Water supply equipment operation state real-time monitoring method and system based on internet of things

Abstract

The present application relates to the technical field of data processing, and especially relates to a water supply equipment operation state real-time monitoring method and system based on the Internet of Things. The method comprises the following steps: acquiring the power value and the flow value of the current time in the operation process of the water supply pump in real time; determining the noise suspicious degree of the current time; determining the noise degree of the current time; identifying whether there is noise at the current time according to the size of the noise degree of the current time; determining the corrected power value of the current time; and acquiring the cumulative sum in real time by using the cumulative sum control chart algorithm to realize the real-time monitoring of the water supply equipment operation state. Through the identification and correction of the noise suspicious degree and the noise degree, the present application reduces the interference of noise on the water supply equipment operation state monitoring, ensures the accuracy of the data, can acquire and correct the power value in real time, uses the cumulative sum control chart algorithm for abnormal detection, and realizes the real-time monitoring of the equipment operation state.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a water supply equipment operation state real-time monitoring method and system based on the Internet of Things. BACKGROUND

[0002] As the living standards of residents continue to improve, the demand for water supply systems also increases, and urban water supply systems are becoming more and more complex. The traditional manual monitoring and management method has been unable to meet the modern water supply demand. The water supply pump plays a crucial role in urban water supply, as it is responsible for transporting water from the water source or water plant to each user. The normal operation of the water supply pump ensures stable water pressure and sufficient water quantity, and is a core component of the urban water supply system. If the power of the water supply pump is abnormal, such as being too high or too low, it may cause the efficiency of the pump to decrease, or even malfunction, affecting the stability of the water supply system. A current method for detecting power data anomalies of a water supply pump is the Cumulative Sum Control Chart (CUSUM) algorithm, which has the advantages of simplicity, effectiveness, strong interpretability, and wide adaptability in detecting power data anomalies of a water supply pump, making it a commonly used method for processing time series data and conducting anomaly detection analysis.

[0003] The patent document with publication number CN112559969B discloses a small leakage detection method based on the cumulative sum algorithm, which includes collecting flow data during a stable water consumption period, then estimating the reference water consumption range of the stable water consumption period through frequency statistics, then verifying the rationality of the estimated reference water consumption range by setting a confidence level, then eliminating the interference of large low-value fluctuations in the flow data according to the reference water consumption range, and finally detecting small leaks in the DMA pipe network using the CUSUM algorithm.

[0004] However, the above patent document does not consider that when collecting and transmitting power data of the water supply pump, electromagnetic interference sources (such as other electrical equipment) around the water supply pump may affect the signal transmission of the sensor, resulting in random noise in the data. The CUSUM algorithm detects anomalies in data points based on the current time and previous time data. If there is noise in the data, the authenticity of the data points will be reduced, resulting in errors in the final anomaly detection results for the current time and previous time. SUMMARY

[0005] To solve the problem of errors in the final anomaly detection results for the current time and previous time due to noise in the data, which affects the accuracy of real-time monitoring of the operation state of the water supply equipment, the present application provides a water supply equipment operation state real-time monitoring method and system based on the Internet of Things.

[0006] In a first aspect, the present application provides a real-time monitoring method for the running state of a water supply device based on the Internet of Things, which adopts the following technical solution:

[0007] The power value and the flow value of the current time in the running process of the water supply pump are acquired in real time; the noise suspiciousness of the current time is determined, and the noise suspiciousness is positively correlated with the difference between the power value of the current time and the power value of each time in the previous several times, the average of the change amount of the power value of all adjacent two times of the current time and the previous several times, and the information entropy value of all power values of the current time and the previous several times; the noise degree of the current time is determined, and the noise degree is positively correlated with the difference between the relative size of the power value and the flow value of the current time, and the difference between the average interval of all adjacent extreme points in the power value and the flow value of the current time and the previous several times; whether noise exists in the current time is identified according to the size of the noise degree of the current time, and the current time is corrected to obtain the corrected power value of the current time; the corrected power values of the current time and the previous several times are detected for abnormality by using the cumulative sum control chart algorithm to obtain the cumulative sum of the current time and the previous several times, so as to realize real-time monitoring of the running state of the water supply device.

