequencies of the smoke concentration sensor and the temperature sensor are always within the physical limits of the device, improving the rationality of dynamically adjusting the acquisition frequency, and enabling the system to ensure the stability and long-term reliability of the sensors when dynamically adjusting the frequency.

[0014] Furthermore, the comprehensive risk index of the smoke concentration and temperature at the current moment is determined based on the following formula:

[0015] In the formula, is the comprehensive risk index of the smoke concentration and temperature at moment is the smoke concentration risk index at moment is the temperature risk index at moment is the weight of the smoke concentration risk index at moment is the weight of the temperature risk index at moment is the normalization function, is the mutual information of the smoke concentration and temperature at the current moment, is the information entropy value of the historical smoke concentration sequence at the is the information entropy value of the historical temperature sequence at the

[0016] This technical solution comprehensively considers the risk factors of smoke concentration and temperature, and through weight adjustment, normalization function, and calculation of mutual information, accurately evaluates the risk level of the current environment. The risk indices of smoke concentration and temperature, combined with the stability of their historical data and the correlation between the two, can comprehensively reflect the complexity of environmental changes and the multi-dimensional characteristics of risks. It not only improves the accuracy and sensitivity of the risk index but also enhances the real-time response ability to environmental changes.

[0017] Furthermore, the comprehensive value index of the smoke concentration and temperature at the current moment is determined based on the following formula;

[0018] In the formula, is the comprehensive value index of the smoke concentration and temperature at the is the information entropy value of the historical smoke concentration sequence at the is the similarity between the historical smoke concentration sequence and the standard smoke concentration sequence at the is the information entropy of the historical temperature sequence at the is the similarity between the historical temperature sequence and the standard temperature sequence at the

[0019] This technical solution comprehensively evaluates the actual value of smoke concentration and temperature data based on the uncertainty of historical data and the similarity between historical data and standard data. The combination of the stability of historical data and its similarity to standard data can dynamically reflect the credibility of real-time data and the contribution degree of risk judgment. Through the comprehensive value index, data with a high contribution to risk assessment can be effectively identified.

[0020] Furthermore, the risk indices of the smoke concentration and temperature at the current moment are determined based on the following formula:

[0021] In the formula, is the risk index of the smoke concentration or temperature at the is the degree of deviation of the smoke concentration or temperature at the is the deviation degree of the smoke concentration or temperature at time the absolute value symbol, is the change rate of the smoke concentration or temperature at time the median of the change rates of the historical smoke concentration sequence or historical temperature sequence at time t; and and and and correspond to the smoke concentration or temperature simultaneously.

[0022] This technical solution comprehensively evaluates the potential risks of the environment by defining the risk indices of smoke concentration and temperature, combines the deviation degree and change rate between the current moment and the previous moment, and through the non-linear weighting of the deviation degree and change rate, makes the risk index more sensitive to sudden changes or abnormal fluctuations, which helps to identify the potential risks in the environment in a timely manner, especially in scenarios with drastic changes.

[0023] Furthermore, the weights of the smoke concentration risk index and the temperature risk index are determined based on the following method: calculate the cumulative value of the coefficient of variation of the historical smoke concentration sequence and the coefficient of variation of the historical temperature sequence at the current moment; take the ratio of the coefficient of variation of the historical smoke concentration sequence at the current moment to this cumulative value as the weight of the smoke concentration risk index at the current moment; take the ratio of the coefficient of variation of the historical temperature sequence at the current moment to this cumulative value as the weight of the temperature risk index at the current moment.

[0024] Furthermore, the historical smoke concentration sequence and the historical temperature sequence are determined according to the following method: all historical smoke concentrations and all temperatures within a preset time period before the current moment respectively constitute the historical smoke concentration sequence and the historical temperature sequence at the current moment.

[0025] Furthermore, the standard smoke concentration sequence and the standard temperature sequence are determined based on the following method: pre-collect the smoke concentration and temperature in the goods area under normal conditions within a preset time period, which respectively constitute the standard smoke concentration sequence and the standard temperature sequence; and the length of this preset time period is the same as that of the preset time period when obtaining the historical smoke concentration sequence and the historical temperature sequence.

[0026] In a second aspect, the present invention provides a data acquisition system based on Internet of Things devices, including: a temperature sensor and a smoke concentration sensor, which are respectively installed in the goods area of the warehouse; a control unit integrated with a computer program, and when the computer program is executed, it responds to the data collected by the smoke concentration sensor and the temperature sensor and executes the steps of the data acquisition method to implement an adaptive data acquisition strategy.

[0027] The present invention has the following effects: By combining the real-time changes in the environmental state, the present invention adaptively adjusts the data acquisition frequency to achieve efficient response and precise perception of environmental changes. In case of emergencies such as fires, the system can automatically increase the acquisition frequency to ensure timely response; when the risk is low or the environment is stable, the system automatically reduces the acquisition frequency, thereby reducing data redundancy and resource waste. Description of the Drawings

[0028] Figure 1 is a schematic flowchart of the method of the present invention; Figure 2 is a schematic flowchart of the method of step S2 of the present invention. Detailed Embodiments

[0029] 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.

[0030] A data acquisition method based on Internet of Things devices provided by the present invention, as Figure 1 shown in, includes: S1: Obtain the data of the temperature sensors and smoke concentration sensors in each cargo area of the warehouse.

