Control method and system for heat exchanger of flue gas waste heat system of gas-fired boiler

Abstract

The invention provides a control method and system for heat exchangers of a flue gas waste heat system of a gas-fired boiler, and the method comprises the steps: connecting a plurality of heat exchangers to a tail flue of the gas-fired boiler, and installing a plurality of sensors on each heat exchanger; according to the collected real-time operation data of the multiple heat exchangers, the concentration trend and the dispersion degree are calculated, and the real-time operation data are divided into multiple sets of data; fusing each group of data, calling real-time inlet and outlet temperatures of cold and hot fluids of the heat exchangers from the fused data, and calculating the real-time heat exchange efficiency of each heat exchanger; the optimal operation state of each heat exchanger is determined through an optimal operation state analysis model; and similarity calculation is conducted on the historical operation data and the real-time operation data, and the heat exchanger to be adjusted is determined and adjusted. According to the method, the real-time heat exchange efficiency of the heat exchanger can be accurately calculated, intelligent adjustment of the heat exchanger is achieved through similarity judgment, and the accuracy and real-time performance of heat exchanger control are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of heat exchanger control, and particularly relates to a control method and system of a heat exchanger of a flue gas waste heat system of a gas-fired boiler. BACKGROUND

[0002] At present, in the flue gas waste heat recovery and utilization technology of a gas-fired boiler, a heat exchanger is a commonly used device. According to the difference in heat exchange modes, the heat exchanger can be divided into a direct contact heat exchange type and an indirect contact heat exchange type. Scientific and reasonable control of the heat exchanger is a key step to improve the flue gas waste heat recovery and utilization efficiency of the boiler.

[0003] However, the control mode of the heat exchanger of the boiler flue gas waste heat system in the related art has some deficiencies. Since the control mode of the heat exchanger of the boiler waste heat system is not intelligent enough, the real-time heat exchange efficiency of the heat exchanger cannot be accurately calculated, and the heat exchanger cannot be adjusted in real time according to the actual working condition, resulting in defects such as energy waste and poor system stability. SUMMARY

[0004] The present application aims to at least solve one of the technical problems in the related art to some extent.

[0005] To this end, a first object of the present application is to provide a control method of a heat exchanger of a flue gas waste heat system of a gas-fired boiler. The method can accurately calculate the real-time heat exchange efficiency of the heat exchanger by analyzing the overall distribution and dispersion of the real-time operation data of the heat exchanger, and realize intelligent adjustment of the heat exchanger through similarity judgment, thereby improving the accuracy and real-time performance of the control of the heat exchanger. The control method of the heat exchanger of the boiler waste heat system is not intelligent enough, cannot accurately calculate the real-time heat exchange efficiency of the heat exchanger, and cannot be adjusted in real time according to the actual working condition.

[0006] A second object of the present application is to provide a control system of a heat exchanger of a flue gas waste heat system of a gas-fired boiler.

[0007] A third object of the present application is to provide an electronic device.

[0008] A fourth object of the present application is to provide a non-transitory computer readable storage medium.

[0009] To achieve the above objects, a first aspect of the present application provides a control method of a heat exchanger of a flue gas waste heat system of a gas-fired boiler, comprising the following steps:

[0010] A plurality of heat exchangers are connected to the tail flue of the gas-fired boiler, and a plurality of types of sensors are installed on each of the heat exchangers to collect real-time operation data of each of the heat exchangers, wherein the real-time operation data includes real-time temperatures of fluid inlets and outlets;

[0011] According to the real-time operation data of the plurality of heat exchangers, a concentration trend and a dispersion degree of each of the heat exchangers are calculated, and the real-time operation data of the plurality of heat exchangers are divided into different types of groups of data based on the concentration trend and the dispersion degree;

[0012] Each group of data is fused respectively to obtain fused groups of heat exchanger real-time operation data, and the real-time temperatures of the hot fluid inlet and outlet and the real-time temperatures of the cold fluid inlet and outlet corresponding to each of the heat exchangers are called from the fused groups of heat exchanger real-time operation data to calculate the real-time heat exchange efficiency of each of the heat exchangers respectively;

[0013] Heat exchanger historical operation data are called from a database, a preset neural network model is trained into a heat exchanger optimal operation state analysis model based on the historical operation data, and the optimal operation state of each of the heat exchangers is determined through the optimal operation state analysis model;

[0014] The historical operation data corresponding to the optimal operation state of each of the heat exchangers are compared with the fused real-time operation data in terms of similarity, and a heat exchanger to be adjusted is determined based on the similarity, and the heat exchanger to be adjusted is adjusted to make the real-time heat exchange efficiency of the adjusted heat exchanger reach an optimal state.

[0015] Optionally, the concentration trend and the dispersion degree of each of the heat exchangers are calculated by calculating the average value of the real-time operation data of each of the heat exchangers, and for each of the heat exchangers, the variance of the real-time operation data is calculated based on the average value respectively, and the variance is taken as the concentration trend; the concentration trend is assigned a concentration trend identification code; each real-time operation data of each heat exchanger is paired with the data corresponding to other heat exchangers in the plurality of heat exchangers one by one to form a plurality of data pairs; the absolute value of the difference of each of the data pairs is calculated, and the cumulative sum of the absolute values of the plurality of data pairs is calculated, and the cumulative sum is taken as the dispersion degree; and the dispersion degree is assigned a dispersion identification code.

