CN118090078B - Leakage online monitoring method for closed circulation water cooling system - Google Patents
Leakage online monitoring method for closed circulation water cooling system Download PDFInfo
- Publication number
- CN118090078B CN118090078B CN202410472879.3A CN202410472879A CN118090078B CN 118090078 B CN118090078 B CN 118090078B CN 202410472879 A CN202410472879 A CN 202410472879A CN 118090078 B CN118090078 B CN 118090078B
- Authority
- CN
- China
- Prior art keywords
- pressure
- data point
- temperature
- pressure data
- scatter diagram
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/26—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to an online leakage monitoring method for a closed circulation water cooling system, which comprises the following steps: the method comprises the steps of obtaining a pressure data sequence and a temperature data sequence of a closed circulation water cooling system, respectively constructing a pressure scatter diagram and a temperature scatter diagram, obtaining the primary noise degree of each pressure data point according to the pressure value of each pressure data point in the pressure scatter diagram and the pressure value of the surrounding pressure data points, combining the correlation of each pressure data point and the temperature data point to obtain the final noise degree of each pressure data point in the pressure scatter diagram, correcting the order of MA items in an ARIMA model, predicting the pressure data sequence, and judging whether leakage occurs in the closed circulation water cooling system. According to the invention, through analyzing the change characteristics of the pressure data and the temperature data, the influence of noise data points is weakened, the order of MA items is corrected, and the accuracy of on-line leakage monitoring of the closed circulation water cooling system is improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an online leakage monitoring method for a closed circulation water cooling system.
Background
The closed circulation water cooling system leakage on-line monitoring is an important technical application, and can effectively ensure the normal operation of the water cooling system and the safety and stability of equipment. Once the closed circulation water cooling system leaks, equipment damage or work abnormality can be caused, the system leakage problem can be found in time through online monitoring and prediction, and loss and maintenance cost are reduced. The existing method for predicting the pressure of the closed circulation water cooling system is an ARIMA model, has the advantages of strong interpretability, wide application range, good prediction capability, and capability of effectively capturing the characteristics of time sequence data and providing accurate prediction results.
The prior art has the problem that various external interference factors such as temperature change, mechanical vibration, electromagnetic interference and the like can exist in the system operation environment in the process of collecting the pressure of the closed circulation water cooling system, and the factors can influence the measurement of the pressure sensor, so that the collected data is interfered to generate noise. The existing ARIMA model obtains the order of MA items by analyzing ACF and PACF graphs of time series data to determine the order of MA items. And the noise data of the pressure may show similar characteristics with the real abnormal data of the pressure in the graph, thereby reducing the accuracy of on-line leakage monitoring of the closed circulation water cooling system.
Disclosure of Invention
The invention provides an online leakage monitoring method for a closed circulation water cooling system, which aims to solve the existing problems.
The invention discloses an on-line leakage monitoring method for a closed circulation water cooling system, which adopts the following technical scheme:
The embodiment of the invention provides an on-line leakage monitoring method for a closed circulation water cooling system, which comprises the following steps:
acquiring a pressure data sequence and a temperature data sequence of a closed circulation water cooling system, and respectively constructing a pressure scatter diagram and a temperature scatter diagram according to the pressure data sequence and the temperature data sequence;
Obtaining the primary noise degree of each pressure data point in the pressure scatter diagram according to the pressure value of each pressure data point in the pressure scatter diagram and the pressure value of the surrounding pressure data point of each pressure data point; obtaining the primary noise degree of each temperature data point in the temperature scatter diagram according to the acquisition mode of the primary noise degree of each pressure data point in the pressure scatter diagram;
According to the primary noise degree of each pressure data point in the pressure scatter diagram and the primary noise degree of each temperature data point in the temperature scatter diagram, obtaining the correlation between each pressure data point in the pressure scatter diagram and each temperature data point in the temperature scatter diagram;
obtaining the final noise degree of each pressure data point in the pressure scatter diagram according to the correlation between each pressure data point in the pressure scatter diagram and each temperature data point in the temperature scatter diagram and the primary noise degree of each pressure data point in the pressure scatter diagram;
Correcting the order of the MA item in the ARIMA model according to the final noise degree of each pressure data point in the pressure scatter diagram to obtain the corrected MA item order;
according to the modified MA item order, predicting the pressure data sequence by using an ARIMA model to obtain a pressure data predicted value; and judging whether the closed circulation water cooling system leaks or not according to the predicted value of the pressure data.