[0008] Through identification and correction of the noise suspiciousness and the noise degree, the interference of noise on the running state monitoring of the water supply device is reduced, and the accuracy of data is ensured; the power value can be acquired and corrected in real time, abnormality detection is performed by using the cumulative sum control chart algorithm, and real-time monitoring of the running state of the device is realized; through analysis of the change of the power value and the flow value, noise is accurately identified and corrected, and the influence of noise on the monitoring result is avoided; in combination with the Internet of Things technology, remote monitoring and data management are realized, and the efficiency and intelligent level of device management are improved.

[0009] Further, the acquisition method of the power value and the flow value of the current time is that the collected water supply pump power data and water supply pump flow data of the current time in the running process of the water supply pump are digitally converted to obtain the power value and the flow value of the current time.

[0010] Further, the noise suspiciousness satisfies the following relationship:

[0011] In the formula, P is the noise suspiciousness of the current time, N is the total number of times of the previous several times of the current time, W is the power value of the current time, W n is the power value of the nth time in the previous several times, is the average of the change amount of the power value of all adjacent two times of the current time and the previous several times, S is the information entropy value of all power values of the current time and the previous several times, a is a hyperparameter, ∏ is a continuous product function, and || is an absolute value symbol.

[0012] By comprehensively considering the differences between the current power value and the historical power value, the mean of power change, and the information entropy, and other factors, the influence of noise can be accurately identified and quantified, and the interference of noise on data can be reduced. By combining multiple dimensions such as power difference, change amount, and information entropy, the influence of noise on monitoring results can be comprehensively evaluated, and the accuracy can be improved.

[0013] Further, the noise degree satisfies the following relationship:

[0014] In the formula, T is the noise degree at the current time, P is the noise suspicious degree at the current time, W min and D min are the minimum values in the power value and the flow value at the current time and several times before, W and D are the power value and the flow value at the current time, J W and are the differences between the maximum value and the minimum value in the power value at the current time and several times before, J D are the differences between the maximum value and the minimum value in the flow value at the current time and several times before, and are the average intervals of all adjacent extreme points in the power value and the flow value at the current time and several times before, respectively, α is a hyperparameter, and || is an absolute value symbol.

[0015] By considering the changes in power and flow at the same time, combining multiple dimensions such as minimum value, maximum value difference, and average interval of extreme points, the influence of noise can be more comprehensively evaluated, and the accuracy of noise detection can be improved. Noise can be effectively identified and quantified, the influence on the monitoring system can be reduced, and the stability and reliability of the system can be improved.

[0016] Further, according to the size of the noise degree at the current time, whether there is noise at the current time is identified, including: in response to the noise degree at the current time being greater than a preset noise threshold, it is determined that there is noise at the current time; in response to the noise degree at the current time being not greater than the preset noise threshold, it is determined that there is no noise at the current time.

[0017] By setting a noise threshold, the noise identification process can be simplified, and it becomes intuitive and efficient to determine whether there is noise. The system can automatically detect the existence of noise according to real-time data without manual intervention, improving the monitoring efficiency. The noise threshold can be adjusted according to different environments and requirements, enhancing the adaptability and robustness of the system in a variable environment.

[0018] Further, the correction of the current time comprises: in response to the current time having noise, the corrected power value of the current time is equal to the average of the power values of the previous several times of the current time, to obtain the corrected power value of the current time; and in response to the current time not having noise, the corrected power value of the current time is equal to the power value of the current time, to obtain the corrected power value of the current time.

[0019] By using the average of the power values of the previous several times to correct the power value of the current time when there is noise, the influence of the instantaneous fluctuation of the noise on the data can be effectively reduced, and the power value is more stable; when there is noise, the corrected power value is closer to the real power change trend, reducing the interference of the noise on the system judgment, thereby improving the accuracy and reliability of the data; according to whether the current time has noise, the correction strategy is flexibly adjusted, the change of the environment is automatically coped with, and the self-adaptive ability of the system is improved; when there is no noise, the current power value is directly used, unnecessary calculation is avoided, and the real-time response ability and efficiency of the system are improved.

