Intelligent water consumption monitoring and early warning method based on Internet of Things

Abstract

The invention relates to the field of water resource monitoring and early warning, in particular to an intelligent water consumption monitoring and early warning method based on the Internet of Things. The method comprises the steps of obtaining water flow data and temperature data, and obtaining a water flow predicted 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 predicted value; calculating a temperature correction coefficient based on the temperature data, and calculating a comprehensive error value; and calculating a risk assessment value based on the comprehensive error value in combination with the temperature correction coefficient, and assessing an abnormal risk. The method solves the problems that a prediction algorithm adopted by a traditional water consumption monitoring mode is too simple, lacks dynamic adaptability to water flow fluctuation and is difficult to effectively cope with sudden water flow changes; the influence of external environment factors on the water flow is neglected, so that the prediction error is large; an adopted fixed threshold cannot adapt to different environment changes, and abnormal risks cannot be accurately detected in real time.

Description

Technical Field

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

[0002] Traditional water use monitoring methods mostly rely on manual inspections and regular checks, which cannot achieve all-weather real-time monitoring and abnormal warnings, often resulting in a large amount of water waste and even affecting the sustainable development of the social economy. Therefore, the Internet of Things technology has been introduced into water resource management. Through real-time monitoring and intelligent analysis, it can realize the automatic collection and warning of water flow data, and timely intervention when water use anomalies occur.

[0003] However, there are still some key problems to be solved in the above technologies: First, the prediction algorithm used by traditional technologies is too simple and lacks dynamic adaptability to water flow fluctuations. Especially when the water flow changes dramatically, the prediction accuracy cannot meet the actual needs and it is difficult to effectively respond to sudden changes in water flow, resulting in the inability to detect potential anomalies in time; secondly, the impact of external environmental factors on water flow is ignored, especially the correction effect of temperature changes on the predicted value of water flow, resulting in large prediction errors, which in turn affects the accuracy and reliability of water use monitoring and early warning; finally, the fixed threshold used cannot adapt to different environmental changes, resulting in insufficient response capabilities of water use monitoring and early warning, and the inability to accurately detect abnormal risks in real time. Therefore, it is urgent to improve it 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 algorithm adopted in the traditional water use monitoring method is too simple and lacks dynamic adaptability to water flow fluctuations. In particular, when the water flow changes drastically, the prediction accuracy cannot meet the actual needs, and it is difficult to effectively respond to sudden water flow changes, resulting in the inability to timely discover potential anomalies; the influence of external environmental factors on the water flow, especially the correction effect of temperature changes on the predicted water flow value, leads to large prediction errors, which in turn affects the accuracy and reliability of water use monitoring and early warning; the fixed threshold adopted cannot adapt to different environmental changes, resulting in insufficient response ability of water use monitoring and early warning, and the problem that abnormal risks cannot be detected in real time and accurately.

[0005] The present invention provides an intelligent water use monitoring and early warning method based on the Internet of Things, which specifically includes the following technical solutions: An intelligent water use monitoring and early warning method based on the Internet of Things comprises the following steps: 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; 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.

[0006] Preferably, 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.

[0007] Preferably, 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:

[0008] 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.

[0009] Preferably, 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.

[0010] Preferably, 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.

[0011] Preferably, 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.

[0012] Preferably, 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.

[0013] Preferably, 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:

[0014] 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.

[0015] The beneficial effects of the technical solution of the present invention are: 1. The present invention adopts a dynamic weighted sliding window prediction algorithm, which can combine historical water flow data, historical water flow fluctuation correction factors and historical water flow weight adjustment factors to provide more accurate water flow prediction, can respond sensitively to the changing trend of water flow, and effectively improve the prediction accuracy, especially when the water flow fluctuates greatly, it can maintain efficient early warning capabilities.

[0016] 2. The present invention can dynamically adjust the water flow prediction results by introducing the temperature correction coefficient and comprehensive error calculation, and take into account the influence of the external environment (such as the influence of temperature changes on water flow), thereby further improving the accuracy and reliability of water flow monitoring. It can avoid the errors caused by the failure to correct temperature changes in time in traditional technologies, and provide stronger support for the accurate management of water resources.

[0017] 3. The present invention introduces a dynamic adjustment mechanism to dynamically adjust the risk threshold according to the comprehensive error value calculated in real time, thereby avoiding the false alarm and missed alarm problems under the traditional fixed threshold setting. It can maintain efficient and accurate anomaly detection capabilities under different water flow fluctuation conditions, respond to potential risks such as water leakage and equipment failure in a timely manner, and ensure the safe use of water resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of an intelligent water use monitoring and early warning method based on the Internet of Things described in the present invention. DETAILED DESCRIPTION

[0019] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0021] The specific scheme of an intelligent water use monitoring and early warning method based on the Internet of Things provided by the present invention is described in detail below with reference to the accompanying drawings.

