A coal ash characteristic evaluation method and a coal ash characteristic evaluation model training method
Through high-temperature furnace image acquisition equipment and image analysis technology, combined with training models, the problem of long and high cost of measuring coal ash viscosity-temperature characteristics is solved, and a fast and low-cost coal ash viscosity-temperature characteristics evaluation is achieved, which is suitable for coal chemical enterprises. Daily operational requirements.
Patent Information
- Application Number
- CN202410950718.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-16
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-07-16
AI Technical Summary
The existing coal ash viscosity-temperature characteristics measurement methods are time-consuming and costly, the equipment investment is expensive and the operation is complex, which limits the daily analysis capabilities of coal chemical companies.
The high-temperature furnace image acquisition equipment is used to obtain the morphological changes of the ash cone process and the temperature data. Through image analysis and feature extraction, the coal ash viscosity and melting characteristics are output in combination with the training model, reducing the measurement time and cost.
It realizes fast and low-cost coal ash viscosity-temperature characteristics assessment, reduces equipment investment and operation complexity, improves analysis frequency and accuracy, and is suitable for the daily operation needs of coal chemical companies.
Smart Images

Figure CN118483113B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of image processing technology, and in particular to a coal ash characteristic evaluation method and a coal ash characteristic evaluation model training method. Background Art
[0002] The viscosity-temperature characteristic is an important physical property of coal ash. It is the flow characteristic of coal ash when it is molten under high temperature conditions, and reflects the relationship between the viscosity and temperature of the coal ash melt.
[0003] The viscosity-temperature characteristics of coal ash have important guiding significance for the operation of liquid slag gasifiers (especially cold-wall gasifiers), boilers and other chemical and power equipment.
[0004] The existing methods for measuring the viscosity-temperature characteristics of coal ash are mainly based on basic principles such as the law of friction, and are measured experimentally using instruments such as high-temperature viscometers. The high-temperature viscometer is mainly composed of a high-temperature heating furnace, a viscosity measuring device, a temperature control program, and software. By measuring the torque of the viscometer at a certain rotational angular velocity, the viscosity of the melt at that temperature is obtained. The coal ash fusibility determination is a detection method for quantitatively describing the fusibility of coal ash. The coal ash is made into a triangular cone of a certain size, heated in a certain gas medium at a certain heating rate, and the morphological changes of the ash cone during the heating process are observed. Its four characteristic melting temperatures are observed and recorded: deformation temperature, softening temperature, hemispherical temperature, and flow temperature.
[0005] The disadvantages of existing measurement methods are mainly time and cost. (1) In terms of time, considering the heating performance and loss, the temperature rise rate of the viscometer is generally 10℃ / min or even lower, so the entire measurement process takes a long time. (2) In terms of cost, in order to protect the viscometer, protective gas and cooling water are also required. At the same time, during the measurement process, the rotor and crucible used in the high-temperature viscometer are disposable consumables. Overall, the cost of each measurement is relatively high. (3) In terms of investment, the purchase price of a single high-temperature viscometer is not cheap. (4) In terms of operation, the use of a high-temperature viscometer requires professionally trained experimental personnel.
[0006] The above four points limit the widespread use of high-temperature viscometers in production enterprises. At present, most coal chemical enterprises do not have the conditions for daily analysis of the viscosity-temperature characteristics of coal ash. Summary of the invention
[0007] The present application provides a coal ash characteristics evaluation method and a coal ash characteristics evaluation model training method to solve the problems existing in the related technology.
[0008] In a first aspect, the present invention provides a method for evaluating coal ash characteristics, comprising acquiring an image of the morphological change of an ash cone during a heating process from a high-temperature furnace image acquisition device; acquiring temperature change data from a high-temperature furnace temperature acquisition module; based on time information, matching the image of the morphological change of the ash cone during the heating process with temperature, wherein the image of the morphological change of the ash cone during the heating process is standardized before matching; inputting the corresponding information into a trained model, and outputting corresponding information of coal ash viscosity and temperature.
[0009] Optionally, the method further includes: outputting a coal ash fusibility evaluation result, wherein the coal ash fusibility evaluation result is a coal ash melting point estimation result, including deformation temperature, softening temperature, hemispherical temperature, and flow temperature.