[0031] The warehouse is divided into multiple cargo areas, and 1 temperature sensor and 1 smoke concentration sensor are installed in each cargo area. The smoke concentration sensor usually collects the change in the concentration of particulate matter or combustible gas in the air. Specifically, a photoelectric smoke concentration sensor is used to collect the smoke concentration in the air, and the unit is usually ppm. The temperature sensor usually collects the ambient temperature, and the unit is .

[0032] For any cargo area, according to the traditional acquisition method, set the fixed acquisition frequencies of the smoke concentration sensor and the temperature sensor, both of which are 1 Hz (acquired once per second), and obtain the smoke concentration and temperature in the cargo area in real time. Taking any moment as the current moment, denoted as moment, the corresponding smoke concentration in the cargo area at moment is , and the temperature is .

[0033] S2: According to the data of the temperature sensors and smoke concentration sensors, evaluate the comprehensive risk index of the smoke concentration and temperature at the current moment in real time.

[0034] In the process of warehousing security monitoring, the significance of real-time assessment of the comprehensive risk index lies in achieving early identification and dynamic response to sudden risks such as fires. A large number of goods are stored inside the warehouse, and changes in temperature and smoke are key precursor signals for the development of a fire. By analyzing the data of temperature sensors and smoke sensors in real time and constructing a comprehensive risk index, the degree of danger of the current environment can be more accurately reflected.

[0035] For example, when the smoke concentration suddenly increases or the temperature fluctuates violently, especially when both show significant changes and have a certain synergistic trend, it is very likely to indicate the initial formation or spread of a fire source, and early warning treatment is required to solve the potential safety hazards in the warehouse.

[0036] In this step, risk quantification is carried out by integrating the deviation degree of data, the change rate of data, and the correlation between modalities, and the comprehensive risk index of the smoke concentration and temperature at the current moment is obtained, which can achieve more fine-grained and physically meaningful real-time perception, providing an accurate basis for subsequent links such as acquisition frequency adjustment and early warning linkage.

[0037] Specifically, first obtain the temperature and smoke concentration within N seconds (the empirical value is 60) before the current moment to obtain the historical temperature sequence and historical smoke concentration sequence at the current moment. Then, obtain the comprehensive risk index of the smoke concentration and temperature at the current moment, as Figure 2 shown in S21: Determine the deviation degree of the smoke concentration and the deviation degree of the temperature at the current moment.

[0038] Divide the absolute value of the difference between the smoke concentration at the current moment and the mean of the historical smoke concentration sequence by the standard deviation of the historical smoke concentration sequence to measure the deviation degree of the smoke concentration at the current moment.

[0039] Specifically, it is expressed by the formula:

[0040] In this formula, is the deviation degree of the smoke concentration at is the smoke concentration at is the mean of the historical smoke concentration sequence at is the standard deviation of the historical smoke concentration sequence at

[0041] Divide the absolute value of the difference between the temperature at the current moment and the mean of the historical temperature sequence (at the current moment) by the standard deviation of the historical temperature sequence to measure the deviation degree of the temperature at the current moment.

[0042] Specifically, it is expressed by the formula:

[0043] In the formula, is the deviation degree of the temperature at time is the temperature at time is the mean value of the historical temperature sequence at time is the standard deviation of the historical temperature sequence at time, and || is the absolute value symbol.

[0044] This method of calculating the data deviation degree is essentially the Z - score (standard score), which is an effective way to measure the difference between the current data and the historical data. Specifically, it standardizes the difference between the current - time data and the historical mean, taking into account the data volatility (standard deviation), thereby eliminating the influence of data units and magnitudes, making the data of different times and different devices comparable. In the warehouse monitoring scenario, when the deviation degree of the smoke concentration or temperature at a certain moment is large, it usually indicates potential anomalies or emergencies, such as a fire, heat causing the temperature to deviate from the historical average level, and smoke accumulation causing the smoke concentration to deviate from the historical average level, etc.

[0045] S22: Evaluate the smoke - concentration risk index and the temperature risk index by combining the respective change rates of the smoke concentration and temperature at the current moment.

[0046] The change rate of the smoke concentration at the current moment is determined by calculating the difference between the smoke concentration at the current moment and the previous moment, which reflects the speed of the smoke - concentration change. It is a crucial real - time feedback index in the monitoring system. Especially in scenarios with potential safety risks such as fire or harmful gas leakage, the change rate can help detect anomalies in a timely manner and avoid the further expansion of accidents. A higher change rate of the smoke concentration may indicate a sudden fire or equipment failure.

[0047] Specifically, the calculation formula is:

[0048] In the formula, is the change rate of the temperature at time is the temperature at time is the temperature at time is the absolute value.

[0049] The rate of temperature change at the current moment is determined by calculating the difference in temperature between the current moment and the previous moment (or over a historical period), which reflects how fast the temperature is changing. It is an important real-time feedback indicator in the monitoring system. Especially in scenarios where sudden temperature changes may lead to safety issues (such as equipment overheating, fires, etc.), the rate of change helps to detect potential risks at an early stage.

[0050] Specifically, the calculation formula is:

[0051] In the formula, is the rate of change of smoke concentration at time is the smoke concentration at time is the smoke concentration at time and || is the absolute value.