Further, the method respectively constructs a pressure scatter diagram and a temperature scatter diagram according to the pressure data sequence and the temperature data sequence, and comprises the following specific steps:
Each pressure data in the pressure data sequence corresponds to one time, the time is taken as a horizontal axis, the pressure data is taken as a vertical axis, and a pressure scatter diagram of the pressure data sequence is constructed; and each temperature data in the temperature data sequence corresponds to one time, the time is taken as a horizontal axis, and the temperature data is taken as a vertical axis, so that a temperature scatter diagram of the temperature data sequence is constructed.
Further, the step of obtaining the primary noise level of each pressure data point in the pressure scatter diagram according to the pressure value of each pressure data point in the pressure scatter diagram and the pressure value of the surrounding pressure data point of each pressure data point comprises the following specific steps:
The method comprises the steps of obtaining a reference data segment of each pressure data point in a pressure scatter diagram, and obtaining a specific calculation formula corresponding to the primary noise degree of each pressure data point according to the pressure value of each pressure data point in the pressure scatter diagram and the pressure value of each pressure data point in the reference data segment of each pressure data point, wherein the specific calculation formula comprises the following steps:
In the method, in the process of the invention, Representing the primary noise level of the nth pressure data point in the pressure scatter plot,Representing the pressure value of the nth pressure data point in the pressure scatter plot,Mean value of pressure values representing all pressure data points in the reference data segment of the nth pressure data point in the pressure scatter plot,Cosine value representing minimum angle between the line connecting the nth and (n-1) th pressure data points and the line connecting the nth and (n+1) th pressure data points in pressure scatter diagram,Representing the number of pressure data points in the reference data segment of the nth pressure data point in the pressure scatter plot,Absolute value representing the difference in pressure values of the nth and nth-1 pressure data points in the pressure scatter plot,Absolute value representing the difference in pressure values of the u-th and u-1-th pressure data points in the reference data segment of the nth pressure data point in the pressure scatter plot,As an exponential function based on natural constants,As a linear normalization function,As a function of absolute value.
Further, the acquiring the reference data segment of each pressure data point in the pressure scatter diagram includes the following specific steps:
in the pressure scatter diagram, a sequence of any one pressure data point and K nearest pressure data points is recorded as a reference data segment of the any one pressure data point, Is a preset quantity threshold.
Further, the step of obtaining the correlation between each pressure data point in the pressure scatter diagram and each temperature data point in the temperature scatter diagram according to the primary noise degree of each pressure data point in the pressure scatter diagram and the primary noise degree of each temperature data point in the temperature scatter diagram comprises the following specific steps:
acquiring a reference data segment of each temperature data point in the temperature scatter diagram;
according to the pressure scatter diagram and the difference of the primary noise degree of the pressure data points and the temperature data points in the temperature scatter diagram, obtaining a first characteristic of each pressure data point in the pressure scatter diagram;
And obtaining the correlation between each pressure data point in the pressure scatter diagram and each temperature data point in the temperature scatter diagram according to the first characteristic of each pressure data point in the pressure scatter diagram and the difference between the pressure data point and the reference data segment of the temperature data point in the pressure scatter diagram and the temperature scatter diagram.
Further, the acquiring the reference data segment of each temperature data point in the temperature scatter diagram includes the following specific steps:
And obtaining the reference data segment of each temperature data point in the temperature scatter diagram according to the acquisition mode of the reference data segment of each pressure data point in the pressure scatter diagram.
Further, according to the first feature of each pressure data point in the pressure scatter diagram and the differences between the pressure data point and the reference data segment of the temperature data point in the pressure scatter diagram and the temperature scatter diagram, the correlation between each pressure data point in the pressure scatter diagram and each temperature data point in the temperature scatter diagram is obtained, and the corresponding specific calculation formula is as follows:
In the middle of Representing the correlation of the nth pressure data point in the pressure scatter plot with the nth temperature data point in the temperature scatter plot,Representing the primary noise level of the nth pressure data point in the pressure scatter plot,Representing a primary noise level of an nth temperature data point in the temperature scatter plot; /(I)Representing the slope of the nth and nth-1 pressure data point line in the pressure scattergram,Representing the slope of the nth and nth-1 temperature data point links in the temperature scattergram; /(I)Representing a number of pressure data points in a reference data segment of an nth pressure data point in the pressure scatter plot; /(I)Slope of the line between the (u) th and (u-1) th pressure data points in the reference data segment representing the (n) th pressure data point in the pressure scatter plot,A slope of a line connecting the (u) th and (u-1) th temperature data points in a reference data segment representing the (n) th temperature data point of the temperature scattergram; /(I)Representing the percentile of the nth pressure data point in its reference data segment in a pressure scatter plot,Representing the percentile of the nth temperature data point in its reference data segment in a temperature scatter plot,For a preset first constant,As an exponential function based on natural constants,As an absolute value function,Is the first feature of the nth pressure data point in the pressure scatter plot.