[0010] Optionally, after inputting the corresponding information into the trained model, the method includes: extracting image-specified features, wherein the features include morphological features, residual height, circularity and contact angle features; determining the viscosity-temperature characteristic curve and the critical point based on the extracted image-specified features and the corresponding temperature, wherein the temperature and viscosity corresponding to the critical point are respectively used as the critical point temperature and the critical point viscosity.
[0011] Optionally, when determining the coal ash melting point estimation result, the method includes: the model determines the coal ash fusibility result based on the extracted image specified features and the corresponding temperature. The model determines the coal ash fusibility result based on the extracted image specified features and the corresponding temperature.
[0012] Optionally, when training the model, the training process includes constructing training data: after obtaining a set of coal ash sample images, establishing a correspondence between each sample image and temperature; extracting specified features of the sample image to obtain a correspondence between the specified features of each sample image and the temperature; determining the state features corresponding to each sample image, and establishing a correspondence between the state feature probability, image specified features, and temperature corresponding to each sample image; obtaining a viscosity data set of samples at different temperatures obtained from a sample test with the same composition as the coal ash sample, and obtaining a correspondence between different temperatures, viscosities, and critical points; merging the above correspondences to obtain a correspondence between the state feature probability, image specified features, temperature, viscosity, and critical point.
[0013] Optionally, when training the model, the specified features of the image and the corresponding temperature are used as inputs of the model, and the corresponding state feature probabilities, viscosities and critical points are used as outputs to train the model.
[0014] In a second aspect, the present invention provides a method for training a coal ash characteristic evaluation model, comprising: after obtaining a set of coal ash sample images, establishing a correspondence between each sample image and temperature; extracting specified features of the sample image to obtain a correspondence between the specified features of each sample image and the temperature; determining the state features corresponding to each sample image, and establishing a correspondence between the state feature probability, image specified features, and temperature corresponding to each sample image; obtaining a viscosity data set of samples at different temperatures obtained in a sample test with the same composition as the coal ash sample, and obtaining a correspondence between different temperatures, viscosities, and critical points; merging the above correspondences to obtain a correspondence between the state feature probability, image specified features, temperature, viscosity, and critical point; using the specified features of the image and the corresponding temperature as input to the model, and using the corresponding state feature probability, viscosity, and critical point as output to train the model.
[0015] In a third aspect, the present invention provides a device for evaluating coal ash characteristics, comprising: an acquisition unit, configured to acquire an image of the morphological change of an ash cone during a heating process from a high-temperature furnace image acquisition device; a temperature acquisition unit, configured to acquire temperature change data from a high-temperature furnace temperature acquisition module; an image processing unit, configured to correspond the image of the morphological change of an ash cone during a heating process to temperature based on time information, wherein the image of the morphological change of an ash cone during a heating process is standardized before the correspondence; and a model processing unit, configured to input the corresponding information into a trained model, and output corresponding information of coal ash viscosity and temperature.
[0016] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the first aspects is implemented.
[0017] In a fifth aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the method provided in the first aspect when executing the program.
[0018] The present invention discloses a method for evaluating coal ash characteristics and a method for training a coal ash characteristics evaluation model, wherein the method for evaluating coal ash characteristics obtains an image of the morphological change of the ash cone during the heating process from a high-temperature furnace image acquisition device; obtains temperature change data from a high-temperature furnace temperature acquisition module; based on time information, the image of the morphological change of the ash cone during the heating process is matched with the temperature, wherein the image of the morphological change of the ash cone during the heating process is standardized before the match; the corresponding information is input into the trained model, and the corresponding information of the coal ash viscosity and temperature is output. By adopting an existing high-temperature furnace for measuring the fusibility of coal ash, supplemented by an image acquisition device and an analysis system, and using methods such as image analysis, feature value extraction, and data analysis, the evaluation of the viscosity-temperature characteristics of coal ash and the fusibility of coal ash is realized, the time and cost required for the evaluation are reduced, and the defects of high cost and low timeliness in the related technology are solved. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0020] Figure 1 A method for evaluating coal ash characteristics is proposed for this application;
[0021] Figure 2a This is the morphological image of the original ash cone during heating process for this application;
[0022] Figure 2b The morphological image of the gray cone during heating after standardization for this application;
[0023] Figure 3 images containing specified features for this application;
[0024] Figure 4 This is a schematic diagram of the model processing for this application;
[0025] Figure 5 A method corresponding to the present application Figure 1 Schematic diagram of an electronic device. DETAILED DESCRIPTION
[0026] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.
