Water supply valve control method and system based on fault monitoring

Abstract

The invention relates to the technical field of valve data prediction, in particular to a water supply valve control method and system based on fault monitoring, and the method comprises the steps: collecting the pressure and caliber data of a valve, and obtaining a pressure sequence and a valve caliber sequence; respectively predicting the pressure sequence and the valve caliber sequence at historical moments based on an HTFE algorithm to obtain a predicted value of the pressure and a predicted value of the valve caliber at the current moment, and correcting the sum of differences between the predicted value of the pressure and the predicted value of the valve caliber and respective actual values by using the reliability of the predicted value at the current moment; and obtaining the fault degree at the current moment. According to the method, the reliability of the prediction value is calculated by considering the relevancy and the change stability between the two dimension data and combining the relevancy and the stability, so that the evaluation on the reliability of the prediction result is increased, and the reliability of the prediction result is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of valve data prediction, and more specifically, to a water supply valve control method and system based on fault monitoring. Background Art

[0002] As an important part of urban infrastructure, the stability and reliability of urban water supply systems are directly related to the production and life of residents. The existing water supply equipment is to install a simple pressure regulating valve at the interface of the main water supply pipeline, and automatically adjust the valve diameter to ensure that the water pressure in the branch pipeline is maintained at the preset value to meet the water demand of different areas, thereby ensuring the normal operation of the water supply system. However, due to long-term operation in a high-humidity environment, internal components may rust or key components may be worn out, causing the pressure regulating valve to malfunction, making the water pressure in the branch pipeline unstable, which may cause pipeline rupture, water leakage and other safety hazards in severe cases.

[0003] In the related technology, for example, a Chinese patent document with a publication number of CN118673387B discloses a high-temperature warning method and system for a pulverized coal gasification burner. The patent document first obtains all combination sequences, and then calculates the preference degree of any combination sequence. The change trend of the combination sequence with the highest preference degree is used as the historical trend when the HTFE algorithm predicts data, so as to predict the temperature data at the next moment and provide a temperature warning for the burner.

[0004] At present, the HTFE algorithm is used to predict different dimensional time series in combination with their respective historical trends and prediction errors. The deviation between the predicted value and the actual value of the main pipeline pressure and pressure regulating valve diameter data at any time is used to evaluate whether a fault has occurred at the current moment. However, in the actual water supply system, the changes in the main pipeline pressure and the pressure regulating valve diameter data respond to each other. If the response relationship between the two is not considered, the actual state of the system cannot be accurately reflected, which will make the prediction results unreliable, thereby reducing the accuracy of fault detection. Summary of the invention

[0005] The present invention provides a water supply valve control method and system based on fault monitoring, aiming to solve the problem that in the water supply system in the related technology, the changes in the main pipeline pressure and the pressure regulating valve caliber data respond to each other, and if the response relationship between the two is not considered, the real state of the system cannot be accurately reflected, which will lead to inaccurate prediction results.

[0006] In the first aspect, the present invention provides a water supply valve control method based on fault monitoring, including: collecting valve pressure and valve diameter data to obtain a pressure sequence and a valve diameter sequence; predicting the pressure sequence and valve diameter sequence at historical moments based on the HTFE algorithm to obtain a predicted value of the pressure and a predicted value of the valve diameter at the current moment, and using the reliability of the predicted value at the current moment to correct the sum of the differences between the predicted value of the pressure and the predicted value of the valve diameter and their actual values ​​to obtain the degree of fault at the current moment, wherein the current moment Reliability of predicted values The calculation formula is: ; In the formula, For the moment The reliability of the predicted value, For the moment The stability of the pressure sequence and valve caliber sequence data changes at previous historical moments; For the moment The correlation between the pressure sequence and the valve caliber sequence at the previous historical moment, wherein the correlation is the Pearson correlation coefficient between the pressure sequence and the valve caliber sequence; the stability is positively correlated with the standard deviation of the difference between the standardized data in the pressure sequence and the valve caliber sequence at the historical moment; and the valve is controlled according to the degree of the fault at the current moment.

