Gypsum dehydration temperature real-time monitoring method and system based on infrared sensing technology
Through the real-time monitoring method of gypsum dehydration temperature based on infrared sensing technology, the temperature monitoring error caused by the random setting of high-temperature resistant thermocouple monitoring points is solved, and the monitoring accuracy and control accuracy of gypsum dehydration temperature are improved.
Patent Information
- Application Number
- CN202411094513.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-10
- Publication Date
- 2024-11-19
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing gypsum dehydration temperature monitoring method through high-temperature resistant thermocouples has a high randomness in monitoring point settings, resulting in poor representativeness of the temperature monitoring results and resulting in large errors in gypsum dehydration temperature monitoring.
Using the real-time monitoring method of gypsum dehydration temperature based on infrared sensing technology, by obtaining the basic information of the gypsum to be dehydrated, the reference temperature is configured according to the gypsum composition, crystal water content and morphology information, and using an infrared thermometer to scan the outer wall of the dehydrator to perform the inner wall temperature. Map and combine gypsum weight and composition for temperature prediction, send the predicted temperature and target temperature to the dehydrator control terminal.
It improves the comprehensiveness and accuracy of gypsum dehydration temperature monitoring, reduces temperature monitoring errors, and achieves the technical effect of precisely controlling gypsum dehydration.
Smart Images

Figure CN118980431A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of gypsum dehydration, and in particular to a real-time monitoring method and system for gypsum dehydration temperature based on infrared sensing technology. Background Art
[0002] High temperature resistant thermocouple is an industrial product used to measure temperature in high temperature environment. It uses the principle of thermoelectric effect to convert temperature signal into electrical signal output, thereby realizing temperature measurement of high temperature objects.
[0003] Gypsum dehydration refers to the process of removing moisture from gypsum raw materials through a gypsum dehydrator. The traditional method of gypsum dehydration temperature monitoring is usually to randomly set multiple temperature monitoring points on the outer wall or inner wall of the gypsum dehydrator, and then collect temperature data from multiple temperature monitoring points through high-temperature resistant thermocouples. Since the temperature monitoring points are usually set manually based on experience and are more random, the temperature monitoring data is less representative, resulting in a larger error in gypsum dehydration temperature monitoring, which ultimately leads to lower accuracy in gypsum dehydration control and affects the quality of gypsum production.
[0004] In summary, the existing method of monitoring gypsum dehydration temperature by high-temperature resistant thermocouples has the technical problem that the monitoring point setting is relatively random, resulting in poor representativeness of the temperature monitoring results and large errors in the gypsum dehydration temperature monitoring. Summary of the invention
[0005] The purpose of this application is to provide a real-time monitoring method and system for gypsum dehydration temperature based on infrared sensing technology, so as to solve the technical problem that the existing method of monitoring gypsum dehydration temperature by high-temperature resistant thermocouples has a large randomness in the setting of monitoring points, resulting in poor representativeness of temperature monitoring results and large errors in gypsum dehydration temperature monitoring.
[0006] In view of the above problems, the present application provides a method and system for real-time monitoring of gypsum dehydration temperature based on infrared sensing technology.
[0007] In a first aspect, the present application provides a real-time monitoring method for gypsum dehydration temperature based on infrared sensing technology, and the method is implemented by a real-time monitoring system for gypsum dehydration temperature based on infrared sensing technology, wherein the method includes: obtaining basic information of the gypsum to be dehydrated, wherein the basic information of the gypsum to be dehydrated includes gypsum composition information, crystal water content information, crystal water morphology information and gypsum weight information; performing reference temperature configuration according to the gypsum composition information, the crystal water content information and the crystal water morphology information to generate a gypsum dehydration target temperature; scanning the outer wall of the dehydrator with an infrared thermometer to obtain an outer wall temperature distribution cloud; mapping the outer wall temperature distribution cloud to an inner wall temperature to obtain an inner wall temperature distribution cloud; performing temperature prediction on the inner wall temperature distribution cloud, the gypsum weight, the gypsum composition and the crystal water content to obtain a gypsum predicted temperature; and sending the gypsum predicted temperature and the gypsum dehydration target temperature to the display interface of the dehydrator control terminal.
[0008] In the second aspect, the present application also provides a real-time monitoring system for gypsum dehydration temperature based on infrared sensing technology, which is used to execute a real-time monitoring method for gypsum dehydration temperature based on infrared sensing technology as described in the first aspect, wherein the system includes: a basic information acquisition module for gypsum to be dehydrated, the basic information acquisition module for gypsum to be dehydrated is used to obtain basic information of gypsum to be dehydrated, wherein the basic information of gypsum to be dehydrated includes gypsum composition information, crystal water content information, crystal water form information and gypsum weight information; a reference temperature configuration module, the reference temperature configuration module is used to configure the reference temperature according to the gypsum composition information, the crystal water content information and the crystal water form information, gypsum dehydration target temperature; an outer wall temperature distribution cloud acquisition module, the outer wall temperature distribution cloud acquisition module is used to scan the outer wall of the dehydrator through an infrared thermometer to obtain the outer wall temperature distribution cloud; an inner wall temperature mapping module, the inner wall temperature mapping module is used to map the outer wall temperature distribution cloud to the inner wall temperature to obtain the inner wall temperature distribution cloud; a temperature prediction module, the temperature prediction module is used to perform temperature prediction on the inner wall temperature distribution cloud, the gypsum weight, the gypsum composition, and the crystal water content to obtain the gypsum predicted temperature; a temperature sending module, the temperature sending module is used to send the gypsum predicted temperature and the gypsum dehydration target temperature to the dehydrator control terminal display interface.
