Biomass calorific value detection method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of calorific value detection, in particular to a biomass calorific value detection method and device, electronic equipment and a storage medium, and the method comprises the steps: collecting the total weight of biomass fuel, and calculating the volume variation of the biomass fuel to calculate first density, and then obtaining a substance image of the biomass fuel, and inputting the biomass into a biomass image recognition model, outputting the type and proportion of the biomass, inputting the type of the biomass into a biomass database to generate a second density and a first calorific value, and further calculating as received basis of moisture and impurities in the biomass fuel to calculate a second calorific value. Therefore, the problems of poor biomass calorific value detection and power generation amount evaluation precision and low efficiency caused by the fact that a rapid calorific value instrument method is difficult to consider the precision and efficiency of initial detection of large-batch samples and an empirical formula estimation method depends on the accuracy of basic data in related technologies are solved.

Description

Technical Field

[0001] This application relates to the field of calorific value detection technology, and in particular to a method, apparatus, electronic device and storage medium for detecting the calorific value of biomass. Background Technology

[0002] With the increasing prominence of energy and environmental issues, biomass energy, as a clean and renewable energy source, is gradually gaining global attention. Technologies for generating electricity using biomass energy mainly include: direct combustion biomass power generation, co-combustion biomass power generation, and biomass gasification power generation. Among these, co-combustion biomass power generation technology can utilize existing coal-fired power plant boiler equipment to mix and burn biomass and coal in a certain proportion, offering advantages such as reduced investment, shorter construction periods, and easier control of fuel costs.

[0003] In related technologies, biomass calorific value detection mainly includes methods such as rapid calorific value measurement and empirical formula estimation. The rapid calorific value measurement method calculates the calorific value by measuring the temperature of combustion gases using an infrared sensor, and is suitable for rapid on-site screening. The empirical formula estimation method estimates the calorific value based on the elemental analysis or industrial analysis data of the sample using mathematical formulas, and is suitable for preliminary resource assessment and rapid estimation when experimental conditions are lacking.

[0004] However, among related technologies, the rapid calorific value meter method is difficult to balance accuracy and efficiency when conducting initial testing of large batches of samples, while the empirical formula estimation method relies on the accuracy of basic data and lacks reliability. This makes it difficult to accurately and quickly detect the calorific value of biomass and to accurately and quickly assess the power generation of biomass fuel. This limits the application of biomass co-firing power generation technology and makes it impossible to effectively supervise power plants, which urgently needs to be addressed. Summary of the Invention

[0005] This application provides a method, apparatus, electronic device, and storage medium for detecting the calorific value of biomass, in order to solve the problems in related technologies, such as the difficulty in balancing accuracy and efficiency when conducting initial testing of large batches of samples using rapid calorific value analyzers, and the reliance on the accuracy of basic data for empirical formula estimation methods, which makes it difficult to accurately and quickly detect the calorific value of biomass and to accurately and quickly assess the power generation of biomass fuel. This limits the application of biomass co-firing power generation technology and makes it impossible to effectively supervise power plants.

[0006] The first aspect of this application provides a method for detecting the calorific value of biomass, comprising the following steps: collecting the total weight of biomass fuel and calculating the volume change of the biomass fuel at preset time intervals, and calculating a first density of the biomass fuel based on the total weight and the volume change; acquiring a material image of the biomass fuel and inputting the material image into a pre-trained biomass image recognition model to output the types and proportions of biomass in the biomass fuel, so as to input the types of biomass into a pre-constructed biomass database to generate a second density and a first calorific value of the corresponding dry biomass; calculating the as-received basis of moisture and impurities in the biomass fuel based on the first density and the second density, and calculating a second calorific value of the biomass fuel based on the as-received basis and the first calorific value.

