Non-contact Temperature Monitoring System and Method for Industrial Kilns Based on Artificial Intelligence

Abstract

The present invention relates to the technical field of temperature measurement, and specifically to a non-contact temperature monitoring system and method for industrial kilns based on artificial intelligence. By performing matching processing on the real-time air environment characteristic data in the industrial plant area and the temperature monitoring air environment impact data, industrial kiln temperature monitoring impact data is generated, and real temperature data metering processing is carried out with the temperature data of the monitored area of the industrial kiln collected, generating the real temperature data of the monitored area of the industrial kiln. According to the real temperature data analysis of the monitored area of the kiln, the real-time operation condition of the industrial kiln is analyzed, industrial kiln monitored area color display data is generated, and the kiln temperature monitoring result display data is constructed. Finally, the kiln temperature monitoring result data is constructed and pushed to the industrial kiln temperature monitoring platform to realize non-contact accurate temperature measurement of the industrial kiln and simultaneously perform intelligent monitoring on the real-time temperature data of the industrial kiln.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature measurement, and particularly to a non-contact temperature monitoring system and method for industrial furnaces based on artificial intelligence. Background Art

[0002] Industrial furnaces are applied in many industrial fields, and the monitoring results of their internal temperatures play an important role in the industrial production process. However, traditional temperature monitoring methods have many limitations and often cannot obtain reliable temperature monitoring results in the high-temperature working environment of industrial furnaces. Therefore, non-contact temperature monitoring technology has gradually become an important technical means for temperature monitoring of industrial furnaces.

[0003] The Chinese invention patent with the publication number CN101762327B introduces an infrared temperature monitoring method and system for the catenary of electrified railways. It collects visible light pictures with catenary information and thermal images with temperature data in real time through an infrared temperature monitoring device, transmits the collected image data to a server, decompresses it through the in-vehicle software centralized control system in the server, and then displays it in real time through a terminal display device. When abnormal temperature occurs, the system will issue an alarm to ensure the normal operation of electric locomotives while monitoring the catenary in real time. However, it cannot comprehensively analyze multiple groups of collected data to obtain the real-time temperature situation of the catenary, and it is difficult to ensure the influence brought by data acquisition errors and the aging of monitoring devices, and cannot ensure the accuracy of the analysis results. Summary of the Invention

[0004] (I) Technical Problems to be Solved

[0005] To solve the deficiencies in the background art, the present invention provides a non-contact temperature monitoring system and method for industrial furnaces based on artificial intelligence, which realizes non-contact accurate temperature measurement of industrial furnaces and simultaneously conducts intelligent monitoring on the real-time temperature data of industrial furnaces.

[0006] (II) Technical Solutions

[0007] A non-contact temperature monitoring method for industrial furnaces based on artificial intelligence includes the following steps:

[0008] S1. Collect real-time air environment characteristic data of the industrial plant area;

[0009] S2. Establish temperature monitoring air environment impact data, perform air environment characteristic data matching processing on the real-time air environment characteristic data of the industrial plant area and the temperature monitoring air environment impact data, and generate industrial furnace temperature monitoring impact data;

[0010] S3. Collect temperature data in the furnace monitoring area;

[0011] S4. Perform real - temperature data measurement and processing based on the kiln temperature monitoring impact data and the kiln monitoring area temperature data to generate the real temperature data of the industrial kiln monitoring area;

[0012] S5. Analyze the real - time operation status of the industrial kiln based on the real temperature data of the kiln monitoring area, and generate color display data for the industrial kiln monitoring area according to the analysis results;

[0013] S6. Construct display data for the kiln temperature monitoring results based on the color display data of the kiln monitoring area;

[0014] S7. Construct kiln temperature monitoring result data based on the real temperature data of the kiln monitoring area and the display data for the kiln temperature monitoring results, and push it to the industrial kiln temperature monitoring platform.

[0015] In the present invention, air - environment characteristic data matching processing is carried out on real - time air - environment characteristic data of the industrial plant area and temperature - monitoring air - environment impact data to generate industrial kiln temperature - monitoring impact data, and real - temperature data measurement and processing is carried out with the temperature data of the industrial kiln monitoring area collected, to generate real temperature data of the industrial kiln monitoring area. The real - time operation status of the industrial kiln is analyzed according to the real temperature data of the kiln monitoring area, color display data for the industrial kiln monitoring area is generated, and display data for the kiln temperature monitoring results is constructed. Finally, kiln temperature monitoring result data is constructed and pushed to the industrial kiln temperature monitoring platform, realizing non - contact accurate temperature measurement of the industrial kiln and simultaneously carrying out intelligent monitoring of the real - time temperature data of the industrial kiln.

[0016] Preferably, the specific steps for collecting real - time air - environment characteristic data of the industrial plant area are as follows:

[0017] S11. Real - time collect air - environment characteristic data in the working area of the target industrial kiln through an air - environment monitoring device to obtain real - time air - environment characteristic data A of the industrial plant area. The air - environment monitoring device includes a temperature sensor, a humidity sensor, a meteorological sensor, a particulate matter sensor, and a gas sensor. The air - environment characteristic data includes, but is not limited to, gas composition data, total suspended particulate concentration, air temperature, air relative humidity, wind direction data, and wind speed data.