[0027] The following is combined with Figure 1The method for evaluating the characteristics of coal ash is exemplified. The method comprises the following steps:
[0028] Step 101: Acquire an image of the morphological change of the ash cone during the heating process from a high-temperature furnace image acquisition device, and acquire temperature change data from a high-temperature furnace temperature acquisition module.
[0029] In this embodiment, an industrial camera or other image acquisition device is used to record the shape changes of the ash cone during the heating process, and a high-temperature furnace data interface is used to record temperature data.
[0030] Step 102: Based on the time information, the ash cone heating process morphological change image and the temperature are matched, wherein the ash cone heating process morphological change image is standardized before the matching.
[0031] In this embodiment, the original image needs to be initialized and preprocessed before feature extraction, which is used to eliminate the differences caused by different devices, eliminate the influence of irrelevant factors, highlight the main features, and form a standardized image. The preprocessing process includes cropping, segmentation, contour extraction, smoothing, etc. Figure 2a The original image and Figure 2b The images after normalization are shown.
[0032] Step 103: input the corresponding information into the trained model, and output the corresponding information of coal ash viscosity and temperature.
[0033] In this embodiment, the trained model analyzes the collected image-temperature correspondence, extracts the quantized image feature-temperature correspondence, and converts the correspondence information into a viscosity-temperature correspondence by the model, and can output the viscosity-temperature curve, critical viscosity and critical temperature.
[0034] The existing high-temperature furnace for measuring the fusibility of coal ash is used together with image acquisition equipment and analysis system. By using image analysis, feature value extraction and data analysis methods, the viscosity-temperature characteristics of coal and the characteristic melting temperature (DT, ST, HT, FT) of coal ash can be estimated at the same time.
[0035] As an optional implementation of this embodiment, the method further includes: outputting a coal ash fusibility evaluation result, wherein the coal ash fusibility evaluation result is a coal ash melting point estimation result, including deformation temperature, softening temperature, hemispherical temperature, and flow temperature.
[0036] In this optional implementation, during the analysis of the above model, the coal ash fusibility evaluation results can be obtained and output simultaneously, including deformation temperature, softening temperature, hemispherical temperature and flow temperature DT, ST, HT, FT.
[0037] As an optional implementation of this embodiment, after the corresponding information is input into the trained model, the method includes: extracting image specified features, wherein the features include morphological features, residual height, circularity and contact angle features; determining the viscosity-temperature characteristic curve and the critical point based on the extracted image specified features and the corresponding temperature, wherein the temperature and viscosity corresponding to the critical point are respectively used as the critical point temperature and the critical point viscosity.
[0038] In this optional implementation, the image can be feature extracted in real time. Figure 3 For the given example, the specific graphic features include:
[0039] ① Morphology: Qualitative classification, including cone (original), fused cone, curved cone, hemispherical / spherical, and flat type.
[0040] ② Residual height: quantitative indicator, residual height = current sample height / original sample height.
[0041] ③ Aspect ratio: quantitative indicator, aspect ratio = current sample height / current sample maximum width.
[0042] ④ Circularity: Quantitative index, circularity = (Pi×A×2) / (P^2), where Pi is the pi, A is the area of the figure, and P is the perimeter of the figure (excluding the part that contacts the bottom plate). The closer this index is to 1, the closer the sample projection shape is to a circle, and the closer the actual sample shape is to a sphere.
[0043] ⑤ Contact angle: A quantitative indicator, which is the angle from the solid-liquid interface through the liquid to the gas-liquid interface at the junction of solid (base plate), liquid (molten sample) and gas (ambient gas).
[0044] Based on the object relationship between the extracted image features and temperature, the model can further convert the image feature-temperature correspondence into the viscosity-temperature correspondence to obtain the viscosity-temperature characteristics of coal ash.
[0045] As an optional implementation of this embodiment, when determining the coal ash melting point estimation result, the method includes: the model determines the coal ash fusibility result based on the extracted image specified features and the corresponding temperature.
[0046] In this optional implementation, the coal ash state characteristics can be further determined by image formulation characteristics and temperature.
