CN117195007A - Heat exchanger performance prediction method and system - Google Patents
Heat exchanger performance prediction method and system Download PDFInfo
- Publication number
- CN117195007A CN117195007A CN202311475356.6A CN202311475356A CN117195007A CN 117195007 A CN117195007 A CN 117195007A CN 202311475356 A CN202311475356 A CN 202311475356A CN 117195007 A CN117195007 A CN 117195007A
- Authority
- CN
- China
- Prior art keywords
- temperature data
- data
- imf component
- heat exchanger
- indicate
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 74
- 230000011218 segmentation Effects 0.000 claims description 25
- 230000008569 process Effects 0.000 claims description 17
- 238000001914 filtration Methods 0.000 claims description 12
- 230000000694 effects Effects 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 8
- 238000001816 cooling Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 2
- 238000003379 elimination reaction Methods 0.000 claims description 2
- 230000008859 change Effects 0.000 abstract description 17
- 238000012545 processing Methods 0.000 abstract description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 239000000758 substrate Substances 0.000 description 3
- 239000012530 fluid Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Indication And Recording Devices For Special Purposes And Tariff Metering Devices (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a heat exchanger performance prediction method and system, comprising the following steps: acquiring temperature data of a heat exchanger, obtaining a plurality of IMF component signals of the temperature data according to the temperature data, obtaining the possible degree when any one IMF component signal is used as a reference signal, and obtaining the noise influence degree according to the reference signal and the possible degree when the IMF component signal is used as the reference signal; obtaining an initial state estimated value of any one temperature data according to a plurality of data intervals and noise influence degrees of any one temperature data; and evaluating the heat exchanger according to the initial state estimation value. According to the method and the device, the initial state is accurately estimated according to the change of the obtained data, so that the noise influence of the data can be accurately reflected, and the acquired data is better denoised.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a heat exchanger performance prediction method and system.
Background
Energy efficiency is one of the important issues of concern in modern industry and life. The heat exchanger is used as a key component for energy transmission and conversion, and the performance optimization of the heat exchanger has important significance for reducing energy waste and carbon emission. Many industrial processes, such as chemical, refrigeration, electricity, etc., require the use of heat exchangers to control temperature and energy transfer, and prediction and optimization of heat exchanger performance is critical to improving the efficiency and productivity of the industrial process. Experimental testing is a method of directly measuring the performance of a heat exchanger, which includes using sensors and measuring equipment to monitor parameters such as temperature, flow rate, pressure, etc., to assess the actual performance of the heat exchanger. However, when the sensor is used to collect various data, noise is present in the obtained data due to the sensor itself, such as heat generation, and thus the obtained data needs to be subjected to denoising processing.
In the prior art, kalman filtering is an optimization technique commonly used for denoising and state estimation of data, and is particularly suitable for monitoring and controlling a dynamic system, and can effectively process measurement data containing noise and provide estimation of system state. However, the kalman filter algorithm has high sensitivity to the initial state estimation, and if the initial estimation is inaccurate, the filter may not be stable or converge to the wrong solution.
Disclosure of Invention
In order to solve the problems, the invention provides a heat exchanger performance prediction method and a heat exchanger performance prediction system.
The invention discloses a heat exchanger performance prediction method and a heat exchanger performance prediction system, which adopt the following technical scheme:
an embodiment of the present invention provides a heat exchanger performance prediction method, including the steps of:
collecting temperature data of the heat exchanger, wherein the temperature data comprises water inlet temperature data and water outlet temperature data;
obtaining a plurality of IMF component signals of temperature data according to the temperature data, obtaining the possible degree when any one IMF component signal of any one temperature data is used as a reference signal according to the amplitude difference and fluctuation of any one IMF component signal of any one temperature data, and obtaining the reference signal according to the possible degree when any one IMF component signal of any one temperature data is used as the reference signal;
obtaining the noise influence degree of any one temperature data according to the reference signal, the amplitude difference of each IMF component signal of any one temperature data and the possible degree when the IMF component signal is used as the reference signal;
obtaining the possible degree of the data point in any one temperature data as a segmentation point according to the amplitude of the data point in any one temperature data, obtaining a plurality of data intervals of any one temperature data according to the possible degree of the data point in any one temperature data as a segmentation point, and obtaining an initial state estimated value of any one temperature data according to the plurality of data intervals of any one temperature data and the noise influence degree of the temperature data;
and evaluating the heat exchanger according to the initial state estimated value of any one temperature data.
Further, the obtaining the plurality of IMF component signals of the temperature data according to the temperature data includes the following specific steps:
and decomposing the water inlet temperature data by using an EMD algorithm to obtain a plurality of IMF component signals of the water inlet temperature data, and decomposing the water outlet temperature data by using the EMD algorithm to obtain a plurality of IMF component signals of the water outlet temperature data.