[0018] Preferably, the specific steps for establishing temperature - monitoring air - environment impact data and performing air - environment characteristic data matching processing on the real - time air - environment characteristic data of the industrial plant area and the temperature - monitoring air - environment impact data to generate industrial kiln temperature - monitoring impact data are as follows:

[0019] S21. Establish a temperature - monitoring air - environment impact data set B = {b 1 , b 2 , …, b i,…,b k}, where b i represents the temperature monitoring influence coefficient corresponding to the i-th type of air environment characteristic data, and k represents the total number of temperature monitoring air environment influence data;

[0020] S22. Perform air environment characteristic data matching processing on the real-time air environment characteristic data A of the industrial plant area and the temperature monitoring air environment influence data in the temperature monitoring air environment influence data set to generate industrial furnace temperature monitoring influence data ;

[0021] S221. Construct an air environment characteristic search pelican population, set the scale of the air environment characteristic search pelican population as N, the current iteration number as t, the maximum iteration number as t max and the dimension of the temperature monitoring air environment influence data search space as P;

[0022] Use the temperature monitoring air environment influence data set as the temperature monitoring air environment influence data search space, randomly generate N temperature monitoring air environment influence data in the temperature monitoring air environment influence data search space, and each temperature monitoring air environment influence data corresponds to an air environment characteristic search pelican individual in the air environment characteristic search pelican population. Initialize the initial position set of the air environment characteristic search pelican population as X = {X 1 , X 2 , …, X i , …, X N}, where X i represents the initial position of the i-th air environment characteristic search pelican individual in the air environment characteristic search pelican population;

[0023] S222. Calculate the fitness function values of each air environment characteristic search pelican individual in the air environment characteristic search pelican population, arrange each air environment characteristic search pelican individual in the air environment characteristic search pelican population in descending order according to the fitness function values, and select the air environment characteristic search pelican individual with the highest fitness function value as the current optimal individual; the fitness function formula is as follows:

[0024] ,

[0025] where Fit i represents the fitness function value of the i-th air environment characteristic search pelican individual, x i represents the deviation value between the air environment characteristic data corresponding to the temperature monitoring air environment influence data corresponding to the i-th pelican individual and the real-time air environment characteristic data of the industrial plant area, represents the correction value;

[0026] S223. Exploration stage: Each individual of the air environment feature search pelican population searches for the position of the prey in the temperature monitoring air environment impact data search space and moves towards the prey position for position update. The position of the prey in the temperature monitoring air environment impact data search space is randomly generated. The position update formula is as follows:

[0027] ,

[0028] where, and X ij respectively represent the position of the i-th individual of the air environment feature search pelican population in the j-th dimension of the temperature monitoring air environment impact data search space after and before position update. α represents a random integer uniformly distributed between [1, 2]. Z j represents the position of the prey locked by the i-th individual of the air environment feature search pelican population in the j-th dimension of the temperature monitoring air environment impact data search space. rand 1 and rand 2 respectively represent random numbers uniformly distributed between (0, 1). Fit z represents the fitness function value of the prey;

[0029] S224. Development stage: Each individual of the air environment feature search pelican population uses the water surface flight strategy to hunt more prey in the temperature monitoring air environment impact data search space for position update. The position update formula is as follows:

[0030] ,

[0031] where, R represents a random integer taking values of 0 or 2. rand 2 represents a random number uniformly distributed between (0, 1);

[0032] S225. Calculate the fitness function value of each individual of the air environment feature search pelican population after position update. If the fitness function value of an individual of the air environment feature search pelican population after position update is less than the original fitness function value, replace the original position with the new position; otherwise, retain the original position;

[0033] Re-arrange each individual of the air environment feature search pelican population in descending order according to the fitness function value, and select the individual of the air environment feature search pelican with the highest fitness function value as the new current optimal individual;

[0034] S226. Determine whether the current iteration number t is less than the maximum iteration number t max . If the current iteration number t is less than the maximum iteration number t max , then increment the current iteration number t by 1 and return to S223; otherwise, take the current optimal individual as the global optimal solution, output the temperature monitoring air environment impact data corresponding to the global optimal solution and perform data identification to generate industrial furnace temperature monitoring impact data .

[0035] Match the real-time air environment characteristic data of the industrial plant area with the temperature monitoring air environment impact data through the pelican optimization algorithm to accurately match the industrial furnace temperature monitoring impact data that matches the current situation, providing a reliable data basis for the calculation of subsequent real temperature data. At the same time, the pelican optimization algorithm can improve the speed and efficiency of the matching process and reduce the response time for obtaining temperature measurement results.

[0036] Preferably, the specific steps for collecting temperature data in the furnace monitoring area are as follows:

[0037] S31. Set the temperature data collection period, evenly divide the temperature data collection period into several temperature data collection time points to obtain a temperature data collection time point set C = {c 1 , c 2 , …, c i , …, c l}, where c i represents the i-th temperature data collection time point obtained by evenly dividing the temperature data collection period, and l represents the total number of temperature data collection time points;

[0038] S32. Evenly divide the industrial furnace temperature monitoring area into several industrial furnace temperature monitoring sub-areas to obtain an industrial furnace temperature monitoring sub-area set D = {d 1 , d 2 , …, d i , …, d p}, where d i represents the i-th industrial furnace temperature monitoring sub-area obtained by evenly dividing the industrial furnace temperature monitoring area, and p represents the total number of industrial furnace temperature monitoring sub-areas;

[0039] S33. Allocate infrared temperature measuring devices to each industrial furnace temperature monitoring sub-area in the furnace temperature monitoring sub-area set, and use the infrared temperature measuring devices to collect the temperature data at the center position of the corresponding industrial furnace temperature monitoring sub-area in each temperature data collection time point in the temperature data collection time point set to obtain an industrial furnace monitoring area temperature data matrix E as follows:

[0040] ,

[0041] Among them, e ij represents the temperature data obtained by real-time collection of the central position of the j-th industrial furnace temperature monitoring sub-region at the i-th temperature data collection time point through an infrared temperature measurement device.