[0007] By analyzing the correlation between the changes in the two-dimensional data at the historical moments, and combining the stability of the changes in the two-dimensional data at the historical moments, the reliability of the predicted value at each moment is comprehensively evaluated. The deviation between the predicted value and the actual value of the two-dimensional data at that moment is corrected using the reliability of the predicted value at that moment, so as to obtain the fault degree at that moment and improve the accuracy of the prediction.

[0008] Furthermore, the valve is controlled according to the current fault level, including: in response to the fault level at the current moment being greater than a preset threshold, the valve is controlled to close and an alarm is issued, thereby improving the safety of the pressure regulating valve during use.

[0009] Furthermore, the calculation formula for the fault degree at the current moment is: ; In the formula, For the moment The degree of failure, For the moment The reliability of the predicted value, For the moment pressure, For the moment The predicted value of pressure, For the moment Valve diameter; For the moment The predicted value of valve diameter, is the standard normalization function. The reliability of the predicted value at each moment is obtained through analysis, and the results of the single-dimensional prediction are weighted and corrected based on the reliability, thereby improving the accuracy of the fault degree assessment at each moment.

[0010] Furthermore, the calculation time Correlation between pressure sequence and valve caliber sequence at previous historical moments , the calculation formula is: ; In the formula, For the moment The first in the sequence of pressures at previous historical moments data values; For the moment The mean of all data values ​​in the pressure series at previous historical moments; For the moment The valve caliber sequence at the previous historical moment data values; For the moment The mean of all data values ​​in the valve caliber sequence at previous historical moments, For the moment The number of data in the previous historical moment sequence. The mutual response relationship between the pressure of the main pipeline and the pressure regulating valve caliber data is quantified to ensure that the prediction model can reflect the real state of the system.

[0011] Furthermore, the calculation time Stability of changes in pressure sequence and valve caliber sequence data at previous historical moments , the calculation formula is: ; In the formula, For the moment The first in the sequence of pressures at previous historical moments data values; For the moment The standard deviation of all data values ​​in the pressure series at previous historical moments; For the moment The valve caliber sequence at the previous historical moment data values; For the moment The standard deviation of all data values ​​in the valve caliber sequence at previous historical moments; is the default value; For the moment The number of data in the previous historical moment series; is a natural exponential function. The smoothness is evaluated by the standard deviation of the difference between the two data at each historical moment. If the standard deviation is small, it means that there is no obvious jump in the changes at the historical moment, and the stability of data changes can be accurately evaluated.

[0012] Further, get the preset value , including: Get the time The difference between the ratios of all data in the pressure sequence and valve caliber sequence at the previous historical moment and their respective standard deviations is then calculated, and the average value is used as the preset value.

[0013] Furthermore, collecting valve pressure and valve caliber data includes: collecting valve pressure and valve caliber data once at every preset time interval.

[0014] Furthermore, the preset time interval is 5 seconds.

[0015] Furthermore, the preset threshold is 0.8. In a second aspect of the present invention, a water supply valve control system based on fault monitoring is also provided, comprising a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to implement any of the above-mentioned water supply valve control methods based on fault monitoring.

