An intelligent water use monitoring and early warning method based on the Internet of Things

Abstract

The present invention relates to the field of water resource monitoring and early warning, and particularly to an intelligent water use monitoring and early warning method based on the Internet of Things. The content includes: obtaining water flow data and temperature data, and obtaining a water flow prediction value through a dynamic weighted sliding window prediction algorithm; calculating a water flow deviation value based on the water flow data and the water flow prediction value; calculating a temperature correction coefficient based on the temperature data, and calculating a comprehensive error value; calculating a risk assessment value based on the comprehensive error value and combining the temperature correction coefficient to evaluate the abnormal risk. It solves the problems that the prediction algorithm adopted by the traditional water use monitoring method is too simple, lacks dynamic adaptability to water flow fluctuations, and is difficult to effectively respond to sudden water flow changes; ignores the influence of external environmental factors on water flow, resulting in large prediction errors; the fixed threshold adopted cannot adapt to different environmental changes and cannot detect abnormal risks in real time and accurately.

Description

Technical Field

[0001] The present invention relates to the field of water resource monitoring and early warning, and particularly to an intelligent water use monitoring and early warning method based on the Internet of Things. Background Art

[0002] Most traditional water use monitoring methods rely on manual inspections and regular checks, and cannot achieve all-weather real-time monitoring and abnormal early warning, often resulting in a large amount of water resource waste and even affecting the sustainable development of the social economy. Therefore, the Internet of Things technology is introduced into water resource management, and through real-time monitoring and intelligent analysis, automatic collection and early warning of water flow data are realized, and intervention is carried out in a timely manner when water use anomalies occur.

[0003] However, there are still some key problems to be solved in the above technology: First, the prediction algorithms adopted by traditional technologies are too simple and lack dynamic adaptability to water flow fluctuations. Especially when the water flow changes violently, the prediction accuracy cannot meet the actual needs, making it difficult to effectively respond to sudden water flow changes and resulting in the inability to detect potential anomalies in a timely manner; Second, the influence of external environmental factors on water flow is ignored, especially the corrective effect of temperature changes on the predicted value of water flow, resulting in large prediction errors and further affecting the accuracy and reliability of water use monitoring and early warning; Finally, the fixed thresholds adopted cannot adapt to different environmental changes, resulting in insufficient response capabilities of water use monitoring and early warning and the inability to detect abnormal risks in real time and accurately. Therefore, it is urgent to improve through a new algorithm and processing technology. Summary of the Invention

[0004] The present invention provides an intelligent water use monitoring and early warning method based on the Internet of Things to solve the problems that the prediction algorithms adopted by traditional water use monitoring methods are too simple and lack dynamic adaptability to water flow fluctuations. Especially when the water flow changes violently, the prediction accuracy cannot meet the actual needs, making it difficult to effectively respond to sudden water flow changes and resulting in the inability to detect potential anomalies in a timely manner; the influence of external environmental factors on water flow is ignored, especially the corrective effect of temperature changes on the predicted value of water flow, resulting in large prediction errors and further affecting the accuracy and reliability of water use monitoring and early warning; the fixed thresholds adopted cannot adapt to different environmental changes, resulting in insufficient response capabilities of water use monitoring and early warning and the inability to detect abnormal risks in real time and accurately.

[0005] An intelligent water use monitoring and early warning method based on the Internet of Things according to the present invention specifically includes the following technical solutions:

[0006] An intelligent water use monitoring and early warning method based on the Internet of Things includes the following steps:

[0007] S1: Obtain water flow data and temperature data, introduce historical water flow data, and use the dynamic weighted sliding window prediction algorithm to obtain the water flow prediction value; calculate the water flow deviation value based on the water flow data and the water flow prediction value.

[0008] S2: Calculate the temperature correction coefficient based on the temperature data; calculate the comprehensive error value based on the temperature correction coefficient and the water flow deviation value; calculate the risk assessment value based on the comprehensive error value and in combination with the temperature correction coefficient; introduce a dynamic adjustment mechanism to adjust the risk threshold to obtain the adjusted risk threshold; compare the risk assessment value with the adjusted risk threshold to evaluate the abnormal risk.