Further, the step of obtaining the probability level of any one IMF component signal of any one temperature data as a reference signal according to the amplitude difference and the fluctuation of any one IMF component signal of any one temperature data includes the following specific steps:
in the method, in the process of the invention,indicate->Seed temperature data->The degree of probability when the IMF component signals are used as reference signals,indicate->Seed temperature data->Variance of the magnitudes of all data points in the IMF component signals, +.>Indicate->Seed temperature data->The (th) of the IMF component signals>Amplitude of data points, +.>Indicate->Seed temperature data->The (th) of the IMF component signals>Amplitude of data points, +.>Indicate->Seed temperature data->The first IMF component signalAbscissa value of data point, +.>Indicate->Seed temperature data->The (th) of the IMF component signals>Abscissa value of data point, +.>Indicate->Seed temperature data->Total number of data points in the IMF component signals, +.>Representing absolute value>An exponential function based on a natural constant is represented.
Further, the reference signal is obtained according to the possible degree when any one IMF component signal of any one temperature data is used as the reference signal, and the specific steps are as follows:
and acquiring the possible degree when each IMF component signal of the water inlet temperature data and the water outlet temperature data is used as a reference signal, and taking the IMF component signal corresponding to the maximum value of the possible degree as the reference signal.
Further, the noise influence degree of any one temperature data is obtained according to the reference signal, the amplitude difference of each IMF component signal of any one temperature data and the possible degree when the IMF component signal is used as the reference signal, and the specific steps include:
in the method, in the process of the invention,indicate->Noise influence degree of seed temperature data, +.>Indicate->Seed temperature data->The (th) of the IMF component signals>Amplitude of data points, +.>Representing the%>Amplitude of data points, +.>Represents the degree of possibility of using the IMF component signal corresponding to the reference signal as the reference signal, < + >>Indicate->Seed temperature data->Individual IMF component messagesThe degree of possibility when the number is used as reference signal, < >>Indicate->Number of component signals of seed temperature data, +.>Representing the total number of data points in the component signal, +.>Indicate->Pearson correlation coefficient between the seed temperature data and the reference signal,representing absolute values.
Further, the method for obtaining the probability degree when the data point in any one temperature data is used as the segmentation point according to the amplitude of the data point in any one temperature data comprises the following specific steps:
in the method, in the process of the invention,indicate->Seed temperature data>The degree of probability when a data point is taken as a segmentation point, < >>Represent the firstSeed temperature data>Amplitude of data points, +.>Indicate->Average amplitude of seed temperature data, +.>The specific acquisition method of (1) is as follows: by->Seed temperature data>The data point is taken as the center, the sequence formed by all data points in the range of the neighborhood radius R is recorded as a neighborhood sequence, and the amplitude of the t data point in the neighborhood sequence is recorded as +.>R is a preset first value, < >>Representing the total number of data points in the neighborhood sequence, +.>Representing absolute value>An exponential function based on a natural constant is represented.
Further, according to the possible degree when the data point in any one temperature data is taken as the segmentation point, a plurality of data intervals of any one temperature data are obtained, and the specific steps are as follows:
presetting a first threshold, namely TH1, if，/>Indicate->Seed temperature data>And taking the ith data point in the a-th temperature data as a segmentation point to obtain all segmentation points in the a-th temperature data, and obtaining a plurality of data sections of the a-th temperature data according to the segmentation points and the a-th temperature data.
Further, the method for obtaining the initial state estimation value of any one temperature data according to the plurality of data intervals of any one temperature data and the noise influence degree of the temperature data comprises the following specific steps:
in the method, in the process of the invention,indicate->Initial state estimate of seed temperature data, +.>Indicate->Noise influence degree of seed temperature data, +.>Indicate->Seed temperature data->All numbers in a data intervalVariance of the amplitude of the data points>Indicate->Index of individual data section->The total number of data sections of the a-th temperature data is represented.
Further, the estimating the heat exchanger according to the initial state estimation value of any one temperature data includes the following specific steps:
denoising the water inlet temperature data by using a Kalman filtering algorithm according to the initial state estimation value of the water inlet temperature data to obtain denoised water inlet temperature data, which is marked as ST1, obtaining denoised water outlet temperature data, which is marked as ST2, and performing noise elimination on the water inlet temperature dataAs a performance evaluation parameter of the heat exchanger, +.>For the numerical mean of all data points in ST1, +.>For the numerical mean of all data points in ST2, +.>The larger the value of (c), the better the cooling effect of the heat exchanger.
The invention also provides a heat exchanger performance prediction system, which comprises a memory and a processor, wherein the processor executes a computer program stored in the memory to realize the steps of the method.