[0052] Next, in the same way, obtain all the smoke concentration change rates corresponding to the historical smoke concentration sequence at the current moment, and all the temperature change rates corresponding to the historical temperature sequence at the current moment.

[0053] Subsequently, based on the deviation degree of the smoke concentration at the current moment and the smoke concentration change rate, calculate the smoke concentration risk index at the current moment. Based on the deviation degree of the temperature at the current moment and the temperature change rate, calculate the temperature risk index at the current moment.

[0054] The core logic of the calculation here is: If a data deviates more from the historical data, and the change rate of this data is faster, then the moment corresponding to this data is more likely to have a risk, and the risk index of this data is larger. Vice versa.

[0055] In one embodiment, the smoke concentration risk index at the current moment is determined based on the following formula:

[0056] In this formula, is the risk index of the smoke concentration at time is the deviation degree of the smoke concentration at time is the deviation degree of the smoke concentration at time || is the absolute value symbol, is the rate of change of the smoke concentration at time is the median of the rates of change of the historical smoke concentration sequence at time

[0057] In this formula, combines the degree of deviation of the smoke concentration at the current moment and the rate of change of the degree of deviation of the smoke concentration at the current moment. If the difference between the smoke concentration at the current moment and the average level of historical smoke concentrations is greater, that is, the degree of deviation is greater, and the rate of change of the degree of deviation is also greater, it indicates that the smoke concentration at the current moment is more likely to be at risk. Dividing by 2 takes into account that the two are equally important, equivalent to assigning the same weight. The main purpose of squaring is to amplify the impact brought by the deviation of the smoke concentration and its rate of change. In fire risk assessment, abnormal deviation and rapid change of smoke concentration are both relatively key signals, and the squaring operation can make these abnormal situations be more prominently reflected in the risk score.

[0058] In this formula, The part represents the relative magnitude relationship between the rate of change of the smoke concentration at the current moment and the historical general level. Adding 1 to this part is to highlight the difference between the rate of change of the smoke concentration at the current moment and the historical situation without changing the original order of magnitude too much, and is used to judge whether the rate of change of the smoke concentration at the current moment is faster or slower than the historical average situation. If the current rate of change is much greater than the historical general level, it indicates that the smoke concentration at the current moment is changing rapidly, which may indicate the occurrence of abnormal situations such as a fire. Through this part, the impact of this rapid change is incorporated into the risk score to improve the timeliness and accuracy of risk assessment.

[0059] Through this design, when the degree of deviation of the smoke concentration is greater and the rate of change of the smoke concentration is also fast, the calculation results of the two parts will both be larger, and the multiplication will make the risk index increase significantly, highlighting this high-risk state; conversely, if the degree of deviation is small and the rate of change is slow, the multiplication result will make the risk index at a relatively low level, reasonably reflecting the low-risk situation. Through multiplication, the risk factors in two dimensions interact with each other, making the risk index of the smoke concentration more in line with the actual risk situation.

[0060] In one embodiment, the temperature risk index at the current moment is determined based on the following formula:

[0061] In the formula, is the temperature risk index at the is the degree of deviation of the temperature at the is the degree of deviation of the temperature at the is the absolute value symbol, is the rate of change of the temperature at the is the Median of the rate of change of the historical temperature sequence at a given moment.

[0062] In this formula, This part first comprehensively considers the degree of temperature deviation and the degree of change in the temperature deviation amplitude at the current moment. The deviation degree measures the difference between the current temperature and the historical average. A larger deviation usually implies potential anomalies. If the change amplitude of the deviation is also large, it indicates that the abnormal temperature fluctuations may be more intense, thus increasing the risk level at the current moment. By calculating the sum of the deviation degree and the change amplitude and dividing by 2, the importance of the two is ensured to be equal. The purpose of the squaring operation is to amplify the impact of temperature deviation and its change amplitude on risk assessment. In the scenarios of fire and overheating, extreme temperature deviations (especially sharp temperature changes) usually indicate serious safety risks. The squaring operation makes these significantly abnormal changes have a stronger amplifying effect on the risk index, further enhancing the system's sensitivity to risks.

[0063] In this formula, This part measures the magnitude of the current temperature change rate relative to the median of the historical temperature change rate. This ratio is used to judge whether the current temperature change rate is faster or slower than the historical temperature change rate. If the current temperature change rate is much greater than the historical temperature change rate, it indicates that the temperature is changing rapidly at the current moment, which may mean the occurrence of dangerous situations such as equipment overheating and fire. By adding 1, the stability of the calculation is ensured, and the difference between the current temperature change rate and the historical level is incorporated into the risk assessment, thus effectively improving the sensitivity to rapid temperature changes.

[0064] Through this design, when both the degree of temperature deviation and the change rate are large, the results of the two calculation parts will be large, and ultimately the risk index will also increase significantly. This highlights the risk state of relatively intense temperature changes (such as environmental overheating or fire). This design enables dangerous situations such as fire to be detected more easily, thereby improving the system's response speed and accuracy. When the temperature changes slowly and the deviation degree is small, the risk index will be low, reasonably reflecting the low-risk situation, helping to avoid over-response, and ensuring that the system does not frequently issue unnecessary alarms under normal circumstances.