[0009] Preferably, S1 specifically includes:

[0010] In the process of obtaining data, first collect the original water flow data and the original temperature data, and transmit the original water flow data and the original temperature data to the data analysis platform through the Internet of Things technology; then preprocess the original water flow data and the original temperature data to obtain the water flow data and the temperature data.

[0011] Preferably, S1 specifically includes:

[0012] In the implementation process of the dynamic weighted sliding window prediction algorithm, smooth the historical water flow data through the sliding window technology, and introduce the historical water flow weight adjustment factor and the historical water flow fluctuation correction factor to calculate the water flow prediction value; the specific calculation formula of the water flow prediction value is as follows:

[0013]

[0014] Where, is the water flow prediction value at time is the time variable; is the size of the sliding window; is the time step variable; is the historical water flow data at time is the historical water flow data at time is the historical water flow weight adjustment factor; is the maximum value of the historical water flow data in the sliding window; is the historical water flow fluctuation correction factor.

[0015] Preferably, S1 specifically includes:

[0016] Based on the water flow data and the water flow prediction value, introduce a correction term for the square difference of the water flow to calculate the water flow deviation value.

[0017] Preferably, the S2 specifically includes:

[0018] Combine the temperature data with the historical average temperature, introduce the square term of the temperature difference, and adjust the temperature correction coefficient.

[0019] Preferably, the S2 specifically includes:

[0020] Combine the temperature correction coefficient with the water flow deviation value, evaluate the overall fluctuation error of the water flow, and calculate the comprehensive error value.

[0021] Preferably, the S2 specifically includes:

[0022] Based on the comprehensive error value and the temperature correction coefficient, introduce the comprehensive adjustment coefficient and the temperature adjustment coefficient, quantify the abnormal risk, and calculate the risk assessment value.

[0023] Preferably, the S2 specifically includes:

[0024] The dynamic adjustment mechanism, based on the comprehensive error value, introduces the comprehensive error value adjustment coefficient, adjusts the risk threshold, and obtains the dynamically adjusted risk threshold; when the risk assessment value is greater than the dynamically adjusted risk threshold, trigger an alarm and send an alarm notification; the risk threshold adjustment formula is as follows:

[0025]

[0026] Wherein, is the dynamically adjusted risk threshold; is the exponential function; is the error adjustment coefficient; is the comprehensive error value at time is the constant for balancing the risk threshold adjustment benchmark; is the comprehensive error value adjustment coefficient.

[0027] The beneficial effects of the technical solution of the present invention are:

[0028] 1. By adopting the dynamic weighted sliding window prediction algorithm, the present invention can combine the historical water flow data, the historical water flow fluctuation correction factor, and the historical water flow weight adjustment factor, provide a more accurate water flow prediction, can make a sensitive response to the change trend of the water flow, and effectively improve the prediction accuracy. Especially in the case of large water flow fluctuations, it can maintain a high warning ability.

[0029] 2. By introducing a temperature correction coefficient and comprehensive error calculation, the present invention can dynamically adjust the water flow prediction result, taking into account the influence of the external environment (such as the influence of temperature change on water flow), further improving the accuracy and reliability of water flow monitoring, avoiding errors caused by the failure to timely correct temperature changes in traditional technologies, and providing stronger support for the accurate management of water resources.

[0030] 3. The present invention introduces a dynamic adjustment mechanism to dynamically adjust the risk threshold according to the comprehensively error value calculated in real time, thus avoiding false alarms and missed alarms under the setting of traditional fixed thresholds. It can maintain efficient and accurate anomaly detection capabilities under different water flow fluctuation conditions, respond in a timely manner to potential risks such as water leakage and equipment failures, and ensure the safe use of water resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flowchart of an intelligent water use monitoring and early warning method based on the Internet of Things according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a 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 of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0034] The following specifically describes the specific solution of an intelligent water use monitoring and early warning method based on the Internet of Things provided by the present invention in conjunction with the drawings.