[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: 1. By obtaining basic information of gypsum to be dehydrated, wherein the basic information of gypsum to be dehydrated includes gypsum composition information, crystal water content information, crystal water form information and gypsum weight information; performing reference temperature configuration according to the gypsum composition information, the crystal water content information and the crystal water form information, and generating a gypsum dehydration target temperature; scanning the outer wall of the dehydrator by an infrared thermometer to obtain an outer wall temperature distribution cloud; performing inner wall temperature mapping on the outer wall temperature distribution cloud to obtain an inner wall temperature distribution cloud; performing temperature prediction on the inner wall temperature distribution cloud, the gypsum weight, the gypsum composition and the crystal water content to obtain a gypsum predicted temperature; sending the gypsum predicted temperature and the gypsum dehydration target temperature to the display interface of the dehydrator control terminal, the comprehensiveness of gypsum dehydration temperature monitoring can be improved, thereby reducing the temperature monitoring error, improving the accuracy of the temperature monitoring result, and indirectly achieving the technical effect of accurately controlling gypsum dehydration.
[0010] 2. By configuring the reference temperature based on the gypsum composition information, crystal water content information and crystal water form information, the matching degree between the gypsum dehydration target temperature and the gypsum to be dehydrated can be improved, thereby improving the accuracy of the gypsum dehydration target temperature setting, and providing support for temperature comparison during the gypsum dehydration process.
[0011] 3. By using an infrared thermometer to scan the temperature, the comprehensiveness of temperature monitoring can be improved. At the same time, by further combining the inner wall temperature distribution cloud, gypsum weight, gypsum composition, and crystal water content for temperature prediction, the accuracy of gypsum temperature prediction can be improved, providing support for the precise control of gypsum dehydration.
[0012] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.
[0014] Figure 1 This is a flow chart of a method for real-time monitoring of gypsum dehydration temperature based on infrared sensing technology in this application.
[0015] Figure 2 This is a schematic diagram of the process of generating a gypsum dehydration target temperature in a real-time monitoring method of gypsum dehydration temperature based on infrared sensing technology in the present application.
[0016] Figure 3 This is a structural schematic diagram of a real-time monitoring system for gypsum dehydration temperature based on infrared sensing technology for this application.
[0017] Description of reference numerals: The basic information acquisition module 11 of the gypsum to be dehydrated, the reference temperature configuration module 12, the outer wall temperature distribution cloud acquisition module 13, the inner wall temperature mapping module 14, the temperature prediction module 15, and the temperature sending module 16. DETAILED DESCRIPTION
[0018] The present application provides a real-time monitoring method and system for gypsum dehydration temperature based on infrared sensing technology, thereby solving the technical problem that the existing method for monitoring gypsum dehydration temperature through high-temperature resistant thermocouples has large randomness in monitoring point settings, resulting in poor representativeness of temperature monitoring results and large errors in gypsum dehydration temperature monitoring. The application can improve the comprehensiveness of gypsum dehydration temperature monitoring, thereby achieving the technical goal of reducing temperature monitoring errors and improving temperature monitoring accuracy, and indirectly achieving the technical effect of accurately controlling gypsum dehydration.
[0019] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.
[0020] Embodiment 1 Please see attached Figure 1 The present application provides a method for real-time monitoring of gypsum dehydration temperature based on infrared sensing technology, wherein the method is applied to a real-time monitoring system for gypsum dehydration temperature based on infrared sensing technology, and the method specifically comprises the following steps: Step 1: obtaining basic information of the gypsum to be dehydrated, wherein the basic information of the gypsum to be dehydrated includes gypsum composition information, crystal water content information, crystal water form information and gypsum weight information; Specifically, gypsum dehydration refers to the process of removing moisture from wet gypsum using equipment such as a gypsum dehydrator, which is mainly based on the action of centrifugal force and gravity to remove moisture from wet gypsum. First, collect and obtain the basic information of the gypsum to be dehydrated, the basic information of the gypsum to be dehydrated includes gypsum composition information, crystal water content information, crystal water form information and gypsum weight information, wherein the gypsum composition information is the component type of the gypsum to be dehydrated, including calcium sulfate, crystal water, etc., which can be set according to actual conditions; crystal water content information refers to the proportion of crystal water in the gypsum to be dehydrated; crystal water form information refers to the type of crystal water molecules in the gypsum to be dehydrated; gypsum weight information is the actual weight of the gypsum to be dehydrated.
[0021] By obtaining the basic information of the gypsum to be dehydrated, a basis is provided for the benchmark temperature configuration for the next step of gypsum dehydration.
[0022] Step 2: configuring the reference temperature according to the gypsum composition information, the crystal water content information and the crystal water form information to generate the gypsum dehydration target temperature; Specifically, the reference temperature is configured according to the gypsum composition information, the crystal water content information, and the crystal water form information, wherein the reference temperature refers to the dehydration standard temperature after the gypsum to be dehydrated completes the entire dehydration process, which can be obtained by analyzing the historical gypsum dehydration data, and then the gypsum dehydration target temperature is obtained according to the data analysis results. By obtaining the gypsum dehydration target temperature based on historical data analysis, the compatibility of the gypsum dehydration target temperature with the gypsum to be dehydrated can be improved, thereby improving the accuracy of the gypsum dehydration target temperature setting.
[0023] Step 3: Scan the outer wall of the dehydrator with an infrared thermometer to obtain the outer wall temperature distribution cloud; Specifically, the outer wall of the dehydrator is scanned by an infrared thermometer, wherein the dehydrator is a device for dehydrating gypsum. The infrared thermometer is a device that uses the principle of infrared radiation to measure the surface temperature of an object. It is usually composed of optical elements, photoelectric detectors, signal enhancers, signal analysis and display output, etc. It has the advantages of non-contact, fast, accurate and safe. The outer wall temperature distribution cloud is obtained according to the scanning results, wherein the outer wall temperature distribution cloud is a visual display result of the temperature distribution state of the outer wall of the dehydrator, and the temperature is usually indicated by the depth of color, so that the temperature distribution of the outer wall of the dehydrator can be intuitively understood.
[0024] By obtaining the outer wall temperature distribution cloud, the temperature distribution state of the outer wall of the dehydrator can be fully obtained, thereby improving the comprehensiveness and authenticity of the temperature information obtained on the outer wall of the dehydrator.