[0065] S23: Introduce the mutual information between smoke concentration and temperature, and determine the comprehensive risk index by combining the risk indices of smoke concentration and temperature respectively.

[0066] In a fire scenario, although the smoke concentration and temperature usually change with the development of the fire, the relationship between them is not a simple linear relationship. By calculating the mutual information, the statistical correlation degree between these two variables can be understood. If the mutual information of the two variables is high, it indicates that there may be a strong synergistic effect between them in fire risk assessment. Then, when calculating the comprehensive risk index, the mutual relationship between them needs to be considered more comprehensively, so as to more accurately reflect the actual fire risk situation and improve the accuracy of risk assessment.

[0067] Specifically, it includes: S231: Obtain the mutual information of the temperature data and smoke data at the current moment.

[0068] Perform normalization operations on both the historical smoke concentration sequence and the historical temperature sequence at the current moment. Specifically, the maximum-minimum normalization method is adopted to normalize the values of each smoke concentration in the historical smoke concentration sequence and each temperature in the historical temperature sequence to the interval.

[0069] Divide the value ranges of the historical smoke concentration sequence and the historical temperature sequence into equal-distance intervals, and combine the intervals of the historical smoke concentration data and the intervals of the historical temperature data pairwise, obtaining a total of kinds of interval combinations; In the historical smoke concentration sequence and the historical temperature sequence, take the smoke concentration and temperature at the same moment as a pair of data combinations. According to the occurrence times of each pair of data combinations in each interval combination, statistically calculate the joint probability distribution and the marginal probability distribution, and calculate the mutual information between the smoke concentration and the temperature based on the joint probability distribution and the marginal probability distribution, and then use it as the mutual information between the temperature and the smoke at the current moment.

[0070] For example, the numerical intervals after the division of the historical smoke concentration sequence and the historical temperature sequence are both: [0, 0.2), [0.2, 0.4), [0.4, 0.6), [0.6, 0.8), [0.8, 1.0]; Denote them as interval 1 to interval 5 respectively. Then the values of the historical smoke concentration sequence are totally divided into interval 1 to interval 5, and the values of the historical temperature sequence are also totally divided into interval 1 to interval 5.

[0071] In the historical smoke concentration sequence and the historical temperature sequence, the smoke concentration and temperature corresponding to the and , is mapped to the smoke concentration interval 3, denoted as C3, is mapped to the temperature interval 4, denoted as T4. Then and Form a pair of data combinations, and the interval combination into which this pair of data combinations falls is .

[0072] Statistical joint probability distribution: The joint probability distribution describes the probabilities of different combinations of smoke concentration and temperature occurring. If the lengths of the historical smoke concentration sequence and the historical temperature sequence are 60, that is, 60 time moments, then a total of 60 pairs of data combinations (without deduplication) will be obtained. If 5 pairs of data combinations among the 60 pairs of data combinations fall into , then the statistical joint probability distribution is:

[0073] In this formula, is the joint probability of this interval combination, which indicates that in the historical smoke concentration sequence and the historical temperature sequence, the probability of the data combination with the smoke concentration in the C3 interval and the temperature in the T4 interval occurring is 0.0833. In a similar way, the joint probabilities of all 25 interval combinations can be calculated.

[0074] Statistical marginal probability distribution: The marginal probability distribution represents the probabilities of a single variable (such as smoke concentration or temperature) taking all possible values, and the marginal probability distribution is calculated through the joint probability distribution.

[0075] The marginal probability of the smoke concentration in the C3 interval is , where 0 represents the 0th temperature interval, represents the joint probability of this interval combination, 0 ranges from 1 to 5, and the marginal probability of the smoke concentration falling in the interval is obtained by accumulating the joint probabilities.

[0076] The marginal probability of the temperature in the T4 interval is , where represents the th smoke concentration interval, represents the joint probability of this interval combination, and the marginal probability of the temperature in the interval is obtained by accumulating the joint probabilities.

[0077] Through the joint probability distribution and the marginal probability distribution, the mutual information between the smoke concentration and the temperature at the current moment can be calculated:

[0078] In this formula, is the mutual information between the smoke concentration and the temperature, reflecting the degree of correlation between the two variables. and are all interval numbers. The smoke concentration is Interval and temperature Interval Combination of intervals The joint probability of The smoke concentration is The marginal probability in the interval is For the temperature The marginal probability in the interval.

[0079] Since mutual information reflects the correlation between two variables, the mutual information between smoke concentration and temperature at the current moment is , whose value is calculated based on the historical smoke concentration series and temperature series at the current moment .

[0080] Calculating mutual information is a dynamic way to reflect the trend of coordinated changes between smoke concentration and temperature at the current moment. Specifically, if the trend of coordinated changes between smoke concentration and temperature at the current moment in the past 60 seconds is stronger, the mutual information value of smoke concentration and temperature at the current moment is considered to be larger, indicating that it is more likely that smoke concentration and temperature will increase together. If the trend of coordinated changes between smoke concentration and temperature is weaker, the mutual information value is smaller, indicating that the changes in smoke concentration and temperature are not driven by the same factors or their mutual influence is relatively weak, and smoke concentration and temperature may be in a relatively independent state, which usually means that the system is in a normal and stable working state.

[0081] S232: Determine the comprehensive risk index of smoke concentration and temperature at the current moment.