The technical scheme of the invention has the beneficial effects that: when the performance of the heat exchanger is evaluated, the acquired temperature data is influenced by noise, so the temperature data is denoised through a Kalman filtering algorithm, and the Kalman filtering algorithm has higher sensitivity to initial state estimation, so the initial state estimation value is obtained by analyzing the change of the monitored data, and further, when the data is denoised through the Kalman filtering algorithm, the self-adaptive denoising of the data can be accurately performed according to the change degree of the data, so that the denoising effect of the monitored data is better, and further, the performance of the heat exchanger is evaluated more accurately.
When an initial state estimated value is obtained according to monitoring data, firstly, the influence relation between a water inlet and a water outlet is analyzed, then temperature data is decomposed through an EMD algorithm, a reference signal is obtained through the change of a decomposed component signal, and then the noise influence degree of an original signal is obtained by taking the reference signal as a benchmark; because the initial state estimation value is more dependent on the change of the initial data, the method and the device divide the interval of the original temperature data according to the change of the data, and further obtain the initial state estimation value according to the change of the data in different intervals; the obtained initial state estimated value can reflect the accurate change condition of the temperature monitoring data, so that the temperature data is more accurate in denoising, and the influence of noise is eliminated.
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 flowchart illustrating a heat exchanger performance prediction method according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purposes, the following detailed description refers to specific implementation, structure, characteristics and effects of a heat exchanger performance prediction method and system according to the present 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 following specifically describes a specific scheme of a heat exchanger performance prediction method provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a heat exchanger performance prediction method according to an embodiment of the present invention is shown, and the method includes the following steps:
and S001, collecting temperature data of the heat exchanger.
It should be noted that, in order to predict and evaluate the performance of the heat exchanger, in this embodiment, an experimental test method is used to evaluate the performance of the heat exchanger, and in the experimental process, a sensor and an experimental device are required to be arranged to monitor and record each item of data of the heat exchanger in the experimental test process. Because the heat exchanger is a device for transferring heat from a hot fluid to a cold fluid to meet the specified process requirements, the most important data is the temperature data of the water inlet and the water outlet.
Specifically, a temperature sensor is arranged at a water inlet of the heat exchanger to output a temperature value every 0.5 seconds, time sequence data formed by all temperature values acquired in the last 1 hour is used as water inlet temperature data, a temperature value is arranged at a water outlet of the heat exchanger to output a temperature value every 0.5 seconds, and time sequence data formed by all temperature values acquired in the last 1 hour is used as water outlet temperature data.
So far, the water inlet temperature data and the water outlet temperature data are obtained.
Step S002, obtaining a plurality of IMF component signals of the temperature data according to the temperature data, obtaining the possibility degree when any one IMF component signal of any one temperature data is used as a reference signal according to the amplitude difference and fluctuation of any one IMF component signal of any one temperature data, and obtaining the reference signal according to the possibility degree when any one IMF component signal of any one temperature data is used as the reference signal.
In the present embodiment, when evaluating the performance of the heat exchanger, the noise in the acquired temperature data affects the accuracy of the performance evaluation, so the obtained temperature data is subjected to the denoising process. When the temperature data is denoised through the Kalman filtering algorithm, the accuracy of the initial state estimation of the data is directly related to the denoising effect of the subsequent algorithm, so that the initial state of the data is accurately estimated according to the change of the data, the influence degree of the noise on the temperature data can be better reflected, and the algorithm can further have a better denoising effect.
It should be further noted that, when the performance of the heat exchanger is evaluated by an experimental method, the cooling effect of the heat exchanger is reflected by the temperature difference between the water inlet and the water outlet, and the temperature of the water inlet is high, so when the temperature of the water inlet is measured by the temperature sensor, the obtained data is greatly affected by noise due to the high temperature of the temperature sensor; the water temperature of the water outlet is lower, so that the temperature sensing has smaller influence degree on the temperature, and the obtained data has smaller influence degree on noise than the data obtained by the water inlet. Because the cooling degree of the heat exchanger is certain, namely the temperature difference between the water inlet and the water outlet is relatively fixed, when the influence degree of noise on the temperature data of the water inlet is evaluated, the temperature data of the water outlet can be used as a reference, and then the accurate noise influence degree can be obtained according to the change of the data.
Specifically, a plurality of IMF component signals of temperature data are obtained according to the temperature data, and specifically the following steps are included:
the water inlet temperature data is decomposed by using an EMD algorithm to obtain a plurality of IMF component signals of the water inlet temperature data, the water outlet temperature data is decomposed by using the EMD algorithm to obtain a plurality of IMF component signals of the water outlet temperature data, and it should be noted that the EMD algorithm is a known technology, and the embodiment is not repeated.
When the EMD algorithm decomposes the signal, the original signal is decomposed into IMF component signals with different frequencies, and when the temperature data is affected by noise, the frequency change of the data is relatively large, and the IMF component signals obtained by decomposing different noise influence degrees are different in change degree. The degree of noise influence of the water inlet temperature data and the water outlet temperature data is thus obtained from the difference between the IMF component signals of the two temperature data, and thus the reference IMF component signal is first obtained from the variation of each IMF component signal.