[0025] Step 4: mapping the outer wall temperature distribution cloud to the inner wall temperature to obtain the inner wall temperature distribution cloud; Specifically, the outer wall temperature distribution cloud is mapped to the inner wall temperature, wherein the inner wall temperature mapping refers to obtaining the inner wall temperature information of the dehydrator with mapping association based on the outer wall temperature distribution cloud intelligent analysis according to the inner and outer wall structure information of the dehydrator, and obtaining the inner wall temperature distribution cloud. By obtaining the inner wall temperature distribution cloud, support is provided for the prediction of gypsum dehydration temperature.
[0026] Step 5: Predict the temperature of the inner wall temperature distribution cloud, the gypsum weight, the gypsum composition, and the crystal water content to obtain the predicted gypsum temperature; Specifically, the temperature of the gypsum to be dehydrated during the gypsum dehydration process is predicted according to the inner wall temperature distribution cloud, the gypsum weight, the gypsum composition, and the crystal water content to obtain the gypsum predicted temperature. By obtaining the gypsum predicted temperature, the gypsum temperature information can be obtained in real time, which provides support for the temperature deviation comparison during the gypsum dehydration process.
[0027] Step 6: Send the predicted gypsum temperature and the gypsum dehydration target temperature to the dehydrator control terminal display interface.
[0028] Specifically, the predicted gypsum temperature and the target gypsum dehydration temperature are finally sent to the display interface of the dehydrator control terminal, and the temperature deviation of the predicted gypsum temperature is calculated according to the target gypsum dehydration temperature, and the gypsum dehydration is controlled according to the temperature deviation calculation result. For example, when the temperature deviation calculation result is less than the preset deviation threshold, it indicates that the gypsum dehydration meets the expected requirements. At this time, the dehydrator can be turned off to complete the gypsum dehydration, and the preset deviation threshold can be set according to the actual situation of the dehydrator.
[0029] By performing gypsum dehydration control based on the temperature deviation calculation result, the accuracy of gypsum dehydration control can be improved.
[0030] The real-time monitoring method for gypsum dehydration temperature based on infrared sensing technology is applied to a real-time monitoring system for gypsum dehydration temperature based on infrared sensing technology, which can solve the technical problems that the existing method for monitoring gypsum dehydration temperature by high-temperature resistant thermocouples has large randomness in setting monitoring points, resulting in poor representativeness of temperature monitoring results and large errors in gypsum dehydration temperature monitoring. First, basic information of the gypsum to be dehydrated is obtained, wherein the basic information of the gypsum to be dehydrated includes gypsum composition information, crystal water content information, crystal water form information and gypsum weight information; then, a reference temperature configuration is performed according to the gypsum composition information, the crystal water content information and the crystal water form information to generate a gypsum dehydration target temperature; then, the outer wall of the dehydrator is scanned by an infrared thermometer to obtain an outer wall temperature distribution cloud; next, the outer wall temperature distribution cloud is mapped to the inner wall temperature to obtain an inner wall temperature distribution cloud; further, the inner wall temperature distribution cloud, the gypsum weight, the gypsum composition and the crystal water content are temperature predicted to obtain a gypsum predicted temperature; finally, the gypsum predicted temperature and the gypsum dehydration target temperature are sent to the display interface of the dehydrator control terminal. By using an infrared thermometer to perform temperature scanning, the comprehensiveness of temperature monitoring can be improved. At the same time, temperature prediction based on the inner wall temperature distribution cloud, gypsum weight, gypsum composition, and crystal water content can improve the accuracy of gypsum temperature prediction, thereby achieving the technical goal of reducing temperature monitoring errors and improving temperature monitoring accuracy. Gypsum dehydration is then controlled based on the temperature deviation between the predicted gypsum temperature and the gypsum dehydration target temperature, thereby achieving the technical effect of accurately controlling gypsum dehydration.
[0031] Further, as attached Figure 2 As shown, step 2 of this application includes: Retrieving a gypsum dehydration process log based on the gypsum composition information, the crystal water content information, and the crystal water form information, wherein the gypsum dehydration process log includes a gypsum dehydration temperature set; Configure the distribution density threshold and neighborhood temperature difference distance threshold; Performing pairwise temperature difference distance enumeration calculation on the gypsum dehydration temperature set to obtain a temperature difference distance set; Traversing the gypsum dehydration temperature set, and configuring a distribution neighborhood set based on the neighborhood temperature difference distance threshold and the temperature difference distance set, wherein the distribution neighborhood set has a distribution density characteristic value, and the distribution density characteristic value is equal to the number of neighborhood temperature distributions; Deleting the gypsum dehydration temperatures whose distribution density characteristic values are less than or equal to the distribution density threshold from the gypsum dehydration temperature set to obtain a polymerization temperature set; The mean of the polymerization temperature set is calculated and set as the gypsum dehydration target temperature.
[0032] Specifically, first, the gypsum composition information, the crystal water content information and the crystal water form information are used as information retrieval constraints to perform information retrieval on the gypsum dehydration process log, that is, to obtain the same historical dehydration process log as the gypsum to be dehydrated, wherein the gypsum dehydration process log includes a gypsum dehydration temperature set, and the gypsum dehydration temperature set includes multiple historical temperature data after gypsum is dehydrated.
[0033] The distribution density threshold and the neighborhood temperature difference distance threshold are configured, where the distribution density refers to the number of temperature data in the field, and the neighborhood temperature difference distance refers to the deviation value of the temperature data in the neighborhood. The distribution density threshold and the neighborhood temperature difference distance threshold can be set by those skilled in the art based on the number and characteristics of the temperature data in the gypsum dehydration temperature set. Then, the gypsum dehydration temperature set is enumerated and calculated by pairwise temperature difference distance, that is, two gypsum dehydration temperatures are randomly selected in the gypsum dehydration temperature set for temperature difference calculation, multiple dehydration temperature difference values are obtained, and a temperature difference distance set is constructed.