Further, the final noise degree of each pressure data point in the pressure scatter diagram is obtained according to the correlation between each pressure data point in the pressure scatter diagram and each temperature data point in the temperature scatter diagram and the primary noise degree of each pressure data point in the pressure scatter diagram, and the corresponding specific calculation formula is as follows:
In the middle of Representing the final noise level of the nth pressure data point in the pressure scatter plot,Representing the primary noise level of the nth pressure data point in the pressure scatter plot,Representing the correlation of the nth pressure data point in the pressure scatter plot with the nth temperature data point in the temperature scatter plot,As a linear normalization function,Is a preset second constant.
Further, the steps of the MA term in the ARIMA model are corrected according to the final noise degree of each pressure data point in the pressure scatter diagram, and the corrected steps of the MA term are obtained, and the corresponding specific calculation formula is as follows:
In the middle of Representing the modified MA item order,Representing the number of pressure data points in the pressure scatter plot,Representing the final noise level of the nth pressure data point in the pressure scatter plot,Representing a preset MA item order,Representing a rounding down, c is a preset third constant.
Further, the method for judging whether the closed circulation water cooling system leaks according to the predicted value of the pressure data comprises the following specific steps:
and when the predicted value of the pressure data is smaller than a preset judging threshold value, judging that the closed circulation water cooling system leaks.
The technical scheme of the invention has the beneficial effects that:
The method comprises the steps of obtaining a pressure data sequence and a temperature data sequence of a closed circulation water cooling system, respectively constructing a pressure scatter diagram and a temperature scatter diagram, accurately reflecting the change trend of data in an image, obtaining the primary noise degree of each pressure data point in the pressure scatter diagram according to the pressure value of each pressure data point in the pressure scatter diagram and the pressure value of surrounding pressure data points, combining the correlation of each pressure data point and the temperature data point, obtaining the final noise degree of each pressure data point in the pressure scatter diagram, correcting the order of MA items in an ARIMA model, weakening the influence of noise data, better describing the short-term fluctuation and random fluctuation of the pressure data, improving the prediction precision of the model, predicting the pressure data sequence, judging whether the closed circulation water cooling system leaks, providing more accurate prediction and analysis, enabling the system to be more convenient to operate and regulate, and improving the efficiency and stability of the system.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the steps of a method for monitoring leakage of a closed circulation water cooling system on line;
FIG. 2 is a graph of pressure data in the present embodiment;
fig. 3 is a graph of temperature data in the present embodiment.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific embodiments, structures, features and effects of a closed circulation water cooling system leakage on-line monitoring method according to the invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
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.
The invention provides a specific scheme of an on-line leakage monitoring method for a closed circulation water cooling system, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flow chart of steps of a leakage online monitoring method for a closed circulation water cooling system according to an embodiment of the invention is shown, and the method includes the following steps:
Step S001: and acquiring a pressure data sequence and a temperature data sequence of the closed circulation water cooling system, and respectively constructing a pressure scatter diagram and a temperature scatter diagram according to the pressure data sequence and the temperature data sequence.
When the pressure data and the temperature data of the closed circulation water cooling system are collected, the closed circulation water cooling system needs to be ensured to be carried out in the same time period, and specifically, the pressure data at each moment can be collected by using a pressure sensor to obtain a pressure data sequence, and the temperature data at each moment can be collected by using a temperature sensor to obtain a temperature data sequence. The specific acquisition duration is thirty minutes, and the acquisition frequency is one second, which is described as an example, but other values may be set in other embodiments, and the embodiment is not limited thereto. Constructing a pressure scatter diagram of a pressure data sequence by taking time as a horizontal axis and pressure data as a vertical axis; and constructing a temperature scatter diagram of the temperature data sequence by taking time as a horizontal axis and temperature data as a vertical axis. Fig. 2 is a graph of pressure data, and fig. 3 is a graph of temperature data. What needs to be described is: in fig. 2, the horizontal axis represents time, the vertical axis represents pressure data, and the unit of pressure data is bar; in fig. 3, the horizontal axis represents time, the vertical axis represents temperature data, and the unit of temperature data is degrees celsius.
Step S002: obtaining the primary noise degree of each pressure data point in the pressure scatter diagram according to the pressure value of each pressure data point in the pressure scatter diagram and the pressure value of the surrounding pressure data point of each pressure data point; and obtaining the primary noise degree of each temperature data point in the temperature scatter diagram according to the acquisition mode of the primary noise degree of each pressure data point in the pressure scatter diagram.
The numerical representation of each pressure data point in the graph and the change characteristics of the surrounding data are analyzed to obtain the primary noise degree. Wherein the more abnormal the numerical performance of each data point, the stronger the abrupt change that occurs at each pressure data point, the greater the primary noise level of that pressure data point.