[0016] Beneficial effects: By considering the interaction between the two-dimensional data and the stability of the changes, the mutual response relationship between the pressure of the main pipeline and the pressure regulating valve caliber data is quantified, ensuring that the prediction model can reflect the real state of the system. The reliability of the predicted value is calculated by combining correlation and stability, which increases the evaluation of the reliability of the prediction results and ensures the reliability of the prediction results. The problem of misjudging the fault point due to inaccurate prediction caused by ignoring the mutual response relationship is solved, thereby improving the accuracy of the fault detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The following detailed description is read with reference to the accompanying drawings, which illustrate several embodiments of the present invention in an exemplary and non-limiting manner, and in which like or corresponding reference numerals represent like or corresponding parts, wherein: Figure 1 FIG. 4 is a schematic diagram schematically illustrating the calculation of the fault degree of a valve at the current moment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0019] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0020] In one embodiment, the traditional HTFE algorithm predicts different dimensional time series in combination with their respective historical trends and prediction errors, and evaluates whether a fault has occurred at the current moment by the deviation between the predicted value and the actual value of the main pipeline pressure and pressure regulating valve caliber data at any moment. However, in the actual water supply system, the changes in the main pipeline pressure and the pressure regulating valve caliber data are mutually responsive. If the response relationship between the two is not considered, the actual state of the system cannot be accurately reflected, which will make the prediction results unreliable, thereby reducing the accuracy of fault detection.

[0021] In one embodiment, a time series adaptive prediction method based on historical trends and prediction errors (HTFE, Historical Trends Forecast Errors) is a method for continuous prediction of continuous states by determining the trend type of recent time series and different repeated "prediction-correction-prediction". It can continuously correct the range of the next prediction through the prediction error, thereby achieving more accurate prediction of the data.

[0022] Therefore, this solution introduces the correlation and stability analysis of the two-dimensional data. By considering the interaction between the two-dimensional data and the stability of the changes, the mutual response relationship between the pressure of the main pipeline and the pressure regulating valve caliber data is quantified, ensuring that the prediction model can reflect the true state of the system. The reliability of the predicted value is calculated in combination with the correlation and stability, which increases the evaluation of the reliability of the prediction results and ensures the reliability of the prediction results. The problem of misjudging the fault point due to inaccurate prediction caused by ignoring the mutual response relationship is solved, thereby improving the accuracy of the fault detection results. The specific steps are as follows.

[0023] like Figure 1 As shown, S101: collecting valve pressure and valve diameter data.

[0024] In one embodiment, the pressure of the main pipeline near the pressure regulating valve area and the valve caliber size of the pressure regulating valve are collected to obtain a pressure sequence and a valve caliber sequence. Specifically, the pressure and valve caliber data of the valve are collected once every preset time interval, so the number of data points in the pressure sequence and the valve caliber sequence are equal. In this embodiment, the preset time interval is 5 seconds. In other embodiments, the preset time interval can be 7 seconds or 10 seconds, etc., which can be set according to specific actual conditions. The specific collection method is as follows: by installing a pressure sensor in the area of ​​the main pipeline near the pressure regulating valve, the pressure is monitored in real time through the pressure sensor and the valve caliber size of the pressure regulating valve is read in real time.

[0025] S102: Calculate the correlation between the pressure sequence and the valve caliber sequence.

[0026] In one embodiment, in the actual application scenario of urban water supply, when the pressure of the main pipeline increases, the pressure regulating valve will automatically increase the valve diameter and reduce the flow of the branch pipeline, thereby achieving the effect of reducing pressure and making the pressure in the branch pipeline within the standard range to ensure that users can obtain stable water supply services. Therefore, if the valve works normally, the change in valve diameter at this time changes with the pressure change of the main pipeline, and presents a trend of change in the same direction as a whole, that is, as the pressure of the main pipeline increases, the valve diameter will also increase. Therefore, considering the correlation between the pressure sequence and the valve diameter sequence at historical moments can distinguish whether the historical data conforms to the actual normal change trend.

[0027] In one embodiment, the Pearson correlation coefficient of the pressure sequence and the valve caliber sequence can be calculated, and the calculated Pearson correlation coefficient value is used as the correlation between the pressure sequence and the valve caliber sequence. It should be noted that when the value of the Pearson correlation coefficient is greater than 0, it means that there is a positive linear correlation between the pressure sequence and the valve caliber sequence, which means that the pressure sequence and the valve caliber sequence show a change trend in the same direction as a whole, which is consistent with the actual normal change trend.