[0082] Under normal circumstances, smoke concentration is usually at a relatively low and stable level. It may fluctuate slightly due to occasional dust, ventilation and other factors in the environment, but generally will not continue to rise or change significantly. Temperature changes are similar. Under normal circumstances, it will show certain regular changes depending on the environment, such as relatively stable fluctuations with the alternation of day and night and the change of seasons, and the range of change is usually within a certain range.

[0083] When a fire occurs, smoke concentration tends to rise rapidly, which is an important indicator of the early stage of the fire. Even if the fire is small, it may produce a lot of smoke, and its changes are characterized by suddenness and rapid growth. The temperature will also gradually rise after the fire occurs, but the temperature rise rate is relatively slow and is affected by many factors such as environmental factors and fire type. It cannot reflect the fire situation clearly and quickly in the early stage of the fire like smoke concentration.

[0084] Therefore, when calculating the comprehensive risk index, it is necessary to set a larger weight for smoke density and a smaller weight for temperature. This is because smoke density can more sensitively and directly reflect the occurrence of fire in the early stage of a fire, and its sudden increase plays a key role in fire warning, which can buy more time for timely detection of fire and taking measures. Temperature changes may not be significant in the early stage of a fire, and the indicative effect on fire is relatively delayed, so a relatively small weight is given, so that the fire risk can be more accurately assessed through the comprehensive risk index, improving the timeliness and accuracy of warnings.

[0085] In one embodiment, the weight is set based on the coefficient of variation of the historical smoke concentration series and the coefficient of variation of the historical temperature series at the current moment. Specifically: Calculate the coefficient of variation of the historical smoke concentration series at the current moment , It is equal to the standard deviation of the historical smoke concentration series divided by the mean of the historical smoke concentration series, and calculates the coefficient of variation of the historical temperature series at the current moment , It is equal to the standard deviation of the historical temperature series divided by the mean of the historical temperature series.

[0086] If the current moment is normal, the coefficient of variation of the historical smoke density series and the coefficient of variation of the historical temperature series are usually small and remain within a relatively stable range. However, when a fire occurs, smoke is a product of the combustion process. Due to the complexity and uncertainty of factors such as combustion intensity and combustion materials, the discreteness of smoke density data will increase significantly, and the coefficient of variation of smoke density data will increase significantly. The temperature will also rise rapidly, but relatively speaking, the temperature rise is more continuous, and it is not as easy to fluctuate violently as smoke density. The change in the discreteness of temperature is smaller than that of smoke density, that is, the increase in the coefficient of variation of temperature is usually smaller than that of smoke density.

[0087] In summary, the comprehensive risk index of smoke concentration and temperature at the current moment is determined based on the following formula:

[0088] In this formula, for The comprehensive risk index of smoke concentration and temperature at the moment, for The smoke concentration risk index at the moment, for Temperature risk index at the moment, for The weight of the smoke concentration risk index at the moment, for The weight of the temperature risk index at a moment is a normalization function. Since is a positive number greater than 0, the value range of this normalization function in the interval from 0 to positive infinity is . By multiplying by 2 and then subtracting 1, make 's value fall within interval, realizing the normalization of . is the mutual information between the smoke concentration and temperature at the current moment, is the information entropy value of the historical smoke concentration sequence at the moment, is the information entropy value of the historical temperature sequence at the moment.

[0089] In this formula, , , where is the coefficient of variation of the historical smoke concentration sequence at the current moment, is the coefficient of variation of the historical temperature sequence at the previous moment. This is because if a fire occurs, the change in the coefficient of variation of the smoke concentration is more significant. Therefore, a larger weight is given to the risk index of the smoke concentration, and the change in the coefficient of variation of the temperature is relatively less obvious, so a smaller weight is given to the risk index of the temperature.

[0090] In this formula, part is a common way of standardizing mutual information, making its value fall within the interval from 0 to 1, is the information entropy value of the historical smoke concentration sequence at the moment, is the information entropy value of the historical temperature sequence at the moment.

[0091] In short, this formula reflects the correlation degree between the smoke concentration and temperature through mutual information. When the change trends of the two are coordinated and the risk indexes of each are higher, the comprehensive risk index is larger and closer to 1, indicating that it is more likely to have a fire at the current moment and there is a high fire risk, and vice versa.

[0092] S3: According to the data of the temperature sensor and the smoke concentration sensor, compare the temperature and smoke concentration data in the standard situation, and evaluate the comprehensive value index of the smoke concentration and temperature at the current moment.

[0093] In fire risk assessment, simply relying on the risk indexes of temperature and smoke concentration may not be sufficient to comprehensively reflect the potential risk level, because these indicators may be affected by environmental fluctuations and show temporary anomalies. Therefore, it is necessary to analyze the abnormality and uncertainty of the data, and then quantify the value index of the data. The value index can more accurately reflect the potential fire risk and help to more effectively evaluate and respond to possible crises.

[0094] Specifically, it includes: Obtain the information entropy of the historical smoke concentration sequence at the current moment and the information entropy of the historical temperature sequence , to measure the uncertainty of the historical smoke concentration sequence and the historical temperature sequence. The larger the information entropy value, the greater the uncertainty, and the higher the potential value for fire risk assessment. Vice versa.