[0007] Based on the above technical means, this application embodiment obtains the first density by collecting the total weight and calculating the volume change over a certain period of time, providing accurate physical parameters for subsequent component proportion analysis and avoiding single parameter measurement errors. In addition, by acquiring material images, model recognition output, and database matching, the second density and the first calorific value are obtained, realizing automated and rapid identification and parameter matching, improving efficiency and adaptability. Furthermore, the second calorific value is obtained by calculating the received basis through density difference and correcting it, simplifying the component detection operation, making the density and calorific value parameters closely related, and outputting heat release capacity data that fits the actual use conditions. Overall, the continuity, convenience, and reliability of the detection are improved, meeting the actual rapid evaluation needs. In this way, the power generation of biomass fuel can be accurately and quickly detected, which not only helps the application of biomass co-firing power generation technology, but also enables effective supervision of power plants.

[0008] Optionally, in one embodiment of this application, before inputting the material image into a pre-trained biomass image recognition model, the method further includes: acquiring a training dataset containing images of multiple types of biomass fuels and multiple proportions; training the model using the training dataset until convergence is achieved, and constructing the biomass image recognition model.

[0009] Based on the above technical means, the embodiments of this application train the model through training dataset, which can enhance the generalization ability of the model and then construct a biomass image recognition model. This model can accurately identify various types of biomass in the material image and accurately analyze their proportions, adapting to the image recognition needs of different types and different mixing ratios of materials, and providing reliable data support for subsequent biomass calorific value detection.

[0010] Optionally, in one embodiment of this application, before inputting the type of biomass into a pre-constructed biomass database, the method further includes: obtaining at least one of the bulk density, calorific value, ash content, volatile matter, and fixed carbon of a specific type of biomass based on industrial analysis and elemental analysis; and constructing the biomass database based on at least one of the bulk density, calorific value, ash content, volatile matter, and fixed carbon of the specific type of biomass.

[0011] Based on the above technical means, the embodiments of this application obtain the bulk density, calorific value, ash content, volatile matter and fixed carbon of specific types of biomass through industrial analysis and elemental analysis. This ensures the scientific nature, accuracy and comparability of the collected data, thereby constructing a biomass database. It can accurately establish the correlation between biomass types and corresponding parameters, providing accurate data support for the subsequent rapid matching of biomass types and output of corresponding parameters, and improving the reliability of biomass calorific value detection.

[0012] Optionally, in one embodiment of this application, the biomass image recognition model includes: a convolutional neural network (CNN) model and a U-shaped network (Unet) model, wherein the Unet model is used to capture the contextual semantic information of the biomass image by encoding, restore the feature map to the original image size by decoding and perform pixel classification, and fuse the encoded shallow details and the decoded deep semantics through skip connections to output a segmentation map; the CNN model is used to extract the type and proportion of biomass from the segmentation map through low-level feature extraction, mid-level feature combination and high-level feature recognition and decision-making.

[0013] Based on the above technical means, the embodiments of this application construct a biomass image recognition model through the collaborative construction of the Unet model and the CNN model. It not only utilizes the pixel-level segmentation capability of the Unet model to effectively separate the target region and the background interference region in the biomass fuel image, ensuring the targeting and accuracy of subsequent feature extraction, but also utilizes the hierarchical feature extraction capability of the CNN model to accurately identify the type and proportion of biomass from the clean segmentation image. The combination of the two makes the model have strong feature extraction accuracy and generalization ability.

[0014] Optionally, in one embodiment of this application, the formula for calculating the received basis may be, but is not limited to, the following: , in, The received basis is for the moisture and impurities in the biomass fuel. The first density of the biomass fuel is... The second density of the dry biomass is given.

[0015] Based on the above technical means, the embodiments of this application obtain the bulk density, calorific value, ash content, volatile matter and fixed carbon of specific types of biomass through industrial analysis and elemental analysis. This ensures the scientific nature, accuracy and comparability of the collected data, thereby constructing a biomass database. It can accurately establish the correlation between biomass types and corresponding parameters, providing accurate data support for the subsequent rapid matching of biomass types and output of corresponding parameters, and improving the reliability of biomass calorific value detection.