Specifically, according to the amplitude difference and fluctuation of any one IMF component signal of any one temperature data, the possible degree when any one IMF component signal of any one temperature data is used as a reference signal is obtained, specifically as follows:
in the method, in the process of the invention,indicate->Seed temperature data->The degree of probability when the IMF component signals are used as reference signals,indicate->Seed temperature data->Variance of the magnitudes of all data points in the IMF component signals, +.>Indicate->Seed temperature data->The (th) of the IMF component signals>Amplitude of data points, +.>Indicate->Seed temperature data->The (th) of the IMF component signals>Amplitude of data points, +.>Indicate->Seed temperature data->The first IMF component signalAbscissa value of data point, +.>Indicate->Seed temperature data->The (th) of the IMF component signals>Abscissa value of data point, +.>Indicate->Seed temperature data->Total number of data points in the IMF component signals, +.>Representing absolute value>Representing an exponential function based on natural constants, the present embodiment employs +.>The model presents an inverse proportional relationship, wherein +.>For model input, the practitioner can set an inverse proportion function according to actual conditions.
It should be noted that the number of the substrates,the variance of the component signal is represented, which represents the degree of fluctuation of the data, because the obtained reference component signal must be a signal less affected by noise when evaluating noise, and therefore the fluctuation of the data is reflected by the variance here, thereby evaluating the noise effect of the component signal. />Representing the amplitude variation of adjacent data points, the larger the amplitude variation degree, the larger the influence degree of the noise possibly affected by the component signal, otherwise, the amplitude of the adjacent data pointsThe smaller the degree of variation, the smaller the degree of influence it is by noise; and the less affected the component signal is by noise, the greater its referenceis, and the greater the likelihood of being a reference signal.
Further, according to the possible degree when any one IMF component signal of any one temperature data is used as a reference signal, the reference signal is obtained, specifically as follows:
and acquiring the possible degree when each IMF component signal of the water inlet temperature data and the water outlet temperature data is used as a reference signal, and taking the IMF component signal corresponding to the maximum value of the possible degree as the reference signal. When the degree of possibility is the maximum, it is explained that the degree of influence of noise is the minimum, and therefore, the component signal is taken as a reference signal, a plurality of component signals exist in both the water inlet temperature data and the water outlet temperature data, and only one of the obtained reference signals is taken as the reference signal of the two data.
Thus, a reference signal is obtained.
Step S003, obtaining the noise influence degree of any one temperature data according to the reference signal, the amplitude difference of each IMF component signal of any one temperature data and the possible degree when the IMF component signal is used as the reference signal.
It should be noted that, step S002 obtains a reference signal, and then obtains the noise influence degree of the different temperature data according to the difference between the obtained reference signal and each component signal.
Specifically, according to the reference signal, the amplitude difference of each IMF component signal of any one temperature data, and the possible degree when the IMF component signal is used as the reference signal, the noise influence degree of any one temperature data is obtained, specifically as follows:
in the method, in the process of the invention,indicate->Noise influence degree of seed temperature data, +.>Indicate->Seed temperature data->The (th) of the IMF component signals>Amplitude of data points, +.>Representing the%>Amplitude of data points, +.>Represents the degree of possibility of using the IMF component signal corresponding to the reference signal as the reference signal, < + >>Indicate->Seed temperature data->The degree of possibility when the IMF component signal is used as reference signal,/for each of the IMF component signals>Indicate->Number of component signals of seed temperature data, +.>Representation ofThe total number of data points in the component signal, it should be noted that the total number of data points in the IMF component signal and the reference signal are equal,indicate->Pearson correlation coefficient between seed temperature data and reference signal, +.>Representing absolute values.
It should be noted that the number of the substrates,indicate->Seed temperature data>The (th) in the individual component signals>Data point and reference signal +.>The larger the difference in amplitude between the data points, the more>The greater the degree of difference between the individual component signals and the reference signal, the greater the degree of noise impact it is subjected to. />The larger the difference of the characteristic values between the component signals and the reference signals, the larger the difference degree is, which indicates that the fluctuation of the data is also larger. Pearson correlation data represents the correlation between two data sequences, the greater the correlation, which indicates that the two data sequences vary more similarly, and thus are inversely related.
Thus, the noise influence degree of the temperature data is obtained.
Step S004, obtaining the possible degree of the data point in any one temperature data as the segmentation point according to the amplitude of the data point in any one temperature data, obtaining a plurality of data intervals of any one temperature data according to the possible degree of the data point in any one temperature data as the segmentation point, and obtaining the initial state estimated value of any one temperature data according to the plurality of data intervals of any one temperature data and the noise influence degree of the temperature data.