[0035] Refer to the attached Figure 1 , which shows a flowchart of an intelligent water use monitoring and early warning method based on the Internet of Things provided by an embodiment of the present invention. The method includes the following steps:

[0036] S1: Obtain water flow data and temperature data, introduce historical water flow data, and obtain a water flow prediction value through a dynamic weighted sliding window prediction algorithm; calculate a water flow deviation value based on the water flow data and the water flow prediction value;

[0037] First, install sensors responsible for collecting real-time water flow data and temperature data. The sensors are installed at key nodes of the water pipe, such as the inlet, outlet, and various control points in the middle. The specific installation location is set according to the specific implementation scenario. The sensors regularly collect the original water flow data and the original temperature data, and transmit the original water flow data and the original temperature data to the data analysis platform through Internet of Things technologies (such as wireless sensor network technology) for subsequent analysis and processing;

[0038] The time interval for data collection is set according to the specific implementation scenario. For example, the original water flow data is collected once per minute or per hour. To ensure the accuracy and reliability of the original water flow data, the collected original water flow data is preprocessed to obtain the water flow data. The preprocessing includes removing noise data and repairing outliers. In the data preprocessing stage, if some original water flow data is missing or abnormal, an interpolation algorithm is used for repair to ensure the normal progress of subsequent data analysis. The above preprocessing is also performed on the original temperature data to obtain the temperature data;

[0039] Introduce historical water flow data and use the dynamic weighted sliding window prediction algorithm to obtain the water flow prediction value. The dynamic weighted sliding window prediction algorithm smooths the historical water flow data through the sliding window technology, and introduces the historical water flow weight adjustment factor and the historical water flow fluctuation correction factor to adjust the influence of the historical water flow data, improving the prediction accuracy so as to better cope with different environmental changes in the case of large water flow changes;

[0040] The specific calculation formula for the water flow prediction value is as follows:

[0041]

[0042] Among them, is the water flow prediction value at time is the time variable; is the size of the sliding window, which is the number of historical water flow data used to calculate the water flow prediction value (such as the historical water flow data of the past 10 moments), and the specific value is set according to the expert experience method; is the time step variable, used to traverse the historical water flow data of the past moments; is the historical water flow data at time is the historical water flow data at time is the historical water flow weight adjustment factor, used to control the influence degree of the historical water flow data in the prediction process, and is set according to the expert experience method; It is the maximum value of the historical water flow data in the sliding window, which is used to standardize the historical water flow value; It is the historical water flow fluctuation correction factor, which is used to correct the fluctuation of historical water flow data to control the influence of the change of historical water flow data in the prediction process, and is set according to the expert experience method; Indicates the absolute value of the change in historical water flow data between two adjacent moments; is a standardized weighting term used to control the degree to which historical water flow affects the current water flow forecast; It is a volatility correction term, which is used to correct the volatility of water flow and correct the influence of the change amplitude of water flow at adjacent moments through a logarithmic function;

[0043] Next, based on the current water flow data and the calculated water flow prediction value, the water flow deviation value is obtained through the water flow deviation value calculation formula. The calculation of the water flow deviation value takes into account the absolute difference between the actual value of the water flow data and the water flow prediction value, and combines the correction term of the square difference of the water flow. The larger the water flow deviation value, the more drastic the change in the current water flow, and the greater the probability of the risk of abnormal fluctuations, which can be used to identify potential faults, water leaks and other abnormal conditions;

[0044] The specific calculation formula for water flow deviation is as follows:

[0045]

[0046] in, yes The water flow deviation value between the water flow data at the moment and the water flow prediction value. If the water flow deviation value Large, indicating that the water flow changes greatly at the current moment, and there may be a risk of abnormal fluctuations; for The water flow data at the moment, that is, the actual value of the water flow, yes The predicted water flow value at the time; is the correction term for the squared difference in water flow; It is the adjustment coefficient of the square difference of water flow, which is set according to expert experience.

[0047] S2: Calculate the temperature correction coefficient based on the temperature data; calculate the comprehensive error value based on the temperature correction coefficient and the water flow deviation value; calculate the risk assessment value based on the comprehensive error value combined with the temperature correction coefficient; introduce a dynamic adjustment mechanism to adjust the risk threshold to obtain the adjusted risk threshold; compare the risk assessment value with the adjusted risk threshold to evaluate the abnormal risk.