[0028] In one embodiment, the calculation time Correlation between pressure sequence and valve caliber sequence at previous historical moments , the calculation formula is: ; In the formula, For the moment The first in the sequence of pressures at previous historical moments data values; For the moment The mean of all data values ​​in the pressure series at previous historical moments; For the moment The valve caliber sequence at the previous historical moment data values; For the moment The mean of all data values ​​in the valve caliber sequence at previous historical moments, For the moment The number of data in the previous historical moment sequence.

[0029] in, Indicates the consistency of the change trend between the pressure and valve caliber sequence at the historical moment. The value is greater than 0, indicating that the change trend direction between the pressure and valve caliber at each moment in history is the same, which is consistent with the change characteristics of the two during normal operation, which means that in the first The higher the overall correlation between the historical pressure before the moment and the valve caliber sequence. It represents the product of the pressure at all historical moments and the standard deviation of the valve diameter. Through standardization, the dimensionality problem of different units and scales is solved, making the consistency of the change trend between the two evaluated sequences more reliable.

[0030] S103: Calculate the stability of the pressure sequence and valve caliber sequence data changes.

[0031] In one embodiment, during normal water supply, the water flow in the pipeline tends to change continuously and smoothly over time, without abrupt changes, and the pressure as an indirect manifestation of the flow also presents similar changes. The main function of the pressure regulating valve is to control the water pressure in the branch pipeline by adjusting the valve caliber to ensure that the system can operate stably under different conditions of use. This means that in the working state, the adjustment of the valve caliber should also be continuous and smooth as the pressure of the main pipeline changes. Therefore, this smoothness can be evaluated by the standard deviation of the difference between the pressure data and the valve caliber data at historical moments. If the standard deviation is small, it means that there is no obvious abrupt change in the changes at historical moments, and it is considered that the valve operation at historical moments is relatively stable.

[0032] In one embodiment, the stability of the changes in the pressure sequence and valve caliber sequence data at the historical moment is calculated, and the stability is positively correlated with the standard deviation of the difference between the standardized data in the pressure sequence and valve caliber sequence at the historical moment.

[0033] In one embodiment, the calculation time Stability of changes in pressure sequence and valve caliber sequence data at previous historical moments , the calculation formula is: ; In the formula, For the moment The first in the sequence of pressures at previous historical moments data values; For the moment The standard deviation of all data values ​​in the pressure series at previous historical moments; For the moment The valve caliber sequence at the previous historical moment data values; For the moment The standard deviation of all data values ​​in the valve caliber sequence at previous historical moments; is the default value; For the moment The number of data in the previous historical moment series; is a natural exponential function.

[0034] In one embodiment, the preset value The methods for obtaining include: obtaining the time The difference between the ratios of all data in the pressure sequence and valve caliber sequence at the previous historical moment and their respective standard deviations is then calculated, and the average value is used as the preset value.

[0035] In one embodiment, the preset value The calculation formula is: , where For the moment The first in the sequence of pressures at previous historical moments data values; For the moment The standard deviation of all data values ​​in the pressure series at previous historical moments; For the moment The valve caliber sequence at the previous historical moment data values; For the moment The standard deviation of all data values ​​in the valve caliber sequence at the previous historical moment, For the moment The number of data in the previous historical moment sequence.

[0036] in, Indicates time The first in the sequence of pressures at previous historical moments The ratio of a data to the standard deviation of all its data, and the time The valve caliber sequence at the previous historical moment The difference between a data point and the ratio of its standard deviation to all data points. Indicates time The stability of the pressure and valve diameter sequence data changes at previous historical moments. The smaller the value, the less obvious the jump in the difference of all data changes in the historical moment sequence, which means that the valve operation at the historical moment is relatively stable. The higher the stability of the changes in the historical pressure and valve diameter sequence data before the moment.