The first obtained from the aboveThe noise influence degree of the temperature data is estimated, and then the initial state is estimated, wherein the initial state estimation approaches to the actual system state, and then the filter can adapt to the behavior of the system more quickly, so that the error of the state estimation is reduced. Otherwise, if the initial estimation is far from the actual state, the filter may take longer to converge to the accurate state estimation, and the accurate initial state estimation may significantly improve the performance of the kalman filtering algorithm, so that the kalman filtering algorithm converges to the accurate state estimation more quickly, reducing estimation errors, and improving the reliability of the estimation. The initial state is estimated based on the degree of noise influence of the different signals obtained as described above.
In order to accurately reflect the local change of the data, the data is divided according to the change, the influence degree of noise is different in each data section, the influence degree of the data is different in each data section, and the influence degree of the data section which is closer to an initial point is larger on the initial state, wherein the initial point is the temperature data and can only be the first data point, so that the data section is divided according to the change of the original data.
Specifically, the possible degree when the data point in any one temperature data is taken as the segmentation point is obtained according to the amplitude of the data point in any one temperature data, and the method specifically comprises the following steps:
in the method, in the process of the invention,indicate->Seed temperature data>The degree of probability when a data point is taken as a segmentation point, < >>Represent the firstSeed temperature data>Amplitude of data points, +.>Indicate->Average amplitude of seed temperature data, +.>The specific acquisition method of (1) is as follows: by->Seed temperature data>The data point is taken as the center, the sequence formed by all data points in the range of the neighborhood radius R is recorded as a neighborhood sequence, and the amplitude of the t data point in the neighborhood sequence is recorded as +.>R is a preset first value, in this embodiment, r=5 is taken as an example, and ++>Representing the total number of data points in the neighborhood sequence, +.>Representing absolute value>Representing an exponential function based on natural constants, the present embodiment employs +.>The model presents an inverse proportional relationship, wherein +.>For model input, the practitioner can set an inverse proportion function according to actual conditions. It should be noted that when the selected center point is near the leftmost or rightmost side in the temperature data, it will result in exceeding +.>The boundary of the seed temperature data, in this case, the present embodiment will exceed the +.>Interpolation of the boundary part of the seed temperature data, i.e. +.>Filling data at the leftmost end and the rightmost end in the temperature data.
It should be noted that the number of the substrates,indicate->The smaller the difference between the data point and the average amplitude of the data sequence, the smaller the value of the difference, which indicates that the fluctuation degree of the data point is, the less the influence degree of noise on the data point is likely to be, and therefore the greater the possibility degree of taking the data point as a division point is; />Indicate->The difference between a data point and its neighborhood data point is because the smaller the degree of variation of the overall data point over a data interval, the greater the likelihood that the data point will be a data segment point.
Further, according to the possible degree when the data point in any one temperature data is taken as the segmentation point, a plurality of data intervals of any one temperature data are obtained, and the specific steps are as follows:
a first threshold is preset, denoted as TH1, and this embodiment is described by th1=0.84, ifAnd taking the ith data point in the a-th temperature data as a segmentation point, acquiring all segmentation points in the a-th temperature data, and obtaining a plurality of data sections of the a-th temperature data according to the segmentation points and the a-th temperature data.
The above-mentioned several data intervals of any one temperature data are obtained, and then the initial state estimation value is obtained according to the change of each data interval.
Specifically, according to a plurality of data intervals of any one temperature data and the noise influence degree of the temperature data, an initial state estimated value of any one temperature data is obtained, and specifically the method comprises the following steps:
in the method, in the process of the invention,indicate->Initial state estimate of seed temperature data, +.>Indicate->Noise influence degree of seed temperature data, +.>Indicate->Seed temperature data->Variance of the magnitudes of all data points in the data interval, +.>Indicate->Index of data section, it should be noted that +.>The index of each data interval is the value of j, < >>The total number of data sections of the a-th temperature data is represented.
The variance represents the degree of fluctuation of the data section, and the larger the degree of fluctuation is, the larger the degree of influence of noise is, and therefore the change of the data of each data section is reflected according to the degree of fluctuation of each data section, multiplied byThe data interval closer to the initial point is more influenced on the initial state, wherein the initial point is the first data point of the temperature data, the data interval closer to the initial point is weighted according to the position of each data interval close to the initial point, the weight of the data interval is greater, and then the average value of all the data intervals is calculated.
Thus, an initial state estimated value of any one of the temperature data is obtained.
And step S005, evaluating the heat exchanger according to the initial state estimated value of any one of the temperature data.
It should be noted that, the obtained initial state estimation values of different temperature data may utilize a kalman filtering algorithm to perform denoising processing on the temperature data, and then obtain the temperature data of the water inlet and the water outlet after denoising, so as to evaluate the performance of the heat exchanger according to the temperature data of the water inlet and the water outlet.