[0048] Considering the impact of temperature changes on water flow, especially the effect of temperature on water fluidity and viscosity, a temperature correction coefficient is introduced, which reflects the sensitivity of temperature changes to water flow changes to improve the accuracy of water use analysis. The temperature correction coefficient is calculated based on the relationship between the real-time temperature and the historical average temperature, and the temperature difference square term is introduced to more accurately adjust the temperature correction coefficient and improve the accuracy and reliability of water resource management;

[0049] The temperature correction coefficient is calculated as follows:

[0050]

[0051] in, yes Temperature data at the moment; It is the historical average temperature, which is obtained by taking the average of the temperature data for a specific period of time selected using the expert experience method; yes The temperature correction coefficient at each moment reflects the impact of temperature changes on water flow volatility, thereby improving the accuracy of volatility analysis; is the adjustment coefficient of the square term of temperature difference, which is set according to the expert experience method; is the square of the temperature difference;

[0052] Based on the water flow deviation value and the temperature correction coefficient, the comprehensive error value is calculated to evaluate the overall fluctuation error of the water flow. The comprehensive error value combines the temperature correction coefficient with the water flow deviation value to reflect the impact of ambient temperature changes on water flow fluctuations and comprehensively evaluate the overall error of water flow fluctuations. The larger the comprehensive error value, the more drastic the current water flow change, and there may be abnormal conditions, such as water leakage, equipment failure, etc., thus providing a basis for subsequent abnormality identification and risk assessment;

[0053] The calculation formula of the comprehensive error value is as follows:

[0054]

[0055] in, yes The comprehensive error value at the moment reflects the fluctuation of water flow. The larger the comprehensive error value, the greater the current water flow fluctuation, and there may be abnormal conditions. yes The water flow deviation value between the water flow data at the moment and the water flow prediction value; yes Temperature correction factor at the moment.

[0056] Based on the comprehensive error value and the temperature correction coefficient, the risk assessment value at the current moment is calculated through the risk assessment value formula. Specifically, the comprehensive error value reflects the deviation between the predicted water flow value and the water flow data, while the temperature correction coefficient takes into account the influence of temperature on the volatility of water flow. After combining the two, the risk assessment formula is used to quantify the abnormal risk, and then evaluate the degree of abnormality of the current water flow situation. The adjustment coefficients (comprehensive adjustment coefficient and temperature adjustment coefficient) in the risk assessment formula can be adjusted according to actual needs to improve the sensitivity and accuracy of risk assessment, thereby improving the accuracy of abnormal monitoring;

[0057] The risk assessment formula is as follows:

[0058]

[0059] Wherein, is the risk assessment value at the moment; is the comprehensive adjustment coefficient, which is used to adjust the sensitivity of the risk assessment value and is set according to the expert experience method; is the temperature adjustment coefficient, which is used to adjust the influence of the temperature correction coefficient on the risk assessment value and is set according to the expert experience method.

[0060] In practical applications, the volatility of water flow will be affected by various factors. To cope with different water flow fluctuation situations, the risk threshold needs to be dynamically adjusted according to the current comprehensive error value. By introducing a dynamic adjustment mechanism, the risk threshold is adjusted according to the change of the comprehensive error value, so as to have better adaptability in different water flow fluctuation situations, avoid false alarms or missed alarms caused by setting a fixed risk threshold, and ensure timely response to abnormalities in both large and small water flow fluctuations;

[0061] The risk threshold adjustment formula is as follows:

[0062]

[0063] Wherein, is the dynamically adjusted risk threshold; is the exponential function; is the error adjustment coefficient, which is used to adjust the influence degree of the comprehensive error value on the risk threshold and is set according to the expert experience method; is the comprehensive error value at the moment; is a constant, which is used to balance the benchmark of risk threshold adjustment and is set according to the expert experience method; is the comprehensive error value adjustment coefficient, which is used to adjust the influence degree of on the risk threshold adjustment and is set according to the expert experience method;

[0064] When the calculated risk assessment value is greater than the dynamically adjusted risk threshold, an alarm is triggered and an alarm notification is sent to relevant personnel; the alarm notification includes information such as the location and time of occurrence, so that managers can quickly locate the problem. After receiving the alarm, relevant personnel can take corresponding countermeasures, such as closing the water source, checking the equipment or performing repairs, to prevent water waste in a timely manner.

[0065] To ensure the long-term stability and accuracy of water use monitoring and warning, it is necessary to continuously monitor and analyze water flow data and temperature data. By regularly updating historical water flow data and historical temperature data, and adjusting the parameters in the formulas of the present invention according to actual needs (such as the parameters in the water flow prediction value calculation formula, water flow deviation value calculation formula, temperature correction coefficient calculation formula, risk assessment value calculation formula, and risk threshold adjustment formula), to adapt to environmental changes and reduce the probability of false alarms and missed alarms.