[0016] Optionally, the variance of the real-time operation data is calculated by the following formula:

[0017]

[0018] wherein D is the variance, n is the number of heat exchanger real-time operation data, xi is the value of the i th real-time operation data, and a is the average value of the heat exchanger real-time operation data. i

[0019] ​Optionally, the dividing the real-time operation data of the plurality of heat exchangers into different types of groups of data comprises: calling a normalization standard and a plurality of heat exchanger operation sample data from a database, and obtaining a range interval of a central tendency ratio and a range interval of a dispersion degree ratio in the data normalization standard; calculating a mean value of the central tendency of the plurality of heat exchanger operation sample data, and respectively calculating a first ratio of the central tendency of each of the heat exchangers to the mean value of the central tendency; calculating a mean value of the dispersion degree of the plurality of heat exchanger operation sample data, and respectively calculating a second ratio of the dispersion degree of each of the heat exchangers to the mean value of the dispersion degree; for each of the heat exchangers, comparing the first ratio with a preset first threshold value and comparing the second ratio with a preset second threshold value, judging whether the central tendency belongs to the range interval of the central tendency ratio and whether the dispersion degree belongs to the range interval of the dispersion degree ratio, and performing data group division based on the judgment result.

[0020] Optionally, the judging whether the central tendency belongs to the range interval of the central tendency ratio and whether the dispersion degree belongs to the range interval of the dispersion degree ratio comprises: in the case that the first ratio is greater than or equal to the first threshold value, determining that the central tendency belongs to the range interval of the central tendency ratio; in the case that the second ratio is greater than or equal to the second threshold value, determining that the dispersion degree belongs to the range interval of the dispersion degree ratio; the performing data group division based on the judgment result comprises: dividing real-time operation data belonging to the range interval of the central tendency ratio and belonging to the range interval of the dispersion degree ratio into first data; dividing real-time operation data not belonging to the range interval of the central tendency ratio and not belonging to the range interval of the dispersion degree ratio into second data; the respectively fusing each group of data to obtain a plurality of groups of fused heat exchanger real-time operation data comprises: respectively fusing the first data and the second data to obtain first fused data and second fused data.

[0021] Optionally, the real-time heat exchange efficiency of each of the heat exchangers is calculated by the following formula:

[0022]

[0023] wherein, ΔT M is the real-time heat exchange efficiency of the heat exchanger, T1 is the called real-time temperature of the hot fluid inlet, T2 is the called real-time temperature of the hot fluid outlet, t1 is the called real-time temperature of the cold fluid inlet, and t2 is the called real-time temperature of the cold fluid outlet.

[0024] Optionally, the training of the preset neural network model into the heat exchanger optimal operation state analysis model based on the historical operation data comprises: constructing an initial heat exchanger optimal operation state analysis model based on a feedforward neural network; labeling and dividing the historical operation data based on machine learning to obtain a training set, a verification set and a test set; and performing supervised training on the initial heat exchanger optimal state operation analysis model by using the training set, the verification set and the test set until the model output meets the requirements.

[0025] Optionally, the similarity calculation is performed by the following formula:

[0026]

[0027] wherein S i is the similarity of the i-th feature of the heat exchanger real-time operation data and the historical operation data corresponding to the heat exchanger optimal operation state, w ij is the j-th feature index value of the i-th feature of the heat exchanger real-time operation data, v ij is the j-th feature index value of the i-th feature of the historical operation data corresponding to the heat exchanger optimal operation state, and n is the total number of index values of the i-th feature; and the determination of the heat exchanger to be adjusted based on the similarity comprises: comparing the similarity value of any heat exchanger calculated with a similarity threshold value; and determining the any heat exchanger as the heat exchanger to be adjusted in the case that the similarity value is less than the similarity threshold value.

[0028] To achieve the above purpose, a second aspect of the present application further proposes a control system of a heat exchanger of a flue gas waste heat system of a gas-fired boiler, comprising the following modules:

[0029] A collection module is configured to connect a plurality of heat exchangers on a tail flue of a gas-fired boiler, and install a plurality of types of sensors on each of the heat exchangers to collect real-time operation data of each of the heat exchangers, wherein the real-time operation data comprises real-time temperatures of fluid inlets and outlets;

[0030] A division module is configured to calculate a concentration tendency and a dispersion degree of each of the heat exchangers according to the real-time operation data of the plurality of heat exchangers, and divide the real-time operation data of the plurality of heat exchangers into a plurality of groups of data of different types based on the concentration tendency and the dispersion degree;

[0031] A calculation module is configured to fuse each group of data respectively to obtain a plurality of groups of fused heat exchanger real-time operation data, and retrieve real-time temperatures of hot fluid inlets and outlets and real-time temperatures of cold fluid inlets and outlets corresponding to each of the heat exchangers from the plurality of groups of fused heat exchanger real-time operation data to calculate real-time heat exchange efficiencies of each of the heat exchangers respectively;

[0032] The determining module is configured to call heat exchanger historical operation data from a database, train a preset neural network model into a heat exchanger optimal operation state analysis model based on the historical operation data, and determine the optimal operation state of each heat exchanger through the optimal operation state analysis model.

[0033] The adjusting module is configured to perform similarity calculation on the historical operation data corresponding to the optimal operation state of each heat exchanger and the fused real-time operation data, determine a heat exchanger to be adjusted based on the similarity, and adjust the heat exchanger to be adjusted so that the real-time heat exchange efficiency of the adjusted heat exchanger reaches an optimal state.

[0034] To achieve the above purpose, the third aspect of the present application further provides an electronic device, comprising: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the control method of the heat exchanger of the flue gas waste heat system of the gas-fired boiler according to any one of the first aspect.

[0035] To achieve the above purpose, the fourth aspect of the present application further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the control method of the heat exchanger of the flue gas waste heat system of the gas-fired boiler according to any one of the first aspect.