[0037] It should be noted that the analysis of changes in the historical data pressure sequence and valve caliber sequence is in line with the actual change trend. If the overall change trend is consistent with the actual change, then the change trend at the historical moment is considered to be in line with expectations. However, if the response changes between the historical data do not meet expectations (for example, there are jump-like changes, but the overall trend is consistent), it is necessary to combine the stability of the data changes in the historical data pressure sequence and the valve caliber sequence to judge. If the stability is higher, it means that the change difference of all data in the historical moment sequence has not shown obvious jump-like changes, that is, the response changes of the two are also in line with expectations, which means that there is a stable and predictable relationship between every two variables in the historical data pressure sequence and the valve caliber sequence, and the reliability of the prediction result at the current moment is higher.

[0038] S104: Calculate the reliability of the current prediction value.

[0039] In one embodiment, the time The reliability of the predicted value The calculation formula is: ; In the formula, For the moment The stability of the pressure sequence and valve caliber sequence data changes at previous historical moments; For the moment The correlation between the pressure sequence and the valve diameter sequence at the previous historical moment, wherein the correlation is the Pearson correlation coefficient between the pressure sequence and the valve diameter sequence. Indicates that The value is limited to within the range.

[0040] in, Indicates time The reliability of the predicted value. The larger the value, the more accurate the prediction is. For example, the change trend of the pressure sequence and valve caliber sequence at the historical moment is more in line with expectations, and the difference of all data in the historical moment sequence does not show obvious jump changes, which means that the moment The prediction value of is more reliable. When, through the function Will The value is mapped in between; on the contrary, Value between; that is, when the overall change trend of the two sequences at the historical moment is consistent with the actual change ( ),at this time Take the larger value.

[0041] S105: Correct the predicted value based on the reliability of the predicted value at the current moment to obtain the degree of fault.

[0042] In one embodiment, the traditional HTFE algorithm is used to predict the pressure sequence and valve diameter sequence data of historical moments to obtain the predicted value at the current moment, wherein the predicted value at the current moment includes the predicted value of the pressure at the current moment and the predicted value of the valve diameter at the current moment, and the reliability of the predicted value at the current moment is calculated by the above method, and based on the reliability of the predicted value at the current moment, the deviation between the predicted value and the actual value of the two-dimensional data at the current moment is corrected, so as to obtain the fault degree at the current moment, thereby improving the accuracy of the prediction result.

[0043] In one embodiment, the calculation formula of the fault degree at the current moment is: ; In the formula, For the moment The degree of failure, For the moment The reliability of the predicted value, For the moment pressure, For the moment The predicted value of pressure, For the moment Valve diameter; For the moment The predicted value of valve diameter, is the standard normalization function.

[0044] in, Indicates time The predicted value of the pressure and the predicted value of the valve diameter are the sum of the deviations from their actual values. The larger the value, the faster the time. The more obvious the actual values ​​of the two data deviate from the predicted values, the more The more likely the pressure regulating valve is to be faulty. The reliability of the predicted value is weighted by the sum of its deviations. The higher the reliability of the time prediction value, the The greater the sum of the deviations between the predicted value of the pressure and the predicted value of the valve diameter data and their actual values, the greater the deviation is. The higher the pressure regulating valve failure rate, the higher the failure rate.

[0045] S106: Control the valve according to the current fault severity.

[0046] In one embodiment, if the fault level at the current moment is greater than a preset threshold, the valve is controlled to close and an alarm is sounded. If the fault level at the current moment is less than or equal to the preset threshold, the valve is kept open or closed. In this embodiment, the preset threshold is 0.8. In other embodiments, the preset threshold may be 0.82 or 0.75, etc., which may be changed according to the specific implementation scenario.

[0047] The present invention also provides a water supply valve control system based on fault monitoring. The system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a water supply valve control method based on fault monitoring according to the first aspect of the present invention is implemented.