[0066] In summary, an intelligent water use monitoring and warning method based on the Internet of Things is completed.

[0067] The order of the invention embodiments is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0068] Each embodiment in this specification is described in a progressive manner. The same or similar parts between each embodiment can be referred to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

[0069] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. An intelligent water use monitoring and early warning method based on the Internet of Things, characterized in that: The following steps are involved: S1: Obtain water flow data and temperature data, introduce historical water flow data, and obtain water flow prediction value through dynamic weighted sliding window prediction algorithm; calculate water flow deviation value based on water flow data and water flow prediction value; S2: Calculate the temperature correction coefficient based on the temperature data. The formula is as follows: in, yes Temperature data at the moment; is the historical average temperature; yes Temperature correction factor at the moment; is the adjustment coefficient of the square term of temperature difference; is the square term of temperature difference; based on the temperature correction coefficient and the water flow deviation value, the comprehensive error value is calculated; based on the comprehensive error value and combined with the temperature correction coefficient, the risk assessment value is calculated; a dynamic adjustment mechanism is introduced to adjust the risk threshold to obtain the adjusted risk threshold; the risk assessment value is compared with the adjusted risk threshold to evaluate the abnormal risk.

2. According to the method of claim 1, the intelligent water use monitoring and early warning method based on the Internet of Things is characterized in that: The S1 specifically includes: In the process of acquiring data, the original water flow data and original temperature data are first collected, and then transmitted to the data analysis platform through the Internet of Things technology; then the original water flow data and original temperature data are preprocessed to obtain water flow data and temperature data.

3. According to the method of intelligent water use monitoring and early warning based on the Internet of Things in claim 2, it is characterized in that: The S1 specifically includes: In the process of implementing the dynamic weighted sliding window prediction algorithm, the historical water flow data is smoothed by the sliding window technology, and the historical water flow weight adjustment factor and the historical water flow fluctuation correction factor are introduced to calculate the water flow prediction value; the specific calculation formula of the water flow prediction value is as follows: in, yes The predicted water flow value at the time; is a time variable; is the size of the sliding window; is the time step variable; yes Historical water flow data at all times; yes Historical water flow data at all times; is the historical water flow weight adjustment factor; is the maximum value of the historical water flow data in the sliding window; is the correction factor for historical water flow fluctuations.

4. According to the method of intelligent water use monitoring and early warning based on the Internet of Things in claim 3, it is characterized in that: The S1 specifically includes: Based on the water flow data and the water flow prediction value, the correction term of the water flow square difference is introduced to calculate the water flow deviation value.

5. According to the method of intelligent water use monitoring and early warning based on the Internet of Things in claim 1, it is characterized in that: The S2 specifically includes: The temperature data is combined with the historical average temperature, and the square term of the temperature difference is introduced to adjust the temperature correction factor.

6. The method for intelligent water use monitoring and early warning based on the Internet of Things according to claim 5 is characterized in that: The S2 specifically includes: The temperature correction coefficient is combined with the water flow deviation value to evaluate the overall fluctuation error of the water flow and calculate the comprehensive error value.

7. The method for intelligent water use monitoring and early warning based on the Internet of Things according to claim 6 is characterized in that: The S2 specifically includes: Based on the comprehensive error value and the temperature correction coefficient, the comprehensive adjustment coefficient and the temperature adjustment coefficient are introduced to quantify the abnormal risk and calculate the risk assessment value.

8. The intelligent water use monitoring and early warning method based on the Internet of Things according to claim 7 is characterized in that: The S2 specifically includes: The dynamic adjustment mechanism introduces a comprehensive error value adjustment coefficient based on the comprehensive error value, adjusts the risk threshold, and obtains the dynamically adjusted risk threshold; when the risk assessment value is greater than the dynamically adjusted risk threshold, an early warning is triggered and an early warning notification is sent; the risk threshold adjustment formula is as follows: in, is the dynamically adjusted risk threshold; is an exponential function; is the error adjustment factor; yes The comprehensive error value at the moment; is a constant used to balance the risk threshold adjustment benchmark; It is the comprehensive error value adjustment coefficient.

Images