[0036] The technical scheme provided by the embodiments of the present application at least brings the following beneficial effects: the present application is connected to the heat exchanger on the tail flue of the boiler, and by installing various types of sensors on the heat exchanger, the running data of the heat exchanger can be monitored in real time, including the real-time temperature of the fluid inlet and outlet and other key information, which helps to discover potential operation problems in time and prevent accidents. Then, the centralized trend and dispersion degree of the real-time operation data are calculated, which helps to understand the overall distribution and dispersion of the data and provides a basis for subsequent data analysis and optimization. By accurately calculating the real-time heat exchange efficiency of the heat exchanger, the performance of the heat exchanger can be intuitively understood, which provides a direct basis for optimizing the heat exchange efficiency. Finally, based on the heat exchanger optimal state operation analysis model, whether the heat exchanger needs to be adjusted is determined through similarity calculation, which realizes intelligent adjustment of the heat exchanger, helps the heat exchanger to always maintain in the optimal working state, improves the heat exchange efficiency of the heat exchanger, and reduces energy consumption. Thus, it helps to improve the stability and reliability of the heat exchange system of the tail flue of the boiler, and also helps to ensure the safe and stable operation of the boiler system and prolong the service life of the equipment. Therefore, the present application improves the accuracy, real-time performance and intelligence of the control of the heat exchanger.

[0037] Additional aspects and advantages of the present application will be made apparent from the following description, which proceeds with reference to the accompanying drawings, wherein: BRIEF DESCRIPTION OF DRAWINGS

[0038] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, taken in conjunction with the accompanying drawings, in which:

[0039] Figure 1 A flow chart of a control method of a gas boiler flue gas waste heat system heat exchanger according to an embodiment of the present application;

[0040] Figure 2 A flow chart of a control method of a gas boiler flue gas waste heat system heat exchanger according to an embodiment of the present application;

[0041] Figure 3 A flow chart of a control method of a gas boiler flue gas waste heat system heat exchanger according to an embodiment of the present application;

[0042] Figure 4 A flow chart of a control method of a gas boiler flue gas waste heat system heat exchanger according to an embodiment of the present application; DETAILED DESCRIPTION

[0043] Embodiments of the present application are described in detail below with reference to the attached drawings, which show by way of example, embodiments in which like reference numerals refer to like elements or elements having similar functions. The embodiments described below are exemplary and are intended to provide examples of the present application, and are not intended to limit the present application.

[0044] A control method and system of a gas boiler flue gas waste heat system heat exchanger according to an embodiment of the present application are described below with reference to the accompanying drawings.

[0045] Figure 1 A flow chart of a control method of a gas boiler flue gas waste heat system heat exchanger according to an embodiment of the present application is shown in FIG. 1, which includes the following steps: Figure 1

[0046] Step S101, connecting a plurality of heat exchangers to the tail flue of the gas boiler, and installing a plurality of types of sensors on each heat exchanger to collect real-time operating data of each heat exchanger, wherein the real-time operating data includes fluid inlet and outlet real-time temperature.

[0047] ​Specifically, the application is first communicated on the boiler tail flue heat exchanger, the number of heat exchanger can be determined according to the scale of the boiler, purpose, heat efficiency requirement and waste heat recovery specific target and a variety of actual factors. Then, a variety of sensors are installed on each heat exchanger, such as temperature sensor, displacement sensor and pressure sensor. The installed sensor is used to monitor the real-time running data of the heat exchanger. Among them, the real-time running data includes fluid inlet and outlet real-time temperature, and can also include voltage, current and temperature data under the working state of the heat exchanger.

[0048] Step S102, according to the real-time running data of the plurality of heat exchangers, the concentration tendency and the dispersion degree of each heat exchanger are calculated, and the real-time running data of the plurality of heat exchangers are divided into different types of groups of data based on the concentration tendency and the dispersion degree.

[0049] Specifically, the concentration tendency and the dispersion degree of each heat exchanger are calculated by using the collected real-time running data corresponding to each heat exchanger, so that the overall distribution and dispersion of the running data of each heat exchanger can be calculated.

[0050] In order to more clearly illustrate the specific implementation process of calculating the concentration tendency and the dispersion degree, the following will be exemplarily described by using a calculation method proposed in the embodiment. Figure 2 The flow chart of the calculation method of the concentration tendency and the dispersion degree proposed in the embodiment is shown in Figure 2 The method comprises the following steps:

[0051] Step S201, the average value of the real-time running data of each heat exchanger is calculated, and for each heat exchanger, the variance of the real-time running data is calculated based on the average value, and the variance is taken as the concentration tendency.

[0052] Specifically, for each heat exchanger, the average value of the real-time running data corresponding to each heat exchanger is calculated, and then based on the average value, the variation degree of the data is calculated by using the formula of variance, that is, the variance is calculated, and the concentration tendency of the data can be measured by the calculated variance.

[0053] In the embodiment, the variance of the real-time running data of a certain heat exchanger can be calculated by the following formula:

[0054]

[0055] Wherein, D is the variance, n is the number of heat exchanger real-time running data, x i is the value of the i th real-time running data, a is the average value of the heat exchanger real-time running data.

[0056] Thus, each heat exchanger can be calculated according to the above-mentioned manner. The embodiment utilizes a set of data of each heat exchanger to calculate the concentration trend of each heat exchanger, which can ensure the independence of the data.

[0057] In order to facilitate the understanding of the implementation process of each step in the calculation method of the embodiment, the following examples of implementing each step in the embodiment by python language code are described. The python code used in this step is as follows:

[0058] “import numpy as np

[0059] def calculate_statistics(data):

[0060] #S201: Calculate mean and variance

[0061] mean = np.mean(data)

[0062] variance = np.var(data)”.

[0063] Step S202, assign a concentration trend identifier to the concentration trend.

[0064] Specifically, in order to facilitate subsequent calculation, a unique identifier, i.e. a concentration trend identifier, is assigned to the calculated concentration trend.

[0065] The python code used in this step is as follows (using “mean” and “variance” as examples):

[0066] concentration_trend_idf = “mean_{mean:.2f}_variance_{variance:.2f}”.

[0067] Step S203, each real-time running data of each heat exchanger is paired with the corresponding data of other heat exchangers in the plurality of heat exchangers to form a plurality of data pairs.

[0068] Specifically, for each heat exchanger, the plurality of real-time running data of the heat exchanger is paired with the corresponding real-time running data of each of the other heat exchangers in the plurality of heat exchangers to form a plurality of data pairs.