[0048] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0049] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0050] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0051] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0052] The above-mentioned embodiments only express several implementation methods of the present invention, and the description is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent application. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A water supply valve control method based on fault monitoring, It is characterized in that include: Collect valve pressure and valve caliber data to obtain pressure sequence and valve caliber sequence; Based on the HTFE algorithm, the pressure sequence and valve caliber sequence at the historical moment are predicted respectively to obtain the predicted value of the pressure and the predicted value of the valve caliber at the current moment, and the sum of the difference between the predicted value of the pressure and the predicted value of the valve caliber and their actual values ​​is corrected by using the reliability of the predicted value at the current moment to obtain the fault degree at the current moment, where the reliability of the predicted value at the current moment is The calculation formula is: ； In the formula, For the moment The reliability of the predicted value, For the moment The stability of the pressure sequence and valve caliber sequence data changes at previous historical moments; For the moment The correlation between the pressure sequence and the valve diameter sequence at the previous historical moment, wherein the correlation is the Pearson correlation coefficient between the pressure sequence and the valve diameter sequence; Among them, stability is positively correlated with the standard deviation of the difference between the standardized data in the pressure series and valve caliber series at historical moments; The valve is controlled according to the severity of the fault at the current moment.

2. The water supply valve control method based on fault monitoring according to claim 1, It is characterized in that According to the current fault severity, the valve can be controlled, including: In response to the fault degree at the current moment being greater than a preset threshold, the valve is controlled to close and an alarm is issued.

3. The water supply valve control method based on fault monitoring according to claim 1, It is characterized in that The calculation formula for the fault degree at the current moment is: ； In the formula, For the moment The degree of failure, For the moment The reliability of the predicted value, For the moment pressure, For the moment The predicted value of pressure, For the moment Valve diameter; For the moment The predicted value of valve diameter, is the standard normalization function.

4. The water supply valve control method based on fault monitoring according to claim 1, It is characterized in that Calculation time Correlation between pressure sequence and valve caliber sequence at previous historical moments , the calculation formula is: ； In the formula, For the moment The first in the sequence of pressures at previous historical moments data values; For the moment The mean of all data values ​​in the pressure series at previous historical moments; For the moment The valve caliber sequence at the previous historical moment data values; For the moment The mean of all data values ​​in the valve caliber sequence at previous historical moments, For the moment The number of data in the previous historical moment sequence.

5. The water supply valve control method based on fault monitoring according to claim 1, It is characterized in that Calculation time Stability of changes in pressure sequence and valve caliber sequence data at previous historical moments , the calculation formula is: ； In the formula, For the moment The first in the sequence of pressures at previous historical moments data values; For the moment The standard deviation of all data values ​​in the pressure series at previous historical moments; For the moment The valve caliber sequence at the previous historical moment data values; For the moment The standard deviation of all data values ​​in the valve caliber sequence at previous historical moments; is the default value; For the moment The number of data in the previous historical moment series; is a natural exponential function.

6. The water supply valve control method based on fault monitoring according to claim 5, It is characterized in that Get preset value ,include: Get the moment The difference between the ratios of all data in the pressure sequence and valve caliber sequence at the previous historical moment and their respective standard deviations is then calculated, and the average value is used as the preset value.

7. The water supply valve control method based on fault monitoring according to claim 1, It is characterized in that Collect valve pressure and valve caliber data, including: The valve pressure and valve diameter data are collected once at a preset time interval.

8. The water supply valve control method based on fault monitoring according to claim 7, It is characterized in that The preset time interval is 5 seconds.

9. The water supply valve control method based on fault monitoring according to claim 2, It is characterized in that The preset threshold is 0.

8.

10. A water supply valve control system based on fault monitoring, comprising a processor and a memory, It is characterized in that The memory stores a computer program, and the processor executes the computer program to implement the water supply valve control method based on fault monitoring as described in any one of claims 1-9.

Images