Specifically, denoising the water inlet temperature data by using a Kalman filtering algorithm according to the initial state estimation value of the water inlet temperature data to obtain denoised water inlet temperature data, which is marked as ST1, obtaining denoised water outlet temperature data, which is marked as ST2, and performing denoising on the water inlet temperature dataAs a performance evaluation parameter of the heat exchanger, +.>For the numerical mean of all data points in ST1, +.>For the numerical mean of all data points in ST2, +.>The larger the value of (c), the better the cooling effect of the heat exchanger. It should be noted that, according to the prior art that the Kalman filtering algorithm is used to denoise the water inlet temperature data according to the initial state estimation value of the water inlet temperature data, the embodiment is not described in detail, the water inlet temperature of the heat exchanger is greater than the water outlet temperature, and the heat exchange efficiency of the heat exchanger is mainly represented by the temperature difference between the water inlet and the water outlet, so that the cooling effect of the heat exchanger is reflected according to the mean value difference of the denoised temperature data.
Through the steps, the heat exchanger performance prediction method is completed.
Another embodiment of the present invention provides a heat exchanger performance prediction system comprising a memory and a processor that, when executing a computer program stored in the memory, performs the following operations:
collecting temperature data of the heat exchanger, wherein the temperature data comprises water inlet temperature data and water outlet temperature data; obtaining a plurality of IMF component signals of temperature data according to the temperature data, obtaining the possible degree when any one IMF component signal of any one temperature data is used as a reference signal according to the amplitude difference and fluctuation of any one IMF component signal of any one temperature data, and obtaining the reference signal according to the possible degree when any one IMF component signal of any one temperature data is used as the reference signal; obtaining the noise influence degree of any one temperature data according to the reference signal, the amplitude difference of each IMF component signal of any one temperature data and the possible degree when the IMF component signal is used as the reference signal; obtaining the possible degree of the data point in any one temperature data as a segmentation point according to the amplitude of the data point in any one temperature data, obtaining a plurality of data intervals of any one temperature data according to the possible degree of the data point in any one temperature data as a segmentation point, and obtaining an initial state estimated value of any one temperature data according to the plurality of data intervals of any one temperature data and the noise influence degree of the temperature data; and evaluating the heat exchanger according to the initial state estimated value of any one temperature data.
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 (10)
1. A method for predicting heat exchanger performance, the method comprising the steps of:
collecting temperature data of the heat exchanger, wherein the temperature data comprises water inlet temperature data and water outlet temperature data;
obtaining a plurality of IMF component signals of temperature data according to the temperature data, obtaining the possible degree when any one IMF component signal of any one temperature data is used as a reference signal according to the amplitude difference and fluctuation of any one IMF component signal of any one temperature data, and obtaining the reference signal according to the possible degree when any one IMF component signal of any one temperature data is used as the reference signal;
obtaining the noise influence degree of any one temperature data according to the reference signal, the amplitude difference of each IMF component signal of any one temperature data and the possible degree when the IMF component signal is used as the reference signal;
obtaining the possible degree of the data point in any one temperature data as a segmentation point according to the amplitude of the data point in any one temperature data, obtaining a plurality of data intervals of any one temperature data according to the possible degree of the data point in any one temperature data as a segmentation point, and obtaining an initial state estimated value of any one temperature data according to the plurality of data intervals of any one temperature data and the noise influence degree of the temperature data;
and evaluating the heat exchanger according to the initial state estimated value of any one temperature data.
2. The method for predicting heat exchanger performance according to claim 1, wherein the obtaining the plurality of IMF component signals of the temperature data according to the temperature data comprises the specific steps of:
and decomposing the water inlet temperature data by using an EMD algorithm to obtain a plurality of IMF component signals of the water inlet temperature data, and decomposing the water outlet temperature data by using the EMD algorithm to obtain a plurality of IMF component signals of the water outlet temperature data.
3. The heat exchanger performance prediction method according to claim 1, wherein the obtaining the probability degree of any one IMF component signal of any one temperature data as the reference signal according to the amplitude difference and fluctuation of any one IMF component signal of any one temperature data comprises the following specific steps:
in the method, in the process of the invention,indicate->Seed temperature data->The degree of possibility when the IMF component signal is used as reference signal,/for each of the IMF component signals>Indicate->Seed temperature data->Variance of the magnitudes of all data points in the IMF component signals, +.>Indicate->Seed temperature data->The (th) of the IMF component signals>Amplitude of data points, +.>Indicate->Seed temperature data->The (th) of the IMF component signals>Amplitude of data points, +.>Indicate->Seed temperature data->The (th) of the IMF component signals>Abscissa value of data point, +.>Indicate->Seed temperature data->The (th) of the IMF component signals>Abscissa value of data point, +.>Indicate->Seed temperature data->Total number of data points in the IMF component signals, +.>Representing absolute value>An exponential function based on a natural constant is represented.