[0069] Step S204, calculate the absolute value of the difference of each data pair, and calculate the cumulative sum of the absolute values of the plurality of data pairs, and take the cumulative sum as the dispersion degree.

[0070] Specifically, for any heat exchanger, the difference between the data in each data pair is calculated, and then the absolute value of the difference is calculated to measure the disparity between them. Then, the difference values ​​of all data pairs (i.e., the calculated absolute values) are summed to obtain a quantitative index of the overall dispersion of the heat exchanger, i.e., the calculated dispersion.

[0071] The Python code used in steps S203 and S204 is shown below:

[0072] n = len(data)

[0073] pairwise_differences=np.abs(np.tile(data,(n,1))-np.tile(data[:,np.newaxis],(1,n)))

[0074] #Exclude the differences between pairs of elements (diagonal elements)

[0075] pairwise_differences[np.eye(n,dtype=bool)]=0

[0076] #Calculate the average of all non-zero paired differences

[0077] discrete_trendnp.mean(pairwise_differences[pairwise_differences>0]".

[0078] As shown in the Python statements above, this example uses the average of the absolute values ​​of the differences across all data points as a measure of dispersion. The degree of dispersion for each heat exchanger can be calculated in the same way.

[0079] Step S205: Assign discrete identification codes to the degree of discreteness.

[0080] Specifically, to facilitate subsequent calculations, another unique identifier, namely the discrete identification code, is assigned to the calculated degree of discreteness.

[0081] The Python code used in this step is shown below (using "discrete_trend" as an example):

[0082] discrete_trend_id=f"discrete_trend_{discrete_trend:.2f}"

[0083] return concentration_trend_id, discrete_trend_id.

[0084] Thus, a concentration trend value and a dispersion degree value are calculated for each heat exchanger, facilitating subsequent operation analysis.

[0085] The real-time running data of a heat exchanger is exemplarily described below.

[0086] The real-time running data of the heat exchanger is obtained through the following statements:

[0087] example_data = [10, 12, 11, 9, 13].

[0088] It should be noted that the above data is only example data, and the real data of the heat exchanger needs to be replaced in actual use.

[0089] The concentration trend identification code and the dispersion identification code are obtained through the following statements:

[0090] concentration_trend_id, discrete_trend_id = calculate_statistics(example_data)

[0091] print(f"concentration trend identification code: {concentration_trend_id}")

[0092] print(f"dispersion identification code: {discrete_trend_id}")

[0093] It should be noted that the calculation process of the specific concentration trend value and the dispersion degree value is described above, and will not be repeated here.

[0094] Further, the concentration trend and the dispersion degree of each heat exchanger are calculated, and the real-time running data of multiple heat exchangers are divided into several groups of different types of data.

[0095] In order to more clearly describe the specific implementation process of dividing the real-time running data of multiple heat exchangers into multiple groups of different types of data, a data division method proposed in the embodiment is exemplarily described below. Figure 3 A flowchart of a data division method proposed in the embodiment is shown in Figure 3 The method includes the following steps:

[0096] Step S301, the normalized standard of the heat exchanger running data and the multiple heat exchanger running sample data are called from the database, and the range interval of the concentration trend ratio and the range interval of the dispersion degree ratio in the data normalization standard are obtained.

[0097] Specifically, a data normalization standard is retrieved from a preset database, the database including historical operation data of the plurality of heat exchangers in the current gas boiler flue gas waste heat system, historical operation data of heat exchangers in other gas boiler flue gas waste heat systems, and related knowledge data in the field of gas boiler flue gas waste heat systems. The data normalization standard is a specific standard range of the operation data of the plurality of heat exchangers in the current gas boiler determined in advance by using the data in the database, or a standard range in the field of gas boiler waste heat systems. The application calls the data normalization standard for operation analysis, which can avoid deviation caused by data scale differences of different types of heat exchangers.

[0098] Then, a range interval of a concentration tendency ratio and a range interval of a dispersion degree ratio in the data normalization standard are obtained. The calculation method of the concentration tendency and the dispersion degree in the data normalization standard is the same as the method described in the above embodiment. The sample data obtained from the database is the data of the plurality of heat exchangers in the current gas boiler under normal operation state.

[0099] Step S302, the mean value of the concentration tendency of the plurality of heat exchanger operation sample data is calculated, and the first ratio of the concentration tendency of each heat exchanger to the mean value of the concentration tendency is calculated respectively.

[0100] Specifically, the mean value of the concentration tendency of the plurality of sample data is calculated first, and then the concentration tendency of each heat exchanger is divided by the mean value of the concentration tendency to obtain the first ratio corresponding to each heat exchanger.

[0101] The mean value of the concentration tendency is used to represent the reference value of the overall data concentration tendency. The mean value can be the average value, the median or other statistical quantity that can reflect the data concentration tendency of the overall data (i.e. the plurality of sample data). The first ratio is the ratio obtained by comparing the concentration tendency of the data to be compared with the reference concentration tendency value.

[0102] Therefore, by calculating the first ratio, it can be judged whether the concentration tendency of the data to be compared is consistent with the concentration tendency of the overall data, i.e. whether it is within the range interval of the concentration tendency ratio in the normalization standard.

[0103] Step S303, the mean value of the dispersion degree of the plurality of heat exchanger operation sample data is calculated, and the second ratio of the dispersion degree of each heat exchanger to the mean value of the dispersion degree is calculated respectively.

[0104] Specifically, the mean value of the dispersion degree of the plurality of sample data is calculated first, and then the dispersion degree of each heat exchanger is divided by the mean value of the dispersion degree to obtain the second ratio corresponding to each heat exchanger.

[0105] The mean of the dispersion degree is used to represent a reference value of the dispersion degree of the overall data. The mean can be a standard deviation, a variance, or other statistical quantity that can reflect the dispersion degree of the data. The second ratio is a ratio obtained by comparing the dispersion degree of the data to be compared with the reference dispersion degree value.