In the pressure scatter diagram, a sequence of any one pressure data point and K nearest pressure data points is recorded as a reference data segment of the any one pressure data point, thereby obtaining a reference data segment of each pressure data point in the pressure scatter diagram,For the preset number threshold, in this embodiment50, Which is described as an example, other values may be set in other embodiments, and the present example is not limited thereto. According to the logical AND operation described above, the primary noise level for each pressure data point is calculated:
In the method, in the process of the invention, Representing the primary noise level of the nth pressure data point in the pressure scatter plot,Representing the pressure value of the nth pressure data point in the pressure scatter plot,Mean value of pressure values representing all pressure data points in the reference data segment of the nth pressure data point in the pressure scatter plot,Cosine value representing minimum angle between the line connecting the nth and (n-1) th pressure data points and the line connecting the nth and (n+1) th pressure data points in pressure scatter diagram,Representing the number of pressure data points in the reference data segment of the nth pressure data point in the pressure scatter plot. /(I)Absolute value representing the difference in pressure values of the nth and nth-1 pressure data points in the pressure scatter plot,Absolute value representing the difference in pressure values of the u-th and u-1-th pressure data points in the reference data segment of the nth pressure data point in the pressure scatter plot,The present embodiment uses/>, as an exponential function based on natural constantsThe inverse proportion relation and normalization processing are presented, and an implementer can set an inverse proportion function and a normalization function according to actual conditions; /(I)Normalizing the data values to/>, as a linear normalization functionWithin the interval,As a function of absolute value.
In the formulaThe relative difference of the nth pressure data point in the pressure scatter plot with respect to the average pressure value in the reference data segment is shown, and the greater the difference value is, the greater the possibility of abrupt change in the pressure data point is, the greater the primary noise level is. /(I)The larger the value is, the sharper the included angle is, the larger the difference between the values of the pressure data points and the values of the data points which are adjacent to the left and right sides is, and the larger the probability of mutation on the corresponding pressure data points is, and the larger the primary noise degree is.The average value representing the absolute value of the difference between the pressure values of the nth and the n-1 th pressure data points in the pressure scatter plot and the absolute value of the difference between the nth and the u-1 th pressure data points in the reference data segment of the nth pressure data point, the greater this value is indicative of the greater the likelihood of a sudden change occurring in the nth pressure data point, the greater its primary noise level.
Obtaining the reference data segment of each temperature data point in the temperature scatter diagram according to the acquisition mode of the reference data segment of each pressure data point in the pressure scatter diagram; and obtaining the primary noise degree of each temperature data point in the temperature scatter diagram according to the acquisition mode of the primary noise degree of each pressure data point in the pressure scatter diagram.
Step S003: and obtaining the correlation between each pressure data point in the pressure scatter diagram and each temperature data point in the temperature scatter diagram according to the primary noise degree of each pressure data point in the pressure scatter diagram and the primary noise degree of each temperature data point in the temperature scatter diagram.
By analyzing the pressure value representation of each pressure data point and its surrounding data change characteristics through the above steps, the primary noise level of each pressure data point is obtained. However, analysis of only the pressure value representation of each pressure data point and the varying characteristics of its surrounding data points does not accurately distinguish between noise data and anomaly data for the pressure. In a closed-cycle water system, when there is a leak in the system, the pressure will drop, while the temperature in the system will rise due to the reduced flow of cooling water. So that the pressure data and the temperature data have a certain negative correlation in the system. Therefore, we can analyze the correlation between the pressure data and the temperature data, and correct the primary noise level of each pressure data point in the pressure scatter plot to obtain the final noise level of each pressure data point.
Calculating a correlation between each pressure data point and a temperature data point:
In the middle of Representing the correlation of the nth pressure data point in the pressure scatter plot with the nth temperature data point in the temperature scatter plot,Representing the primary noise level of the nth pressure data point in the pressure scatter plot,Representing the primary noise level of the nth temperature data point in the temperature scatter plot. /(I)Representing the slope of the nth and nth-1 pressure data point line in the pressure scattergram,The slope of the nth and nth-1 temperature data point lines in the temperature scattergram is shown. /(I)Representing the number of pressure data points in the reference data segment of the nth pressure data point in the pressure scatter plot. /(I)Slope of the line between the (u) th and (u-1) th pressure data points in the reference data segment representing the (n) th pressure data point in the pressure scatter plot,The slope of the line connecting the (u) th and (u-1) th temperature data points in the reference data segment of the nth temperature data point of the temperature scattergram is represented. /(I)Representing the percentile of the nth pressure data point in its reference data segment in a pressure scatter plot,Representing the percentile of the nth temperature data point in its reference data segment in a temperature scatter plot,For a preset first constant, the denominator is avoided to be 0, in this embodimentThis is described as an example, but other values may be set in other embodiments, and the present example is not limited thereto. What needs to be described is: the percentile is a well known technique, e.g. the percentile of 3 in the sequences 1,2,3,4,5 is 50%. The data points in the reference data segment are ordered by time,The present embodiment uses an exponential function based on natural constantsThe inverse proportion relation and normalization processing are presented, and an implementer can set an inverse proportion function and a normalization function according to actual conditions; /(I)As an absolute value function,Is the first feature of the nth pressure data point in the pressure scatter plot.