[0042] Preferably, the specific steps for generating the real temperature data of the industrial furnace monitoring area by performing real temperature data measurement processing according to the furnace temperature monitoring influence data and the furnace monitoring area temperature data are as follows:

[0043] S41. Perform real temperature data measurement processing on the furnace temperature monitoring influence data and the industrial furnace monitoring area temperature data in the industrial furnace monitoring area temperature data matrix E to generate an industrial furnace monitoring area real temperature data matrix as follows:

[0044] ,

[0045] Among them, represents the real temperature data of the industrial furnace monitoring area obtained after real temperature data measurement processing of the temperature data obtained by real-time collection of the central position of the j-th industrial furnace temperature monitoring sub-region at the i-th temperature data collection time point through an infrared temperature measurement device; the real temperature data calculation formula is as follows:

[0046] ,

[0047] Among them, D i represents the distance between the central position of the i-th industrial furnace temperature monitoring sub-region and its corresponding infrared temperature measurement device, and D 0 represents the unit distance.

[0048] By performing real temperature data measurement processing on the furnace temperature monitoring influence data and the furnace monitoring area temperature data through the real temperature data calculation formula, precise correction of the collected real-time temperature data is realized, effectively reducing the influence brought by the air environment and the temperature measurement distance in the non-contact temperature measurement of industrial furnaces, and ensuring the accuracy and reliability of the obtained real temperature data.

[0049] Preferably, the specific steps for generating the industrial furnace monitoring area color display data according to the analysis result by analyzing the real-time operation condition of the industrial furnace based on the real temperature data of the industrial furnace monitoring area are as follows:

[0050] S51. Set a real temperature threshold, and use the industrial furnace monitoring area real temperature data matrix The true temperature data of each industrial furnace monitoring area is numerically compared with the true temperature threshold respectively, and the total number of true temperature data of the industrial furnace monitoring area corresponding to each industrial furnace temperature monitoring sub-area that is greater than the true temperature threshold is counted, obtaining the industrial furnace monitoring area abnormal temperature number set F = {f 1 , f 2 , …, f i , …, f p}, where f i represents the total number of true temperature data greater than the true temperature threshold obtained by collecting temperature data for the i-th industrial furnace temperature monitoring sub-area;

[0051] S52. Calculate the abnormal temperature ratio of each industrial furnace temperature monitoring sub-area based on the abnormal temperature number of the industrial furnace monitoring area in the abnormal temperature number set of the furnace monitoring area, obtaining the abnormal temperature ratio set of the industrial furnace monitoring area, where represents the abnormal temperature ratio of the i-th industrial furnace temperature monitoring sub-area, and ;

[0052] S53. Set the first threshold as η 1 and the second threshold as η 2 , and numerically compare each abnormal temperature ratio of the industrial furnace monitoring area in the abnormal temperature ratio set of the furnace monitoring area with the first threshold η 1 and the second threshold η 2 in turn, and generate the industrial furnace monitoring area color display data set according to the numerical comparison result, where represents the industrial furnace monitoring area color display data corresponding to the i-th industrial furnace temperature monitoring sub-area;

[0053] The generating the industrial furnace monitoring area color display data set according to the numerical comparison result includes the following steps:

[0054] S531. Select the abnormal temperature ratio of the i-th industrial furnace monitoring area and numerically compare it with the first threshold η 1 and the second threshold η 2 ;

[0055] If , it means that the i-th industrial furnace temperature monitoring sub-area is in a non-working state, and output the industrial furnace monitoring area color display data corresponding to the i-th industrial furnace temperature monitoring sub-area as black;

[0056] If , it indicates that the temperature monitoring sub-region of the i-th industrial kiln is in a low-temperature state, and the color display data of the industrial kiln monitoring region corresponding to the i-th industrial kiln temperature monitoring sub-region is output as yellow;

[0057] If , it indicates that the temperature monitoring sub-region of the i-th industrial kiln is in a normal-temperature state, and the color display data of the industrial kiln monitoring region corresponding to the i-th industrial kiln temperature monitoring sub-region is output as orange;

[0058] If , it indicates that the temperature monitoring sub-region of the i-th industrial kiln is in a high-temperature state, and the color display data of the industrial kiln monitoring region corresponding to the i-th industrial kiln temperature monitoring sub-region is output as red;

[0059] S532. Repeat the operation in S531 until all the abnormal temperature ratios of the industrial kiln monitoring regions in the abnormal temperature ratio set of the kiln monitoring region are traversed, and then generate a color display data set for the industrial kiln monitoring region.

[0060] By counting the number of abnormal temperatures in each sub-region within a single cycle and calculating the abnormal temperature ratio, comparing the abnormal temperature ratio with the set threshold value, analyzing the real-time temperature conditions of each sub-region, setting corresponding color display data according to different real-time temperature conditions, highlighting the real-time temperature characteristics through different colors, visually displaying the real-time monitoring results of each sub-region, realizing the visualization of the non-contact temperature monitoring results of the industrial kiln, and at the same time analyzing the real-time temperature conditions of each sub-region through multiple groups of collected data to ensure the comprehensiveness and accuracy of the temperature analysis results.

[0061] Preferably, the specific steps for constructing the temperature monitoring result display data of the kiln based on the color display data of the kiln monitoring region are as follows:

[0062] S61. Construct the graphic feature data of the industrial kiln monitoring region, and fill the color of the graphic feature data of the kiln monitoring region according to the color display data of the industrial kiln monitoring region in the color display data set of the kiln monitoring region corresponding to the position of the industrial kiln temperature monitoring sub-region, and generate the temperature monitoring result display data Q of the kiln.

[0063] Preferably, the specific steps for constructing the temperature monitoring result data of the kiln based on the real temperature data of the kiln monitoring region and the temperature monitoring result display data of the kiln and pushing it to the industrial kiln temperature monitoring platform are as follows:

[0064] S71. Combine the real temperature data matrix of the kiln monitoring region and the temperature monitoring result display data Q to construct the temperature monitoring result data of the kiln ;

[0065] S72. Transmit the data of the monitored kiln temperature to the industrial kiln temperature monitoring platform through the Internet of Things communication network and display it on the display screen. Push it to the industrial kiln temperature monitoring platform and display it on the display screen.