[0095] Pre-collect the smoke concentration and temperature within 60 seconds in the warehouse area under normal conditions (when there is no trend of any fire risk), which are used as the standard smoke concentration sequence and the standard temperature sequence respectively.

[0096] Use the DTW (Dynamic Time Warping) algorithm to calculate the DTW distance between the historical smoke concentration sequence at the current moment and the standard smoke concentration sequence. The reciprocal of the DTW distance reflects the similarity between the historical smoke concentration sequence and the standard smoke concentration sequence. The higher the similarity, the closer the smoke concentration at the current moment is to the historical normal state, and the less likely the smoke concentration at the current moment is to be abnormal, and the lower the potential value for risk assessment. Vice versa.

[0097] Similarly, use the DTW algorithm to calculate the DTW distance between the historical temperature sequence at the current moment and the standard temperature sequence. The reciprocal of the DTW distance reflects the similarity between the historical temperature sequence and the standard temperature sequence. The higher the similarity, the closer the temperature at the current moment is to the historical normal state, and the less likely the temperature at the current moment is to be abnormal, and the lower the potential value for risk assessment. Vice versa.

[0098] To sum up, comprehensively evaluate the comprehensive value index of the smoke concentration and temperature at the current moment based on entropy value and similarity:

[0099] In this formula, is the comprehensive value index of the smoke concentration and temperature at is the information entropy value of the historical smoke concentration sequence at is the similarity between the historical smoke concentration sequence and the standard smoke concentration sequence at is the information entropy of the historical temperature sequence at is the similarity between the historical temperature sequence and the standard temperature sequence at.

[0100] In this formula, a higher entropy value means greater volatility of the data, which may represent higher risks. In fire monitoring, a higher entropy value usually indicates a greater difference between the current data and the historical normal state, and a higher potential fire risk. As a basic indicator, information entropy can provide an assessment of the environmental data itself. Similarity measurement is used to evaluate the matching degree of the current smoke concentration and temperature with the normal state. A higher similarity indicates that the temperature and smoke concentration at the current moment are close to the normal state, with lower risk and value at the current moment. On the contrary, when the similarity is low, it indicates that the data at the current moment is quite different from the historical normal state. At this time, the risk and the possibility of potential abnormal events increase, and the value index rises accordingly.

[0101] In the formula, and when the data is quite different from the standard state, the comprehensive value index increases, directly reflecting the abnormality and risk at the current moment. The product of information entropy further amplifies the comprehensive value index through the uncertainty of the data, reflecting the potential risk of higher uncertainty.

[0102] In short, through the dynamic calculation of information entropy and similarity, this formula can adjust the evaluation value as the environmental conditions change. Under normal circumstances, the temperature and smoke concentration may be highly similar to the standard state, with a small information entropy and a low value index. However, once a fire occurs, the volatility of the temperature and smoke concentration increases, the information entropy rises, and the similarity with the standard state decreases, while the value index rises, helping to detect potential fire risks in a timely manner. It evaluates the potential value of the current smoke concentration and temperature for fire risk assessment from multiple dimensions.

[0103] S4: Dynamically adjust the acquisition frequencies of the smoke concentration sensor and the temperature sensor using the comprehensive risk index and the comprehensive value index to implement an adaptive data acquisition strategy.

[0104] In the fire monitoring of a warehouse, the real-time and accuracy of sensor data are crucial for risk assessment. However, due to the complexity and uncertainty of environmental changes, a fixed acquisition frequency often cannot flexibly cope with scenarios of different risk levels.

[0105] By adaptively adjusting the data acquisition strategy, the data acquisition frequency can be dynamically optimized according to the risk assessment results at the current moment, thereby improving the system efficiency and response speed. The main significance of adaptive adjustment lies in: reducing the acquisition frequency to save energy and storage resources when the risk is low; while increasing the acquisition frequency when the risk is high to ensure timely acquisition of key data and improve the monitoring accuracy and response ability. This dynamic adjustment can effectively cope with complex environmental changes, improve the intelligence and flexibility of the system, and provide more accurate data support for fire early warning.

[0106] Specifically, first, according to the respective hardware parameters of the smoke concentration sensor and the temperature sensor, the maximum acquisition frequency and the minimum acquisition frequency of the smoke concentration sensor are obtained as and , respectively. The maximum acquisition frequency and the minimum acquisition frequency of the temperature sensor are and , respectively. The initial acquisition frequencies of the smoke concentration sensor and the temperature sensor in step S1 are and , respectively.

[0107] For the smoke concentration sensor, the dynamic adjustment of the acquisition frequency is performed based on the following formula:

[0108] In the formula, is the adjusted acquisition frequency of the smoke concentration sensor, is the initial acquisition frequency of the smoke concentration sensor, is the comprehensive risk index of temperature and smoke concentration at time is the sign function, is the comprehensive value index of temperature and smoke concentration at time is the theoretical median value of , specifically 0.5 (empirical value).