[0034] The gypsum dehydration temperatures in the gypsum dehydration temperature set are clustered according to the neighborhood temperature difference distance threshold and the temperature difference distance set, that is, the gypsum dehydration temperatures with a temperature difference distance less than or equal to the neighborhood temperature difference distance threshold are clustered into one field, and a distribution neighborhood set is constructed. The distribution neighborhood set includes multiple fields, and the distribution neighborhood set has a distribution density characteristic value, wherein the distribution density characteristic value is equal to the number of neighborhood temperature distributions, that is, the more the number of temperature distributions in a field, the larger the corresponding distribution density characteristic value.
[0035] The distribution density characteristic values in the distribution neighborhood set are screened according to the distribution density threshold, and the gypsum dehydration temperatures in the areas where the distribution density characteristic values are less than or equal to the distribution density threshold are deleted from the gypsum dehydration temperature set to obtain an aggregate temperature set. Finally, the temperature data in the aggregate temperature set are averaged, and the temperature average calculation result is set as the gypsum dehydration target temperature to obtain the gypsum dehydration target temperature.
[0036] By setting the neighborhood temperature difference distance threshold to perform neighborhood clustering on the gypsum dehydration temperature set and screening the field according to the distribution density threshold, the authenticity and accuracy of the aggregated temperature set can be improved. Finally, the temperature mean of the aggregated temperature set is used as the gypsum dehydration target temperature, which can improve the accuracy and rationality of the gypsum dehydration target temperature setting.
[0037] Further, step 4 of this application includes: Get the dehydrator model and activate the inner wall temperature mapping channel; Specifically, the dehydrator model information is obtained, wherein the dehydrator model information includes equipment capacity, equipment structure, size specifications, operating power and other information, and the inner wall temperature mapping channel is activated, wherein the inner wall temperature mapping channel is used for intelligent analysis of the inner wall temperature mapping.
[0038] Furthermore, the present application also includes the following steps: Configure monitoring features window; According to the monitoring feature window, partitioning the three-dimensional wall model of the dehydrator of the dehydrator model to generate a partitioned wall model; Based on the partitioned wall model, a graph neural network topology is constructed, wherein the graph neural network topology has a plurality of prediction partitions, the partitioned wall model has a plurality of wall partitions, and the plurality of prediction partitions and the plurality of wall partitions have the same distribution topology; Based on the outer wall partition topology of the partitioned wall model, the input network of the graph neural network topology is configured; based on the inner wall partition topology of the partitioned wall model, the output network of the graph neural network topology is configured to generate an inner wall temperature mapping channel network structure; The inner wall temperature mapping channel network structure is trained to obtain a unique association between the inner wall temperature mapping channel and the dehydrator model.
[0039] Specifically, first, configure the monitoring feature window, wherein the monitoring feature window is a window with a size identifier, wherein the specific size of the monitoring feature window can be set according to the dehydrator model. The three-dimensional wall model of the dehydrator can be obtained by simulation modeling in a three-dimensional visualization simulation platform according to the dehydrator model, wherein commonly used three-dimensional visualization simulation platforms include Maya software, AutoCAD software, etc., and the appropriate software can be selected for simulation modeling according to actual conditions. Then, the three-dimensional wall model of the dehydrator of the dehydrator model is partitioned according to the monitoring feature window, wherein the partition area and size of each wall are less than or equal to the area and size of the monitoring feature window, and a partitioned wall model is generated according to the wall partition result, wherein the partitioned wall model has a plurality of wall partitions.
[0040] Based on the partitioned wall model, a graph neural network topology is constructed. The graph neural network is a neural network that specifically processes graph data. It realizes analysis and prediction of graph data by performing feature learning and information transmission on nodes and edges in the graph. The graph neural network topology has several prediction partitions, and the distribution topologies of the several prediction partitions and the several wall partitions are the same, that is, each prediction partition corresponds to a wall partition distribution topology.
[0041] Further based on the neural network principle, the outer wall partition topology of the partitioned wall model is used as the input network of the graph neural network topology, and the inner wall partition topology of the partitioned wall model is used as the output network of the graph neural network topology to construct an inner wall temperature mapping channel network structure, wherein the inner wall temperature mapping channel is a neural network model that can be iteratively optimized in machine learning, and is obtained through supervised training with a training data set.
[0042] Then, the training data is obtained to train the inner wall temperature mapping channel network structure, and the trained inner wall temperature mapping channel is obtained, and the inner wall temperature mapping channel is uniquely associated with the dehydrator model. By constructing the inner wall temperature mapping channel based on the graph neural network topology, support is provided for inner wall temperature mapping, and the accuracy and efficiency of obtaining the inner wall temperature distribution cloud can be improved.
[0043] Furthermore, the present application also includes the following steps: According to the partition wall model and dehydrator model, collect the ambient temperature record data set, the outer wall temperature record data set and the inner wall temperature record data set to build a training data set; Divide the training data set into k equal parts, and extract k parts with replacement to obtain a first training data set; Repeat the process N times to obtain the first training data set, the second training data set, and finally the Nth training data set; The inner wall temperature mapping channel network structure is trained according to the first training data set to obtain a first inner wall temperature mapping node, and the inner wall temperature mapping channel network structure is trained according to the second training data set to obtain a second inner wall temperature mapping node, until the inner wall temperature mapping channel network structure is trained according to the Nth training data set to obtain an Nth inner wall temperature mapping node; The first inner wall temperature mapping node, the second inner wall temperature mapping node and the Nth inner wall temperature mapping node are merged to generate the inner wall temperature mapping channel, wherein the output temperature of any partition of the output network of the inner wall temperature mapping channel is equal to the mode value of the output temperature of the same partition of the output network of the N inner wall temperature mapping nodes.
[0044] Specifically, the method for training the inner wall temperature mapping channel network structure is as follows: first, information is collected based on the partition wall model and the dehydrator model to obtain an ambient temperature recording data set, an outer wall temperature recording data set and an inner wall temperature recording data set, wherein the ambient temperature recording data, the outer wall temperature recording data set and the inner wall temperature recording data set have a corresponding relationship, and a training data set is built based on the ambient temperature recording data set, the outer wall temperature recording data set and the inner wall temperature recording data set.