[0047] As an optional implementation method of this embodiment, when training the model, the training process includes constructing training data: after obtaining a set of coal ash sample images, establishing a correspondence between each sample image and temperature; extracting specified features of the sample image to obtain a correspondence between the specified features of each sample image and the temperature; determining the state features corresponding to each sample image, and establishing a correspondence between the state feature probability, image specified features, and temperature corresponding to each sample image; obtaining a viscosity data set of samples at different temperatures obtained from a sample test with the same composition as the coal ash sample, and obtaining a correspondence between different temperatures, viscosities, and critical points; merging the above correspondences to obtain a correspondence between the state feature probability, image specified features, temperature, viscosity, and critical point.
[0048] In this optional implementation, n-dimensional feature data (value range 0-255) of the sample image is extracted, and the image feature data, the characteristic probability value of the sample's current state (deformation point, softening point, hemisphere point, flow point, 4-dimensional floating point label data), and temperature (1-dimensional label data) are integrated into an image-temperature data set DataSet1, as shown in Table 1.
[0049] Table 1
[0050]
[0051] The coal ash samples with the same composition were tested in a high temperature viscometer to obtain the viscosity data set DataSet2 of the samples at different temperatures, where the temperature and viscosity corresponding to the critical point are the critical viscosity and critical temperature, as shown in Table 2:
[0052] Table 2
[0053]
[0054] The datasets DataSet1 and DataSet2 are merged and refer to Table 3 to obtain the image feature-viscosity dataset DataSet as shown below, where feature1...featureN and temperature are feature data, and the change point, softening point, hemisphere point, flow point probability value, and viscosity are label data. The annotated dataset contains a large number of correspondences between viscosity-temperature-image features-images, which are used to train image feature analysis models and graphic feature extraction models.
[0055] Table 3
[0056]
[0057] As an optional implementation of this embodiment, when training the model, the specified features of the image and the corresponding temperature are used as inputs of the model, and the corresponding state feature probability, viscosity and critical point are used as outputs to train the model.
[0058] In this optional implementation, reference Figure 4 , a multi-layer perceptron (MLP) model is trained based on the dataset (DataSet) to obtain the model F(feature1, feature2,…, featureN, temperature). Then, when the N-dimensional image features of the gray cone are input to the model, the corresponding feature probability value and viscosity can be calculated.
[0059] In this embodiment, the cost of analyzing a single set of samples is very low, the equipment investment is reduced to tens of thousands of yuan, and no specially trained operators are required. The cost reduction will enable production companies to obtain the viscosity-temperature characteristics of coal ash at an affordable cost, thereby better guiding production and setting more reasonable process parameters. At the same time, due to the low cost, the number of samples in a single set of samples can be increased to reduce the deviation caused by the unevenness of the samples themselves during sampling.
[0060] The analysis time of a single set of samples is shortened. Due to the short analysis time and low cost, the analysis frequency can be greatly increased, so that enterprises can obtain this information before the raw coal enters the production link. Assisted by the corresponding production experience or mechanism model, the control of operating conditions can be transformed from post-effect-based feedback adjustment to prediction-based pre-adjustment, avoiding production anomalies and accidents caused by rapid mutations in the viscosity-temperature characteristics of coal.
[0061] This embodiment provides a fast and low-cost method for evaluating the viscosity-temperature characteristics of coal ash. To a certain extent, it replaces the traditional method of measuring the viscosity-temperature characteristics by a high-temperature viscometer, and provides a reference for daily operations for coal chemical enterprises. At the same time, the present invention can also automatically extract and determine the characteristic melting temperature of coal ash, thereby reducing the manpower consumption in the process of coal ash fusibility determination and improving accuracy.
[0062] The above is a method provided by one or more embodiments of the present application. Based on the same idea, the present application also provides a corresponding method for training a coal ash characteristic evaluation model. After obtaining a set of coal ash sample images, a correspondence is established between each sample image and temperature; the specified features of the sample image are extracted to obtain the correspondence between the specified features of each sample image and the temperature; the state features corresponding to each sample image are determined, and the correspondence between the state feature probability, image specified features, and temperature corresponding to each sample image is established; a viscosity data set of samples at different temperatures obtained in the test of samples with the same composition as the coal ash sample is obtained to obtain the correspondence between different temperatures, viscosities, and critical points; the above correspondences are merged to obtain the correspondence between the state feature probability, image specified features, temperature, viscosity, and critical point; the specified features of the image and the corresponding temperature are used as the input of the model, and the corresponding state feature probability, viscosity, and critical point are used as output to train the model.
[0063] The above is a method provided by one or more embodiments of the present application. Based on the same idea, the present application also provides a corresponding coal ash characteristic evaluation model training device, including an image acquisition unit, configured to acquire an image of the morphological change of the ash cone during the heating process from a high-temperature furnace image acquisition device; a temperature acquisition unit, configured to acquire temperature change data from a high-temperature furnace temperature acquisition module; an image processing unit, configured to correspond the image of the morphological change of the ash cone during the heating process and the temperature based on time information, wherein the image of the morphological change of the ash cone during the heating process is standardized before the correspondence; a model processing unit, configured to input the corresponding information into a trained model, and output the corresponding information of coal ash viscosity and temperature.
[0064] As an optional implementation method of this embodiment, the model outputs a coal ash fusibility evaluation result, wherein the coal ash fusibility evaluation result is a coal ash melting point estimation result, including deformation temperature, softening temperature, hemispherical temperature, and flow temperature.
[0065] As an optional implementation of this embodiment, the model processing unit is further configured to, after inputting the corresponding information into the trained model, the method includes: extracting image specified features, wherein the features include morphological features, residual height, circularity and contact angle features; determining the viscosity-temperature characteristic curve and the critical point based on the extracted image specified features and the corresponding temperature, wherein the temperature and viscosity corresponding to the critical point are respectively used as the critical point temperature and the critical point viscosity.
[0066] As an optional implementation of this embodiment, the model determines the coal ash fusibility result based on the extracted image specified features and the corresponding temperature.
[0067] As an optional implementation method of this embodiment, when training the model, the training process includes constructing training data: after obtaining a set of coal ash sample images, establishing a correspondence between each sample image and temperature; extracting specified features of the sample image to obtain a correspondence between the specified features of each sample image and the temperature; determining the state features corresponding to each sample image, and establishing a correspondence between the state feature probability, image specified features, and temperature corresponding to each sample image; obtaining a viscosity data set of samples at different temperatures obtained from a sample test with the same composition as the coal ash sample, and obtaining a correspondence between different temperatures, viscosities, and critical points; merging the above correspondences to obtain a correspondence between the state feature probability, image specified features, temperature, viscosity, and critical point.
[0068] As an optional implementation of this embodiment, when training the model, the specified features of the image and the corresponding temperature are used as inputs of the model, and the corresponding state feature probability, viscosity and critical point are used as outputs to train the model.
[0069] Figure 5 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention, such as Figure 5 As shown, the electronic device 50 includes: a processor 501 (processor), a memory 502 (memory) and a bus 503;
[0070] The processor 501 and the memory 502 communicate with each other via the bus 503 ; the processor 501 is used to call program instructions in the memory 502 to execute the methods provided by the above-mentioned method embodiments.
[0071] This embodiment provides a non-transitory computer-readable storage medium, which stores computer instructions. The computer instructions enable a computer to execute the methods provided by the above method embodiments.
[0072] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various storage media that can store program codes.
[0073] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.
[0074] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.
[0075] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.
Claims
1. A method for evaluating coal ash characteristics, characterized in that: include: Acquire the morphological change image of the ash cone during the heating process from the high-temperature furnace image acquisition device, and acquire the temperature change data from the high-temperature furnace temperature acquisition module; Based on the time information, the morphological change image of the ash cone during the heating process and the temperature are matched, wherein the morphological change image of the ash cone during the heating process is standardized before the matching; Inputting the corresponding information into the trained model, and outputting the corresponding information of the coal ash viscosity and temperature; After the corresponding information is input into the trained model, the method includes: extracting image-specified features, wherein the features include morphological features, residual height, circularity, and contact angle features; determining a viscosity-temperature characteristic curve and a critical point based on the extracted image-specified features and the corresponding temperature, wherein the temperature and viscosity corresponding to the critical point are used as the critical point temperature and the critical point viscosity, respectively; Wherein, when training the model, the training process includes constructing training data: after obtaining a set of coal ash sample images, establishing a corresponding relationship between each sample image and temperature; extracting designated features of the sample images, and obtaining a corresponding relationship between the designated features of each sample image and temperature; determining the state features corresponding to each sample image, and establishing a corresponding relationship between the state feature probability, image designated features, and temperature corresponding to each sample image; obtaining a viscosity data set of samples at different temperatures obtained in a sample test with the same composition as the coal ash sample, and obtaining a corresponding relationship between different temperatures, viscosities, and critical points; merging the above corresponding relationships, and obtaining a corresponding relationship between the state feature probability, image designated features, temperature, viscosity, and critical point; When training the model, the specified features of the image and the corresponding temperature are used as inputs of the model, and the corresponding state feature probabilities, viscosities and critical points are used as outputs to train the model.
2. The method for evaluating coal ash characteristics according to claim 1, characterized in that: The method also includes: The coal ash fusibility evaluation result is output, wherein the coal ash fusibility evaluation result includes deformation temperature, softening temperature, hemisphere temperature, and flow temperature.
3. The method for evaluating coal ash characteristics according to claim 2, characterized in that: When determining the coal ash fusibility evaluation result, the method includes: The model determines the coal ash fusibility evaluation result based on the extracted image specified features and the corresponding temperatures.
4. A method for training a coal ash characteristic evaluation model, characterized in that: include: After obtaining the coal ash sample image set, a corresponding relationship is established between each sample image and temperature; Extracting designated features of the sample images, and obtaining the corresponding relationship between the designated features of each sample image and the temperature; Determine the state features corresponding to each sample image, and establish the corresponding relationship between the state feature probability, the image specified features, and the temperature corresponding to each sample image; Obtain the viscosity data set of samples at different temperatures obtained from the test of samples with the same composition as the coal ash sample, and obtain the corresponding relationship between different temperatures, viscosities and critical points; The above correspondences are combined to obtain the correspondences among state feature probability, image specified features, temperature, viscosity and critical point; The specified features of the image and the corresponding temperature are used as the input of the model, and the corresponding state feature probability, viscosity and critical point are used as output to train the model.
5. A coal ash characteristics evaluation device, characterized in that: include: An image acquisition unit is configured to acquire an image of the morphological change of the ash cone during the heating process from a high-temperature furnace image acquisition device; A temperature acquisition unit is configured to acquire temperature change data from a high temperature furnace temperature acquisition module; An image processing unit is configured to correspond the morphological change image of the ash cone during heating to the temperature based on time information, wherein the morphological change image of the ash cone during heating is subjected to standardization processing before the correspondence; A model processing unit is configured to input the corresponding information into the trained model and output the corresponding information of the coal ash viscosity and temperature; After the corresponding information is input into the trained model, the image specified features are extracted, wherein the features include morphological features, residual height, circularity and contact angle features; based on the extracted image specified features and the corresponding temperature, the viscosity-temperature characteristic curve and the critical point are determined, wherein the temperature and viscosity corresponding to the critical point are respectively used as the critical point temperature and the critical point viscosity; Wherein, when training the model, the training process includes constructing training data: after obtaining a set of coal ash sample images, establishing a corresponding relationship between each sample image and temperature; extracting designated features of the sample images, and obtaining a corresponding relationship between the designated features of each sample image and temperature; determining the state features corresponding to each sample image, and establishing a corresponding relationship between the state feature probability, image designated features, and temperature corresponding to each sample image; obtaining a viscosity data set of samples at different temperatures obtained in a sample test with the same composition as the coal ash sample, and obtaining a corresponding relationship between different temperatures, viscosities, and critical points; merging the above corresponding relationships, and obtaining a corresponding relationship between the state feature probability, image designated features, temperature, viscosity, and critical point; When training the model, the specified features of the image and the corresponding temperature are used as inputs of the model, and the corresponding state feature probabilities, viscosities and critical points are used as outputs to train the model.
6. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of claims 1 to 4 is implemented.
7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method described in any one of claims 1 to 4 is implemented.
Citation Information
Patent Citations
Method for predicting viscosity-temperature characteristics of coal ash
CN107045658A
Method for predicting melting temperature of coal ash based on mineral phase and neural network composite model
CN112881455A
Method for testing viscosity-temperature characteristic
CN117517386A
Method for rapidly predicting viscosity-temperature characteristics of coal ash
CN117949435A