[0020] Further, the real-time monitoring of the running state of the water supply equipment comprises: in response to the cumulative value being greater than the determination threshold, it is determined that the water supply pump is abnormal at the current time and the previous several times, and a warning prompt is sent, to complete the real-time monitoring of the running state of the water supply equipment based on the Internet of Things.

[0021] In a second aspect, the present application provides a real-time monitoring system for the running state of a water supply equipment based on the Internet of Things, which adopts the following technical solution:

[0022] The real-time monitoring system for the running state of the water supply equipment based on the Internet of Things comprises a processor and a memory, and the memory stores computer program instructions; when the computer program instructions are executed by the processor, the above-mentioned real-time monitoring method for the running state of the water supply equipment based on the Internet of Things is realized.

[0023] By adopting the above-mentioned technical solution, the above-mentioned real-time monitoring method for the running state of the water supply equipment based on the Internet of Things is generated into a computer program and stored in the memory to be loaded and executed by the processor, so that a terminal device is made according to the memory and the processor, and the use is convenient.

[0024] The present application has the following technical effects:

[0025] Since the detection accuracy of the CUSUM algorithm is disturbed by the noise data, the influence of the abnormal value on the CUSUM algorithm can be reduced and the abnormal detection accuracy can be improved by identifying and correcting the noise data; since the power value is collected in real time and corrected, an accurate and stable data sequence can be obtained, so that the requirements of the CUSUM algorithm can be better met and the robustness of the algorithm is improved; by analyzing the correlation between the power value and the flow value of the water supply pump, the noise can be processed more targetedly and accurately; the corrected data sequence usually reduces the noise component, so that the CUSUM algorithm can capture the real signal change more, and the reliability and accuracy of the CUSUM algorithm abnormal detection result are improved; in summary, by combining the feature analysis and correlation information of the noise data, the power value of the water supply pump is judged and corrected in real time, which can significantly improve the abnormal detection effect of the CUSUM algorithm, so that the CUSUM algorithm can better reflect the real data trend and change, thereby enhancing its reliability and practicality in actual application. BRIEF DESCRIPTION OF DRAWINGS

[0026] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which a number of embodiments of the application are illustrated by way of example and not limitation. Like or corresponding reference numerals are used to indicate like or corresponding parts throughout the several drawings.

[0027] Figure 1 is a method flowchart in the method for real-time monitoring of the running state of the water supply equipment based on the Internet of Things according to the embodiments of the present application. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0029] It should be understood that when the claims, the specification and the drawings of the present application use the terms "first", "second", etc., they are only used to distinguish different objects, and are not used to describe a specific order. The terms "include" and "contain" used in the specification and claims of the present application indicate the existence of the described features, whole, steps, operations, elements and / or components, but do not exclude the existence or addition of one or more other features, whole, steps, operations, elements, components and / or sets thereof.

[0030] The core purpose of the scheme is to use the CUSUM algorithm for real-time anomaly detection of power data, and the power value is judged and corrected in real time during the process, which is mainly based on the analysis of the numerical change characteristics of the power data and the flow data of the water supply pump.

[0031] The embodiment of the application discloses a water supply equipment operation state real-time monitoring method based on Internet of Things, referring to Figure 1 , comprising steps S1-S6:

[0032] S1: real-time acquisition of the power value and the flow value at the current time in the operation process of the water supply pump.

[0033] When collecting the power data and the flow data of the water supply pump in the operation process of the water supply pump, a power analyzer and a flowmeter are used to collect and record the power data and the flow data respectively, so that the collection time length and frequency are ensured to be the same; for example, the collection time length is one hour, and the collection frequency is one second once. Then, an analog-to-digital conversion device is used to digitally convert the power data and the flow data, so that the power value and the flow value are obtained.

[0034] Specifically, the acquisition method of the power value and the flow value at the current time is as follows:

[0035] The collected water supply pump power data and water supply pump flow data at the current time in the operation process of the water supply pump are digitally converted to obtain the power value and the flow value at the current time.

[0036] S2: determining the noise suspicious degree at the current time.