[0045] The training data set is divided into k parts, where k is an integer greater than 2, and the value of k can be set according to the number of training data in the training data set, to obtain k training data sets. Then, k training data sets are extracted with replacement k times, and a first training data set is constructed according to the extraction results. The above method is repeated N times, and then the second training data set is obtained in sequence until the Nth training data set, where N is an integer greater than k, and the value of N can be set according to actual conditions.
[0046] Then, the inner wall temperature mapping channel network structure is trained according to the first training data set to obtain a first inner wall temperature mapping node, wherein the training process of the inner wall temperature mapping channel network structure is as follows: first, first training data is randomly selected from the first training data set, wherein the first training data includes first ambient temperature recording data, first outer wall temperature recording data and first inner wall temperature recording data; the inner wall temperature mapping channel network structure is trained according to the first training data to obtain a first output result; then the first output result is compared with the first inner wall temperature recording data, and when the two are consistent, another training data is randomly selected for supervised training; when the two are inconsistent, the temperature deviation between the two is calculated, and the weight parameter of the inner wall temperature mapping channel network structure is optimized according to the temperature deviation, and then another training data is randomly selected for supervised training, and iterative training is continuously performed until the output result of the inner wall temperature mapping channel is greater than or equal to a preset accuracy index, then the first inner wall temperature mapping node after training is obtained, wherein the preset accuracy index can be set based on actual conditions, for example: the preset accuracy index is set to an accuracy of 95%. Then, the inner wall temperature mapping channel network structure is trained according to the second training data set using the same training method to obtain a second inner wall temperature mapping node; and iterative training is continuously performed until the inner wall temperature mapping channel network structure is trained according to the Nth training data set to obtain an Nth inner wall temperature mapping node.
[0047] The first inner wall temperature mapping node, the second inner wall temperature mapping node, and up to the Nth inner wall temperature mapping node are merged to generate an inner wall temperature mapping channel, wherein the output temperature of any partition of the output network of the inner wall temperature mapping channel is equal to the mode value of the output temperatures of the same partition of the output network of the N inner wall temperature mapping nodes, that is, the temperature data that appears most times in the output results of the N inner wall temperature mapping nodes is selected as the output result.
[0048] By setting multiple inner wall temperature mapping nodes and selecting the temperature data that appears most frequently in the output results of the inner wall temperature mapping nodes as the output results of the inner wall temperature mapping channel, the accuracy and rationality of the output results can be improved.
[0049] Obtain ambient temperature information through the temperature sensor; The outer wall temperature distribution and the ambient temperature information are processed through the inner wall temperature mapping channel to obtain the inner wall temperature distribution cloud.
[0050] Specifically, first, the ambient temperature of the dehydrator is collected by a temperature sensor to obtain ambient temperature information. Then, the outer wall temperature distribution and the ambient temperature information are input into the inner wall temperature mapping channel to perform inner wall temperature mapping, and an inner wall temperature distribution cloud is output. By obtaining the inner wall temperature distribution cloud, support is provided for the prediction of gypsum temperature in the next step of the dehydration process.
[0051] Furthermore, step five of this application also includes: Performing neighborhood aggregation analysis on the inner wall temperature distribution cloud to obtain an aggregated inner wall temperature; Specifically, a neighborhood aggregation analysis is performed on the inner wall temperature distribution cloud, wherein the neighborhood aggregation analysis refers to performing a cluster analysis on the inner wall temperature distribution cloud, and obtaining the aggregated inner wall temperature by weighted calculation based on the analysis results.
[0052] Furthermore, the present application also includes the following steps: Configure the disturbance temperature difference threshold; Randomly selecting a first partition from the inner wall temperature distribution cloud as a first aggregation starting point, wherein the first partition has a first partition inner wall temperature; Selecting the inner wall temperature of the second partition according to the inner wall temperature of the first partition, wherein the second partition is an adjacent partition to the first partition; Calculating a temperature difference modulus between the inner wall temperature of the first partition and the inner wall temperature of the second partition; When the temperature difference modulus is less than or equal to the disturbance temperature difference threshold, the second partition is added into the first aggregation region of the first partition, and the inner wall temperature of the first aggregation region is updated to the average temperature of the inner wall temperature of the first partition and the inner wall temperature of the second partition; When the temperature difference modulus is greater than the disturbance temperature difference threshold, the second partition is set as a second aggregation starting point to perform neighborhood aggregation analysis; Repeat the aggregation analysis, and when all the partitions of the inner wall temperature distribution cloud are traversed, obtain a plurality of aggregation partitions and a plurality of partition aggregation temperatures; Calculate the area ratios of the multiple aggregated partitions and set them as multiple aggregated partition weights; A weighted mean analysis is performed on the multiple partition aggregation temperatures according to the multiple aggregation partition weights to obtain the aggregation inner wall temperature.
[0053] Specifically, the method of performing neighborhood aggregation analysis on the inner wall temperature distribution cloud to obtain the aggregated inner wall temperature is as follows: first, configure a disturbance temperature difference threshold, wherein the disturbance temperature difference threshold is used to judge the temperature difference of adjacent inner wall partitions and can be set according to actual conditions. Then, a first partition is randomly selected from the inner wall temperature distribution cloud as the first aggregation starting point, wherein the first partition is any one of the multiple inner wall partitions contained in the inner wall temperature distribution cloud, wherein the first partition has a first partition inner wall temperature. Then, the second partition inner wall temperature is selected according to the first partition inner wall temperature, wherein the second partition is any one of the multiple adjacent partitions of the first partition.
[0054] Calculate the temperature difference modulus between the inner wall temperature of the first partition and the inner wall temperature of the second partition, wherein the temperature difference modulus refers to the absolute value of the partition inner wall temperature deviation, and then judge the temperature difference modulus according to the disturbance temperature difference threshold. When the temperature difference modulus is less than or equal to the disturbance temperature difference threshold, add the second partition to the first aggregation area of the first partition, and then calculate the temperature mean of the inner wall temperature of the first partition and the inner wall temperature of the second partition, and set the temperature mean as the inner wall temperature of the first aggregation area.