[0106] Thus, by calculating the second ratio, it can be determined whether the dispersion degree of the data to be compared is consistent with the dispersion degree of the overall data, i.e., whether it is within the range interval of the dispersion trend ratio in the normalization standard.

[0107] In step S304, for each heat exchanger, the first ratio is compared with a preset first threshold value and the second ratio is compared with a preset second threshold value to determine whether the concentration trend belongs to the range interval of the concentration trend ratio and whether the dispersion degree belongs to the range interval of the dispersion degree ratio, and data groups are divided based on the determination result.

[0108] Specifically, the first ratio of each heat exchanger is compared with a preset first threshold value and the second ratio is compared with a preset second threshold value, and it is determined whether the concentration trend of the heat exchanger belongs to the range interval of the concentration trend ratio and whether the dispersion degree belongs to the range interval of the dispersion degree ratio according to the comparison result. Thus, the real-time running data of each heat exchanger can be grouped according to the determination result.

[0109] In the embodiment, determining whether the concentration trend belongs to the range interval of the concentration trend ratio and whether the dispersion degree belongs to the range interval of the dispersion degree ratio comprises:

[0110] In the case where the first ratio is greater than or equal to the first threshold value, it is determined that the concentration trend belongs to the range interval of the concentration trend ratio;

[0111] In the case where the first ratio is less than the first threshold value, it is determined that the concentration trend does not belong to the range interval of the concentration trend ratio;

[0112] In the case where the second ratio is greater than or equal to the second threshold value, it is determined that the dispersion degree belongs to the range interval of the dispersion degree ratio;

[0113] In the case where the second ratio is less than the second threshold value, it is determined that the dispersion degree does not belong to the range interval of the dispersion degree ratio.

[0114] Further, data groups are divided based on the determination result, comprising: dividing the real-time running data belonging to the range interval of the concentration trend ratio and belonging to the range interval of the dispersion degree ratio into first data; and dividing the real-time running data not belonging to the range interval of the concentration trend ratio and not belonging to the range interval of the dispersion degree ratio into second data.

[0115] It can be understood that, based on the calculated first ratio and second ratio corresponding to each heat exchanger, the application embodiments group the real-time running data of all heat exchangers to obtain several groups of different kinds of data groups, including the first data group and the second data group, and a data group that does not meet the above division condition.

[0116] In step S103, the data in each group is fused respectively to obtain fused multiple groups of heat exchanger real-time running data, and the real-time temperatures of the hot fluid inlet and outlet and the real-time temperatures of the cold fluid inlet and outlet corresponding to each heat exchanger are called from the fused multiple groups of heat exchanger real-time running data to calculate the real-time heat exchange efficiency of each heat exchanger respectively.

[0117] Specifically, the several groups of heat exchanger real-time running data divided are fused respectively to obtain fused several groups of heat exchanger real-time running data. In an embodiment of the application, the data in each group is fused respectively to obtain fused multiple groups of heat exchanger real-time running data, including: the first data and the second data are fused respectively to obtain first fused data and second fused data.

[0118] It should be noted that the real-time running data of each heat exchanger collected in step S101 is discrete, and if the collected real-time running data of the heat exchanger is directly used for calculation, the accuracy of the calculated real-time heat exchange efficiency of the heat exchanger is low and there will be deviation. The application performs grouping and fusion of real-time running data, and the data with the same characteristics is fused, and in the fusion process, the data values and distribution change rules of other data in the same group can be used to adjust the real-time temperatures of the fluid inlet and outlet in the real-time running data of each heat exchanger, so that the fused data is targeted and the accuracy of the subsequently calculated real-time heat exchange efficiency is improved.

[0119] Further, according to the fused multiple groups of heat exchanger real-time running data, the real-time heat exchange efficiency of each heat exchanger is calculated respectively. Specifically, the real-time temperatures of the hot fluid inlet and outlet and the real-time temperatures of the cold fluid inlet and outlet of each heat exchanger are called from the fused several groups of heat exchanger real-time running data, and then the real-time heat exchange efficiency is calculated.

[0120] In an embodiment of the application, the real-time heat exchange efficiency of each heat exchanger is calculated by the following formula:

[0121]

[0122] Where, ΔT Mis the real-time heat exchange efficiency of the heat exchanger, T1 is the real-time temperature of the hot fluid inlet obtained from the fused real-time running data of multiple groups of heat exchangers, T2 is the real-time temperature of the hot fluid outlet obtained from the fused real-time running data of multiple groups of heat exchangers, t1 is the real-time temperature of the cold fluid inlet obtained from the fused real-time running data of multiple groups of heat exchangers, and t2 is the real-time temperature of the cold fluid outlet obtained from the fused real-time running data of multiple groups of heat exchangers.

[0123] Step S104, historical running data of the heat exchanger is called from the database, a preset neural network model is trained into a heat exchanger optimal running state analysis model based on the historical running data, and the optimal running state analysis model is used to determine the optimal running state of each heat exchanger.

[0124] Specifically, the historical running data of each heat exchanger is called from the database in step S102, the historical running data of the heat exchanger is labeled and divided based on the neural network model, and the processed historical running data is used to determine the optimal state running analysis model of the heat exchanger. In this application, one optimal running state analysis model can be trained for each heat exchanger, or one optimal state running analysis model can be trained for multiple heat exchangers.

[0125] In an embodiment of the present application, the preset neural network model is trained into a heat exchanger optimal running state analysis model based on historical running data, including: based on a feedforward neural network, an initial heat exchanger optimal running state analysis model is constructed; based on machine learning, the historical running data is labeled and divided to obtain a training set, a validation set and a test set; the training set, the validation set and the test set are used to supervise the training of the initial heat exchanger optimal state running analysis model until the model output meets the requirements.

[0126] Specifically, in this embodiment, a feedforward neural network is used to construct an initial heat exchanger optimal state running analysis model to be trained. The type of feedforward neural network selected can be determined based on whether it is suitable for analysis of the running state of the heat exchanger. For example, based on the complex data relationship of the heat exchanger running data, a multilayer perceptron (MLP) is selected to construct a heat exchanger optimal state running analysis model, or a radial basis function network (RBF) is selected to construct a heat exchanger optimal state running analysis model to handle local temperature changes of the heat exchanger.

[0127] Then, based on machine learning technology, the historical running data of multiple heat exchangers called can be labeled and divided by a neural network model to obtain a training set, a validation set and a test set. In the labeling process, manual confirmation of the labeling method can also be combined to provide a clear prediction target for the model through the labeled data, so that the model can learn the relationship between the input data and the output result, i.e. the relationship between the real-time running data of the heat exchanger and the running state.

[0128] Finally, the initial heat exchanger optimal state operation analysis model is supervised training, verification and testing by using the training set, the verification set and the test set, until the accuracy of the output result of the training completed heat exchanger optimal state operation analysis model meets the preset accuracy requirement.

[0129] It should be noted that the training process of the heat exchanger optimal operation state analysis model can refer to the training mode of the classification model or the prediction model in the related art, and the present application does not limit this.

[0130] Further, the optimal operation state of each heat exchanger is determined by the training completed heat exchanger optimal operation state analysis model, and the various historical operation data under the optimal operation state are determined by using the above database.

[0131] In step S105, the historical operation data corresponding to the optimal operation state of each heat exchanger is calculated with the fused real-time operation data, and the heat exchanger to be adjusted is determined based on the similarity, and the heat exchanger to be adjusted is adjusted to make the real-time heat exchange efficiency of the adjusted heat exchanger reach the optimal state.

[0132] Specifically, the real-time operation data of each heat exchanger is calculated with the historical operation data of the heat exchanger in the optimal state, and whether adjustment is needed is determined according to the calculated similarity value, if adjustment is needed, the heat exchanger is adjusted in multiple ways to make the real-time heat exchange efficiency of the heat exchanger optimal.

[0133] In an embodiment of the present application, the similarity calculation is performed by the following formula:

[0134]

[0135] Wherein, S i is the similarity of the i-th feature of the heat exchanger real-time operation data and the historical operation data corresponding to the optimal operation state of the heat exchanger, w ij is the j-th feature index value of the i-th feature of the heat exchanger real-time operation data, v ij is the j-th feature index value of the i-th feature of the historical operation data corresponding to the optimal operation state of the heat exchanger, and n is the total number of index values of the i-th feature.

[0136] It should be noted that the above features can be voltage, current and temperature of the heat exchanger and other features in actual application, such as, the real-time heat exchange efficiency can also be calculated as a kind of feature, and the real-time heat exchange efficiency is directly used as the basis for optimizing the heat exchange efficiency.

[0137] Further, the heat exchanger to be adjusted is determined based on the similarity. In an embodiment of the present application, the heat exchanger to be adjusted is determined based on the similarity, comprising: comparing the calculated similarity value of any heat exchanger with a similarity threshold value; and determining that the any heat exchanger is the heat exchanger to be adjusted in the case that the similarity value is less than the similarity threshold value.

[0138] Specifically, the calculated similarity value is compared with a threshold value; if the calculated similarity value is greater than or equal to the threshold value, it means that the similarity is too large and no adjustment is needed; if the calculated similarity value is less than the threshold value, it means that the similarity is too small and adjustment is needed so that the real-time heat exchange efficiency of the heat exchanger is optimal. The above judgment mode is used to traverse and judge multiple heat exchangers, and all heat exchangers that need to be adjusted are screened out.

[0139] Further, in combination with various adjustment modes, such as manually adjusting the PLC button or increasing the voltage and various modes, the running state of the heat exchanger is adjusted so that the real-time heat exchange efficiency of the heat exchanger gradually changes to the heat exchange efficiency in the optimal running state.

[0140] In summary, the control method of the heat exchanger of the flue gas waste heat system of the gas-fired boiler according to the embodiments of the present application can realize the following effects. The heat exchanger is connected to the boiler tail flue, various types of sensors are installed on the heat exchanger, the running data of the heat exchanger can be monitored in real time, including the real-time temperature of the fluid inlet and outlet and other key information, which helps to find potential running problems in time and prevent accidents. The centralized trend and dispersion degree of the real-time running data are calculated, which helps to understand the overall distribution and dispersion of the data and provides a basis for subsequent data analysis and optimization. The real-time heat exchange efficiency of the heat exchanger is accurately calculated, which can intuitively understand the performance of the heat exchanger and provide a direct basis for optimizing the heat exchange efficiency. Finally, based on the optimal state running analysis model of the heat exchanger, whether the heat exchanger needs to be adjusted is determined by similarity calculation, which realizes the intelligent adjustment of the heat exchanger and helps to keep the heat exchanger in the optimal working state, improve the heat exchange efficiency of the heat exchanger, and reduce energy consumption. Thus, the method helps to improve the stability and reliability of the boiler tail flue heat exchange system, ensures the safe and stable operation of the boiler system, and prolongs the service life of the equipment. Therefore, the method improves the accuracy, real-time performance and intelligence of the heat exchanger control.

[0141] In order to realize the above-mentioned embodiments, the present application further provides a control system of a heat exchanger of a flue gas waste heat system of a gas-fired boiler, Figure 4 A structural schematic diagram of a control system of a heat exchanger of a flue gas waste heat system of a gas-fired boiler according to an embodiment of the present application is shown in Figure 4 As shown, the system comprises: an acquisition module 100, a division module 200, a calculation module 300, a determination module 400 and an adjustment module 500.

[0142] The collection module 100 is used for connecting a plurality of heat exchangers on the tail flue of the gas-fired boiler, and installing a plurality of types of sensors on each heat exchanger to collect real-time operation data of each heat exchanger, wherein the real-time operation data includes real-time temperatures of fluid inlet and outlet.

[0143] The division module 200 is used for calculating a central tendency and a dispersion degree of each heat exchanger according to the real-time operation data of the plurality of heat exchangers, and dividing the real-time operation data of the plurality of heat exchangers into a plurality of groups of data of different types based on the central tendency and the dispersion degree.

[0144] The calculation module 300 is used for respectively fusing each group of data to obtain a plurality of groups of fused heat exchanger real-time operation data, and calling real-time temperatures of hot fluid inlet and outlet and real-time temperatures of cold fluid inlet and outlet of each heat exchanger from the plurality of groups of fused heat exchanger real-time operation data to respectively calculate real-time heat exchange efficiencies of the heat exchangers.

[0145] The determination module 400 is used for calling heat exchanger historical operation data from a database, training a preset neural network model into a heat exchanger optimal operation state analysis model based on the historical operation data, and determining optimal operation states of the heat exchangers through the optimal operation state analysis model.

[0146] The adjustment module 500 is used for performing similarity calculation on the historical operation data corresponding to the optimal operation states of each heat exchanger and the fused real-time operation data, and determining a heat exchanger to be adjusted based on the similarity, and adjusting the heat exchanger to be adjusted to make the real-time heat exchange efficiency of the adjusted heat exchanger reach an optimal state.

[0147] It should be noted that the foregoing explanation and description of the embodiment of the control method of the heat exchanger of the gas-fired boiler flue gas waste heat system also applies to the system of the embodiment, which will not be described here again.

[0148] In summary, the control system of the heat exchanger of the gas-fired boiler flue gas waste heat system of the embodiment of the application realizes intelligent adjustment of the heat exchanger, helps to keep the heat exchanger in an optimal working state at all times, improves the heat exchange efficiency of the heat exchanger, and reduces energy consumption. Thus, it helps to improve the stability and reliability of the boiler tail flue heat exchange system, and also helps to ensure safe and stable operation of the boiler system and prolong the service life of the equipment. Therefore, the system improves the accuracy, real-time performance and intelligence of heat exchanger control

[0149] In order to realize the above-mentioned embodiments, the application further provides an electronic device, which comprises at least one processor, and

[0150] The memory is in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the control method of the flue gas waste heat recovery system heat exchanger of the gas-fired boiler according to any one of the first aspect.

[0151] To achieve the above-mentioned embodiments, the application further provides a non-transitory computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the control method of the flue gas waste heat recovery system heat exchanger of the gas-fired boiler according to any one of the first aspect embodiments.

[0152] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0153] In addition, the terms "first", "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless otherwise specifically limited.

[0154] Any process or method descriptions in flow charts or described elsewhere herein can be understood as representing code modules, segments, or portions of code which include one or more executable instructions for implementing specific logic functions (or steps) in the process, and that the various embodiments of the preferred application can include additional or fewer steps or codes, and that the method can be implemented by additional processes or machines in the alternative (such as a centrally managed server or a personnel digital assistant) as one of ordinary skill in the art would recognize (for example, a process can be machine or computer-implemented, and / or can occur or be supported by other processes and machines available in the art).

[0155] The logic and / or steps represented in the flowcharts and / or described herein, for example, can be considered as a sequence of executable instructions stored in a computer readable medium, which can be executed by an instruction execution system, apparatus or device, such as a computer-based system, a processor-based system, or other system that can fetch the instructions from the instruction execution system, apparatus or device and execute the instructions, or a combination thereof. For the purposes of this specification, a "computer readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus or device. The computer readable medium can specifically be, but is not limited to, the following: an electronic connection (electronic apparatus) having one or more wires, a portable computer diskette (magnetic apparatus), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disk read-only memory (CDROM). In addition, the computer readable medium can even be paper or other suitable medium upon which the program can be printed, because the program can be electronically obtained, for example, by optically scanning the paper or other medium, then

[0156] It should be understood that portions of the present application can be realized with hardware, software, firmware or a combination thereof. In the foregoing embodiments, a plurality of steps or methods can be realized as software or firmware to be executed by a suitable instruction-executing system. As such, if realized with hardware, and in another embodiment, any one or a combination of the following technologies known in the art can be used: discrete logic circuitry having a logic gate circuit for implementing logical functions of data signals, application specific integrated circuits (ASICs) having a suitable combination of logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

[0157] Those skilled in the art can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by programs instructing relevant hardware, and the programs can be stored in a computer readable storage medium. When the programs are executed, one or a combination of the steps of the method embodiments is included.

[0158] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing module, or each of the units can be physically present separately, or two or more units can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0159] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A control method for a heat exchanger in a waste heat system of a gas-fired boiler flue gas, characterized in that, Includes the following steps: Multiple heat exchangers are connected to the tail flue of the gas boiler, and various types of sensors are installed on each heat exchanger to collect real-time operating data of each heat exchanger, wherein the real-time operating data includes the real-time temperature of the fluid inlet and outlet. Based on the real-time operating data of the multiple heat exchangers, the central tendency and dispersion of each heat exchanger are calculated, and based on the central tendency and dispersion, the real-time operating data of the multiple heat exchangers are divided into multiple groups of data of different types. Each set of data is fused to obtain multiple sets of real-time operating data of heat exchangers. The real-time inlet and outlet temperatures of hot fluid and cold fluid corresponding to each heat exchanger are retrieved from the fused multiple sets of real-time operating data of heat exchangers to calculate the real-time heat exchange efficiency of each heat exchanger. Retrieve historical operating data of heat exchangers from the database, train a preset neural network model into a heat exchanger optimal operating state analysis model based on the historical operating data, and determine the optimal operating state of each heat exchanger through the optimal operating state analysis model. The historical operating data corresponding to the optimal operating state of each heat exchanger is compared with the fused real-time operating data to calculate the similarity. Based on the similarity, the heat exchanger to be adjusted is determined and adjusted so that the real-time heat exchange efficiency of the adjusted heat exchanger reaches the optimal state.