[0016] A second aspect of this application provides a biomass calorific value detection device, comprising: a calculation module, configured to collect the total weight of biomass fuel, calculate the volume change of the biomass fuel at preset time intervals, and calculate a first density of the biomass fuel based on the total weight and the volume change; a generation module, configured to acquire a material image of the biomass fuel, input the material image into a pre-trained biomass image recognition model to output the types and proportions of biomass in the biomass fuel, input the types of biomass into a pre-constructed biomass database, and generate a corresponding second density and a first calorific value of dry biomass; and a detection module, configured to calculate the received basis of moisture and impurities in the biomass fuel based on the first density and the second density, and calculate the second calorific value of the biomass fuel based on the received basis and the first calorific value.

[0017] Based on the above technical means, this application embodiment obtains the first density by collecting the total weight and calculating the volume change over a certain period of time, providing accurate physical parameters for subsequent component proportion analysis and avoiding single parameter measurement errors. In addition, by acquiring material images, model recognition output, and database matching, the second density and the first calorific value are obtained, realizing automated and rapid identification and parameter matching, improving efficiency and adaptability. Furthermore, the second calorific value is obtained by calculating the received basis through density difference and correcting it, simplifying the component detection operation, making the density and calorific value parameters closely related, and outputting heat release capacity data that fits the actual use conditions. Overall, the continuity, convenience, and reliability of the detection are improved, meeting the actual rapid evaluation needs. In this way, the power generation of biomass fuel can be accurately and quickly detected, which not only helps the application of biomass co-firing power generation technology, but also enables effective supervision of power plants.

[0018] Optionally, in one embodiment of this application, it further includes: a first acquisition module, used to acquire a training dataset containing images of multiple types of biomass fuels and multiple proportions; and a first construction module, used to train a model using the training dataset until a convergence condition is reached, and to construct the biomass image recognition model.

[0019] Based on the above technical means, the embodiments of this application train the model through training dataset, which can enhance the generalization ability of the model and then construct a biomass image recognition model. This model can accurately identify various types of biomass in the material image and accurately analyze their proportions, adapting to the image recognition needs of different types and different mixing ratios of materials, and providing reliable data support for subsequent biomass calorific value detection.

[0020] Optionally, in one embodiment of this application, it further includes: a second acquisition module, used to acquire at least one of the bulk density, calorific value, ash content, volatile matter and fixed carbon of a specific type of biomass based on industrial analysis and elemental analysis; and a second construction module, used to construct the biomass database based on at least one of the bulk density, calorific value, ash content, volatile matter and fixed carbon of the specific type of biomass.

[0021] Based on the above technical means, the embodiments of this application obtain the bulk density, calorific value, ash content, volatile matter and fixed carbon of specific types of biomass through industrial analysis and elemental analysis. This ensures the scientific nature, accuracy and comparability of the collected data, thereby constructing a biomass database. It can accurately establish the correlation between biomass types and corresponding parameters, providing accurate data support for the subsequent rapid matching of biomass types and output of corresponding parameters, and improving the reliability of biomass calorific value detection.

[0022] Optionally, in one embodiment of this application, the biomass image recognition model includes: a convolutional neural network (CNN) model and a U-shaped network (Unet) model, wherein the Unet model is used to capture the contextual semantic information of the biomass image by encoding, restore the feature map to the original image size by decoding and perform pixel classification, and fuse the encoded shallow details and the decoded deep semantics through skip connections to output a segmentation map; the CNN model is used to extract the type and proportion of biomass from the segmentation map through low-level feature extraction, mid-level feature combination and high-level feature recognition and decision-making.