[0066] The present invention further includes an artificial intelligence-based non-contact temperature monitoring system for industrial kilns, including an industrial plant area real-time air environment characteristic data acquisition module, an industrial kiln temperature monitoring impact data matching module, an industrial kiln monitoring area temperature data acquisition module, an industrial kiln monitoring area real temperature data measurement module, an industrial kiln real-time operation condition analysis module, a kiln temperature monitoring result display data construction module, and a kiln temperature monitoring result display module;

[0067] The industrial plant area real-time air environment characteristic data acquisition module uses an air environment monitoring device to collect real-time air environment characteristic data in the working area of the target industrial kiln to obtain industrial plant area real-time air environment characteristic data;

[0068] The kiln temperature monitoring impact data matching module performs air environment characteristic data matching processing on the industrial plant area real-time air environment characteristic data and the established temperature monitoring air environment impact data through the pelican optimization algorithm to generate industrial kiln temperature monitoring impact data;

[0069] The kiln monitoring area temperature data acquisition module uses an infrared temperature measuring device to collect temperature data at the central position of the corresponding industrial kiln temperature monitoring sub-area at each temperature data acquisition time point to obtain industrial kiln monitoring area temperature data;

[0070] The kiln monitoring area real temperature data measurement module performs real temperature data measurement processing on the kiln temperature monitoring impact data and the kiln monitoring area temperature data according to the real temperature data calculation formula to generate industrial kiln monitoring area real temperature data;

[0071] The kiln real-time operation condition analysis module compares the kiln monitoring area real temperature data with the real temperature threshold value respectively, counts the total number of the kiln monitoring area real temperature data greater than the real temperature threshold value and calculates the abnormal temperature ratio of the industrial kiln monitoring area, compares the abnormal temperature ratio of the industrial kiln monitoring area with the set first threshold value and second threshold value, and generates industrial kiln monitoring area color display data according to the numerical comparison result;

[0072] The kiln monitoring result display data construction module performs color filling on the constructed industrial kiln monitoring area graphic characteristic data based on the kiln monitoring area color display data to generate kiln temperature monitoring result display data;

[0073] The kiln monitoring result display module combines the real temperature data of the kiln monitoring area and the kiln monitoring result display data to construct the kiln temperature monitoring result data, which is pushed to the industrial kiln temperature monitoring platform through the Internet of Things communication network and displayed on the display screen.

[0074] (III) Beneficial effects

[0075] 1. In the present invention, the air environment characteristic data of the industrial plant area in real time is matched with the air environment impact data of temperature monitoring to generate the industrial kiln temperature monitoring impact data, and the real temperature data metering process is carried out with the temperature data of the industrial kiln monitoring area collected, to generate the real temperature data of the industrial kiln monitoring area. According to the real temperature data analysis of the kiln monitoring area, the real-time operation condition of the industrial kiln is obtained, the industrial kiln monitoring area color display data is generated, and the kiln temperature monitoring result display data is constructed. Finally, the kiln temperature monitoring result data is constructed and pushed to the industrial kiln temperature monitoring platform, realizing non-contact accurate temperature measurement of the industrial kiln and simultaneously intelligently monitoring the real-time temperature data of the industrial kiln.

[0076] 2. The pelican optimization algorithm is used to match the air environment characteristic data of the industrial plant area in real time with the air environment impact data of temperature monitoring, accurately matching the industrial kiln temperature monitoring impact data that matches the current situation, providing a reliable data basis for the subsequent calculation of real temperature data. At the same time, the pelican optimization algorithm can improve the speed and efficiency of the matching process and reduce the response time for obtaining temperature measurement results.

[0077] 3. The real temperature data calculation formula is used to carry out the real temperature data metering process on the kiln temperature monitoring impact data and the kiln monitoring area temperature data, realizing accurate correction of the collected real-time temperature data, effectively reducing the influence brought by the air environment and temperature measurement distance in the non-contact temperature measurement of the industrial kiln, and ensuring the accuracy and reliability of the obtained real temperature data.

[0078] 4. By counting the number of abnormal temperatures in each sub-region within a single cycle and calculating the abnormal temperature ratio, comparing the abnormal temperature ratio with the set threshold value, analyzing the real-time temperature condition of each sub-region, setting corresponding color display data according to different real-time temperature conditions, highlighting the real-time temperature characteristics through different colors, visually displaying the real-time monitoring results of each sub-region, realizing the visualization of the non-contact temperature monitoring results of the industrial kiln, and at the same time analyzing the real-time temperature condition of each sub-region through multiple groups of collected data to ensure the comprehensiveness and accuracy of the temperature analysis results. Description of the drawings

[0079] To more clearly illustrate the technical solutions of the embodiments of the invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0080] Figure 1 It is a flowchart of a non-contact temperature monitoring method for industrial kilns based on artificial intelligence provided by the present invention;

[0081] Figure 2 It is a schematic diagram of the modules of a non-contact temperature monitoring system for industrial kilns based on artificial intelligence provided by the present invention. Detailed implementation manners

[0082] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0083] In the description of the present invention, it should be understood that the terms "opening", "upper", "lower", "top", "middle", "inner", etc. indicating the orientation or position relationship are only for the convenience of describing the invention and simplifying the description, rather than indicating or implying that the components or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be construed as a limitation of the invention.