[0055] When the temperature difference modulus is greater than the disturbance temperature difference threshold, the second partition is set as the second aggregation starting point for neighborhood aggregation analysis; the aggregation analysis is repeated until all partitions of the inner wall temperature distribution cloud are traversed, and multiple aggregation partitions and multiple partition aggregation temperatures are obtained. The area proportions of the multiple aggregation partitions are calculated in sequence, and the area proportions are set as the aggregation partition weights to obtain the aggregation partition weights corresponding to the multiple aggregation partitions, where the larger the area proportion, the larger the aggregation partition weight. Then, the weighted mean of the multiple partition aggregation temperatures is calculated according to the multiple aggregation partition weights, and the weighted calculation result is set as the aggregation inner wall temperature.
[0056] By performing neighborhood aggregation analysis on the inner wall temperature distribution cloud and obtaining the aggregated inner wall temperature through weighted calculation, the accuracy and rationality of the aggregated inner wall temperature can be improved.
[0057] Searching according to the polymerization inner wall temperature, the gypsum weight, the gypsum composition, and the crystal water content to obtain a gypsum temperature true value record set; Mode analysis is performed on the true value record set of the gypsum temperature to obtain the predicted gypsum temperature.
[0058] Specifically, the gypsum dehydration temperature is retrieved according to the polymerization inner wall temperature, the gypsum weight, the gypsum composition, and the crystal water content to obtain a gypsum temperature true value record set, wherein the gypsum temperature true value refers to historical gypsum temperature data obtained by a very accurate or reliable measurement method. Finally, the gypsum temperature true value that appears the most times in the gypsum temperature true value record set is selected as the gypsum predicted temperature to obtain the gypsum predicted temperature.
[0059] In summary, the real-time monitoring method of gypsum dehydration temperature based on infrared sensing technology provided by the present application has the following technical effects: 1. By using an infrared thermometer to scan the temperature, the comprehensiveness of temperature monitoring can be improved. At the same time, temperature prediction can be performed in combination with the inner wall temperature distribution cloud, gypsum weight, gypsum composition, and crystal water content to improve the accuracy of gypsum temperature prediction, thereby achieving the technical goal of reducing temperature monitoring errors and improving temperature monitoring accuracy. Then, gypsum dehydration is controlled based on the temperature deviation between the predicted gypsum temperature and the gypsum dehydration target temperature, which can achieve the technical effect of accurately controlling gypsum dehydration.
[0060] 2. By setting the neighborhood temperature difference distance threshold to perform neighborhood clustering on the gypsum dehydration temperature set, and screening the field according to the distribution density threshold, the authenticity and accuracy of the aggregated temperature set can be improved. Finally, the temperature mean of the aggregated temperature set is used as the gypsum dehydration target temperature, which can improve the accuracy and rationality of the gypsum dehydration target temperature setting.
[0061] 3. By constructing an inner wall temperature mapping channel based on the graph neural network topology, it provides support for inner wall temperature mapping and improves the accuracy and efficiency of obtaining the inner wall temperature distribution cloud.
[0062] Embodiment 2 Based on the same inventive concept as the method for real-time monitoring of gypsum dehydration temperature based on infrared sensing technology in the aforementioned embodiment, the present application also provides a real-time monitoring system for gypsum dehydration temperature based on infrared sensing technology. Figure 3 , the system comprising: A module 11 for obtaining basic information of gypsum to be dehydrated, wherein the module 11 is used to obtain basic information of gypsum to be dehydrated, wherein the basic information of gypsum to be dehydrated includes gypsum composition information, crystal water content information, crystal water form information and gypsum weight information; A reference temperature configuration module 12, the reference temperature configuration module 12 is used to configure the reference temperature according to the gypsum composition information, the crystal water content information and the crystal water form information to generate a gypsum dehydration target temperature; An outer wall temperature distribution cloud obtaining module 13, wherein the outer wall temperature distribution cloud obtaining module 13 is used to scan the outer wall of the dehydrator by an infrared thermometer to obtain an outer wall temperature distribution cloud; An inner wall temperature mapping module 14, the inner wall temperature mapping module 14 is used to perform inner wall temperature mapping on the outer wall temperature distribution cloud to obtain an inner wall temperature distribution cloud; A temperature prediction module 15, the temperature prediction module 15 is used to perform temperature prediction on the inner wall temperature distribution cloud, the gypsum weight, the gypsum composition, and the crystal water content to obtain a predicted gypsum temperature; The temperature sending module 16 is used to send the predicted gypsum temperature and the gypsum dehydration target temperature to the dehydrator control terminal display interface.
[0063] Furthermore, the reference temperature configuration module 12 in the system is also used for: Retrieving a gypsum dehydration process log based on the gypsum composition information, the crystal water content information, and the crystal water form information, wherein the gypsum dehydration process log includes a gypsum dehydration temperature set; Configure the distribution density threshold and neighborhood temperature difference distance threshold; Performing pairwise temperature difference distance enumeration calculation on the gypsum dehydration temperature set to obtain a temperature difference distance set; Traversing the gypsum dehydration temperature set, and configuring a distribution neighborhood set based on the neighborhood temperature difference distance threshold and the temperature difference distance set, wherein the distribution neighborhood set has a distribution density characteristic value, and the distribution density characteristic value is equal to the number of neighborhood temperature distributions; Deleting the gypsum dehydration temperatures whose distribution density characteristic values are less than or equal to the distribution density threshold from the gypsum dehydration temperature set to obtain a polymerization temperature set; The mean of the polymerization temperature set is calculated and set as the gypsum dehydration target temperature.
[0064] Further, the inner wall temperature mapping module 14 in the system is also used for: Get the dehydrator model and activate the inner wall temperature mapping channel; Obtain ambient temperature information through the temperature sensor; The outer wall temperature distribution and the ambient temperature information are processed through the inner wall temperature mapping channel to obtain the inner wall temperature distribution cloud.