[0037] It should be noted that the noise suspicious degree at the current time is obtained by analyzing the numerical performance and the numerical change characteristics of the real-time power value of the water supply pump. When analyzing this index, the more special the power value at the current time is, and the more intense the data numerical change characteristics around it are, the greater the noise suspicious degree of the power value at the current time is.

[0038] The noise suspicious degree is positively correlated with the difference between the power value at the current time and the power value at each time in the previous several times, the mean value of the change amount of the power values of all adjacent two times at the current time and the previous several times, and the information entropy value of all the power values at the current time and the previous several times.

[0039] The number of previous times can be set by the implementer according to the specific implementation, for example, 50. If the number of previous times is less than 50, pre-collection can be performed when the equipment is started to ensure that there are enough historical data for each time point as a reference when the monitoring starts.

[0040] Specifically, the noise suspicious degree satisfies the following relationship:

[0041]

[0042] In the formula, P is the noise suspicious degree of the current time, N is the total number of times of the previous several times of the current time, W is the power value of the current time, W n is the power value of the nth time of the previous several times, is the average of the change amount of the power values of all adjacent two times of the current time and the previous several times, S is the information entropy value of all power values of the current time and the previous several times, a is a hyperparameter, Π is a continuous product function, and || is an absolute value symbol.

[0043] The implementer can set the hyperparameter according to the specific implementation, for example, 0.001. The hyperparameter exists to prevent |W-W n |=0, so that the formula is meaningless.

[0044] wherein, represents the continuous product of the difference between the power value of the current time and each power value in the reference data segment (i.e., the previous several times) of the current time. The greater the value, the more special the numerical performance of the power value of the current time compared with all the power values in the reference data segment, the greater the possibility that the power value belongs to a noise data point, and the greater the corresponding noise suspicious degree. The greater the value, the more intense the change characteristics between the power values in the reference data segment of the power value of the current time, the greater the rationality of the sudden change of the power value of the current time, the greater the possibility that the power value belongs to a noise data point, and the greater the corresponding noise suspicious degree. The greater S, the greater the credibility of the change characteristics between the power values in the reference data segment of the power value of the current time, and the greater the possibility that the power value of the current time changes abnormally, and the greater the corresponding noise suspicious degree.

[0045] S3: Determine the noise degree of the current time.

[0046] It should be noted that, since the noise data that may be encountered is similar to the true abnormal data value generated by the water supply pump, according to the scene investigation, the relationship between the flow and the power of the water supply pump is closely related. Generally, when the water supply pump is running normally, the power is usually a certain function of the flow, and as the flow increases, the power also increases. Therefore, the noise suspicious degree of the current time can be optimized by combining the analysis of the correlation between the change characteristics of the flow data and the power data of the water supply pump to obtain the noise degree of the current time. The weaker the correlation between the power value and the flow value, the stronger the possibility that there is noise data at this time, and the greater the noise degree.

[0047] The noise level is positively correlated with the noise suspicion level at the current moment, the relative size difference between the power value and flow value at the current moment, and the difference between the average intervals of all adjacent extreme value points in the power value and flow value at the current moment and several previous moments.

[0048] Specifically, the noise level satisfies the following relationship:

[0049]

[0050] Where T is the noise level at the current moment, P is the noise suspicion level at the current moment, and W min and D min are the minimum values ​​of power and flow at the current moment and several previous moments, respectively. W and D are the power and flow at the current moment, respectively. J W The sum is the difference between the maximum and minimum power values ​​at the current moment and several previous moments, J D is the difference between the maximum and minimum flow values ​​at the current moment and several previous moments. and are the average intervals of all adjacent extreme points in power and flow values ​​at the current moment and several previous moments, α is a hyperparameter, and || is the absolute value symbol.

[0051] Implementers can set hyperparameters according to specific implementation conditions, for example, 0.001. The existence of hyperparameters is to prevent and , making the formula meaningless.