[0084] Embodiment 1 is as follows:

[0085] Please refer to Figure 1 , a non-contact temperature monitoring method for industrial kilns based on artificial intelligence, including the following steps:

[0086] S1. Collect real-time air environment characteristic data of the industrial plant area;

[0087] S11. Collect real-time air environment characteristic data in the working area of the target industrial kiln through an air environment monitoring device to obtain real-time air environment characteristic data A of the industrial plant area. The air environment monitoring device includes a temperature sensor, a humidity sensor, a meteorological sensor, a particulate matter sensor, and a gas sensor. The air environment characteristic data includes, but is not limited to, gas composition data, total suspended particulate concentration, air temperature, air relative humidity, wind direction data, and wind speed data.

[0088] S2. Establish the temperature monitoring air environment impact data, perform air environment characteristic data matching processing on the real-time air environment characteristic data of the industrial plant area and the temperature monitoring air environment impact data, and generate industrial furnace temperature monitoring impact data;

[0089] S21. Establish a temperature monitoring air environment impact data set B = {b 1 , b 2 , …, b i , …, b k}, where b i represents the temperature monitoring impact coefficient corresponding to the i-th type of air environment characteristic data, and k represents the total number of temperature monitoring air environment impact data;

[0090] S22. Perform air environment characteristic data matching processing on the real-time air environment characteristic data A of the industrial plant area and the temperature monitoring air environment impact data in the temperature monitoring air environment impact data set through the pelican optimization algorithm, and generate industrial furnace temperature monitoring impact data ;

[0091] S221. Construct an air environment characteristic search pelican population, set the scale of the air environment characteristic search pelican population to N, the current iteration number to t, the maximum iteration number to t max and the dimension of the temperature monitoring air environment impact data search space to P;

[0092] Take the temperature monitoring air environment impact data set as the temperature monitoring air environment impact data search space, randomly generate N temperature monitoring air environment impact data in the temperature monitoring air environment impact data search space, and each temperature monitoring air environment impact data corresponds to an air environment characteristic search pelican individual in the air environment characteristic search pelican population. Initialize the initial position set of the air environment characteristic search pelican population as X = {X 1 , X 2 , …, X i , …, X N}, where X i represents the initial position of the i-th air environment characteristic search pelican individual in the air environment characteristic search pelican population;

[0093] S222. Calculate the fitness function values of each air environment characteristic search pelican individual in the air environment characteristic search pelican population, arrange each air environment characteristic search pelican individual in the air environment characteristic search pelican population in descending order according to the fitness function values, and select the air environment characteristic search pelican individual with the highest fitness function value as the current optimal individual; the fitness function formula is as follows:

[0094] ,

[0095] Among them, Fit i represents the fitness function value of the i-th pelican individual searching for air environment characteristics, and x i represents the deviation value between the air environment characteristic data corresponding to the temperature monitoring air environment impact data of the i-th pelican individual and the real-time air environment characteristic data of the industrial plant area; represents the correction value;

[0096] S223. Exploration stage: Each pelican individual searching for air environment characteristics in the pelican population of air environment characteristics locks the prey position in the search space of the temperature monitoring air environment impact data and moves towards the prey position for position update. The position of the prey in the search space of the temperature monitoring air environment impact data is randomly generated. The position update formula is as follows:

[0097] ,

[0098] Among them, and X ij respectively represent the position of the i-th pelican individual searching for air environment characteristics in the pelican population of air environment characteristics after and before position update in the j-th dimensional search space of the temperature monitoring air environment impact data. α represents a random integer uniformly distributed between [1, 2], and Z j represents the prey position locked by the i-th pelican individual searching for air environment characteristics in the pelican population of air environment characteristics in the j-th dimensional search space of the temperature monitoring air environment impact data. rand 1 and rand 2 respectively represent random numbers uniformly distributed between (0, 1), and Fit z represents the fitness function value of the prey;

[0099] S224. Development stage: Each pelican individual searching for air environment characteristics in the pelican population of air environment characteristics uses the water surface flight strategy to hunt more prey in the search space of the temperature monitoring air environment impact data for position update. The position update formula is as follows:

[0100] ,

[0101] Among them, R represents a random integer with a value of 0 or 2, and rand 2 represents a random number uniformly distributed between (0, 1);

[0102] S225. Calculate the fitness function values of each air environment feature search pelican individual in the air environment feature search pelican population after position update. If the fitness function value of an air environment feature search pelican individual after position update is less than the original fitness function value, replace the original position with the new position; otherwise, retain the original position.

[0103] Re - arrange each air environment feature search pelican individual in the air environment feature search pelican population in descending order according to the fitness function value, and select the air environment feature search pelican individual with the highest fitness function value as the new current optimal individual.

[0104] S226. Determine whether the current iteration number t is less than the maximum iteration number t max , if the current iteration number t is less than the maximum iteration number t max , then increment the current iteration number t by 1 and return to S223; otherwise, take the current optimal individual as the global optimal solution, output the temperature monitoring air environment impact data corresponding to the global optimal solution and perform data identification to generate industrial furnace temperature monitoring impact data. 。

[0105] S3. Collect temperature data in the furnace monitoring area;

[0106] S31. Set the temperature data collection period, evenly divide the temperature data collection period into several temperature data collection time points, and obtain the temperature data collection time point set C = {c 1 , c 2 , …, c i , …, c l}, where c i represents the i - th temperature data collection time point obtained by evenly dividing the temperature data collection period, and l represents the total number of temperature data collection time points.

[0107] S32. Evenly divide the industrial furnace temperature monitoring area into several industrial furnace temperature monitoring sub - areas, and obtain the industrial furnace temperature monitoring sub - area set D = {d 1 , d 2 , …, d i , …, d p}, where d i represents the i - th industrial furnace temperature monitoring sub - area obtained by evenly dividing the industrial furnace temperature monitoring area, and p represents the total number of industrial furnace temperature monitoring sub - areas.