In the formulaThe difference value between the primary noise degree of the nth pressure data point in the pressure scatter diagram and the nth temperature data point in the temperature scatter diagram is shown, and the smaller the difference value is, the smaller the numerical performance of the two data at the corresponding moment of the nth pressure data point and the smaller the difference of the data change characteristics is, and the stronger the correlation of the two data is. /(I)The ratio of the slope of the nth and nth-1 pressure data point lines in the pressure scatter diagram to the slope of the nth and nth-1 temperature data point lines in the temperature scatter diagram is shown, and the relative magnitude relation of the slope and the slope is shown. /(I)An average value representing a ratio of a slope of the nth and nth-1 pressure data point lines in the pressure scattergram to a slope of the nth and nth-1 temperature data point lines in the reference data segment of the nth temperature data point of the temperature scattergram. /(I)The smaller the value, the more strongly the pressure data is correlated with the temperature data change at that time.The larger the difference between the relative magnitudes of the pressure data and the temperature data in the respective reference data segments at the time corresponding to the nth pressure data point, the stronger the negative correlation therebetween.
Step S004: and obtaining the final noise degree of each pressure data point in the pressure scatter diagram according to the correlation of each pressure data point in the pressure scatter diagram and each temperature data point in the temperature scatter diagram and the primary noise degree of each pressure data point in the pressure scatter diagram.
After the correlation between the pressure data and the temperature data at the corresponding time of each pressure data point is obtained, the primary noise degree of each pressure data point is combined for analysis, and the final noise degree of each pressure data point is obtained. The concrete calculation mode is as follows:
In the middle of Representing the final noise level of the nth pressure data point in the pressure scatter plot. /(I)Representing the primary noise level of the nth pressure data point in the pressure scatter plot, the greater the value will correspond to the greater the final noise level. /(I)The correlation of the nth pressure data point in the pressure scatter plot and the nth temperature data point in the temperature scatter plot is shown, and the larger the value is, the more the change characteristic between the pressure data and the temperature data accords with the characteristics in the system, and the smaller the corresponding final noise degree is. End useNormalize the final noise level for each pressure data point toBetween,For a preset second constant, in this embodiment2, Which is described by way of example, other values may be set in other embodiments, and the example is not limited thereto,Normalizing the data values to/>, as a linear normalization functionWithin the interval.
Step S005: and correcting the order of the MA item in the ARIMA model according to the final noise degree of each pressure data point in the pressure scatter diagram to obtain the corrected MA item order.
By the analysis of the above steps, the final noise level of each pressure data point in the pressure scatter plot is obtained. The final noise level of each pressure data point in the pressure data is then combined with the MA term order obtained by the prior art to obtain an accurate MA term order, and this is taken as an example to describe an initial value 2 of the MA term order preset in this embodiment, and other values may be set in other embodiments, which is not limited in this embodiment. In the ARIMA model, more noise data means more random and unpredictable fluctuations in the time series, which can have an impact on the observations, resulting in more complex data and more fluctuations. To better capture the effects of these noise data, a higher order MA model needs to be used to improve the adaptation of the model. According to the logic, the order of the corrected MA item is obtained:
In the middle of Representing the modified MA term order. /(I)Representing the number of pressure data points in the pressure scatter plot,Representing the final noise level of the nth pressure data point in the pressure scatter plot,Representing the average of the final noise levels for all pressure data points in the pressure scatter plot. /(I)Representing a preset MA item order,The third constant is a predetermined value, and c is 0.5 in this embodiment, which is described as an example, but other values may be set in other embodiments, and this embodiment is not limited thereto.
What needs to be described is: the ARIMA (Autoregressive Integrated Moving Average) model is a commonly used time series prediction model for analyzing and predicting the trend and periodicity of time series data. The ARIMA model consists of three parts: autoregressive (AR), differential (I), and Moving Average (MA), which are well known techniques, and specific methods are not described herein. The MA term order is a parameter in the ARIMA model.
Step S006: according to the modified MA item order, predicting the pressure data sequence by using an ARIMA model to obtain a pressure data predicted value; and judging whether the closed circulation water cooling system leaks or not according to the predicted value of the pressure data.