[0052] Among them, the formula Indicates the relative size of the power value at the current moment in its reference data segment. Indicates the relative size of the current flow value in its reference data segment; Indicates the difference between the two. The larger the value, the lower the correlation between the power value and the flow value at the current moment. Then, the possibility that the power value at the current moment belongs to noise data is greater, and its noise level is greater. It represents the difference between the average intervals of all adjacent extreme points in the power value and flow value at the current moment and its reference data segment respectively. The larger the value is, the greater the difference in the changing patterns of the two data during this period, and the lower the correlation between the changes of the two data during this period. It can be explained that the lower the correlation between the power value and the flow value at the current moment, the greater the credibility. Therefore, the possibility that the power value at the current moment belongs to noise data will be greater, and the noise degree of the power value at the current moment will be greater.

[0053] S4: Identify whether there is noise at the current moment according to the noise level at the current moment.

[0054] Specifically, the size of the noise degree of the current moment is used to identify whether noise exists in the current moment, including:

[0055] In response to the noise degree of the current moment being greater than the preset noise threshold, it is determined that noise exists in the current moment;

[0056] In response to the noise degree of the current moment being not greater than the preset noise threshold, it is determined that noise does not exist in the current moment.

[0057] The noise threshold can be set by the implementer according to the actual implementation, for example, 0.9.

[0058] S5: determining a corrected power value of the current moment.

[0059] The current moment is corrected to obtain a corrected power value of the current moment.

[0060] Specifically, the correction of the current moment includes:

[0061] In response to noise existing in the current moment, the corrected power value of the current moment is equal to the average of the power values of the previous moments of the current moment, to obtain the corrected power value of the current moment;

[0062] In response to noise not existing in the current moment, the corrected power value of the current moment is equal to the power value of the current moment, to obtain the corrected power value of the current moment.

[0063] The number of previous moments can be set by the implementer according to the actual implementation, for example, 20.

[0064] S6: using a cumulative sum control chart algorithm to obtain a cumulative sum in real time, to realize real-time monitoring of the running state of the water supply equipment.

[0065] The cumulative sum control chart algorithm is used to detect the corrected power values of the current moment and the previous moments, to obtain the cumulative sum of the current moment and the previous moments, to realize real-time monitoring of the running state of the water supply equipment.

[0066] The implementer can set various parameters of the CUSUM algorithm according to the specific implementation, for example, the target value is 10KW; the sliding threshold is 0.05KW; the initial value of the cumulative sum is 0; when detecting the data points, a total of 50 data points of the time moments immediately before the sampling time of the data points are selected.

[0067] Specifically, the real-time monitoring of the running state of the water supply equipment includes:

[0068] In response to the cumulative sum being greater than the determination threshold, it is determined that the water supply pump has an abnormality at the current moment and the previous moments, and a warning prompt is issued, to complete the real-time monitoring of the running state of the water supply equipment based on the Internet of Things.

[0069] The implementer can set the determination threshold according to the actual implementation, for example, 0.6KW.

[0070] The embodiment of the present application also discloses a water supply equipment operation state real-time monitoring system based on Internet of Things, comprising a processor and a memory, and the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the water supply equipment operation state real-time monitoring method based on Internet of Things according to the present application is realized.

[0071] The water supply equipment real-time monitoring system based on Internet of Things can identify potential problems of the water supply pump in time and give early warning by monitoring the water supply pump power data in real time and intelligently analyzing, so that the automation and intelligent level of the water supply system are improved, manual intervention is reduced, and management efficiency is improved.

[0072] The above system also comprises other components such as communication bus and communication interface which are well known to those skilled in the art, and the setting and functions thereof are known in the art, so they will not be described here.

[0073] In the present application, the aforementioned memory can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, device or apparatus. For example, the computer readable storage medium can be any appropriate magnetic storage medium or magneto-optical storage medium, or any other medium that can be used to store desired information and can be accessed by an application, a module or both. Any such computer storage medium can be part of a device or accessible or connectable to the device.

[0074] Although the present application has been shown and described with respect to several embodiments thereof, it will be apparent that equivalents, modifications and variations of these embodiments can be made by those skilled in the art without departing from the spirit and scope of the present application. It is therefore intended that the present application encompass all such modifications and variations as fall within the scope of the appended claims.