2. The method according to claim 1, characterized in that, The calculation of the central tendency and dispersion of each of the heat exchangers includes: Calculate the average value of the real-time operating data for each heat exchanger, and for each heat exchanger, calculate the variance of the real-time operating data based on the average value, and use the variance as the central tendency; Assign a central trend identifier to the central trend; Each real-time operating data of each heat exchanger is paired with the corresponding data of other heat exchangers in the plurality of heat exchangers to form multiple data pairs. Calculate the absolute value of the difference between each of the data pairs, and calculate the sum of the absolute values ​​of the multiple data pairs, using the sum as the degree of dispersion; Assign discrete identification codes to the degree of discreteness.

3. The method according to claim 2, characterized in that, The variance of the real-time running data is calculated using the following formula: Where D is the variance, n is the number of real-time operating data points of the heat exchanger, and x i Let be the value of the i-th real-time operating data, and a be the average value of the real-time operating data of the heat exchanger.

4. The method according to claim 1, characterized in that, The real-time operating data of the multiple heat exchangers is divided into multiple groups of different types, including: Retrieve the normalization standard of heat exchanger operating data and multiple heat exchanger operating sample data from the database, and obtain the range of the central tendency ratio and the range of the dispersion ratio in the data normalization standard. Calculate the mean of the central tendency of the operating sample data of the multiple heat exchangers, and calculate the first ratio of the central tendency of each heat exchanger to the mean of the central tendency; Calculate the mean of the dispersion of the operating sample data of the plurality of heat exchangers, and calculate the second ratio of the dispersion of each heat exchanger to the mean of the dispersion; For each heat exchanger, the first ratio is compared with a preset first threshold and the second ratio is compared with a preset second threshold to determine whether the central tendency belongs to the range of the central tendency ratio and whether the dispersion belongs to the range of the dispersion ratio, and the data group is divided based on the determination results.

5. The method according to claim 4, characterized in that, The determination of whether the central tendency falls within the range of the central tendency ratio and whether the dispersion falls within the range of the dispersion ratio includes: If the first ratio is greater than or equal to the first threshold, it is determined that the central tendency belongs to the range of the central tendency ratio. If the second ratio is greater than or equal to the second threshold, it is determined that the degree of dispersion belongs to the range of the degree of dispersion ratio. The data group division based on the judgment result includes: Real-time running data that falls within both the range of the central tendency ratio and the range of the dispersion ratio is classified as the first data. Real-time running data that does not fall within the range of the central tendency ratio and the range of the dispersion ratio is classified as second data. The process of fusing each set of data to obtain multiple sets of merged real-time operating data for the heat exchanger includes: The first data and the second data are fused separately to obtain first fused data and second fused data.

6. The method according to claim 1, characterized in that, The real-time heat exchange efficiency of each heat exchanger is calculated using the following formula: Where, ΔT M T1 is the real-time heat exchange efficiency of the heat exchanger, T2 is the real-time temperature of the hot fluid inlet, t1 is the real-time temperature of the cold fluid inlet, and t2 is the real-time temperature of the cold fluid outlet.

7. The method according to claim 1, characterized in that, The step of training a preset neural network model into an analysis model for the optimal operating state of the heat exchanger based on the historical operating data includes: Based on a feedforward neural network, an analysis model for the optimal operating state of the initial heat exchanger is constructed. Based on machine learning, the historical running data is labeled and divided to obtain training set, validation set and test set; The initial heat exchanger optimal state operation analysis model is trained under supervision using the training set, the validation set, and the test set until the model output meets the requirements.

8. The method according to claim 1, characterized in that, Similarity is calculated using the following formula: Among them, S i It is the similarity of the i-th feature between the real-time operating data of the heat exchanger and the historical operating data corresponding to the optimal operating state of the heat exchanger, w ij It is the j-th characteristic index value of the i-th feature of the real-time operating data of the heat exchanger, v ij It is the j-th feature index value of the i-th feature in the historical operating data corresponding to the optimal operating state of the heat exchanger, and n is the total number of index values ​​of the i-th feature; The method of determining the heat exchanger to be adjusted based on similarity includes: The calculated similarity value of any heat exchanger is compared with the similarity threshold. If the similarity value is less than the similarity threshold, then any heat exchanger is determined to be a heat exchanger to be adjusted.

9. A control system for a heat exchanger in a waste heat system of gas-fired boiler flue gas, characterized in that, Includes the following modules: The data acquisition module is used to connect multiple heat exchangers to the tail flue of the gas boiler and install various types of sensors on each heat exchanger to acquire real-time operating data of each heat exchanger, wherein the real-time operating data includes the real-time temperature of the fluid inlet and outlet. The partitioning module is used to calculate the central tendency and dispersion of each heat exchanger based on the real-time operating data of the multiple heat exchangers, and to partition the real-time operating data of the multiple heat exchangers into multiple groups of data of different types based on the central tendency and the dispersion. The calculation module is used to fuse each set of data to obtain multiple sets of real-time operating data of heat exchangers after fusion, and to retrieve the real-time inlet and outlet temperatures of hot fluid and cold fluid corresponding to each heat exchanger from the multiple sets of real-time operating data of heat exchangers after fusion, so as to calculate the real-time heat exchange efficiency of each heat exchanger. The determination module is used to retrieve historical operating data of heat exchangers from the database, train a preset neural network model into an optimal operating state analysis model of heat exchangers based on the historical operating data, and determine the optimal operating state of each heat exchanger through the optimal operating state analysis model. The adjustment module is used to calculate the similarity between the historical operating data corresponding to the optimal operating state of each heat exchanger and the fused real-time operating data, and to determine the heat exchanger to be adjusted based on the similarity, and to adjust the heat exchanger to be adjusted so that the real-time heat exchange efficiency of the adjusted heat exchanger reaches the optimal state.

10. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the control method for the heat exchanger of the flue gas waste heat system of the gas boiler as described in any one of claims 1-8.

Images