[0109] In this formula, reflects the product of the comprehensive risk index and the comprehensive value index at time . The larger the product, the greater the risk and the higher the credibility. The acquisition frequency of the smoke concentration sensor should be increased to capture high-value and high-risk smoke changes through a higher frequency; vice versa. When the two are closer to 1, the product is closer to 1 and reaches the maximum value, indicating that the acquisition frequency needs to be increased to the greatest extent. If either is close to 0, it indicates that the risk is not high or the value is not large, and the acquisition frequency can be appropriately reduced to save resources. The theoretical median value of this product is used to measure the relative size of , as the median value is a symmetric midpoint numerically. It is equal to a neutral value (reference value) of the product of the risk and value indices, meaning that when the value of the product is close to , the risk and value indices are in a balanced state, not biased towards high risk or low risk, and the sensor should maintain the original acquisition frequency. When the value of the product is greater than , it indicates a relatively high fire risk and strong credibility, and the sensor should increase the acquisition frequency to better capture the changes in the fire. When the product is less than , it indicates a relatively low fire risk and poor credibility, and the acquisition frequency should be reduced to save system resources.

[0110] In this formula, reflects the magnitude difference from the theoretical median value. If is greater than , it indicates that the risk coefficient is high and the value index is large at this time. The acquisition frequency of the smoke concentration sensor needs to be increased. At this time, is greater than 0, and the acquisition frequency of the smoke concentration sensor is increased to better capture the fire risk and give an early warning in a timely manner. Moreover, the greater the difference, the greater the increase amplitude. If is equal to , , it indicates that the risk coefficient and the value index are at a general medium level at this time, and the original acquisition frequency of the smoke concentration sensor is retained. If is less than , , it indicates that both the risk coefficient and the value index are relatively low at this time. The acquisition frequency of the smoke concentration sensor is decreased to save resources, and the greater the difference, the greater the decrease amplitude.

[0111] Furthermore, boundary restrictions are added: to ensure that the acquisition frequency of the smoke concentration sensor does not exceed the normal range.

[0112] For the temperature sensor, the acquisition frequency is dynamically adjusted based on the following formula:

[0113] In the formula, is the adjusted acquisition frequency of the temperature sensor, is the initial acquisition frequency of the temperature sensor, is the comprehensive risk index of the temperature and smoke concentration at time is the sign function, is the comprehensive value index of the temperature and smoke concentration at time is the theoretical median value of , specifically 0.5 (empirical value).

[0114] In this formula, reflects the product of the current comprehensive risk index and the comprehensive value index at time t. The larger the product, the greater the risk and the higher the credibility. The acquisition frequency should be increased to capture high-value and high-risk temperature changes at a higher frequency; vice versa. When the two are closer to 1, the product is closer to 1 and reaches the maximum value, indicating that the acquisition frequency of the temperature sensor needs to be increased to the greatest extent. If either is close to 0, it indicates that the risk is not high or the value is not large, and the acquisition frequency of the temperature sensor can be appropriately decreased to save resources.

[0115] In this formula, reflects the magnitude difference from the theoretical intermediate value. If is greater than , it indicates that the risk coefficient is high and the value index is large at this time. The acquisition frequency of the temperature sensor needs to be increased. At this time, is greater than 0, and the acquisition frequency of the temperature sensor is increased to better capture fire risk data and give early warnings in a timely manner. Moreover, the greater the difference, the greater the increase amplitude. If is equal to , it indicates that the risk coefficient and the value index are at a general medium level at this time. At this time, , by retaining the original acquisition frequency of the temperature sensor. If is less than , , it indicates that both the risk coefficient and the value index are relatively low at this time. The acquisition frequency of the temperature sensor is reduced to save resources, and the greater the difference, the greater the reduction amplitude.

[0116] Furthermore, boundary restrictions are added: , to ensure that the acquisition frequency of the temperature sensor does not exceed the normal range.

[0117] In summary, the adjustment mechanism of the acquisition frequency combines the comprehensive risk index and the comprehensive value index, dynamically adjusts the initial acquisition frequencies of the smoke concentration sensor and the temperature sensor up and down, and has good scene adaptability and responsiveness. When the system detects high risk and high data value, it automatically increases the sampling frequency, which helps to capture key abnormal information in a timely manner; conversely, when both the risk and the value are relatively low, the sampling frequency is reduced to save resources. This method introduces the theoretical intermediate value as the adjustment reference, and cooperates with the sign function and boundary control to ensure that the adjustment logic is clear, the implementation is simple, and the frequency is stable within a reasonable range, reflecting the system's dynamic balance ability of energy consumption and risk perception, and improving the intelligent level and practical application efficiency of the acquisition system.

[0118] The present invention also provides a data acquisition system based on Internet of Things devices, including: a temperature sensor and a smoke concentration sensor, which are respectively installed in the goods area of the warehouse; a control unit integrated with a computer program, and when the computer program is executed, it responds to the data collected by the smoke concentration sensor and the temperature sensor and executes the data acquisition method as described in steps S1 - S4 to implement an adaptive data acquisition strategy.

Claims

1. A data acquisition method based on Internet of Things devices, characterized in that, Including: Install smoke concentration sensors and temperature sensors in the goods area of the warehouse; Taking any moment as the current moment, determine the smoke concentration risk index and temperature risk index at the current moment according to the deviation degrees of the smoke concentration and temperature at the current moment respectively, and the change rates of the smoke concentration and temperature at the current moment respectively; Determine the mutual information of the smoke concentration and temperature at the current moment according to the historical smoke concentration sequence and historical temperature sequence at the current moment, and combine the mutual information, the smoke concentration risk index and the temperature risk index to determine the comprehensive risk index of the smoke concentration and temperature at the current moment; Determine the comprehensive value index of the smoke concentration and temperature at the current moment according to the uncertainties of the historical smoke concentration sequence and historical temperature sequence at the current moment respectively and the similarities between them and the corresponding standard sequences; wherein, the uncertainty is determined based on the information entropy value; Use the comprehensive risk index and comprehensive value index to dynamically adjust the acquisition frequencies of the smoke concentration sensors and temperature sensors to implement an adaptive data acquisition strategy.