4. The heat exchanger performance prediction method according to claim 1, wherein the obtaining the reference signal according to the possible degree of any one IMF component signal of any one temperature data as the reference signal includes the following specific steps:
and acquiring the possible degree when each IMF component signal of the water inlet temperature data and the water outlet temperature data is used as a reference signal, and taking the IMF component signal corresponding to the maximum value of the possible degree as the reference signal.
5. The method for predicting performance of a heat exchanger according to claim 1, wherein the obtaining the noise influence degree of any one temperature data according to the reference signal, the amplitude difference of each IMF component signal of any one temperature data and the possible degree of the IMF component signal as the reference signal comprises the following specific steps:
in the method, in the process of the invention,indicate->Noise influence degree of seed temperature data, +.>Indicate->Seed temperature data->The (th) of the IMF component signals>Amplitude of data points, +.>Representing the%>Amplitude of data points, +.>Represents the degree of possibility of using the IMF component signal corresponding to the reference signal as the reference signal, < + >>Indicate->Seed temperature data->The degree of possibility when the IMF component signal is used as reference signal,/for each of the IMF component signals>Indicate->Number of component signals of seed temperature data, +.>Representing the total number of data points in the component signal, +.>Indicate->Pearson correlation coefficient between seed temperature data and reference signal, +.>Representing absolute values.
6. The method for predicting the performance of a heat exchanger according to claim 1, wherein the step of obtaining the probability of using the data point in any one of the temperature data as the segment point according to the magnitude of the data point in any one of the temperature data comprises the following specific steps:
in the method, in the process of the invention,indicate->Seed temperature data>The degree of probability when a data point is taken as a segmentation point, < >>Indicate->Seed temperature data>Amplitude of data points, +.>Indicate->Average amplitude of seed temperature data, +.>The specific acquisition method of (1) is as follows: by->Seed temperature data>The data point is taken as the center, the sequence formed by all data points in the range of the neighborhood radius R is recorded as a neighborhood sequence, and the amplitude of the t data point in the neighborhood sequence is recorded as +.>R is a preset first value, < >>Representing the total number of data points in the neighborhood sequence, +.>Representing absolute value>An exponential function based on a natural constant is represented.
7. The method for predicting the performance of a heat exchanger according to claim 1, wherein the obtaining a plurality of data intervals of any one temperature data according to the possible degree when the data points of any one temperature data are used as the segmentation points comprises the following specific steps:
presetting a first threshold, namely TH1, if，/>Indicate->Seed temperature data>And taking the ith data point in the a-th temperature data as a segmentation point to obtain all segmentation points in the a-th temperature data, and obtaining a plurality of data sections of the a-th temperature data according to the segmentation points and the a-th temperature data.
8. The method for predicting the performance of a heat exchanger according to claim 1, wherein the obtaining the initial state estimation value of any one temperature data according to the plurality of data intervals of any one temperature data and the noise influence degree of the temperature data comprises the following specific steps:
in the method, in the process of the invention,indicate->Initial state estimate of seed temperature data, +.>Indicate->Noise influence degree of seed temperature data, +.>Indicate->Seed temperature data->Variance of the magnitudes of all data points in the data interval, +.>Indicate->Index of individual data section->The total number of data sections of the a-th temperature data is represented.
9. The heat exchanger performance prediction method according to claim 1, wherein the estimating the heat exchanger according to the initial state estimation value of any one of the temperature data comprises the following specific steps:
denoising the water inlet temperature data by using a Kalman filtering algorithm according to the initial state estimation value of the water inlet temperature data to obtain denoised water inlet temperature data, which is marked as ST1, obtaining denoised water outlet temperature data, which is marked as ST2, and performing noise elimination on the water inlet temperature dataAs a performance evaluation parameter of the heat exchanger, +.>For the numerical mean of all data points in ST1, +.>For the numerical mean of all data points in ST2, +.>The larger the value of (c), the better the cooling effect of the heat exchanger.