[0108] S33. Allocate infrared temperature measuring devices to the industrial furnace temperature monitoring sub - regions in the kiln furnace temperature monitoring sub - regions. At each temperature data acquisition time point in the concentrated temperature data acquisition time points, use the infrared temperature measuring devices to collect the temperature data at the central position of the corresponding industrial furnace temperature monitoring sub - region in real time, and obtain the industrial furnace monitoring region temperature data matrix E as follows:

[0109] ,

[0110] where, e ij represents the temperature data obtained by using the infrared temperature measuring device to collect the temperature at the central position of the j - th industrial furnace temperature monitoring sub - region in real time at the i - th temperature data acquisition time point.

[0111] S4. Perform real - temperature data measurement processing based on the kiln furnace temperature monitoring influence data and the kiln furnace monitoring region temperature data to generate the real - temperature data of the industrial furnace monitoring region;

[0112] S41. Perform real - temperature data measurement processing on the kiln furnace temperature monitoring influence data and the industrial furnace monitoring region temperature data in the industrial furnace monitoring region temperature data matrix E to generate the real - temperature data matrix of the industrial furnace monitoring region as follows:

[0113] ,

[0114] where, represents the real - temperature data of the industrial furnace monitoring region obtained after performing real - temperature data measurement processing on the temperature data obtained by using the infrared temperature measuring device to collect the temperature at the central position of the j - th industrial furnace temperature monitoring sub - region in real time at the i - th temperature data acquisition time point. The real - temperature data calculation formula is as follows:

[0115] ,

[0116] where, D i represents the distance between the central position of the i - th industrial furnace temperature monitoring sub - region and its corresponding infrared temperature measuring device, and D 0 represents the unit distance.

[0117] S5. Analyze the real - time operation status of the industrial furnace based on the real - temperature data of the kiln furnace monitoring region, and generate the color display data of the industrial furnace monitoring region according to the analysis results;

[0118] S51. Set a real - temperature threshold, and use the real - temperature data matrix of the kiln furnace monitoring region The true temperature data of each industrial furnace monitoring area are numerically compared with the true temperature threshold respectively, and the total number of true temperature data of the industrial furnace monitoring area corresponding to each industrial furnace temperature monitoring sub-area that is greater than the true temperature threshold is counted, obtaining the industrial furnace monitoring area abnormal temperature number set F = {f 1 , f 2 , …, f i , …, f p}, where f i represents the total number of true temperature data greater than the true temperature threshold obtained by collecting temperature data for the i-th industrial furnace temperature monitoring sub-area;

[0119] S52. Calculate the abnormal temperature ratio of each industrial furnace temperature monitoring sub-area based on the abnormal temperature number of the industrial furnace monitoring area in the abnormal temperature number set of the furnace monitoring area, obtaining the abnormal temperature ratio set of the industrial furnace monitoring area , where represents the abnormal temperature ratio of the i-th industrial furnace temperature monitoring sub-area, and ;

[0120] S53. Set the first threshold as η 1 and the second threshold as η 2 , and compare each abnormal temperature ratio of the industrial furnace monitoring area in the abnormal temperature ratio set of the furnace monitoring area with the first threshold η 1 and the second threshold η 2 numerically, and generate the industrial furnace monitoring area color display data set according to the numerical comparison result, where represents the industrial furnace monitoring area color display data corresponding to the i-th industrial furnace temperature monitoring sub-area;

[0121] The generating the industrial furnace monitoring area color display data set according to the numerical comparison result includes the following steps:

[0122] S531. Select the abnormal temperature ratio of the i-th industrial furnace monitoring area and compare it numerically with the first threshold η 1 and the second threshold η 2 ;

[0123] If , it means that the i-th industrial furnace temperature monitoring sub-area is in a non-working state, and output the industrial furnace monitoring area color display data corresponding to the i-th industrial furnace temperature monitoring sub-area as black;

[0124] If , it indicates that the temperature monitoring sub-region of the i-th industrial kiln is in a low-temperature state, and the industrial kiln monitoring area color display data corresponding to the i-th industrial kiln temperature monitoring sub-region is output as yellow;

[0125] If , it indicates that the temperature monitoring sub-region of the i-th industrial kiln is in a normal-temperature state, and the industrial kiln monitoring area color display data corresponding to the i-th industrial kiln temperature monitoring sub-region is output as orange;

[0126] If , it indicates that the temperature monitoring sub-region of the i-th industrial kiln is in a high-temperature state, and the industrial kiln monitoring area color display data corresponding to the i-th industrial kiln temperature monitoring sub-region is output as red;

[0127] S532. Repeat the operation in S531 until all the abnormal temperature ratios of the industrial kiln monitoring areas in the abnormal temperature ratio set of the kiln monitoring area are traversed, and then generate an industrial kiln monitoring area color display data set.

[0128] S6. Construct the kiln temperature monitoring result display data based on the color display data of the kiln monitoring area;

[0129] S61. Construct the graphic feature data of the industrial kiln monitoring area, and fill the graphic feature data of the kiln monitoring area with the industrial kiln monitoring area color display data in the industrial kiln monitoring area color display data set according to the position of the corresponding industrial kiln temperature monitoring sub-region to generate the kiln temperature monitoring result display data Q.

[0130] S7. Construct the kiln temperature monitoring result data based on the real temperature data of the kiln monitoring area and the kiln temperature monitoring result display data, and push it to the industrial kiln temperature monitoring platform;

[0131] S71. Combine the real temperature data matrix of the kiln monitoring area and the kiln temperature monitoring result display data Q to construct the kiln temperature monitoring result data ;

[0132] S72. Push the kiln temperature monitoring result data to the industrial kiln temperature monitoring platform through the Internet of Things communication network and display it on the display screen.