2. The data acquisition method based on the Internet of Things device according to claim 1, wherein The dynamic adjustment of the acquisition frequencies of the smoke concentration sensors and temperature sensors is carried out based on the following formula: ； In the formula, is the adjusted acquisition frequency of the smoke concentration sensor or the temperature sensor, is the initial acquisition frequency of the smoke concentration sensor or the temperature sensor, is the comprehensive risk index of the temperature and smoke concentration at time is the sign function, is the comprehensive value index of the temperature and smoke concentration at time is the theoretical median value of and correspond to the smoke concentration sensor or the temperature sensor simultaneously.

3. The data acquisition method based on the IoT device according to claim 1, characterized in that, The dynamic adjustment of the acquisition frequencies of the smoke concentration sensors and temperature sensors further includes adding boundary restrictions to the adjusted acquisition frequencies of the smoke concentration sensors and temperature sensors respectively, including: Obtain the maximum acquisition frequency and minimum acquisition frequency of each of the smoke concentration sensors and temperature sensors according to their respective hardware parameters; If the adjusted acquisition frequency of a smoke concentration sensor or a temperature sensor is less than its respective minimum acquisition frequency, set the adjusted acquisition frequency to its respective minimum acquisition frequency; If the adjusted acquisition frequency of a smoke concentration sensor or a temperature sensor is greater than its respective minimum acquisition frequency, set the adjusted acquisition frequency to its respective maximum acquisition frequency.

4. The data acquisition method based on the IoT device according to claim 2, characterized in that The comprehensive risk index of the smoke concentration and temperature at the current moment is determined based on the following formula: ； In the formula, is the comprehensive risk index of smoke concentration and temperature at time is the smoke concentration risk index at time is the temperature risk index at time is the weight of the smoke concentration risk index at time is the weight of the temperature risk index at time is the normalization function, is the mutual information of the smoke concentration and temperature at the current time, is the information entropy value of the historical smoke concentration sequence at time is the information entropy value of the historical temperature sequence at time 5. The data acquisition method based on the Internet of Things device according to claim 2, wherein The comprehensive value index of the smoke concentration and temperature at the current moment is determined based on the following formula; ； In the formula, is the comprehensive value index of the smoke concentration and temperature at time is the information entropy value of the historical smoke concentration sequence at time is the similarity between the historical smoke concentration sequence and the standard smoke concentration sequence at time is the information entropy of the historical temperature sequence at time is the similarity between the historical temperature sequence and the standard temperature sequence at time 6. The data acquisition method based on the Internet of Things device according to claim 4, wherein The smoke concentration risk index and temperature risk index at the current moment are determined based on the following formula: ； In the formula, is the risk index of the smoke concentration or temperature at time is the degree of deviation of the smoke concentration or temperature at time is the degree of deviation of the smoke concentration or temperature at time is the absolute value sign is the change rate of the smoke concentration or temperature at time is the median of the change rates of the historical smoke concentration sequence or historical temperature sequence at time t; 、 、 、 and correspond to the smoke concentration or temperature simultaneously.

7. The data acquisition method based on the IoT device according to claim 4, wherein the smoke The weights of the concentration risk index and the temperature risk index are determined based on the following method: Calculate the cumulative value of the coefficient of variation of the historical smoke concentration sequence and the coefficient of variation of the historical temperature sequence at the current moment; take the ratio of the coefficient of variation of the historical smoke concentration sequence at the current moment to this cumulative value as the weight of the smoke concentration risk index at the current moment; Take the ratio of the coefficient of variation of the historical temperature sequence at the current moment to this cumulative value as the weight of the temperature risk index at the current moment.

8. The data acquisition method based on IoT devices according to claim 5, characterized in that, The historical smoke concentration sequence and historical temperature sequence are determined according to the following method: All historical smoke concentrations and all temperatures within a preset time period before the current moment respectively constitute the historical smoke concentration sequence and historical temperature sequence at the current moment.

9. The data acquisition method based on the IoT device according to claim 8, wherein The standard smoke concentration sequence and standard temperature sequence are determined based on the following method: Pre-collect the smoke concentration and temperature in the goods area under normal conditions within a preset time period, respectively, to form a standard smoke concentration sequence and a standard temperature sequence; Moreover, the length of the preset time period is the same as that of the preset time period when obtaining the historical smoke concentration sequence and the historical temperature sequence.

10. A data acquisition system based on Internet of Things devices, characterized in that, It includes: A temperature sensor and a smoke concentration sensor, which are respectively installed in the goods area of the warehouse; A control unit integrated with a computer program, and when the computer program is executed, it responds to the data collected by the smoke concentration sensor and the temperature sensor, and executes the data collection method according to any one of claims 1-9 to implement an adaptive data collection strategy.

Images