According to the modified MA term order, the ARIMA model is used to predict the pressure data sequence to obtain a pressure data predicted value, and the preset judgment threshold value in this embodiment is 1, which is described by way of example, other values may be set in other embodiments, and this embodiment is not limited, and when the pressure data predicted value is smaller than the preset judgment threshold value, it is determined that leakage occurs in the closed circulation water cooling system.
The present invention has been completed.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (5)
1. The on-line leakage monitoring method for the closed circulation water cooling system is characterized by comprising the following steps of:
acquiring a pressure data sequence and a temperature data sequence of a closed circulation water cooling system, and respectively constructing a pressure scatter diagram and a temperature scatter diagram according to the pressure data sequence and the temperature data sequence;
Obtaining the primary noise degree of each pressure data point in the pressure scatter diagram according to the pressure value of each pressure data point in the pressure scatter diagram and the pressure value of the surrounding pressure data point of each pressure data point; obtaining the primary noise degree of each temperature data point in the temperature scatter diagram according to the acquisition mode of the primary noise degree of each pressure data point in the pressure scatter diagram;
the primary noise degree of each pressure data point in the pressure scatter diagram is obtained according to the pressure value of each pressure data point in the pressure scatter diagram and the pressure value of the surrounding pressure data point of each pressure data point, and the method comprises the following specific steps:
The method comprises the steps of obtaining a reference data segment of each pressure data point in a pressure scatter diagram, and obtaining a specific calculation formula corresponding to the primary noise degree of each pressure data point according to the pressure value of each pressure data point in the pressure scatter diagram and the pressure value of each pressure data point in the reference data segment of each pressure data point, wherein the specific calculation formula comprises the following steps:
In the method, in the process of the invention, Representing the primary noise level of the nth pressure data point in the pressure scatter plot,Representing the pressure value of the nth pressure data point in the pressure scatter plot,Mean value of pressure values representing all pressure data points in the reference data segment of the nth pressure data point in the pressure scatter plot,Cosine value representing minimum angle between the line connecting the nth and (n-1) th pressure data points and the line connecting the nth and (n+1) th pressure data points in pressure scatter diagram,Representing the number of pressure data points in the reference data segment of the nth pressure data point in the pressure scatter plot,Absolute value representing the difference in pressure values of the nth and nth-1 pressure data points in the pressure scatter plot,Absolute value representing the difference in pressure values of the u-th and u-1-th pressure data points in the reference data segment of the nth pressure data point in the pressure scatter plot,As an exponential function based on natural constants,As a linear normalization function,As a function of absolute value;
According to the primary noise degree of each pressure data point in the pressure scatter diagram and the primary noise degree of each temperature data point in the temperature scatter diagram, obtaining the correlation between each pressure data point in the pressure scatter diagram and each temperature data point in the temperature scatter diagram;
the method comprises the following specific steps of:
acquiring a reference data segment of each temperature data point in the temperature scatter diagram;
according to the pressure scatter diagram and the difference of the primary noise degree of the pressure data points and the temperature data points in the temperature scatter diagram, obtaining a first characteristic of each pressure data point in the pressure scatter diagram;
According to the first characteristic of each pressure data point in the pressure scatter diagram and the difference between the pressure data point in the pressure scatter diagram and the reference data segment of the pressure data point and the temperature data point in the temperature scatter diagram, obtaining the correlation between each pressure data point in the pressure scatter diagram and each temperature data point in the temperature scatter diagram;
according to the first characteristic of each pressure data point in the pressure scatter diagram and the difference between the pressure data point in the pressure scatter diagram and the reference data segment of the temperature data point in the temperature scatter diagram, the correlation between each pressure data point in the pressure scatter diagram and each temperature data point in the temperature scatter diagram is obtained, and the corresponding specific calculation formula is as follows:
In the middle of Representing the correlation of the nth pressure data point in the pressure scatter plot with the nth temperature data point in the temperature scatter plot,Representing the primary noise level of the nth pressure data point in the pressure scatter plot,Representing a primary noise level of an nth temperature data point in the temperature scatter plot; /(I)Representing the slope of the nth and nth-1 pressure data point line in the pressure scattergram,Representing the slope of the nth and nth-1 temperature data point links in the temperature scattergram; /(I)Representing a number of pressure data points in a reference data segment of an nth pressure data point in the pressure scatter plot; /(I)Slope of the line between the (u) th and (u-1) th pressure data points in the reference data segment representing the (n) th pressure data point in the pressure scatter plot,A slope of a line connecting the (u) th and (u-1) th temperature data points in a reference data segment representing the (n) th temperature data point of the temperature scattergram; /(I)Representing the percentile of the nth pressure data point in its reference data segment in a pressure scatter plot,Representing the percentile of the nth temperature data point in its reference data segment in a temperature scatter plot,For a preset first constant,As an exponential function based on natural constants,As an absolute value function,A first feature that is an nth pressure data point in the pressure scatter plot;
obtaining the final noise degree of each pressure data point in the pressure scatter diagram according to the correlation between each pressure data point in the pressure scatter diagram and each temperature data point in the temperature scatter diagram and the primary noise degree of each pressure data point in the pressure scatter diagram;
The final noise degree of each pressure data point in the pressure scatter diagram is obtained according to the correlation between each pressure data point in the pressure scatter diagram and each temperature data point in the temperature scatter diagram and the primary noise degree of each pressure data point in the pressure scatter diagram, and the corresponding specific calculation formula is as follows:
In the middle of Representing the final noise level of the nth pressure data point in the pressure scatter plot,Representing the primary noise level of the nth pressure data point in the pressure scatter plot,Representing the correlation of the nth pressure data point in the pressure scatter plot with the nth temperature data point in the temperature scatter plot,As a linear normalization function,Is a preset second constant;
Correcting the order of the MA item in the ARIMA model according to the final noise degree of each pressure data point in the pressure scatter diagram to obtain the corrected MA item order;
correcting the order of the MA item in the ARIMA model according to the final noise degree of each pressure data point in the pressure scatter diagram to obtain the corrected MA item order, wherein the corresponding specific calculation formula is as follows:
In the middle of Representing the modified MA item order,Representing the number of pressure data points in the pressure scatter plot,Representing the final noise level of the nth pressure data point in the pressure scatter plot,Representing a preset MA item order,Representing downward rounding, c being a preset third constant;
according to the modified MA item order, predicting the pressure data sequence by using an ARIMA model to obtain a pressure data predicted value; and judging whether the closed circulation water cooling system leaks or not according to the predicted value of the pressure data.
2. The method for on-line monitoring leakage of a closed circulation water cooling system according to claim 1, wherein the method comprises the following steps of:
Each pressure data in the pressure data sequence corresponds to one time, the time is taken as a horizontal axis, the pressure data is taken as a vertical axis, and a pressure scatter diagram of the pressure data sequence is constructed; and each temperature data in the temperature data sequence corresponds to one time, the time is taken as a horizontal axis, and the temperature data is taken as a vertical axis, so that a temperature scatter diagram of the temperature data sequence is constructed.
3. The method for on-line monitoring leakage of a closed circulation water cooling system according to claim 1, wherein the step of obtaining the reference data segment of each pressure data point in the pressure scatter diagram comprises the following specific steps:
in the pressure scatter diagram, a sequence of any one pressure data point and K nearest pressure data points is recorded as a reference data segment of the any one pressure data point, Is a preset quantity threshold.
4. The method for on-line monitoring leakage of a closed circulation water cooling system according to claim 1, wherein the step of obtaining the reference data segment of each temperature data point in the temperature scatter diagram comprises the following specific steps:
And obtaining the reference data segment of each temperature data point in the temperature scatter diagram according to the acquisition mode of the reference data segment of each pressure data point in the pressure scatter diagram.
5. The method for on-line monitoring leakage of a closed circulation water cooling system according to claim 1, wherein the step of judging whether leakage occurs in the closed circulation water cooling system according to the predicted value of the pressure data comprises the following specific steps:
and when the predicted value of the pressure data is smaller than a preset judging threshold value, judging that the closed circulation water cooling system leaks.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410472879.3A CN118090078B (en) | 2024-04-19 | 2024-04-19 | Leakage online monitoring method for closed circulation water cooling system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410472879.3A CN118090078B (en) | 2024-04-19 | 2024-04-19 | Leakage online monitoring method for closed circulation water cooling system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118090078A CN118090078A (en) | 2024-05-28 |