[0023] Based on the above technical means, the embodiments of this application construct a biomass image recognition model through the collaborative construction of the Unet model and the CNN model. It not only utilizes the pixel-level segmentation capability of the Unet model to effectively separate the target region and the background interference region in the biomass fuel image, ensuring the targeting and accuracy of subsequent feature extraction, but also utilizes the hierarchical feature extraction capability of the CNN model to accurately identify the type and proportion of biomass from the clean segmentation image. The combination of the two makes the model have strong feature extraction accuracy and generalization ability.

[0024] Optionally, in one embodiment of this application, the formula for calculating the received basis may be, but is not limited to, the following: , in, The received basis is for the moisture and impurities in the biomass fuel. The first density of the biomass fuel is... The second density of the dry biomass is given.

[0025] Based on the above technical means, the embodiments of this application obtain the bulk density, calorific value, ash content, volatile matter and fixed carbon of specific types of biomass through industrial analysis and elemental analysis. This ensures the scientific nature, accuracy and comparability of the collected data, thereby constructing a biomass database. It can accurately establish the correlation between biomass types and corresponding parameters, providing accurate data support for the subsequent rapid matching of biomass types and output of corresponding parameters, and improving the reliability of biomass calorific value detection.

[0026] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the biomass calorific value detection method as described in the above embodiments.

[0027] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described biomass calorific value detection method.

[0028] A fifth aspect of this application provides a computer program product, including a computer program that, when executed, implements the above-described method for detecting the calorific value of biomass.

[0029] This application embodiment obtains the first density by collecting the total weight and calculating the volume change over a certain period of time, providing accurate physical parameters for subsequent component proportion analysis and avoiding single-parameter measurement errors. In addition, the second density and the first calorific value are obtained through material image acquisition, model recognition output, and database matching, realizing automated and rapid identification and parameter matching, improving efficiency and adaptability. Furthermore, the second calorific value is obtained by calculating the received basis through density difference and correcting it, simplifying the component detection operation and making the density and calorific value parameters closely correlated. The output of heat release capacity data that fits the actual use conditions improves the overall continuity, convenience, and reliability of the detection, meeting the actual rapid evaluation needs. In this way, the power generation of biomass fuel can be accurately and quickly detected, which not only helps the application of biomass co-firing power generation technology, but also enables effective supervision of power plants. This solves the problems in related technologies, such as the difficulty in balancing accuracy and efficiency when conducting initial testing of large batches of samples using rapid calorific value analyzers, and the difficulty in accurately and quickly detecting the calorific value of biomass and accurately and quickly assessing the power generation of biomass fuels. These problems limit the application of biomass co-firing power generation technology and make it impossible to effectively supervise power plants.

[0030] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0031] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a schematic diagram of a biomass calorific value detection system according to an embodiment of this application; Figure 2 This is a flowchart of a method for detecting the calorific value of biomass according to an embodiment of this application; Figure 3 This is a block diagram of a biomass calorific value detection device provided according to an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application.

[0032] Reference numerals: 30-Calcinality detection device for biomass; 100-Calculation module, 200-Generation module, 300-Detection module; 401-Memory, 402-Processor, 403-Communication interface. Detailed Implementation