[0022] See attached Figure 1 , which shows a flow chart 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 comprising the following steps: 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; First, install sensors to collect 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 of the water pipe. The specific installation location is set according to the specific implementation scenario. The sensors regularly collect raw water flow data and raw temperature data, and transmit the raw water flow data and raw temperature data to the data analysis platform through Internet of Things technology (such as wireless sensor network technology) for subsequent analysis and processing; The time interval for data collection is set according to the specific implementation scenario, for example, the original water flow data is collected once every minute or every hour; in order to ensure the accuracy and reliability of the original water flow data, the collected original water flow data is preprocessed to obtain water flow data; the preprocessing includes removing noise data and repairing abnormal values. In the data preprocessing stage, if some original water flow data is missing or abnormal, an interpolation algorithm is used to repair it to ensure that subsequent data analysis can proceed normally; the original temperature data is also preprocessed as above to obtain temperature data; The historical water flow data is introduced, and the dynamic weighted sliding window prediction algorithm is used to obtain the water flow prediction value. The dynamic weighted sliding window prediction algorithm uses the sliding window technology to smooth the historical water flow data, and introduces the historical water flow weight adjustment factor and the historical water flow fluctuation correction factor to adjust the impact of the historical water flow data, thereby improving the prediction accuracy, so that it can better cope with different environmental changes when the water flow changes greatly; The specific calculation formula for the water flow prediction value is as follows:

[0023] in, yes The predicted water flow value at the time; is a time variable; is the size of the sliding window, which is the number of historical water flow data (such as historical water flow data at the past 10 moments) used to calculate the water flow forecast value. The specific value is set according to the expert experience method; is the time step variable used to traverse the past Historical water flow data at each moment; yes Historical water flow data at all times; yes Historical water flow data at all times; It is the historical water flow weight adjustment factor, which is used to control the influence of 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; 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; The specific calculation formula for water flow deviation is as follows:

[0024] 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.

[0025] 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.

[0026] 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; The temperature correction coefficient is calculated as follows:

[0027] 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; 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; The calculation formula of the comprehensive error value is as follows:

[0028] 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.

[0029] 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 water flow prediction value and the water flow data, while the temperature correction coefficient takes into account the impact 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; The risk assessment formula is as follows:

[0030] in, yes The risk assessment value at the moment; It is a comprehensive adjustment coefficient, which is used to adjust the sensitivity of the risk assessment value and is set according to the expert experience method; It is the temperature adjustment coefficient, which is used to adjust the impact of the temperature correction coefficient on the risk assessment value and is set according to expert experience.

[0031] In practical applications, water flow fluctuations are affected by many factors. To cope with different water flow fluctuations, 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 that it has better adaptability under different water flow fluctuations, avoiding false alarms or missed alarms caused by setting a fixed risk threshold, and ensuring timely response to abnormalities in the case of large or small water flow fluctuations; The risk threshold adjustment formula is as follows:

[0032] in, is the dynamically adjusted risk threshold; is an exponential function; is the error adjustment coefficient, which is used to adjust the impact of the comprehensive error value on the risk threshold and is set according to the expert experience method; yes The comprehensive error value at the moment; is a constant used to balance the benchmark for risk threshold adjustment and is set based on expert experience; Is the comprehensive error value adjustment coefficient, used to adjust The degree of impact on risk threshold adjustment is set based on expert experience; When the calculated risk assessment value is greater than the dynamically adjusted risk threshold, an early warning is triggered and an early warning notification is sent to relevant personnel; the early warning notification includes information such as the location and time of occurrence, so that managers can quickly locate the problem. After receiving the early warning, relevant personnel can take corresponding countermeasures, such as shutting off the water source, checking the equipment or performing repairs, to prevent the waste of water resources in a timely manner.

[0033] In order to ensure the long-term stability and accuracy of water use monitoring and early 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 formula of the present invention (such as 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) according to actual needs, it is possible to adapt to environmental changes and reduce the probability of false alarms and missed alarms.

[0034] In summary, an intelligent water use monitoring and early warning method based on the Internet of Things has been completed.

[0035] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0036] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0037] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should 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; Calculate the comprehensive error value based on the temperature correction coefficient and the water flow deviation value; Based on the comprehensive error value and combined with the temperature correction factor, the risk assessment value is calculated; Introduce a dynamic adjustment mechanism to adjust the risk threshold and obtain the adjusted risk threshold; Compare the risk assessment value with the adjusted risk threshold to assess 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