| CN118090078B true CN118090078B (en) | 2024-06-25 |
Family
ID=91154893
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410472879.3A Active CN118090078B (en) | 2024-04-19 | 2024-04-19 | Leakage online monitoring method for closed circulation water cooling system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118090078B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120258388B (en) * | 2025-03-17 | 2026-01-06 | 山东泰开机器人有限公司 | Cloud-based intelligent operation and maintenance management system for water cooling systems |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537034B (en) * | 2014-12-22 | 2017-11-10 | 国家电网公司 | The Condition Monitoring Data cleaning method of power transmission and transforming equipment based on time series analysis |
| KR101956715B1 (en) * | 2017-09-01 | 2019-03-11 | 군산대학교산학협력단 | Wind direction prediction method and apparatus for yaw control of wind turbines |
| US10685159B2 (en) * | 2018-06-27 | 2020-06-16 | Intel Corporation | Analog functional safety with anomaly detection |
| CN210603662U (en) * | 2019-11-02 | 2020-05-22 | 山东艾克索仑电气有限公司 | Temperature measurement structure for permanent magnet electric roller bearing |
| JP7759273B2 (en) * | 2022-02-03 | 2025-10-23 | 大成建設株式会社 | Air leak detection method |
| KR102736919B1 (en) * | 2022-03-21 | 2024-12-02 | 주식회사 플로워크연구소 | detecting method of pipe abnormality using artificial intelligence |
| CN115099143B (en) * | 2022-06-22 | 2024-08-02 | 青岛理工大学 | An early fault diagnosis method for all-electric actuator based on uncertainty reasoning drive |
| CN116320042B (en) * | 2023-05-16 | 2023-08-04 | 陕西思极科技有限公司 | IoT Terminal Monitoring and Control System Based on Edge Computing |
| CN116738353B (en) * | 2023-08-15 | 2023-10-13 | 安拓思纳米技术（苏州）有限公司 | Pharmaceutical workshop air filter element performance detection method based on data analysis |
| CN116881745B (en) * | 2023-09-07 | 2023-12-19 | 深圳市特安工业科技有限公司 | Pressure transmitter abnormality monitoring method based on big data |
| CN117167903B (en) * | 2023-11-03 | 2024-01-30 | 江苏中安建设集团有限公司 | Artificial intelligence-based foreign matter fault detection method for heating ventilation equipment |
| CN117725792A (en) * | 2023-12-18 | 2024-03-19 | 清华大学合肥公共安全研究院 | Building safety monitoring and early warning method based on time series and model modification |
| CN117870943B (en) * | 2024-01-22 | 2024-08-20 | 中国三峡建工(集团)有限公司 | Multi-sensor-based data optimization acquisition system in grouting process |
-
2024
- 2024-04-19 CN CN202410472879.3A patent/CN118090078B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| 基于ARIMA和LSTM组合模型的核电厂主泵状态预测;朱少民 等;核动力工程;20220430;全文 * |
| 基于XGBoost-LSTM组合模型的光伏发电功率预测;谭海旺 等;太阳能学报;20220831;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118090078A (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111275288A (en) | XGboost-based multi-dimensional data anomaly detection method and device | |
| CN102736546A (en) | State monitoring device of complex electromechanical system for flow industry and method | |
| CN119691664B (en) | Hydropower station computer monitoring system fault prediction method based on big data analysis | |
| CN115248558B (en) | A dynamic process fault detection method based on variational Bayesian probabilistic latent variable model | |
| CN114692723B (en) | Reverse osmosis membrane fouling and blocking early warning method and system | |
| CN111855219A (en) | A method for predicting security parameters of diesel engine lubricating oil entering the engine based on grey theory | |
| CN118090078B (en) | Leakage online monitoring method for closed circulation water cooling system | |
| Pan et al. | Multi-sensor signal fusion method for rolling bearing based on the standard relative mean–variance value and random weighting algorithm | |
| CN117610725A (en) | Life prediction method of typical ship equipment based on multi-sensor data fusion | |
| CN114879612A (en) | Blast furnace iron-making process monitoring method based on Local-DBKSSA | |
| CN117786371A (en) | A temperature monitoring data optimization and prediction analysis method and system | |
| CN120671056A (en) | Centrifugal fan fault trend prediction method based on multi-source information fusion | |
| CN118629160A (en) | A landslide early warning method based on adaptive local regression | |
| CN120492817B (en) | Chemical data processing and analyzing method and system for chemical production | |
| CN120969155A (en) | Mechanical pump self-adaptive threshold predictive maintenance diagnostic system | |
| CN119848436B (en) | Hydraulic and hydroelectric engineering data management method based on BIM information processing | |
| CN120373155A (en) | Service life prediction method and system for fire valve | |
| CN113283157A (en) | System, method, terminal and medium for predicting life cycle of intelligent stamping press part | |
| CN110516323B (en) | Pressure pipeline damage prediction method based on time sequence analysis | |
| Perry | Identifying the time of polynomial drift in the mean of autocorrelated processes | |
| CN114112390B (en) | Nonlinear complex system early fault diagnosis method | |
| CN116641941A (en) | A dynamic detection method for early faults in hydraulic systems based on canonical variable analysis | |
| Lv et al. | A method combining dynamic path matching with multipath adaptive drift Lévy stable motion for performance degradation prediction | |
| CN120145128B (en) | Cooler blockage prediction method based on deep learning coupled with physical constraints | |
| CN119917985B (en) | Photovoltaic power distribution operation early warning method, system, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |