An energy-saving heating furnace abnormal state evaluation identification method and system

Abstract

The application provides an energy-saving heating furnace abnormal state evaluation and identification method and system, and relates to the technical field of heating furnaces.The energy-saving heating furnace abnormal state evaluation and identification method comprises the following steps: obtaining temperature data and position data of each monitoring node inside the energy-saving heating furnace; constructing a spatial distribution map of the internal temperature of the energy-saving heating furnace by using the inverse distance weighted interpolation method according to the temperature data and the position data; establishing a semi-variance function of the internal temperature of the energy-saving heating furnace based on the spatial distribution map of the internal temperature of the energy-saving heating furnace; and calculating a temperature variation index of the energy-saving heating furnace; evaluating the running state of the energy-saving heating furnace according to the temperature variation index, and identifying the abnormal area of the energy-saving heating furnace based on the evaluation result.The application can timely warn the abnormal running state of the heating furnace and identify the abnormal area based on the evaluation result.

Description

Technical Field

[0001] This invention relates to the field of heating furnace technology, and more specifically, to a method and system for assessing and identifying abnormal states in an energy-saving heating furnace. Background Technology

[0002] Energy-efficient heating furnaces, as highly efficient and environmentally friendly industrial equipment, play a vital role in modern industrial production. With the growth of global energy demand and increasing environmental awareness, the industrial sector is placing greater emphasis on the application and development of energy-saving and emission-reduction technologies. These furnaces utilize advanced technologies and designs to minimize energy loss and optimize thermal efficiency, thereby significantly reducing energy consumption and greenhouse gas emissions. By improving combustion technology, enhancing heat exchange efficiency, and introducing intelligent control systems, energy-efficient heating furnaces can achieve lower operating costs and higher energy utilization efficiency while meeting production needs. Furthermore, the application of energy-efficient heating furnaces helps improve the automation and precision of production processes, directly impacting product quality and increased production efficiency.

[0003] Currently, temperature monitoring systems for traditional heating furnaces typically rely on a limited number of monitoring points. This restricts the scope and accuracy of monitoring, making it impossible to comprehensively cover all areas within the furnace. Temperature changes in critical areas may not be detected in a timely manner. This limitation not only affects heating performance and energy efficiency but can also lead to uneven heating. Furthermore, in existing technologies, the identification of abnormal areas often depends on operator experience or simple threshold settings. This approach is susceptible to human error or may overlook minute but critical temperature changes due to insufficient data processing, increasing risks and uncertainties in the production process.

[0004] No effective solutions have yet been proposed to address the problems in the relevant technologies. Summary of the Invention

[0005] In view of this, and in response to the problems in the related technologies, the present invention provides an energy-saving heating furnace abnormal state assessment and identification method and system to solve the aforementioned problems.

[0006] To solve the above problems, the specific technical solution adopted by the present invention is as follows:

[0007] According to one aspect of the present invention, a method for assessing and identifying abnormal states of an energy-saving heating furnace is provided, the method comprising the following steps:

[0008] S1. Obtain temperature and location data of each monitoring node inside the energy-saving heating furnace;

[0009] S2. Clean the temperature and location data of each monitoring node; divide the internal space of the energy-saving heating furnace into multiple search areas based on the cleaned location data; calculate the unknown points inside the energy-saving heating furnace using the inverse distance weighted interpolation method within each search area based on the cleaned temperature data; construct a spatial distribution map of the internal temperature of the energy-saving heating furnace based on the interpolation results.

[0010] S3. Based on the spatial distribution map of the internal temperature of the energy-saving heating furnace, establish the semivariance function of the internal temperature of the energy-saving heating furnace; and calculate the temperature variation index of the energy-saving heating furnace.

[0011] S4. Assess the operating status of the energy-saving heating furnace based on the temperature variation index, and identify abnormal areas of the energy-saving heating furnace based on the assessment results;

[0012] Preferably, constructing a spatial distribution map of the internal temperature of an energy-saving heating furnace using inverse distance weighted interpolation based on temperature and location data includes the following steps:

[0013] The temperature and location data of each monitoring node are cleaned and processed.

[0014] Based on the location data after cleaning, the internal space of the energy-saving heating furnace is divided into multiple search areas;

[0015] Based on the temperature data after cleaning, the unknown points inside the energy-saving heating furnace are interpolated using the inverse distance weighted interpolation method within each search area.

[0016] Based on the interpolation results, a spatial distribution map of the internal temperature of the energy-saving heating furnace is constructed.

[0017] Preferably, based on the temperature and location data after cleaning, the internal space of the energy-saving heating furnace is divided into multiple search areas, including the following steps:

[0018] Obtain the structural parameters of the energy-saving heating furnace, and make preliminary divisions of the internal space of the energy-saving heating furnace into equal areas;

[0019] Based on the location data of the monitoring nodes after cleaning, analyze the distribution of the monitoring nodes in the initially divided areas;

[0020] Based on the node distribution, the initially divided areas are adjusted to obtain multiple search areas.

[0021] Preferably, based on the temperature data after cleaning, the inverse distance weighted interpolation method is used to perform interpolation calculations for unknown points inside the energy-saving heating furnace within each search area, including the following steps:

[0022] The grey relational analysis method was used to determine the dynamic and static index factors for temperature control in energy-saving heating furnaces.

[0023] Based on the determined dynamic and static index factors, and according to the cleaned temperature data, the temperature data, location data, and dynamic and static indexes of the known nodes in each search area are determined.

[0024] Calculate the distance between unknown nodes and known nodes within each search region;

[0025] Calculate the distance weight of each known node based on the distance between unknown nodes and known nodes within each search area;

[0026] Based on the distance weights of each known node, the estimated temperature value of the unknown node is calculated using the weighted average method, and the interpolation result is obtained.

[0027] Preferably, the determination of dynamic and static index factors for temperature control of energy-saving heating furnaces using the grey relational analysis method includes the following steps:

[0028] Collect control parameters of energy-saving heating furnaces, use the control parameters as independent variables to form a comparison ratio, and use the temperature data of monitoring nodes as dependent variables to form a reference sequence;

[0029] The reference sequence and the comparison sequence are standardized separately.

[0030] Calculate the absolute difference between the standardized reference sequence and each comparison sequence to obtain the absolute difference matrix, and select the maximum and minimum values ​​in the absolute difference matrix;

[0031] Based on the absolute difference matrix and the preset resolution coefficients, calculate the correlation coefficient between each comparison sequence and the reference sequence;

[0032] The correlation coefficient of each comparison sequence is averaged to obtain the correlation degree, and dynamic and static index factors that meet the preset number are selected based on the magnitude of the correlation degree.

[0033] Preferably, the formula for calculating the distance weight of each known node based on the distance between unknown nodes and known nodes within each search area is as follows:

[0034] ;

[0035] In the formula, W i Represents known nodes i Distance weights;

[0036] λ k Representing unknown nodes and known nodes i Distance coefficient;

[0037] β i , k The first indicator of temperature control in energy-saving heating furnaces i The node of the first k A combination of dynamic and static indicators;

[0038] β j , k The first indicator of temperature control in energy-saving heating furnaces j The node of the first k A combination of dynamic and static indicators;

[0039] m This represents the total number of dynamic and static indicators for temperature control in energy-saving heating furnaces;

[0040] ω k The first indicator of temperature control in energy-saving heating furnaces k Weights of dynamic and static indicators.

[0041] Preferably, the formula for calculating the estimated temperature value of the unknown node using the weighted average method based on the distance weights of each known node is as follows:

[0042] ;

[0043] In the formula, G ( x , y , z () represents the estimated temperature value of an unknown node;

[0044] W i Represents known nodes i Distance weights;

[0045] F i Represents known nodes i Temperature data;

[0046] n This indicates the number of known nodes.

[0047] Preferably, based on the spatial distribution map of the internal temperature of the energy-saving heating furnace, a semivariance function of the internal temperature of the energy-saving heating furnace is established; and the temperature variation index of the energy-saving heating furnace is calculated, including the following steps:

[0048] For each node in the spatial distribution diagram of the internal temperature of the energy-saving heating furnace, determine the temperature difference and distance between that node and other nodes;

[0049] Based on the determined temperature difference and distance values, calculate the semivariogram value between each pair of nodes and construct the semivariogram function of temperature;

[0050] Calculate the total volume of temperature variation inside the furnace based on the semivariance function of temperature;

[0051] The temperature variation index of the energy-saving furnace is calculated based on the total volume of temperature variation inside the furnace and the average variance of the temperature inside the furnace.

[0052] Preferably, the formula for calculating the semivariance function of temperature is:

[0053] ;

[0054] In the formula, R ( h () indicates at a preset distance h The semivariance function between each pair of nodes;

[0055] F i and F i+h Indicates at the preset distance h Temperature data at the tail and head positions of all nodes;

[0056] N ( h () indicates at a preset distance h The number of all nodes;

[0057] i Indicates at the preset distance h The index of the node below.

[0058] Preferably, assessing the operating status of the energy-saving furnace based on the temperature variation index and identifying abnormal areas of the energy-saving furnace based on the assessment results includes the following steps:

[0059] The calculated temperature variation index is compared and analyzed with the preset benchmark value;

[0060] If the comparison results show that the temperature variation index exceeds the preset benchmark value, it is determined that the energy-saving heating furnace is in an abnormal operating state.

[0061] The spatial distribution map of the internal temperature of an energy-saving heating furnace is used to identify abnormal areas in the furnace's operating status.

[0062] According to another aspect of the present invention, an energy-saving heating furnace abnormal state assessment and identification system is provided. The energy-saving heating furnace abnormal state assessment and identification system includes: a data acquisition module, a spatial distribution map construction module, a variation index calculation module, and an abnormal state assessment module, and the data acquisition module, the spatial distribution map construction module, the variation index calculation module, and the abnormal state assessment module are connected in sequence.

[0063] The data acquisition module is used to acquire temperature and location data of each monitoring node inside the energy-saving heating furnace;

[0064] The spatial distribution map construction module is used to clean the temperature and location data of each monitoring node; based on the cleaned location data, the internal space of the energy-saving heating furnace is divided into multiple search areas; based on the cleaned temperature data, in each search area, the inverse distance weighted interpolation method is used to interpolate the unknown points inside the energy-saving heating furnace; based on the interpolation results, a spatial distribution map of the internal temperature of the energy-saving heating furnace is constructed.

[0065] The variation index calculation module is used to establish the semivariance function of the internal temperature of the energy-saving heating furnace based on the spatial distribution map of the internal temperature of the energy-saving heating furnace; and to calculate the temperature variation index of the energy-saving heating furnace.

[0066] The abnormal status assessment module is used to assess the operating status of the energy-saving furnace based on the temperature variation index and identify abnormal areas of the energy-saving furnace based on the assessment results.

[0067] Compared with the prior art, the present invention provides a method and system for assessing and identifying abnormal states of energy-saving heating furnaces, which has the following beneficial effects:

[0068] (1) By monitoring the temperature and location data of each node, this invention can more accurately understand the temperature distribution inside the heating furnace, which helps to adjust and optimize the heating process, thereby improving energy efficiency and energy saving. The spatial distribution map of the internal temperature of the energy-saving heating furnace is constructed by using the inverse distance weighted interpolation method, so that the temperature data can be displayed intuitively and visually, which helps operators and engineers to understand the temperature distribution inside the heating furnace more intuitively, and facilitates the timely detection of temperature anomalies or hot spots. The semivariance function of the internal temperature of the energy-saving heating furnace is established, and the temperature variation index is calculated, which helps to more accurately judge the operating status of the heating furnace. By evaluating the temperature variation index, the abnormal operating status of the heating furnace can be warned in time, and the abnormal area can be identified based on the evaluation results.

[0069] (2) Based on the structural parameters of the energy-saving heating furnace and the location data of the monitoring nodes, the present invention divides the internal space of the heating furnace into multiple search areas. The refined division helps to perform temperature interpolation calculations more accurately in each area. The grey relational method is used to determine the dynamic and static index factors of the temperature control of the energy-saving heating furnace, so that the temperature interpolation calculation is not only based on distance, but also considers the actual operating conditions and control parameters of the heating furnace, which improves the accuracy and practicality of interpolation. The constructed temperature spatial distribution map realizes the visualization of the internal temperature of the heating furnace, which makes it convenient for operators and engineers to monitor the operating status of the heating furnace in real time.

[0070] (3) By calculating the temperature difference and distance between each pair of nodes and constructing the semivariance function of temperature, this invention can accurately quantify the temperature variability inside the heating furnace, which helps to understand the non-uniformity of temperature distribution more accurately. The temperature variability index, as an indicator for evaluating the operating status of the heating furnace, can comprehensively reflect the temperature distribution and operating stability inside the heating furnace. By comparing and analyzing with the preset benchmark value, abnormal operating status of the heating furnace can be detected in a timely manner, providing an effective method for the dynamic operation evaluation of energy-saving heating furnaces. Attached Figure Description

[0071] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly described below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0072] Figure 1 This is a flowchart of an energy-saving heating furnace abnormal state assessment and identification method according to an embodiment of the present invention;

[0073] Figure 2 This is a schematic diagram of the energy-saving heating furnace abnormal state assessment and identification method system according to an embodiment of the present invention.

[0074] In the picture:

[0075] 1. Data acquisition module; 2. Spatial distribution map construction module; 3. Variation index calculation module; 4. Abnormal state assessment module. Detailed Implementation

[0076] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0077] According to an embodiment of the present invention, a method and system for assessing and identifying abnormal states of an energy-saving heating furnace are provided.

[0078] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments, such as... Figure 1 As shown, according to an embodiment of the present invention, an energy-saving heating furnace abnormal state assessment and identification method is provided, which includes the following steps:

[0079] S1. Obtain temperature and location data of each monitoring node inside the energy-saving heating furnace;

[0080] It should be noted that before acquiring temperature and location data for each monitoring node inside the energy-saving heating furnace, temperature sensors, such as thermocouples, resistance temperature detectors (RTDs), or infrared temperature sensors, should be installed at key locations inside the furnace. These sensors can measure and transmit temperature data in real time. Location data for each monitoring node can be obtained by setting up a coordinate system inside the furnace or by using GPS.

[0081] S2. Clean the temperature and location data of each monitoring node; divide the internal space of the energy-saving heating furnace into multiple search areas based on the cleaned location data; calculate the unknown points inside the energy-saving heating furnace using the inverse distance weighted interpolation method within each search area based on the cleaned temperature data; construct a spatial distribution map of the internal temperature of the energy-saving heating furnace based on the interpolation results.

[0082] It should be noted that the cleaning process includes handling missing values, removing outliers, and data smoothing.

[0083] As a preferred embodiment, dividing the internal space of the energy-saving heating furnace into multiple search areas based on the temperature and location data after cleaning includes the following steps:

[0084] Obtain the structural parameters of the energy-saving heating furnace, and make preliminary divisions of the internal space of the energy-saving heating furnace into equal areas;

[0085] Based on the location data of the monitoring nodes after cleaning, analyze the distribution of the monitoring nodes in the initially divided areas;

[0086] Based on the node distribution, the initially divided areas are adjusted to obtain multiple search areas, ensuring that each search area has a sufficient number of monitoring nodes.

[0087] For example, suppose the internal structural parameters of an energy-saving heating furnace are as follows: the furnace shape is cylindrical; the diameter is 1 meter; the height is 2 meters; and several temperature sensors are evenly distributed on the furnace wall; the number of monitoring nodes is set to 12 temperature sensors; based on the furnace size, the internal space can be initially divided into 4 or 8 sector regions. The location data of the monitoring nodes is read, and the number of monitoring nodes in each initially divided region is calculated. If a sector region has a low number of monitoring nodes, it can be merged with adjacent sector regions, or the densely populated area can be divided into smaller search areas.

[0088] As a preferred embodiment, based on the temperature data after cleaning, the unknown points inside the energy-saving heating furnace are interpolated using the inverse distance weighted interpolation method within each search area, including the following steps:

[0089] The grey relational analysis method was used to determine the dynamic and static index factors for temperature control in energy-saving heating furnaces.

[0090] As a preferred embodiment, determining the dynamic and static index factors for temperature control of an energy-saving heating furnace using the grey relational analysis method includes the following steps:

[0091] Collect control parameters of energy-saving heating furnaces, use the control parameters as independent variables to form a comparison ratio, and use the temperature data of monitoring nodes as dependent variables to form a reference sequence;

[0092] It should be noted that the control parameters to be collected are determined based on the actual operating conditions and control strategy of the heating furnace. These parameters include the furnace power, fuel flow rate, air flow rate, furnace pressure, flue gas temperature, and feedwater temperature. Historical data of these control parameters are collected through the furnace's control system or relevant sensors.

[0093] In grey relational analysis, independent variables are the factors that influence the dependent variable. Control parameters are used as independent variables because they directly affect the furnace temperature. The data sequence for each control parameter is used as a comparison sequence to compare with a reference sequence (i.e., the temperature data from the monitoring nodes). The number of comparison sequences depends on the number of control parameters. The dependent variable is the variable affected by the independent variables. The temperature data from the monitoring nodes are used as the dependent variable because they are an important reflection of the furnace's operating status. The temperature data from the monitoring nodes are arranged in a time series to form a reference sequence. This reference sequence is used to compare with the comparison sequences to analyze the impact of the control parameters on temperature.

[0094] The reference sequence and the comparison sequence are standardized separately.

[0095] It should be noted that standardization is performed to eliminate the influence of dimensions and orders of magnitude between different sequences, making them comparable. Commonly used standardization methods include the range method and the mean method.

[0096] Calculate the absolute difference between the standardized reference sequence and each comparison sequence to obtain the absolute difference matrix, and select the maximum and minimum values ​​in the absolute difference matrix;

[0097] It should be noted that all calculated absolute differences are arranged in the order of the comparison sequence and time points to form a matrix, namely the absolute difference matrix. Based on the absolute difference matrix and the preset resolution coefficient, the correlation coefficient between each comparison sequence and the reference sequence is calculated.

[0098] Specifically, the resolution coefficient is used to measure the small variations in absolute differences that need to be considered when calculating the correlation coefficient. A large resolution coefficient means that only large absolute differences will affect the correlation coefficient; conversely, a small resolution coefficient means that even small absolute differences will be included in the calculation of the correlation coefficient. The resolution coefficient is a number between 0 and 1, typically taken as 0.5.

[0099] For each comparison sequence, the maximum absolute difference between that sequence and the reference sequence is found. The correlation coefficient between each comparison sequence and the reference sequence is obtained by subtracting the maximum absolute difference from the resolution coefficient. The closer the correlation coefficient is to 1, the more similar the comparison sequence and the reference sequence are; the closer it is to 0, the greater the difference between them.

[0100] The correlation coefficient of each comparison sequence is averaged to obtain the correlation degree, and dynamic and static index factors that meet the preset number are selected based on the magnitude of the correlation degree.

[0101] Specifically, based on the degree of correlation, a number of dynamic and static indicator factors are selected as important dynamic and static indicator factors.

[0102] Based on the determined dynamic and static index factors, and according to the cleaned temperature data, the temperature data, location data, and dynamic and static indexes of the known nodes in each search area are determined.

[0103] Calculate the distance between unknown nodes and known nodes within each search region;

[0104] It should be noted that for each unknown node, the distance between two nodes can be calculated using the Euclidean distance formula.

[0105] Calculate the distance weight of each known node based on the distance between unknown nodes and known nodes within each search area;

[0106] As a preferred embodiment, the formula for calculating the distance weight of each known node based on the distance between unknown nodes and known nodes within each search area is as follows:

[0107] ;

[0108] In the formula, W i Represents known nodes i Distance weights;

[0109] λ k Representing unknown nodes and known nodes i Distance coefficient;

[0110] βi , k The first indicator of temperature control in energy-saving heating furnaces i The node of the first k A combination of dynamic and static indicators;

[0111] β j , k The first indicator of temperature control in energy-saving heating furnaces j The node of the first k A combination of dynamic and static indicators;

[0112] m This represents the total number of dynamic and static indicators for temperature control in energy-saving heating furnaces;

[0113] ω k The first indicator of temperature control in energy-saving heating furnaces k Weights of dynamic and static indicators.

[0114] It should be noted that the distance coefficient and the weights of dynamic and static indicators are pre-set parameters, usually determined by expert experience or experimental data. The distance coefficient is an adjustment factor used to balance the influence of distance. When the distance coefficient is larger, the influence of distance is greater, and vice versa. Typically, the distance coefficient can be determined through experiments or expert experience, or it can be adjusted according to actual application needs. The weights of dynamic and static indicators are parameters reflecting the relative importance of different dynamic and static indicators. The importance of each indicator can be determined based on the actual situation and objectives. For example, some indicators may contribute more to energy saving, so their corresponding weights should be higher. Similarly, these weights can also be determined through expert experience or experimental data.

[0115] Based on the distance weights of each known node, the estimated temperature value of the unknown node is calculated using the weighted average method, and the interpolation result is obtained.

[0116] As a preferred embodiment, the formula for calculating the estimated temperature value of the unknown node using a weighted average method based on the distance weights of each known node is as follows:

[0117] ;

[0118] In the formula, G ( x , y , z () represents the estimated temperature value of an unknown node;

[0119] W i Represents known nodes i Distance weights;

[0120] F i Represents known nodes i Temperature data;

[0121] n This indicates the number of known nodes.

[0122] Specifically, constructing a spatial distribution map of the internal temperature of an energy-saving heating furnace based on the interpolation calculation results includes the following steps: selecting a 3D visualization tool that supports the establishment of a 3D coordinate system and the visualization of temperature data; establishing a 3D coordinate system in the visualization tool based on the actual size and shape of the heating furnace, and marking the coordinate positions of each node in this coordinate system; mapping the estimated temperature values ​​obtained from the interpolation calculation to the corresponding 3D coordinate nodes, and using the functions provided by the visualization tool, such as color mapping and isosurface plotting, to represent the temperature data in an intuitive way; typically, different colors can be used to represent different temperatures, such as red for high temperature and blue for low temperature.

[0123] Taking a certain energy-saving heating furnace as an example, its actual dimensions are a cubic structure with a length of 5 meters, a width of 3 meters, and a height of 2 meters. First, select a 3D visualization tool and establish a 3D coordinate system based on the actual dimensions of the heating furnace: with the lower left corner of the furnace body as the origin (0,0,0), the length direction as the X-axis (0-5 meters), the width direction as the Y-axis (0-3 meters), and the height direction as the Z-axis (0-2 meters).

[0124] The estimated temperature values ​​for each node inside the furnace are obtained through interpolation calculation. For example, the interpolated temperature of the central area at the bottom of the heating furnace (2.5, 1.5, 0.2) is 1200℃ (high temperature zone), which is mapped to red; the interpolated temperature of the central edge area of ​​the heating furnace (4.8, 0.5, 1.0) is 700℃ (medium temperature zone), which is mapped to orange; and the interpolated temperature of the corner area at the top of the heating furnace (0.2, 2.8, 1.8) is 400℃ (low temperature zone), which is mapped to blue.

[0125] In the visualization tool, these temperature values ​​are mapped to corresponding 3D coordinate nodes, and a color gradient mapping function is used: a temperature gradient bar is set, with temperatures above 1200℃ set to a red gradient, 800-1200℃ to an orange gradient, 400-800℃ to a yellow gradient, and below 400℃ to a blue gradient. At this point, the temperature distribution inside the furnace will show clear color stratification, with large areas of red in the high-temperature zone near the burner, gradually transitioning to orange, yellow, and finally blue in the lower-temperature zone further away from the burner.

[0126] Further utilizing the isosurface plotting function, a 900℃ isothermal surface is extracted. This isothermal surface forms a continuous curved surface that envelops the high-temperature core region, visually displaying the temperature decay trend from the core to the edge. For example, on a longitudinal section of X=2.5 meters in the middle of the furnace body, the isothermal surface shows a longitudinal temperature gradient from 1200℃ (red) at the bottom to 600℃ (yellow) at the top; on a transverse section of Y=1.5 meters, it shows a lateral diffusion characteristic from high temperature at the center to medium temperature on both sides. The generated three-dimensional temperature distribution map can be rotated for observation, and the temperature field characteristics can be clearly identified from any angle: the high-temperature red area near the burner at the bottom of the furnace is concentrated, gradually transitioning to orange and yellow towards the top and sides, and finally forming a blue low-temperature area at the corner of the furnace top.

[0127] Based on the spatial distribution map of the internal temperature of the energy-saving heating furnace, a semivariance function of the internal temperature of the energy-saving heating furnace is established; and the temperature variation index of the energy-saving heating furnace is calculated.

[0128] As a preferred embodiment, based on the spatial distribution map of the internal temperature of the energy-saving heating furnace, a semivariance function of the internal temperature of the energy-saving heating furnace is established; and the temperature variation index of the energy-saving heating furnace is calculated, including the following steps:

[0129] For each node in the spatial distribution diagram of the internal temperature of the energy-saving heating furnace, determine the temperature difference and distance between that node and other nodes;

[0130] Based on the determined temperature difference and distance values, calculate the semivariogram value between each pair of nodes and construct the semivariogram function of temperature;

[0131] As a preferred embodiment, the formula for calculating the semivariance function of temperature is:

[0132] ;

[0133] In the formula, R ( h () indicates at a preset distance h The semivariance function between each pair of nodes;

[0134] F i and F i+h Indicates at the preset distance h Temperature data at the tail and head positions of all nodes;

[0135] N ( h () indicates at a preset distance h The number of all nodes;

[0136] i Indicates at the preset distance hThe index of the node below.

[0137] in, F i - F i+h This represents the temperature difference.

[0138] Calculate the total volume of temperature variation inside the furnace based on the semivariance function of temperature;

[0139] Specifically, calculating the total volume of temperature variation inside the furnace based on the semivariance function of temperature is an integral process involving the accumulation of the area under the semivariance function curve. This includes the following steps: determining the effective integration interval of the semivariance function, which typically starts from 0 and extends to a certain maximum distance. h max ,in, h max This is the maximum distance between nodes inside the heating furnace. Based on the shape and characteristics of the semivariance function, the trapezoidal rule and Simpson's rule are used to analyze the semivariance function. R ( h In the integration interval [0, h max Integrate on [the surface]. The result of the integration is the total volume of temperature variation inside the heating furnace. V The total variability volume V reflects the overall temperature variability inside the furnace. A larger V value indicates more drastic spatial temperature changes, while a smaller V value... V The value indicates that the temperature is relatively more uniform.

[0140] The temperature variation index of the energy-saving furnace is calculated based on the total volume of temperature variation inside the furnace and the average variance of the temperature inside the furnace.

[0141] Specifically, the temperature variability index of an energy-saving heating furnace is an indicator used to quantify the temperature variability inside the furnace. It is calculated based on the total volume of temperature variation and the average variance within the furnace. The specific steps include:

[0142] Temperature data from all nodes are statistically analyzed, and the average of the squares of their differences from the mean temperature is calculated. The total volume of temperature variation inside the furnace, calculated previously, is used. The temperature variability index is calculated by dividing the total volume of variation by the mean variance. The temperature variability index provides a standardized measure for comparing temperature variability across different furnaces or operating conditions.

[0143] S4. Assess the operating status of the energy-saving heating furnace based on the temperature variation index, and identify abnormal areas of the energy-saving heating furnace based on the assessment results;

[0144] As a preferred embodiment, assessing the operating status of the energy-saving heating furnace based on the temperature variation index and identifying abnormal areas of the energy-saving heating furnace based on the assessment results includes the following steps:

[0145] The calculated temperature variation index is compared and analyzed with the preset benchmark value;

[0146] It should be noted that the preset benchmark value is set based on historical data or industry standards during normal operation of the heating furnace, and it represents an acceptable range of temperature variability. By comparing the calculated temperature variability index with the preset benchmark value, it can be determined whether the current temperature variability of the heating furnace is within the normal range.

[0147] If the comparison results show that the temperature variation index exceeds the preset benchmark value, it is determined that the energy-saving heating furnace is in an abnormal operating state.

[0148] Specifically, if the temperature variation index exceeds the preset benchmark value, it indicates that there is a significant unevenness in the temperature distribution inside the heating furnace, which may be caused by some abnormal factors. Therefore, it can be determined that the operating status of the energy-saving heating furnace is abnormal and further inspection and adjustment are required.

[0149] The spatial distribution map of the internal temperature of an energy-saving heating furnace is used to identify abnormal areas in the furnace's operating status.

[0150] Specifically, identifying abnormal areas in the operating status of an energy-saving heating furnace using a spatial distribution map of its internal temperature includes the following steps:

[0151] Observe the spatial distribution map of the internal temperature of the energy-saving heating furnace. The spatial distribution map clearly shows the temperature distribution in various areas inside the furnace. On the spatial distribution map, identify areas where the temperature deviates significantly from the normal range. These areas may be too hot or too cold, showing a significant difference compared to the surrounding areas. For the identified abnormal temperature areas, further analyze the causes of the anomalies. For example, heating element failure, insulation layer damage, and cooling system failure can all lead to localized temperature anomalies. Mark the abnormal areas on the spatial distribution map for subsequent handling and monitoring. Different colors or symbols can be used to highlight these areas for easy identification. Based on the analysis results of the abnormal areas, formulate corresponding handling measures.

[0152] For example, taking an energy-saving heating furnace as an example, its internal temperature distribution diagram shows that the right side of the top of the furnace body (coordinate range X=4.5-5.0m, Y=2.5-3.0m, Z=1.5-2.0m) exhibits a distinct blue low-temperature patch with a temperature of only 350℃, while the surrounding area maintains a stable temperature of 600-800℃ (orange-red area). Steps to identify abnormal areas:

[0153] Color mapping visually reveals a significant temperature difference (over 250°C) between this area and its surroundings, creating a cold island anomaly. Using a three-dimensional coordinate system, the anomaly area is located in a corner of the furnace top near the flue gas outlet, with an area of ​​approximately 0.5 m³.

[0154] Analysis of possible causes revealed a 5cm crack in the insulation layer in the area, causing heat to dissipate directly to the outside of the furnace. Temperature gradient analysis indicated that the burner nozzle below the abnormal area may have been affected by flame deviation, resulting in insufficient local heating. Comparison with historical data showed that the temperature in this area had decreased by 15% compared to the same period last month, consistent with the aging characteristics of the insulation material.

[0155] The abnormal area is highlighted in dark blue in the visualization system, and a temperature threshold alarm is set so that an automatic warning is issued when the area temperature is below 400℃.

[0156] Develop appropriate measures, including temporarily installing removable insulation modules to reduce heat loss; or replacing the refractory insulation material in the area and adjusting the burner nozzle angle to optimize flame coverage.

[0157] like Figure 2 As shown, according to another embodiment of the present invention, an energy-saving heating furnace abnormal state assessment and identification system is provided. The energy-saving heating furnace abnormal state assessment and identification system includes: a data acquisition module 1, a spatial distribution map construction module 2, a variation index calculation module 3, and an abnormal state assessment module 4, and the data acquisition module 1, the spatial distribution map construction module 2, the variation index calculation module 3, and the abnormal state assessment module 4 are connected in sequence.

[0158] Data acquisition module 1 is used to acquire temperature and location data of each monitoring node inside the energy-saving heating furnace;

[0159] The spatial distribution map construction module 2 is used to clean the temperature and location data of each monitoring node; based on the cleaned location data, the internal space of the energy-saving heating furnace is divided into multiple search areas; based on the cleaned temperature data, in each search area, the inverse distance weighted interpolation method is used to interpolate the unknown points inside the energy-saving heating furnace; based on the interpolation results, a spatial distribution map of the internal temperature of the energy-saving heating furnace is constructed.

[0160] The variation index calculation module 3 is used to establish the semivariance function of the internal temperature of the energy-saving heating furnace based on the spatial distribution map of the internal temperature of the energy-saving heating furnace; and to calculate the temperature variation index of the energy-saving heating furnace.

[0161] The abnormal state assessment module 4 is used to assess the operating status of the energy-saving heating furnace based on the temperature variation index, and to identify abnormal areas of the energy-saving heating furnace based on the assessment results.

[0162] In summary, by utilizing the above-mentioned technical solutions of this invention, the present invention can more accurately understand the temperature distribution inside the heating furnace by monitoring the temperature and location data of each node, which helps to adjust and optimize the heating process, thereby improving energy efficiency and energy saving. By using the inverse distance weighted interpolation method to construct a spatial distribution map of the internal temperature of the energy-saving heating furnace, the temperature data can be displayed intuitively and visually, which helps operators and engineers to understand the internal temperature distribution of the heating furnace more intuitively, and facilitates the timely detection of temperature anomalies or hot spots. By establishing a semivariance function of the internal temperature of the energy-saving heating furnace and calculating the temperature variation index, it helps to more accurately judge the operating status of the heating furnace. By evaluating the temperature variation index, it is possible to provide timely warnings of abnormal operating conditions of the heating furnace and identify abnormal areas based on the evaluation results. This invention divides the internal space of an energy-saving heating furnace into multiple search regions based on its structural parameters and monitoring node location data. This refined division facilitates more accurate temperature interpolation calculations within each region. The grey relational analysis method is used to determine the dynamic and static indices for temperature control in the energy-saving heating furnace. This ensures that temperature interpolation calculations are not only based on distance but also consider the actual operating conditions and control parameters of the furnace, improving the accuracy and practicality of the interpolation. The constructed temperature spatial distribution map provides a visual display of the furnace's internal temperature, facilitating real-time monitoring of the furnace's operating status by operators and engineers. By calculating the temperature difference and distance values ​​between each pair of nodes and constructing a semivariance function for temperature, this invention can accurately quantify the variability of the furnace's internal temperature, helping to more accurately understand the non-uniformity of temperature distribution. The temperature variability index, as an indicator for evaluating the furnace's operating status, comprehensively reflects the internal temperature distribution and operational stability. Through comparative analysis with preset benchmark values, abnormal operating conditions of the furnace can be detected promptly, providing an effective method for the dynamic evaluation of energy-saving heating furnaces.

[0163] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, etc.) containing computer-usable program code.

[0164] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An energy-saving heating furnace abnormal state evaluation identification method, characterized in that, The abnormal state evaluation and identification method of the energy-saving heating furnace comprises the following steps: S1, acquiring temperature data and position data of each monitoring node inside the energy-saving heating furnace; S2, performing cleaning processing on the temperature data and position data of each monitoring node; dividing the internal space of the energy-saving heating furnace into multiple search regions according to the cleaned position data; performing interpolation calculation on unknown points inside the energy-saving heating furnace in each search region by using the inverse distance weighted interpolation method according to the cleaned temperature data; and constructing a spatial distribution map of the internal temperature of the energy-saving heating furnace according to the interpolation calculation result; S3, based on the spatial distribution map of the internal temperature of the energy-saving heating furnace, establishing a semi-variance function of the internal temperature of the energy-saving heating furnace; and calculating a temperature variation index of the energy-saving heating furnace; S4, evaluating the running state of the energy-saving heating furnace according to the temperature variation index, and identifying the abnormal region of the energy-saving heating furnace based on the evaluation result; The step of dividing the internal space of the energy-saving heating furnace into multiple search regions according to the cleaned temperature data and position data comprises the following steps: acquiring the structure parameters of the energy-saving heating furnace, and performing preliminary equal-area division on the internal space of the energy-saving heating furnace; analyzing the distribution of the monitoring nodes in each region in the preliminary division according to the position data of the monitoring nodes after cleaning; adjusting the preliminary divided regions according to the node distribution to obtain multiple search regions; The step of performing interpolation calculation on unknown points inside the energy-saving heating furnace in each search region by using the inverse distance weighted interpolation method according to the cleaned temperature data comprises the following steps: determining the dynamic and static index factors of the temperature control of the energy-saving heating furnace by using the grey correlation method; based on the determined dynamic and static index factors, determining the temperature data, position data and dynamic and static index of the known nodes in each search region according to the cleaned temperature data; calculating the distance between the unknown nodes and the known nodes in each search region; calculating the distance weight of each known node according to the distance between the unknown nodes and the known nodes in each search region; calculating the estimated temperature value of the unknown node by the weighted average method according to the distance weight of each known node to obtain the interpolation calculation result; The calculation formula of the distance weight of each known node according to the distance between the unknown nodes and the known nodes in each search region is: ； wherein W i distance weight of a known node i to the known node λ k denotes the distance coefficient between the unknown node and the known node i denotes the distance coefficient between the unknown node and the known node β i , k representing the first dynamic-static index of the first node of the energy-saving type heating furnace temperature control i k control​ β j , k representing the first dynamic-static index of the first node of the energy-saving type heating furnace temperature control j k node​ m Total number of dynamic and static indexes representing energy-efficient heating furnace temperature control; ω k The first indicator of temperature control in energy-saving heating furnaces k Weights of dynamic and static indicators.

2. The method according to claim 1, wherein The step of determining the dynamic and static index factors of the temperature control of the energy-saving heating furnace by using the grey correlation method comprises the following steps: collecting the control parameters of the energy-saving heating furnace, taking the control parameters as independent variables and forming comparison ratios, and taking the temperature data of the monitoring nodes as dependent variables and forming reference sequences; respectively performing standardization processing on the reference sequences and the comparison sequences; calculating the absolute difference value between the standardized reference sequence and each comparison sequence to obtain an absolute difference value matrix, and selecting the maximum value and the minimum value in the absolute difference value matrix; calculating the correlation coefficients between each comparison sequence and the reference sequence according to the absolute difference value matrix and a preset resolution coefficient; averaging the correlation coefficients of each comparison sequence to obtain a correlation degree, and selecting dynamic and static index factors satisfying a preset number according to the size of the correlation degree.

3. The method according to claim 2, wherein The calculation formula for calculating the estimated temperature value of the unknown node by the weighted average method according to the distance weight of each known node is: ； wherein G x y z represents the estimated temperature value of the unknown node;​​​ W i representing a distance weight of a known node i ; F i represents known node i temperature data; n represents the known number of nodes.

4. The method according to claim 1, wherein The semi-variance function of the internal temperature of the energy-saving heating furnace is established based on the spatial distribution map of the internal temperature of the energy-saving heating furnace, and the temperature variation index of the energy-saving heating furnace is calculated, including the following steps: For each node in the spatial distribution map of the internal temperature of the energy-saving heating furnace, the temperature difference value and the distance value between the node and other nodes are determined; According to the determined temperature difference value and distance value, the semi-variation function value between each pair of nodes is calculated, and the semi-variance function of the temperature is constructed; The total variation volume of the internal temperature of the heating furnace is calculated according to the semi-variance function of the temperature; The temperature variation index of the energy-saving heating furnace is calculated according to the total variation volume of the internal temperature of the heating furnace and the average variance of the internal temperature of the heating furnace.

5. The method according to claim 4, wherein The calculation formula of the semi-variance function of the temperature is: ； In the formula, R ( h () indicates at a preset distance h The semivariance function between each pair of nodes; F i and F i+h representing the temperature data at the tail and head positions in all nodes at a preset distance h from the tail position N h ) represents the number of all nodes within a preset distance h from the current node.​ i an index representing a node at a preset distance h under the node.

6. The method of claim 1, wherein the method further comprises: The running state of the energy-saving heating furnace is evaluated according to the temperature variation index, and the abnormal area of the energy-saving heating furnace is identified based on the evaluation result, including the following steps: The calculated temperature variation index is compared with the preset reference value; If the comparison result shows that the temperature variation index exceeds the preset reference value, it is judged that the running state of the energy-saving heating furnace is abnormal; The abnormal area of the energy-saving heating furnace is identified by using the spatial distribution map of the internal temperature of the energy-saving heating furnace.

7. An abnormal state evaluation identification system for an energy-saving heating furnace according to any one of claims 1 to 6, characterized by The energy-saving heating furnace abnormal state evaluation and identification system comprises a data acquisition module, a spatial distribution map construction module, a variation index calculation module and an abnormal state evaluation module, and the data acquisition module, the spatial distribution map construction module, the variation index calculation module and the abnormal state evaluation module are connected in sequence; The data acquisition module is used for acquiring the temperature data and position data of each monitoring node in the energy-saving heating furnace; The spatial distribution map construction module is used for cleaning the temperature data and position data of each monitoring node; according to the cleaned position data, the internal space of the energy-saving heating furnace is divided into a plurality of search areas; according to the cleaned temperature data, the unknown points in the internal space of the energy-saving heating furnace are calculated by using the inverse distance weighted interpolation method in each search area; according to the interpolation calculation result, the spatial distribution map of the internal temperature of the energy-saving heating furnace is constructed; The variation index calculation module is used for establishing the semi-variance function of the internal temperature of the energy-saving heating furnace based on the spatial distribution map of the internal temperature of the energy-saving heating furnace, and calculating the temperature variation index of the energy-saving heating furnace; The abnormal state evaluation module is used for evaluating the running state of the energy-saving heating furnace according to the temperature variation index, and identifying the abnormal area of the energy-saving heating furnace based on the evaluation result.

Images