[0033] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0034] The following description, with reference to the accompanying drawings, outlines a method, apparatus, electronic device, and storage medium for detecting the calorific value of biomass according to embodiments of this application. Addressing the issues raised in the background section, rapid calorific value analysis methods struggle to balance accuracy and efficiency in initial testing of large batches of samples, while empirical formula estimation methods rely heavily on the accuracy of basic data. This results in difficulties in accurately and quickly detecting the calorific value of biomass and accurately and quickly assessing the power generation capacity of biomass fuel, thus limiting the application of biomass co-firing power generation technology and hindering effective monitoring of power plants. This application provides a method for detecting the calorific value of biomass. In this method, the total weight is collected, and the volume change over a certain period is calculated to obtain the first density, providing accurate physical parameters for subsequent component proportion analysis and avoiding the problems associated with single-parameter measurement. In addition to reducing errors, by acquiring material images, recognizing models, and matching data to the database, the second density and the first calorific value are obtained, enabling automated and rapid identification and parameter matching, thus improving efficiency and adaptability. Furthermore, the second calorific value is obtained by calculating the density difference and correcting it, simplifying the component detection operation and ensuring a close correlation between density and calorific value parameters. This outputs exothermic capacity data that closely matches actual usage conditions, improving the overall consistency, convenience, and reliability of the detection results, meeting the needs of rapid assessment in practice. Consequently, it can accurately and quickly detect the power generation of biomass fuel, not only facilitating the application of biomass co-firing power generation technology but also enabling effective supervision of power plants. This solves the problems in related technologies, such as the difficulty in balancing accuracy and efficiency in the initial testing of large batches of samples using rapid calorific value meters, and the reliance on the accuracy of basic data for empirical formula estimation methods, which makes it difficult to accurately and quickly detect the calorific value of biomass and accurately and quickly assess the power generation of biomass fuel. These limitations restrict the application of biomass co-firing power generation technology and hinder effective supervision of power plants.

[0035] Before introducing the biomass calorific value detection method provided in the embodiments of this application, we will first introduce the biomass calorific value detection system that applies the biomass calorific value detection method.

[0036] Figure 1 This is a schematic diagram of a biomass calorific value detection system according to an embodiment of this application.

[0037] like Figure 1 As shown, the biomass calorific value detection system may include, but is not limited to, a weighbridge 1, a biomass silo inlet 2, a biomass silo 3, a 3D scanning device and its supporting purging device 4, an image acquisition device and its supporting purging and lighting device 5, a biomass stockpile 6, a biomass silo outlet 7, an auger 8, a biomass crushing device 9, a biomass fuel conveyor belt or pneumatic conveying system 10, and a boiler 11.

[0038] Understandably, after the biomass fuel is transported to the power plant by truck, it is first placed on weighbridge 1 for weighing to obtain the total weight of the biomass fuel. The weighed biomass fuel enters the biomass silo 3 from the biomass silo inlet 2 via a conveyor device.

[0039] 3D scanning components and their associated purging devices 4, along with image acquisition components and their associated purging and lighting devices 5, are arranged on both sides of the top of the biomass silo 3. The 3D scanning components are used to periodically scan the entire biomass pile inside the silo to obtain the volume of the biomass fuel. The image acquisition unit is used to periodically photograph the surface of the biomass stockpile to obtain material images of the biomass fuel; the matching purging device is used to purge the 3D scanning unit and image acquisition unit on time to ensure data accuracy; the lighting device is used to provide sufficient light for the photography environment to ensure clear material images.

[0040] The biomass stockpile 6 is discharged from the biomass silo outlet 7 and enters the screw conveyor 8. After passing through the biomass crushing device 9, it enters the boiler 11 through the biomass fuel conveyor belt or pneumatic conveying system 10.

[0041] Specifically, Figure 2 This is a flowchart of a biomass calorific value detection method provided according to an embodiment of this application.

[0042] like Figure 2 As shown, the method for detecting the calorific value of biomass includes the following steps: In step S201, the total weight of the biomass fuel is collected, and the volume change of the biomass fuel at preset intervals is calculated. Based on the total weight and volume change, the first density of the biomass fuel is calculated.

[0043] In the embodiments of this application, a certain duration can be understood as the time interval used to monitor changes in the volume of biomass fuel, and can be understood as the time difference between the initial moment before the biomass fuel enters the silo and the target moment after entering the silo. In addition, the target moment can be understood as the selected time node after the biomass fuel completes the operation of entering the silo, and can be adaptively set according to the characteristics of the biomass fuel (such as the stacking state and fluidity) and the processing requirements of the silo.

[0044] In addition, the first density can be understood as the density of biomass fuel in its actual state (i.e., in its natural state including moisture and impurities). It is obtained by collecting the total weight of the biomass fuel and calculating the volume change of the biomass fuel at regular intervals, and then calculating based on the total weight and the volume change.