[0133] The second embodiment is as follows:

[0134] Please refer to Figure 2, an artificial intelligence-based non-contact temperature monitoring system for industrial furnaces, including a real-time air environment characteristic data acquisition module for industrial plants, a temperature monitoring impact data matching module for industrial furnaces, a temperature data acquisition module for the monitoring area of industrial furnaces, a true temperature data measurement module for the monitoring area of industrial furnaces, a real-time operation analysis module for industrial furnaces, a data construction module for displaying the results of furnace temperature monitoring, and a display module for the results of furnace temperature monitoring;

[0135] The real-time air environment characteristic data acquisition module for industrial plants collects real-time air environment characteristic data within the working area of the target industrial furnace through an air environment monitoring device to obtain real-time air environment characteristic data for industrial plants;

[0136] The temperature monitoring impact data matching module for industrial furnaces performs air environment characteristic data matching processing on the real-time air environment characteristic data for industrial plants and the established temperature monitoring air environment impact data through the pelican optimization algorithm to generate temperature monitoring impact data for industrial furnaces;

[0137] The temperature data acquisition module for the monitoring area of industrial furnaces collects temperature data at the center position of the corresponding temperature monitoring sub-area of the industrial furnace in real time at each temperature data acquisition time point through an infrared temperature measurement device to obtain temperature data for the monitoring area of industrial furnaces;

[0138] The true temperature data measurement module for the monitoring area of industrial furnaces performs true temperature data measurement processing on the temperature monitoring impact data and the temperature data for the monitoring area of industrial furnaces according to the true temperature data calculation formula to generate true temperature data for the monitoring area of industrial furnaces;

[0139] The real-time operation analysis module for industrial furnaces numerically compares the true temperature data for the monitoring area of industrial furnaces with the true temperature threshold respectively, counts the total number of the true temperature data for the monitoring area of industrial furnaces that is greater than the true temperature threshold and calculates the abnormal temperature ratio for the monitoring area of industrial furnaces, numerically compares the abnormal temperature ratio for the monitoring area of industrial furnaces with the set first threshold and second threshold, and generates color display data for the monitoring area of industrial furnaces according to the numerical comparison result;

[0140] The data construction module for displaying the results of furnace temperature monitoring performs color filling on the constructed graphic feature data for the monitoring area of industrial furnaces based on the color display data for the monitoring area of industrial furnaces to generate data for displaying the results of furnace temperature monitoring;

[0141] The display module for the results of furnace temperature monitoring combines the true temperature data for the monitoring area of industrial furnaces and the data for displaying the results of furnace temperature monitoring to construct data for the results of furnace temperature monitoring, and pushes it to the industrial furnace temperature monitoring platform through the Internet of Things communication network and displays it on the display screen.

[0142] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0143] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not exhaust all the details and do not limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification in order to better explain the principles and practical applications of the invention, so that those skilled in the art can well understand and utilize the invention.

Claims

1. A non-contact temperature monitoring method for industrial furnaces based on artificial intelligence, characterized in that: The steps include: S1. Collect real-time air environment characteristic data of industrial plants; S2. Establish temperature monitoring air environment impact data, perform air environment feature data matching processing on the real-time air environment feature data of the industrial plant area and the temperature monitoring air environment impact data, and generate industrial kiln temperature monitoring impact data; S3, collect temperature data of the kiln monitoring area; S4, performing real temperature data measurement processing according to the kiln temperature monitoring influence data and the kiln monitoring area temperature data to generate the real temperature data of the industrial kiln monitoring area; S5. Analyze the real-time operation status of the industrial kiln based on the real temperature data of the kiln monitoring area, and generate color display data of the industrial kiln monitoring area according to the analysis results; S6. Constructing kiln temperature monitoring result display data according to the kiln monitoring area color display data; S7. constructing kiln temperature monitoring result data based on the real temperature data of the kiln monitoring area and the kiln monitoring result display data, and pushing it to the industrial kiln temperature monitoring platform; The S1 comprises the following steps: S11, collecting air environment characteristic data in the working area of ​​the target industrial kiln in real time through an air environment monitoring device to obtain real-time air environment characteristic data A of the industrial plant area; The S2 comprises the following steps: S21. Establish temperature monitoring air environment impact data set B={b1,b2,…,b i ,…,b k }, where b i represents the temperature monitoring influence coefficient corresponding to the i-th type of air environment characteristic data, and k represents the total number of temperature monitoring air environment influence data; S22, using the Pelican optimization algorithm to perform air environment feature data matching processing on the temperature monitoring air environment impact data in the temperature monitoring air environment impact data set, and generate industrial kiln temperature monitoring impact data .

2. According to claim 1, a non-contact temperature monitoring method for industrial furnaces based on artificial intelligence is characterized in that: The S22 comprises the following steps: S221. Construct an air environment feature search for a pelican population, set the air environment feature search for a pelican population size to N, the current number of iterations to t, and the maximum number of iterations to t. max And the search space dimension of temperature monitoring air environment impact data is P; The temperature monitoring air environment impact data set is used as a temperature monitoring air environment impact data search space, and N temperature monitoring air environment impact data are randomly generated in the temperature monitoring air environment impact data search space, each temperature monitoring air environment impact data corresponds to an air environment feature to search for a pelican individual; S222, calculating the fitness function value of each air environment characteristic to search for the pelican individual; S223, in the exploration stage, each pelican individual searches for air environment characteristics to lock the position of the prey in the temperature monitoring air environment impact data search space, and moves towards the prey position to update the position, wherein the position of the prey in the temperature monitoring air environment impact data search space is randomly generated; S224, in the development stage, each air environment feature searches for pelicans that adopt a surface flight strategy to hunt more prey in the temperature monitoring air environment impact data search space to update their positions; S225, calculating the fitness function value of each air environment feature search pelican individual after the position is updated, if the fitness function value of the air environment feature search pelican individual after the position is updated is less than the original fitness function value, then the new position is used to replace the original position; otherwise, the original position is retained; Rearrange the pelican individuals according to the fitness function value from large to small, and select the pelican individual with the highest fitness function value as the new current optimal individual; S226, determine whether t is less than t max , if t is less than t max , then t is increased by 1, and the process returns to S223; otherwise, the current optimal individual is taken as the global optimal solution, the temperature monitoring air environment impact data corresponding to the global optimal solution is output and the data is marked, and the industrial kiln temperature monitoring impact data is generated. .