[0065] Further, the inner wall temperature mapping module 14 in the system is also used for: Configure monitoring features window; According to the monitoring feature window, partitioning the three-dimensional wall model of the dehydrator of the dehydrator model to generate a partitioned wall model; Based on the partitioned wall model, a graph neural network topology is constructed, wherein the graph neural network topology has a plurality of prediction partitions, the partitioned wall model has a plurality of wall partitions, and the plurality of prediction partitions and the plurality of wall partitions have the same distribution topology; Based on the outer wall partition topology of the partitioned wall model, the input network of the graph neural network topology is configured; based on the inner wall partition topology of the partitioned wall model, the output network of the graph neural network topology is configured to generate an inner wall temperature mapping channel network structure; The inner wall temperature mapping channel network structure is trained to obtain a unique association between the inner wall temperature mapping channel and the dehydrator model.
[0066] Further, the inner wall temperature mapping module 14 in the system is also used for: According to the partition wall model and dehydrator model, collect the ambient temperature record data set, the outer wall temperature record data set and the inner wall temperature record data set to build a training data set; Divide the training data set into k equal parts, and extract k parts with replacement to obtain a first training data set; Repeat the process N times to obtain the first training data set, the second training data set, and finally the Nth training data set; The inner wall temperature mapping channel network structure is trained according to the first training data set to obtain a first inner wall temperature mapping node, and the inner wall temperature mapping channel network structure is trained according to the second training data set to obtain a second inner wall temperature mapping node, until the inner wall temperature mapping channel network structure is trained according to the Nth training data set to obtain an Nth inner wall temperature mapping node; The first inner wall temperature mapping node, the second inner wall temperature mapping node and the Nth inner wall temperature mapping node are merged to generate the inner wall temperature mapping channel, wherein the output temperature of any partition of the output network of the inner wall temperature mapping channel is equal to the mode value of the output temperature of the same partition of the output network of the N inner wall temperature mapping nodes.
[0067] Furthermore, the temperature prediction module 15 in the system is also used for: Performing neighborhood aggregation analysis on the inner wall temperature distribution cloud to obtain an aggregated inner wall temperature; Searching according to the polymerization inner wall temperature, the gypsum weight, the gypsum composition, and the crystal water content to obtain a gypsum temperature true value record set; Mode analysis is performed on the true value record set of the gypsum temperature to obtain the predicted gypsum temperature.
[0068] Furthermore, the temperature prediction module 15 in the system is also used for: Configure the disturbance temperature difference threshold; Randomly selecting a first partition from the inner wall temperature distribution cloud as a first aggregation starting point, wherein the first partition has a first partition inner wall temperature; Selecting the inner wall temperature of the second partition according to the inner wall temperature of the first partition, wherein the second partition is an adjacent partition to the first partition; Calculating a temperature difference modulus between the inner wall temperature of the first partition and the inner wall temperature of the second partition; When the temperature difference modulus is less than or equal to the disturbance temperature difference threshold, the second partition is added into the first aggregation region of the first partition, and the inner wall temperature of the first aggregation region is updated to the average temperature of the inner wall temperature of the first partition and the inner wall temperature of the second partition; When the temperature difference modulus is greater than the disturbance temperature difference threshold, the second partition is set as a second aggregation starting point to perform neighborhood aggregation analysis; Repeat the aggregation analysis, and when all the partitions of the inner wall temperature distribution cloud are traversed, obtain a plurality of aggregation partitions and a plurality of partition aggregation temperatures; Calculate the area ratios of the multiple aggregated partitions and set them as multiple aggregated partition weights; A weighted mean analysis is performed on the multiple partition aggregation temperatures according to the multiple aggregation partition weights to obtain the aggregation inner wall temperature.
[0069] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The real-time monitoring method for gypsum dehydration temperature based on infrared sensing technology and the specific examples in the aforementioned embodiment 1 are also applicable to the real-time monitoring system for gypsum dehydration temperature based on infrared sensing technology in this embodiment. Through the aforementioned detailed description of the real-time monitoring method for gypsum dehydration temperature based on infrared sensing technology, those skilled in the art can clearly know the real-time monitoring system for gypsum dehydration temperature based on infrared sensing technology in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.
[0070] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
[0071] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.
Claims
1. A real-time monitoring method for gypsum dehydration temperature based on infrared sensing technology, characterized in that: include: Obtaining basic information of the gypsum to be dehydrated, wherein the basic information of the gypsum to be dehydrated includes gypsum composition information, crystal water content information, crystal water form information and gypsum weight information; Perform reference temperature configuration according to the gypsum composition information, the crystal water content information and the crystal water form information to generate a gypsum dehydration target temperature; Scan the outer wall of the dehydrator with an infrared thermometer to obtain the outer wall temperature distribution cloud; Performing inner wall temperature mapping on the outer wall temperature distribution cloud to obtain an inner wall temperature distribution cloud; Performing temperature prediction on the inner wall temperature distribution cloud, the gypsum weight, the gypsum composition, and the crystal water content to obtain the gypsum predicted temperature; The predicted gypsum temperature and the target gypsum dehydration temperature are sent to a display interface of a dehydrator control terminal.
2. The method according to claim 1, characterized in that The reference temperature is configured according to the gypsum composition information, the crystal water content information and the crystal water form information to generate the gypsum dehydration target temperature, including: Retrieving a gypsum dehydration process log based on the gypsum composition information, the crystal water content information, and the crystal water form information, wherein the gypsum dehydration process log includes a gypsum dehydration temperature set; Configure the distribution density threshold and neighborhood temperature difference distance threshold; Performing pairwise temperature difference distance enumeration calculation on the gypsum dehydration temperature set to obtain a temperature difference distance set; Traversing the gypsum dehydration temperature set, and configuring a distribution neighborhood set based on the neighborhood temperature difference distance threshold and the temperature difference distance set, wherein the distribution neighborhood set has a distribution density characteristic value, and the distribution density characteristic value is equal to the number of neighborhood temperature distributions; Deleting the gypsum dehydration temperatures whose distribution density characteristic values are less than or equal to the distribution density threshold from the gypsum dehydration temperature set to obtain a polymerization temperature set; The mean of the polymerization temperature set is calculated and set as the gypsum dehydration target temperature.