[0075] The above are the preferred embodiments of the present application, and are not intended to limit the protection scope of the present application, therefore: any equivalent changes made on the structure, shape, principle of the present application should be covered within the protection scope of the present application.

Claims

1. A real-time monitoring method for the operation status of water supply equipment based on the Internet of Things, characterized in that: include: Real-time acquisition of the power and flow values ​​of the water supply pump at the current moment of operation; Determine the noise suspicion at the current moment. The noise suspicion is positively correlated with the difference between the power value at the current moment and the power values ​​at each of the previous moments, the average of the changes in the power values ​​between the current moment and the previous moments, and the information entropy of all power values ​​at the current moment and the previous moments. Determine the noise degree at the current moment. The noise degree is positively correlated with the noise suspicion at the current moment, the difference in the relative sizes of the power value and the flow value at the current moment, and the difference between the average intervals of all adjacent extreme value points in the power value and flow value at the current moment and the previous moments. The noise suspicion satisfies the following relationship: ； is the noise suspicion at the current moment, is the total number of moments before the current moment, is the power value at the current moment, For the first of several moments before The power value at a moment, is the average of the power value changes between the current moment and all two adjacent moments in the previous moments. is the information entropy value of all power values ​​at the current moment and several previous moments, is a hyperparameter, is the continuous product function, is the absolute value symbol; According to the noise level at the current moment, whether there is noise at the current moment is identified, and the current moment is corrected to obtain the corrected power value at the current moment; The cumulative sum control chart algorithm is used to detect abnormalities in the corrected power values ​​at the current moment and several previous moments, and the cumulative sum of the current moment and several previous moments is obtained to achieve real-time monitoring of the operating status of the water supply equipment.

2. The method for real-time monitoring of the operating status of water supply equipment based on the Internet of Things according to claim 1 is characterized in that: The method for obtaining the power value and flow value at the current moment is: The collected water supply pump power data and water supply pump flow data at the current moment during the operation of the water supply pump are digitally converted to obtain the power value and flow value at the current moment.

3. The method for real-time monitoring of the operating status of water supply equipment based on the Internet of Things according to claim 1 is characterized in that: The noise level satisfies the following relationship: ； Where, is the noise level at the current moment, is the noise suspicion at the current moment, and are the maximum values ​​of power and flow at the current moment and several previous moments, and are the power value and flow value at the current moment respectively, The sum is the difference between the maximum and minimum power values ​​at the current moment and several previous moments. is the difference between the maximum and minimum flow values ​​at the current moment and several previous moments. and are the average intervals between all adjacent extreme value points in power and flow values ​​at the current moment and several previous moments, is a hyperparameter, is the absolute value symbol.

4. The method for real-time monitoring of the operating status of water supply equipment based on the Internet of Things according to claim 1 is characterized in that: The step of identifying whether noise exists at the current moment according to the noise level at the current moment includes: In response to the noise level at the current moment being greater than a preset noise threshold, determining that noise exists at the current moment; In response to the noise level at the current moment being not greater than the preset noise threshold, it is determined that there is no noise at the current moment.

5. The method for real-time monitoring of the operating status of water supply equipment based on the Internet of Things according to claim 1 is characterized in that: The correcting of the current moment includes: In response to the presence of noise at the current moment, the corrected power value at the current moment is equal to the average of the power values ​​at several moments before the current moment, thereby obtaining the corrected power value at the current moment; In response to the absence of noise at the current moment, the corrected power value at the current moment is equal to the power value at the current moment, thereby obtaining the corrected power value at the current moment.

6. The method for real-time monitoring of the operating status of water supply equipment based on the Internet of Things according to claim 1 is characterized in that: The method for realizing real-time monitoring of the operating status of the water supply equipment includes: In response to the cumulative sum being greater than a determination threshold, it is determined that an abnormality has occurred in the water supply pump at the current moment and several moments before, and an early warning is issued, completing real-time monitoring of the operating status of the water supply equipment based on the Internet of Things.

7. The real-time monitoring system for the operation status of water supply equipment based on the Internet of Things is characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the real-time monitoring method for the operating status of water supply equipment based on the Internet of Things according to any one of claims 1 to 6 is implemented.

Images