10. A heat exchanger performance prediction system comprising a memory and a processor, wherein the processor executes a computer program stored in the memory to implement the steps of a heat exchanger performance prediction method as claimed in any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311475356.6A CN117195007B (en) | 2023-11-08 | 2023-11-08 | Heat exchanger performance prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311475356.6A CN117195007B (en) | 2023-11-08 | 2023-11-08 | Heat exchanger performance prediction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117195007A true CN117195007A (en) | 2023-12-08 |
| CN117195007B CN117195007B (en) | 2024-02-06 |
Family
ID=88987309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311475356.6A Active CN117195007B (en) | 2023-11-08 | 2023-11-08 | Heat exchanger performance prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117195007B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117494028A (en) * | 2023-12-29 | 2024-02-02 | 山东国华科技发展有限公司 | Energy storage data anomaly detection method and system for energy storage power station |
| CN117493778A (en) * | 2024-01-03 | 2024-02-02 | 河北雄安睿天科技有限公司 | On-line monitoring method and system for associated data of water supply and drainage equipment |
| CN117540220A (en) * | 2024-01-09 | 2024-02-09 | 巨洋神州科技集团有限公司 | Near-zero carbon park source network load matching method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111983489A (en) * | 2020-08-18 | 2020-11-24 | 华中科技大学鄂州工业技术研究院 | Method for detecting discharge fault of SOFC (solid oxide Fuel cell) system with transition mode |
| CN116304751A (en) * | 2023-05-23 | 2023-06-23 | 天佑京铁轨道技术有限公司 | Operation data processing method for overhauling motor train unit components |
| CN116644281A (en) * | 2023-07-27 | 2023-08-25 | 东营市艾硕机械设备有限公司 | Yacht hull deviation detection method |
-
2023
- 2023-11-08 CN CN202311475356.6A patent/CN117195007B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111983489A (en) * | 2020-08-18 | 2020-11-24 | 华中科技大学鄂州工业技术研究院 | Method for detecting discharge fault of SOFC (solid oxide Fuel cell) system with transition mode |
| CN116304751A (en) * | 2023-05-23 | 2023-06-23 | 天佑京铁轨道技术有限公司 | Operation data processing method for overhauling motor train unit components |
| CN116644281A (en) * | 2023-07-27 | 2023-08-25 | 东营市艾硕机械设备有限公司 | Yacht hull deviation detection method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117494028A (en) * | 2023-12-29 | 2024-02-02 | 山东国华科技发展有限公司 | Energy storage data anomaly detection method and system for energy storage power station |
| CN117494028B (en) * | 2023-12-29 | 2024-04-19 | 山东国华科技发展有限公司 | Energy storage data anomaly detection method and system for energy storage power station |
| CN117493778A (en) * | 2024-01-03 | 2024-02-02 | 河北雄安睿天科技有限公司 | On-line monitoring method and system for associated data of water supply and drainage equipment |
| CN117493778B (en) * | 2024-01-03 | 2024-03-22 | 河北雄安睿天科技有限公司 | On-line monitoring method and system for associated data of water supply and drainage equipment |
| CN117540220A (en) * | 2024-01-09 | 2024-02-09 | 巨洋神州科技集团有限公司 | Near-zero carbon park source network load matching method and system |
| CN117540220B (en) * | 2024-01-09 | 2024-04-05 | 巨洋神州科技集团有限公司 | Near-zero carbon park source network load matching method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117195007B (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117195007B (en) | Heat exchanger performance prediction method and system | |
| WO2022068155A1 (en) | State estimation method for system under intermittent anomaly measurement detection | |
| CN113671917B (en) | Detection method, system and equipment for abnormal state of multi-modal industrial process | |
| CN106971027B (en) | Water chilling unit fault feature selection method based on DR-BN model | |
| CN117167903A (en) | Artificial intelligence-based foreign matter fault detection method for heating ventilation equipment | |
| CN118211082B (en) | Oil filter element residual life prediction method and system based on data analysis | |
| WO2018181120A1 (en) | Information processing device, information processing method, and program | |
| CN118072994A (en) | Nuclear island equipment cooling water heat exchanger health state monitoring and fault diagnosis method | |
| CN117313014B (en) | Real-time monitoring and early warning method for abnormal energy consumption data of kiln operation | |
| CN117288348B (en) | Bus duct temperature measurement method and system | |
| US20230280240A1 (en) | Abnormality diagnosis device and abnormality diagnosis method | |
| CN117611031B (en) | Real-time monitoring method and system for logistics temperature of cold chain Internet of things | |
| CN116738859A (en) | Online nondestructive life assessment method and system for copper pipe | |
| CN116297013B (en) | Monitoring method and system for viscosity fluctuation of hydraulic oil | |
| CN117131977A (en) | Runoff forecasting sample set partitioning method based on misjudgment risk minimum criterion | |
| CN107083951B (en) | Oil and gas well monitoring method and device | |
| CN118499705B (en) | Hierarchical early warning method, device, equipment and medium for leakage event of water supply network | |
| CN113266449A (en) | Method and system for predicting air leakage situation in front of aftertreatment system | |
| CN118090078B (en) | Leakage online monitoring method for closed circulation water cooling system | |
| CN103759894B (en) | A kind of detection method of heat exchanger leakage current and system | |
| CN117554109B (en) | Intelligent monitoring method and system for fault data information of heat exchanger | |
| CN118426393B (en) | Equipment operation data early warning method and system based on industrial personal computer | |
| CN118427537B (en) | Intelligent data acquisition method and system for semiconductor equipment | |
| CN118656580A (en) | Sample cleaning method for fan icing prediction model training | |
| CN118465475A (en) | Ultrahigh frequency partial discharge stability test method and device for hydraulic generator |
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 |