3. The method according to claim 1, characterized in that Performing inner wall temperature mapping on the outer wall temperature distribution cloud to obtain the inner wall temperature distribution cloud includes: Get the dehydrator model and activate the inner wall temperature mapping channel; Obtain ambient temperature information through the temperature sensor; The outer wall temperature distribution and the ambient temperature information are processed through the inner wall temperature mapping channel to obtain the inner wall temperature distribution cloud.
4. The method according to claim 3, characterized in that Get the dehydrator model and activate the wall temperature mapping channel, which previously included: Configure monitoring features window; According to the monitoring feature window, partitioning the three-dimensional wall model of the dehydrator of the dehydrator model to generate a partitioned wall model; Based on the partitioned wall model, a graph neural network topology is constructed, wherein the graph neural network topology has a plurality of prediction partitions, the partitioned wall model has a plurality of wall partitions, and the plurality of prediction partitions and the plurality of wall partitions have the same distribution topology; Based on the outer wall partition topology of the partitioned wall model, the input network of the graph neural network topology is configured; based on the inner wall partition topology of the partitioned wall model, the output network of the graph neural network topology is configured to generate an inner wall temperature mapping channel network structure; The inner wall temperature mapping channel network structure is trained to obtain a unique association between the inner wall temperature mapping channel and the dehydrator model.
5. The method according to claim 4, characterized in that Training the inner wall temperature mapping channel network structure to obtain the inner wall temperature mapping channel includes: According to the partition wall model and dehydrator model, collect the ambient temperature record data set, the outer wall temperature record data set and the inner wall temperature record data set to build the training data set; Divide the training data set into k equal parts, and extract k parts with replacement to obtain a first training data set; Repeat the process N times to obtain the first training data set, the second training data set, and finally the Nth training data set; The inner wall temperature mapping channel network structure is trained according to the first training data set to obtain a first inner wall temperature mapping node, and the inner wall temperature mapping channel network structure is trained according to the second training data set to obtain a second inner wall temperature mapping node, until the inner wall temperature mapping channel network structure is trained according to the Nth training data set to obtain an Nth inner wall temperature mapping node; The first inner wall temperature mapping node, the second inner wall temperature mapping node and the Nth inner wall temperature mapping node are merged to generate the inner wall temperature mapping channel, wherein the output temperature of any partition of the output network of the inner wall temperature mapping channel is equal to the mode value of the output temperature of the same partition of the output network of the N inner wall temperature mapping nodes.
6. The method according to claim 1, characterized in that The temperature distribution cloud of the inner wall, the weight of the gypsum, the composition of the gypsum, and the crystal water content are used to predict the temperature of the gypsum, and the predicted temperature of the gypsum is obtained, including: Performing neighborhood aggregation analysis on the inner wall temperature distribution cloud to obtain an aggregated inner wall temperature; Searching according to the polymerization inner wall temperature, the gypsum weight, the gypsum composition, and the crystal water content to obtain a gypsum temperature true value record set; Mode analysis is performed on the true value record set of the gypsum temperature to obtain the predicted gypsum temperature.
7. The method according to claim 6, characterized in that Performing neighborhood aggregation analysis on the inner wall temperature distribution cloud to obtain the aggregated inner wall temperature includes: Configure the disturbance temperature difference threshold; Randomly selecting a first partition from the inner wall temperature distribution cloud as a first aggregation starting point, wherein the first partition has a first partition inner wall temperature; Selecting the inner wall temperature of the second partition according to the inner wall temperature of the first partition, wherein the second partition is an adjacent partition to the first partition; Calculating a temperature difference modulus between the inner wall temperature of the first partition and the inner wall temperature of the second partition; When the temperature difference modulus is less than or equal to the disturbance temperature difference threshold, the second partition is added into the first aggregation region of the first partition, and the inner wall temperature of the first aggregation region is updated to the average temperature of the inner wall temperature of the first partition and the inner wall temperature of the second partition; When the temperature difference modulus is greater than the disturbance temperature difference threshold, the second partition is set as a second aggregation starting point to perform neighborhood aggregation analysis; Repeat the aggregation analysis, and when all the partitions of the inner wall temperature distribution cloud are traversed, obtain a plurality of aggregation partitions and a plurality of partition aggregation temperatures; Calculate the area ratios of the multiple aggregated partitions and set them as multiple aggregated partition weights; A weighted mean analysis is performed on the multiple partition aggregation temperatures according to the multiple aggregation partition weights to obtain the aggregation inner wall temperature.
8. The real-time monitoring system of gypsum dehydration temperature based on infrared sensing technology is characterized by: The steps for implementing the method according to any one of claims 1 to 7 include: A module for obtaining basic information of gypsum to be dehydrated, wherein the module is used to obtain basic information of gypsum to be dehydrated, wherein the basic information of gypsum to be dehydrated includes gypsum composition information, crystal water content information, crystal water form information and gypsum weight information; A reference temperature configuration module, the reference temperature configuration module is used to configure the reference temperature according to the gypsum composition information, the crystal water content information and the crystal water form information to generate a gypsum dehydration target temperature; An outer wall temperature distribution cloud obtaining module, wherein the outer wall temperature distribution cloud obtaining module is used to scan the outer wall of the dehydrator through an infrared thermometer to obtain an outer wall temperature distribution cloud; An inner wall temperature mapping module, the inner wall temperature mapping module is used to perform inner wall temperature mapping on the outer wall temperature distribution cloud to obtain an inner wall temperature distribution cloud; A temperature prediction module, the temperature prediction module is used to perform temperature prediction on the inner wall temperature distribution cloud, the gypsum weight, the gypsum composition, and the crystal water content to obtain a predicted gypsum temperature; A temperature sending module is used to send the predicted gypsum temperature and the gypsum dehydration target temperature to the display interface of the dehydrator control terminal.
