Gas-fired boiler temperature control method and system

Abstract

The invention relates to the technical field of gas-fired boiler control, in particular to a gas-fired boiler temperature control method and system.The method comprises the steps that raw material hyperspectral data of the lubricating oil preparation heating process in a heating stirring furnace at all moments are collected; obtaining a raw material heating uniform change coefficient at each moment according to the wave band reflectivity difference and the spatial distribution characteristic difference of pixels in the raw material hyperspectral data at the historical moment of each moment; and the temperature adaptation degree of the heating stirring furnace is obtained by combining the raw material heating uniformity and the raw material heating uniformity change coefficient, and the temperature of the heating stirring furnace is controlled according to numerical distribution of the temperature adaptation degrees of the heating stirring furnace at all moments before the current moment. Intelligent control over the temperature of the gas-fired boiler in the lubricating oil preparation process can be achieved, and the temperature control precision is improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of gas boiler control, in particular to a gas boiler temperature control method and system. BACKGROUND

[0002] The preparation of lubricating oil is mainly prepared by adding rust inhibitor, friction moderator and other auxiliary materials into base oil, and heating and stirring by using a gas boiler. However, when the traditional gas boiler is heated, the heating device of the heating and stirring furnace is at the bottom of the furnace body, and the heat is transferred from bottom to top. The temperature of the raw materials in the local area is relatively low, and the flowability is relatively weak. Therefore, the heat transfer of the lubricating oil raw materials is not uniform, which causes heat loss, and the heat received by the upper layer of raw materials is low and the heating is not uniform. Therefore, the temperature control precision of the gas boiler in the raw material stirring process is poor, and the quality of the finally prepared lubricating oil is poor. SUMMARY

[0003] In order to solve the above technical problems, the purpose of the present application is to provide a gas boiler temperature control method and system, and the technical scheme adopted is as follows: In a first aspect, the embodiments of the present application provide a gas boiler temperature control method, which comprises the following steps: S1, collecting raw material hyperspectral data of the lubricating oil preparation heating process in the heating and stirring furnace at each time; the raw material hyperspectral data comprises: the band reflectivity of each pixel corresponding position to all bands; S2, obtaining the raw material heating uniformity coefficient and the raw material heating uniformity according to the band reflectivity difference and the spatial distribution characteristic difference of the pixels in the raw material hyperspectral data of each time and the historical time, specifically comprising: S21, obtaining the raw material distribution density of each time according to the band reflectivity difference of the pixels in the raw material hyperspectral data of each time and the spatial distribution characteristics of the pixels; S22, obtaining the raw material stirring flowability coefficient of each time according to the band reflectivity difference and the spatial distribution characteristic difference of all pixels in the raw material hyperspectral data of adjacent time; S23, obtaining the raw material heating uniformity by combining the raw material stirring flowability coefficient and the raw material distribution density of each time; S24, obtaining the raw material heating and stirring speed of each time according to the difference in the distribution confusion degree of the band reflectivity of all pixels in the raw material hyperspectral data of adjacent time; obtaining the raw material temperature balance index of each time according to the discrete degree of the change trend of the raw material heating and stirring speed of the historical time; obtaining the raw material heating uniformity coefficient of each time according to the numerical distribution of the raw material temperature balance index of all times; S3, a heating and stirring furnace temperature adaptation degree is obtained by combining the raw material heating uniformity and the raw material heating uniformity change coefficient, and the temperature of the heating and stirring furnace is controlled according to the numerical distribution of the heating and stirring furnace temperature adaptation degree of all time points before the current time point.

[0004] Further, the method for obtaining the raw material distribution density of each time point comprises: A sequence composed of the band reflectivity of each pixel corresponding position to all bands is recorded as the spectral sequence of each pixel; the distance between the spectral sequences of any two pixels is taken as the metric distance, and density clustering is performed on all pixels to obtain each raw material clustering cluster; For each raw material clustering cluster, the Euclidean distance between any two pixels is taken as the metric distance, and density clustering is performed on all pixels contained in the raw material clustering cluster to obtain each sub-clustering cluster; For each raw material clustering cluster, the pixel with the minimum abscissa in each sub-clustering cluster in the raw material clustering cluster is recorded as the representative pixel of each sub-clustering cluster; for any two sub-clustering clusters, the Euclidean distance between the representative pixels of the two sub-clustering clusters is calculated and recorded as the first distance; the mean value of the first distance of all sub-clustering clusters contained in the raw material clustering cluster is obtained; and the ratio of the total number of pixels in the raw material clustering cluster to the mean value is taken as the raw material convergence degree of each raw material clustering cluster; The sum value of the mean values of all raw material clustering clusters is recorded as the total value of raw material density; and the cumulative sum value of the raw material convergence degrees of all raw material clustering clusters is calculated, and the ratio of the cumulative sum value to the total value of raw material density is taken as the raw material distribution density of each time point.

[0005] Further, the method for obtaining the raw material stirring flowability coefficient of each time point comprises: The maximum value of the band reflectivity of each pixel corresponding position to all bands is selected as the representative reflectivity value of each pixel; the Euclidean distance between any two pixels in each raw material clustering cluster is obtained; and the average value of all the Euclidean distances in each raw material clustering cluster is obtained; For the raw material hyperspectral data of each time point, the information entropy of the representative reflectivity value of all pixels in the raw material hyperspectral data is calculated; and the sum value of the average values of all raw material clustering clusters in the raw material hyperspectral data is recorded as the total value of raw material dispersion of each time point; According to the numerical distribution difference of the representative reflectivity value of all pixels in the raw material hyperspectral data of adjacent time points and the difference of the total value of raw material dispersion, the raw material stirring flowability coefficient of each time point is obtained.

[0006] Further, the method for obtaining the raw material stirring flowability coefficient of each time point comprises: For each time point except the initial time point, the difference between the information entropy of the time point and the previous time point is calculated, denoted as information difference; the difference between the raw material discrete total value of the time point and the previous time point is obtained, denoted as raw material distribution difference; the fusion result of the raw material distribution difference and the information difference of the time point and the previous time point is denoted as the raw material stirring fluidity coefficient of the time point.

[0007] Further, the raw material stirring fluidity coefficient of each time point is combined with the raw material distribution density to obtain the raw material heating uniformity, including: taking the ratio of the raw material stirring fluidity coefficient of each time point to the raw material distribution density as the raw material heating uniformity of each time point.

[0008] Further, the method for obtaining the raw material heating stirring speed of each time point comprises: The information entropy of the representative reflectivity value of all pixels in the raw material hyperspectral data of each time point is calculated, denoted as the raw material discrete value of each time point; the ratio of the difference between the raw material discrete value of each time point and the previous time point to the preset sampling interval T is denoted as the raw material heating stirring speed of each time point.

[0009] Further, the method for obtaining the raw material temperature uniformity index of each time point comprises: A sequence composed of the raw material heating stirring speeds of a preset number of time points before each time point is denoted as the trend sequence of each time point; The sum value of the average values of all raw material clustering clusters of each time point is calculated, denoted as the raw material temperature discrete value of each time point; the difference between the raw material temperature discrete value of each time point and the previous time point is calculated, denoted as the first difference; the variance of the trend sequence of each time point is calculated, and the ratio of the first difference to the variance is taken as the raw material temperature uniformity index of each time point.

[0010] Further, the method for obtaining the raw material heating uniformity change coefficient of each time point comprises: The trend intensity of the trend sequence of each time point is obtained, denoted as the raw material mixing trend coefficient of each time point; threshold segmentation is performed on the raw material mixing trend coefficients of all time points to obtain a mixing judgment threshold; if the raw material mixing trend coefficient of each time point is greater than or equal to the mixing judgment threshold, the raw material heating uniformity change coefficient of each time point is the raw material temperature uniformity index of each time point; otherwise, the raw material heating uniformity change coefficient of each time point is the inverse of the raw material temperature uniformity index of each time point.

[0011] Further, the heating stirring furnace temperature adaptation degree is obtained by combining the raw material heating uniformity and the raw material heating uniformity change coefficient, and the temperature of the heating stirring furnace is controlled according to the numerical distribution of the heating stirring furnace temperature adaptation degree of all time points before the current time point, including: The product of the raw material heating uniformity and the raw material heating uniformity change coefficient of each time point is taken as the heating stirring furnace temperature adaptation degree of each time point. The heating and stirring furnace temperature adaptation degree of all time points before the current time point is obtained by using a prediction algorithm, and the heating and stirring furnace temperature adaptation degree of all time points is threshold segmented to obtain an optimal segmentation threshold; If the heating and stirring furnace temperature adaptation degree of the current time point is less than or equal to the optimal segmentation threshold, the temperature of the heating and stirring furnace is adjusted.

[0012] In a second aspect, the embodiments of the present application further provide a gas boiler temperature control system for lubricating oil preparation, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the gas boiler temperature control method of any one of the above.

[0013] The present application has at least the following beneficial effects: The present application obtains the distribution density of raw materials at each time point by analyzing the hyperspectral data distribution characteristics and band reflectivity differences of raw materials at each time point in the heating and stirring mixing process of lubricating oil preparation, accurately reflecting the distribution characteristics of different raw materials. Further, the raw material stirring flowability coefficient is obtained by analyzing the change of data distribution characteristics and band reflectivity differences of adjacent time points, reflecting the gradual change of raw material distribution in the stirring process. The raw material heating uniformity obtained by combining the raw material stirring flowability coefficient and the raw material distribution density reflects the uniformity of the overall heating at a single time point. Further, the raw material heating uniformity change coefficient is obtained according to the uniformity difference of the heating at the historical time point combined with the change of stirring speed, more accurately reflecting the uniformity of the heating change in the heating and stirring process. Further, the heating and stirring furnace temperature adaptation degree is constructed to represent the heating temperature suitability of the current heating and stirring furnace, and the heating temperature suitability is used to determine whether the heating temperature needs to be adjusted. The present application solves the problem of poor temperature control precision of the gas boiler caused by uneven heating of raw materials during stirring and heating in the lubricating oil preparation process. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creating any creative labor.

[0015] Figure 1 A step flow chart of a gas boiler temperature control method provided by an embodiment of the present application is shown in the figure; Figure 2 A raw material hyperspectral data acquisition scene schematic diagram provided by an embodiment of the present application is shown in the figure. Figure 3 The acquisition block diagram of the uniform change coefficient of the raw material at each time point is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present application will be clearly and completely described in connection with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. In the case of no conflict, the technical features in the embodiments of the present application and the technical features in the embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative labor are within the scope of protection of the present application.

[0017] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0018] The specific scheme of the gas boiler temperature control method and system provided by the present application will be specifically described below in connection with the drawings.

[0019] Please refer to Figure 1 which shows a step flowchart of a gas boiler temperature control method provided by an embodiment of the present application, and the method comprises the following steps. S1, collecting raw material hyperspectral data of a heating and stirring furnace in a lubricating oil preparation heating process at each time point.

[0020] A specific implementation scenario of an embodiment of the present application is a gas boiler temperature control scenario in a lubricating oil heating preparation process. In the heating process of the lubricating oil raw material in the heating and stirring furnace, the heat transfer of the heating and stirring furnace is not uniform, which can cause the problem that the upper raw material receives less heat and is not uniformly heated, so that the flowability of the raw material is poor, and finally the prepared lubricating oil has poor quality. Therefore, the temperature data in the heating and stirring furnace need to be monitored in real time.

[0021] At present, the method for monitoring the temperature of the gas boiler is to analyze the spectral data after spectral imaging, and to interpret the actual heating condition of the raw material in the heating and stirring process. However, in the process of lubricating oil preparation, the heating and stirring of the heating and stirring furnace is gradually carried out, and the uneven heating leads to relatively poor flowability of the raw material. Therefore, the dispersion speed of the raw material under the action of stirring is slow, which affects the real-time judgment of the heating condition according to the spectral data.

[0022] Therefore, in the embodiments of the present application, as Figure 2As shown, above the infrared window B of the heating stirring furnace C, a hyperspectral camera A is arranged to take vertical pictures, and the raw material hyperspectral data of the lubricating oil in the heating stirring furnace are collected every interval T=2s, and the mean filtering method is used for denoising. The mean filtering is a known technology, and the process will not be described herein. Taking a single time as an example, the raw material hyperspectral data include the band reflectivity of each pixel corresponding position to all bands.

[0023] According to the numerical distribution of the representative reflectivity values of the pixels distributed at different times and different positions, the heating temperature of the heating stirring furnace can be adjusted.

[0024] S2, the band reflectivity difference and the spatial distribution characteristic difference of the pixels in the raw material hyperspectral data at each historical time are obtained to obtain the raw material heating uniformity change coefficient and the raw material heating uniformity at each time.

[0025] In the process of heating the raw material of the lubricating oil, the flowability of the raw material is enhanced, but when the overall raw material is unevenly heated, the temperature of the raw material in the local area may be lower, and thus the flowability is weaker. In the process of stirring, the raw material in the local area is more dispersed under the same stirring degree, and the change of the raw material hyperspectral data position at the position in the hyperspectral image is not obvious. The unevenly heated raw material will gather in the uneven area, and a small part will be more dispersed.

[0026] S21, the band reflectivity difference and the spatial distribution characteristic of the pixels in the raw material hyperspectral data at each time are obtained to obtain the raw material distribution density at each time.

[0027] Through the above analysis, the unevenly heated raw material in the heating stirring furnace will gather in the uneven area, and a small part will be more dispersed, and has different distribution characteristics. In addition, the unevenly heated raw material has different reflection degrees of spectrum at different positions. Therefore, the raw material distribution density can be obtained according to the band reflectivity difference and the spatial distribution characteristic of each pixel to all bands.

[0028] Firstly, a sequence composed of the band reflectivity of each pixel corresponding position to all bands is recorded as the spectrum sequence of each pixel; the distance between the spectrum sequences of any two pixels is taken as the measurement distance, and density clustering is performed on all pixels to obtain each raw material clustering cluster; For each raw material clustering cluster, the Euclidean distance between any two pixels is taken as the measurement distance, and density clustering is performed on all pixels contained in the raw material clustering cluster to obtain each sub-clustering cluster; It should be noted that the density clustering is an algorithm for clustering based on the density structure of data points without pre-specifying the number of clusters, and the implementer can select the DPC clustering, DBSCAN clustering and OPTICS clustering and other density clustering algorithms according to actual conditions, which are not limited in the application; in the embodiment, the distance between the spectral sequences of any two pixels is taken as the metric distance, and the DPC clustering algorithm is used for clustering all pixels, the truncation distance is set to 3, and the metric distance is the distance between the spectral sequences between the pixels; wherein the distance between two sequences represents the difference between the two sequences, and the implementer can select the dtw distance, Euclidean distance and Manhattan distance according to actual conditions, which are not limited in the application. In the embodiment, the dtw distance is selected as the distance metric between the spectral sequences between the pixels; further, the DBSCAN clustering algorithm is used for density clustering of all pixels contained in the raw material clustering cluster. The calculation of the DPC clustering algorithm, the DBSCAN clustering algorithm and the dtw distance are all known technologies, and the process will not be repeated here.

[0029] The pixels in each raw material clustering cluster represent the pixels of one raw material. Taking a raw material clustering cluster as an example, the Euclidean distance between all pixels in the raw material clustering cluster is calculated, the DBSCAN clustering algorithm is used, the minimum density is set to 5, the neighborhood radius is set to 3, and the output is a plurality of sub-clustering clusters.

[0030] For each raw material clustering cluster, the pixel with the smallest horizontal coordinate in each sub-clustering cluster in the raw material clustering cluster is obtained, which is denoted as the representative pixel of each sub-clustering cluster; for any two sub-clustering clusters, the Euclidean distance between the representative pixels of the two sub-clustering clusters is calculated, denoted as the first distance; the mean value of the first distance of all sub-clustering clusters contained in the raw material clustering cluster is obtained; the ratio of the total number of pixels in the raw material clustering cluster to the mean value is taken as the raw material convergence degree of each raw material clustering cluster.

[0031] The sum value of the mean values of all raw material clustering clusters is obtained, denoted as the total raw material density value; the cumulative sum value of the raw material convergence degrees of all raw material clustering clusters is calculated, and the ratio of the cumulative sum value to the total raw material density value is taken as the raw material distribution density at each moment.

[0032] The smaller the raw material distribution density at a single moment, the greater the uniformity of the corresponding raw material heating, which indicates that the current distribution of each raw material is relatively discrete, the overall heating of the raw material is relatively uniform, and the mixing effect is good.

[0033] S22, obtaining the raw material stirring fluidity coefficient at each moment according to the band reflectance difference and spatial distribution feature difference of all pixels in the raw material hyperspectral data at adjacent moments.

[0034] Since the reflectivity of different wave bands at different positions in the stirring process of the heating stirring furnace has great difference, in order to more clearly reflect the temperature distribution at different positions, combined with the position distribution change of the unevenly heated lubricating oil raw material in the heating stirring furnace at adjacent moments, the raw material stirring fluidity coefficients at each moment are constructed.

[0035] The maximum value of the wave band reflectivity of all wave bands at the corresponding position of each pixel is selected as the representative reflectivity value of each pixel; the Euclidean distance between any two pixels in each raw material clustering cluster is obtained; the average value of all the Euclidean distances in each raw material clustering cluster is obtained; For the raw material hyperspectral data at each moment, the information entropy of the representative reflectivity value of all pixels in the raw material hyperspectral data is calculated; the sum value of the average values of all raw material clustering clusters in the raw material hyperspectral data is obtained, which is recorded as the raw material discrete total value at each moment; For each moment except the initial moment, the difference between the information entropy at each moment and the previous moment is calculated, which is recorded as the information difference; the difference between the raw material discrete total value at each moment and the previous moment is obtained, which is recorded as the raw material distribution difference; the fusion result of the raw material distribution difference and the information difference between each moment and the previous moment is recorded as the raw material stirring fluidity coefficient at each moment.

[0036] It should be noted that fusion represents that the larger the fusion data is, the greater the fusion result is, and the fusion can be multiplication relationship, addition relationship, etc., which is determined by actual application, and the present application does not make special limitation. Difference represents the difference between two values, and in the present embodiment, the difference is calculated by the absolute value of the difference.

[0037] As an embodiment of the present application, the raw material stirring fluidity coefficient at each moment is the product of the raw material distribution difference and the information difference between each moment and the previous moment; As another embodiment of the present application, the raw material stirring fluidity coefficient at each moment is the sum value of the raw material distribution difference and the information difference between each moment and the previous moment.

[0038] When the raw material stirring fluidity coefficient at a single moment is larger, the corresponding raw material heating uniformity is larger, which indicates that the distribution of all raw material pixels is more chaotic compared with the previous moment, and the position change speed caused by stirring is faster, the fluidity is stronger, and the heating uniformity is higher.

[0039] S23, combined with the raw material stirring fluidity coefficient at each moment and the raw material distribution density, the raw material heating uniformity is obtained.

[0040] The raw material stirring fluidity coefficient at a single moment can be determined by the raw material pixel chaos degree at a single moment and the raw material distribution change speed.

[0041] Specifically, the ratio of the raw material stirring fluidity coefficient at each time to the raw material distribution density is taken as the raw material heating uniformity at each time.

[0042] When the raw material heating uniformity at a single time is greater, it indicates that the lubricating oil raw material distribution at the current time is more discrete, and the raw material fluidity is stronger, the raw material is heated more uniformly in the heating process, the heating effect of the heating and stirring furnace is better, and the temperature is more suitable, and the heating and stirring furnace does not need to be controlled in temperature.

[0043] S24, the difference between the distribution disorder degree of the band reflectance of all pixels in the raw material hyperspectral data at adjacent times is obtained to obtain the raw material heating and stirring speed at each time.

[0044] Because the heating and stirring of the heating and stirring furnace is gradually performed in the process of lubricating oil preparation, in the initial stage of heating, the temperature of the lubricating oil raw material has not completely risen, and the fluidity is also relatively poor, so the raw material is dispersed slowly under the action of stirring, and the heating action of the heating and stirring furnace is from bottom to top, so the raw material in the upper layer of the heating and stirring furnace will be heated slower than the lower layer, and needs to be stirred for a certain time to complete uniform heating. Therefore, only by controlling the temperature of the heating and stirring furnace through the raw material heating uniformity, the temperature may be too high, which will affect the preparation quality of the lubricating oil. Therefore, the heating process in the preparation process needs to be analyzed.

[0045] The information entropy of the representative reflectance value of all pixels in the raw material hyperspectral data at each time is calculated, which is recorded as the raw material dispersion value at each time; the ratio of the difference between the raw material dispersion values at each time and the previous time to the preset sampling interval T is recorded as the raw material heating and stirring speed at each time; A sequence composed of the raw material heating and stirring speeds of the previous preset number M=10 times at each time is recorded as the trend sequence at each time; the trend intensity of the trend sequence is obtained, which is recorded as the raw material mixing trend coefficient at each time; It should be noted that the trend intensity of the sequence can be obtained by calculating the trend intensity formula in the STL sequence decomposition algorithm, which is a known technology, and the process will not be described herein. When there are less than 10 times before the time, the data is filled by the mean filling method, which is a known technology, and the process will not be described herein.

[0046] When the raw material mixing trend coefficient at a single time is greater, it indicates that the heating and stirring speed of the raw material at this time has a stronger trend of increasing, and it is more likely to be in the heating stage. On the contrary, it indicates that the heating and stirring speed of the raw material at this time is small, and the time may be in the heating and stirring holding stage after heating.

[0047] The material temperature uniformity index of the single time is determined according to the mean value change of the distance between all the pixels of each material at the single time and the change stable state.

[0048] Specifically, the sum of the average values of all the material clustering clusters at each time is calculated, denoted as the material temperature dispersion value at each time; the difference between the material temperature dispersion values at each time and the previous time is calculated, denoted as the first difference; the variance of the trend sequence at each time is calculated, and the ratio of the first difference to the variance is taken as the material temperature uniformity index at each time.

[0049] When the material temperature uniformity index of the single time is larger, and the corresponding time is the initial heating stage of the material heating and stirring, and the corresponding material heating uniformity change coefficient is larger, it indicates that the temperature change of the material in the heating process is more balanced, and the current heating temperature of the heating and stirring furnace is more suitable; when the material temperature uniformity index of the single time is smaller, and the corresponding time is the holding stage of the material heating and stirring, and the corresponding material heating uniformity change coefficient is larger, it indicates that the temperature of the material heating and stirring is more uniform at this time.

[0050] Further, according to the above analysis of the influence of the material temperature uniformity index change on the uniformity of the material heating and stirring, the material heating uniformity change coefficient is determined according to the material mixing trend coefficient of the single time and the material temperature uniformity index.

[0051] The degree of material mixing is divided into two cases: the mixing initial stage, the degree of material mixing rises; the mixing is basically completed, the degree of material mixing does not change; further, the mixing initial stage and the mixing completion stage are distinguished according to the change of the uniformity of the material heating.

[0052] Specifically, the material mixing trend coefficients of all the times are threshold segmented to obtain a mixing judgment threshold; if the material mixing trend coefficient of each time is greater than or equal to the mixing judgment threshold, the material heating uniformity change coefficient of each time is the material temperature uniformity index of each time; otherwise, the material heating uniformity change coefficient of each time is the reciprocal of the material temperature uniformity index of each time.

[0053] In this embodiment, the material mixing trend coefficients of all the times are taken as inputs, and the Otsu threshold method is used to output the material mixing progress judgment threshold. The Otsu threshold method is a known technology, and its process will not be described herein. The implementer can select a threshold segmentation method according to the actual situation, and the present application does not limit it.

[0054] When the material heating uniformity change coefficient of the single time is larger, it indicates that the temperature rising change state of the material in the heating process is more uniform, and the heating temperature of the heating and stirring furnace is more suitable at this time.

[0055] The acquisition block diagram of the material heating uniformity change coefficient of each time is shown in FIG. 4. Figure 3shown S3, the heating and stirring furnace temperature adaptation degree is obtained by combining the raw material heating uniformity and the raw material heating uniformity change coefficient, and the temperature of the heating and stirring furnace is controlled according to the numerical distribution of the heating and stirring furnace temperature adaptation degree at all times before the current time.

[0056] The heating and stirring furnace temperature adaptation degree is constructed according to the raw material heating uniformity and the raw material heating uniformity change coefficient at a single time.

[0057] The product of the raw material heating uniformity and the raw material heating uniformity change coefficient at each time is taken as the heating and stirring furnace temperature adaptation degree at each time.

[0058] The greater the heating and stirring furnace temperature adaptation degree at a single time, the better the heating or holding state of the lubricating oil raw material at the current temperature of the heating and stirring furnace, the more suitable the temperature, and the higher the flowability and the better the reaction rate.

[0059] The heating and stirring furnace temperature adaptation degrees at all times before the current time are arranged in time sequence to obtain a heating and stirring furnace temperature adaptation degree sequence, the heating and stirring furnace temperature adaptation degree sequence is taken as input, the ARIMA prediction algorithm is used with parameters p, d, and q set to (1, 1, 2), and the output is the heating and stirring furnace temperature adaptation degree at the current time. All the heating and stirring furnace temperature adaptation degrees are taken as input, and the cross-validation method is used to output the optimal segmentation threshold of the heating and stirring furnace temperature adaptation degree. As other embodiments of the present application, the optimal segmentation threshold can be obtained by using the Otsu threshold segmentation method.

[0060] When the heating and stirring furnace temperature adaptation degree is less than or equal to the optimal segmentation threshold, it is considered that the temperature of the current heating and stirring furnace is no longer suitable for the current lubricating oil raw material heating and stirring process, and needs to be adjusted.

[0061] The heating and stirring furnace intelligent control system judges the temperature adaptation of the current heating and stirring furnace according to the predicted heating and stirring furnace temperature adaptation degree and the segmentation threshold. When the temperature of the heating and stirring furnace is adapted, the heating and stirring furnace intelligent control system continues to monitor; when the temperature of the heating and stirring furnace is not adapted, the heating and stirring furnace intelligent control system outputs a temperature control signal of the heating and stirring furnace to adjust the heating temperature of the electric heating unit at the bottom of the heating and stirring furnace, thereby realizing a gas boiler temperature control method.

[0062] Based on the same inventive concept as the above method, the embodiments of the present application also provide a gas boiler temperature control system for lubricating oil preparation, which comprises a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of any one of the above gas boiler temperature control methods when executing the computer program.

[0063] Those skilled in the art can understand that, for the convenience and brevity of description, only the above-mentioned division of functional modules is taken as an example, and in actual application, the above-mentioned functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0064] The above merely describes a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for temperature control of a gas-fired boiler, characterized in that, The method includes the following steps: S1, Collect the raw material hyperspectral data of the heating process of lubricating oil preparation in the heating and stirring furnace at each time point; the raw material hyperspectral data includes: the band reflectance of each pixel position to all bands; S2, based on the differences in band reflectance and spatial distribution characteristics of pixels in the historical hyperspectral data of the raw materials at each time point, the uniformity of heating of the raw materials at each time point is obtained, specifically including: S21. Based on the differences in band reflectance of pixels in the hyperspectral data of raw materials at each time point and the spatial distribution characteristics of pixels, the density of raw material distribution at each time point is obtained. S22. Based on the differences in band reflectance and spatial distribution characteristics of all pixels in the hyperspectral data of the raw materials at adjacent time points, the stirring fluidity coefficient of the raw materials at each time point is obtained. S23, combining the raw material stirring fluidity coefficient and raw material distribution density at each moment, to obtain the raw material heating uniformity; S24. Based on the difference in the degree of disorder of the distribution of band reflectance of all pixels in the hyperspectral data of raw materials at adjacent time points, the raw material heating and stirring speed at each time point is obtained; based on the degree of dispersion of the trend of the change of the raw material heating and stirring speed at each time point, the raw material temperature uniformity index at each time point is obtained; based on the numerical distribution of the raw material temperature uniformity index at all time points, the raw material heating uniformity variation coefficient at each time point is obtained. S3, combining the uniformity of raw material heating and the uniformity of raw material heating variation coefficient, obtains the temperature adaptability of the heating and stirring furnace. Based on the numerical distribution of the temperature adaptability of the heating and stirring furnace at all times before the current time, the temperature of the heating and stirring furnace is controlled.

2. The method for temperature control of a gas-fired boiler as described in claim 1, characterized in that, The method for obtaining the raw material distribution density at each time point includes: The sequence of band reflectance of each pixel's corresponding position for all bands is denoted as the spectral sequence of each pixel; the distance between the spectral sequences of any two pixels is used as the metric distance, and density clustering is performed on all pixels to obtain each raw material cluster; For each raw material cluster, the Euclidean distance between any two pixels is used as the metric distance. Density clustering is performed on all pixels contained within the raw material cluster to obtain each sub-cluster. For each raw material cluster, the pixel with the smallest x-coordinate in each sub-cluster of the raw material cluster is obtained and denoted as the representative pixel of each sub-cluster; for any two sub-clusters, the Euclidean distance between the representative pixels of the two sub-clusters is calculated and denoted as the first distance; the mean of the first distances of all sub-clusters contained in the raw material cluster is obtained; the ratio of the total number of pixels in the raw material cluster to the mean is taken as the raw material aggregation degree of each raw material cluster. Obtain the sum of the mean values ​​of all raw material clusters, and record it as the total raw material density value; calculate the cumulative sum of the raw material aggregation degree of all raw material clusters, and use the ratio of the cumulative sum to the total raw material density value as the raw material distribution density at each time point.

3. The method for temperature control of a gas-fired boiler as described in claim 2, characterized in that, The method for obtaining the material stirring fluidity coefficient at each time point includes: The maximum value of the band reflectance of each pixel's corresponding position for all bands is selected as the representative reflectance value of each pixel; the Euclidean distance between any two pixels within each raw material cluster is obtained; the average value of all the Euclidean distances within each raw material cluster is obtained. For the raw material hyperspectral data at each time point, calculate the information entropy of the representative reflectance values ​​of all pixels in the raw material hyperspectral data; obtain the sum of the average values ​​of all raw material clusters in the raw material hyperspectral data, and record it as the discrete total value of the raw material at each time point; Based on the differences in the numerical distribution of representative reflectance values ​​of all pixels in the hyperspectral data of the raw material at adjacent time points, as well as the differences in the total discrete value of the raw material, the stirring fluidity coefficient of the raw material at each time point is obtained.

4. The method for temperature control of a gas-fired boiler as described in claim 3, characterized in that, The method for obtaining the material stirring fluidity coefficient at each time point includes: For each time other than the initial time, calculate the difference in information entropy between each time and the previous time, and denot it as information difference; obtain the difference in the total discrete value of raw materials between each time and the previous time, and denot it as raw material distribution difference; and fused the raw material distribution difference and information difference between each time and the previous time, and denot it as the raw material mixing fluidity coefficient at each time.

5. The method for temperature control of a gas-fired boiler as described in claim 1, characterized in that, The method of combining the raw material stirring fluidity coefficient and the raw material distribution density at each time point to obtain the raw material heating uniformity includes: taking the ratio of the raw material stirring fluidity coefficient to the raw material distribution density at each time point as the raw material heating uniformity at each time point.

6. The method for temperature control of a gas-fired boiler as described in claim 1, characterized in that, The method for obtaining the raw material heating and stirring speed at each time point includes: Calculate the information entropy of the representative reflectance values ​​of all pixels in the hyperspectral data of the raw material at each time point, and record it as the discrete value of the raw material at each time point; record the ratio of the difference between the discrete value of the raw material at each time point and the previous time point to the preset sampling interval T as the heating and stirring rate of the raw material at each time point.

7. The method for temperature control of a gas-fired boiler as described in claim 3, characterized in that, The method for obtaining the raw material temperature equilibrium index at each time point specifically includes: The sequence of raw material heating and stirring speeds at a predetermined number of time points prior to each time point is denoted as the trend sequence at each time point. Calculate the sum of the average values ​​of all raw material clusters at each time point, and record it as the raw material temperature discrete value at each time point; calculate the difference between the raw material temperature discrete value at each time point and the previous time point, and record it as the first difference; calculate the variance of the trend sequence at each time point, and use the ratio of the first difference to the variance as the raw material temperature equilibrium index at each time point.

8. The method for temperature control of a gas-fired boiler as described in claim 7, characterized in that, The method for obtaining the uniformity variation coefficient of raw material heating at each time point includes: Obtain the trend strength of the trend sequence at each time point, denoted as the raw material mixing trend coefficient at each time point; perform threshold segmentation on the raw material mixing trend coefficients at all times points to obtain the mixing judgment threshold; if the raw material mixing trend coefficient at each time point is greater than or equal to the mixing judgment threshold, then the raw material heating uniformity change coefficient at each time point is the raw material temperature equilibrium index at each time point; otherwise, the raw material heating uniformity change coefficient at each time point is the reciprocal of the raw material temperature equilibrium index at each time point.

9. The method for temperature control of a gas-fired boiler as described in claim 1, characterized in that, The temperature adaptability of the heating and stirring furnace is obtained by combining the uniformity of raw material heating and the coefficient of variation of raw material heating uniformity. Based on the numerical distribution of the temperature adaptability of the heating and stirring furnace at all times prior to the current moment, the temperature of the heating and stirring furnace is controlled, including: The product of the uniformity of raw material heating and the coefficient of variation of raw material heating uniformity at each time moment is taken as the temperature adaptability of the heating and stirring furnace at each time moment. A prediction algorithm is used to obtain the heating and stirring furnace temperature fit at the current moment by considering the heating and stirring furnace temperature fit at all moments before the current moment; threshold segmentation is performed on the heating and stirring furnace temperature fit at all moments to obtain the optimal segmentation threshold. If the temperature fit of the heating and stirring furnace at the current moment is less than or equal to the optimal segmentation threshold, then adjust the temperature of the heating and stirring furnace.

10. A temperature control system for a gas-fired boiler used for lubricating oil preparation, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the gas boiler temperature control method as described in any one of claims 1-9.

Images