3. The method for non-contact temperature monitoring of industrial furnaces based on artificial intelligence according to claim 2 is characterized in that: The S3 comprises the following steps: S31, setting a temperature data collection period, and evenly dividing the temperature data collection period into a number of temperature data collection time points, to obtain a temperature data collection time point set C = {c1, c2, ..., c i ,…,c l }, where c i represents the i-th temperature data collection time point obtained by evenly dividing the temperature data collection period, and l represents the total number of temperature data collection time points; S32, evenly divide the industrial kiln temperature monitoring area into several industrial kiln temperature monitoring sub-areas, and obtain the industrial kiln temperature monitoring sub-area set D = {d1, d2, ..., d i ,…,d p }, where d i represents the i-th industrial kiln temperature monitoring sub-area obtained by evenly dividing the industrial kiln temperature monitoring area, and p represents the total number of industrial kiln temperature monitoring sub-areas; S33. Allocate an infrared temperature measuring device to each industrial kiln temperature monitoring sub-area in the kiln temperature monitoring sub-area set, and use the infrared temperature measuring device to collect the temperature data of the center position of the corresponding industrial kiln temperature monitoring sub-area in real time at each temperature data collection time point in the temperature data collection time point set to obtain the industrial kiln monitoring area temperature data matrix E.

4. The method for non-contact temperature monitoring of industrial furnaces based on artificial intelligence according to claim 3 is characterized in that: The S4 comprises the following steps: S41, calculating the temperature according to the actual temperature data formula The temperature data of the industrial kiln monitoring area in E is processed by real temperature data measurement to generate the real temperature data matrix of the industrial kiln monitoring area .

5. The method for non-contact temperature monitoring of industrial furnaces based on artificial intelligence according to claim 4 is characterized in that: The S5 comprises the following steps: S51, set the real temperature threshold, The real temperature data of each industrial kiln monitoring area in the temperature monitoring sub-area are numerically compared with the real temperature threshold, and the total number of industrial kiln monitoring area real temperature data corresponding to each industrial kiln temperature monitoring sub-area greater than the real temperature threshold is counted to obtain the industrial kiln monitoring area abnormal temperature number set F={f1,f2,…,f i ,…,f p }, where f i Indicates the total number of real temperature data obtained by collecting temperature data for the i-th industrial furnace temperature monitoring sub-area that are greater than the real temperature threshold; S52, based on the abnormal temperature number of the industrial kiln monitoring area in the kiln monitoring area abnormal temperature number set, calculate the abnormal temperature ratio of each industrial kiln temperature monitoring sub-area, and obtain the industrial kiln monitoring area abnormal temperature ratio set. ,in, represents the abnormal temperature ratio of the temperature monitoring sub-area of ​​the i-th industrial kiln, and ; S53, setting the first threshold value as η1 and the second threshold value as η2, comparing the abnormal temperature ratios of each industrial kiln monitoring area in the kiln monitoring area abnormal temperature ratio set with the η1 and the η2 in turn, and generating an industrial kiln monitoring area color display data set according to the numerical comparison results. ,in, Indicates the color display data of the industrial kiln monitoring area corresponding to the i-th industrial kiln temperature monitoring sub-area; Generating the industrial furnace monitoring area color display data set according to the numerical comparison result comprises the following steps: S531, selecting the abnormal temperature ratio of the i-th industrial furnace monitoring area and comparing it with the η1 and the η2; like , it means that the i-th industrial kiln temperature monitoring sub-area is in a non-working state, and the color display data of the industrial kiln monitoring area corresponding to the i-th industrial kiln temperature monitoring sub-area is output as black; like , it means that the ith industrial kiln temperature monitoring sub-area is in a low temperature state, and the color display data of the industrial kiln monitoring area corresponding to the ith industrial kiln temperature monitoring sub-area is output as yellow; like , it means that the ith industrial kiln temperature monitoring sub-area is at room temperature, and the color display data of the industrial kiln monitoring area corresponding to the ith industrial kiln temperature monitoring sub-area is output as orange; like , it means that the temperature monitoring sub-area of ​​the i-th industrial kiln is in a high temperature state, and the color display data of the industrial kiln monitoring area corresponding to the temperature monitoring sub-area of ​​the i-th industrial kiln is output as red; S532, repeating the operation in S531 until all the abnormal temperature ratios of the industrial kiln monitoring areas in the kiln monitoring area abnormal temperature ratio set are traversed, and a color display data set of the industrial kiln monitoring area is generated.

6. The method for non-contact temperature monitoring of industrial furnaces based on artificial intelligence according to claim 5 is characterized in that: The S6 comprises the following steps: S61. Construct graphic feature data of the industrial kiln monitoring area, fill the graphic feature data of the kiln monitoring area with color according to the corresponding industrial kiln temperature monitoring sub-area position using the industrial kiln monitoring area color display data in the kiln monitoring area color display data set, and generate kiln temperature monitoring result display data Q.

7. The method for non-contact temperature monitoring of industrial furnaces based on artificial intelligence according to claim 6 is characterized in that: The S7 comprises the following steps: S71, the Combine the data with Q to construct the kiln temperature monitoring result data ; S72, through the Internet of Things communication network Push to the industrial kiln temperature monitoring platform and display on the display screen.

8. A system for implementing the artificial intelligence-based non-contact temperature monitoring method for an industrial furnace as described in any one of claims 1 to 7.

Images