[0045] In actual implementation, the total weight of this batch of biomass fuel can be obtained at weighbridge 1. Then, the initial moment before a batch of biomass fuel enters the silo is... And the target time after biomass fuel enters the silo is And obtain using 3D scans Corresponding to the volume of the material pile at any time V 0、 Corresponding to the volume of the material pile at any time V 1. Considering the discharge velocity of the silo as s, calculate the volume change of this batch of biomass fuel at regular intervals. The expression for the volume change can be, but is not limited to, the following: , in, This represents the volume change of this batch of biomass fuel at regular intervals. for The volume of the material pile should be considered at all times. for The volume of the material pile should be considered at all times. The discharge volume velocity from the silo. This refers to the target time after biomass fuel enters the silo. This refers to the initial moment before biomass fuel enters the silo.

[0046] Furthermore, the embodiments of this application are based on the total weight of this batch of biomass fuel. The volume change of this batch of biomass fuel at regular intervals Calculate the first density of this batch of biomass fuel. The expression for the first density can be, but is not limited to, as follows: , in, This is the first density of this batch of biomass fuel. This represents the total weight of this batch of biomass fuel. This represents the volume change of this batch of biomass fuel at regular intervals.

[0047] In step S202, a material image of the biomass fuel is acquired and input into a pre-trained biomass image recognition model to output the types and proportions of biomass in the biomass fuel. The types of biomass are then input into a pre-constructed biomass database to generate the corresponding second density and first calorific value of the dry biomass.

[0048] In the embodiments of this application, a material image can be understood as a visual image obtained by image acquisition of the biomass fuel (pile) to be detected. It contains visual information such as the shape, texture, color and mixed distribution of different types of biomass. It is the core data carrier that is subsequently input into the biomass image recognition model, and is used to provide a visual feature basis for the model to identify the types and proportions of biomass.

[0049] Furthermore, biomass image recognition models can be understood as artificial intelligence models trained to convergence. They typically integrate image segmentation and feature recognition modules (such as Unet and CNN models), enabling pixel-level region segmentation and hierarchical feature extraction of input biomass images, and outputting the types and proportions of biomass in the images, providing accurate species matching basis for subsequent calls to biomass databases.

[0050] In addition, a biomass database can be understood as a pre-built structured data storage carrier that stores the mapping relationship between different biomass types and their corresponding parameters. After inputting biomass type data, it can quickly match and output the physical property parameters corresponding to that type, providing data support for subsequent density calculations.

[0051] In addition, the second density can be understood as the dry biomass density of a specific type of biomass, that is, the density of the biomass in its pure dry state after removing moisture and impurities.

[0052] In addition, the first calorific value can be understood as the dry basis calorific value of a specific type of biomass, that is, the heat parameter released when the biomass is completely burned in a dry matter state after removing moisture and impurities.

[0053] In actual implementation, in the embodiment of this application, the material image of biomass fuel (such as a color image of a biomass fuel pile) can be acquired through an image acquisition device in the silo, and then the material image is input into a pre-trained biomass image recognition model to output the type and proportion of biomass in the biomass fuel.

[0054] Furthermore, in this embodiment, the types of biomass are input into a pre-constructed biomass database to generate the corresponding second density of dry biomass. and primary calorific value .

[0055] Optionally, in one embodiment of this application, before inputting the material image into the pre-trained biomass image recognition model, the method further includes: acquiring a training dataset containing images of multiple types of biomass fuels and multiple proportions; training the model using the training dataset until convergence is achieved, thereby constructing a biomass image recognition model.

[0056] In the embodiments of this application, the training dataset can be understood as a sample set used to train the biomass image recognition model. It includes images covering multiple types of biomass fuels and multiple ratio combinations. The samples cover the visual features of biomass in different shapes, textures, and mixed scenes, which can provide rich learning materials for the model. This allows the model to fully learn the visual features and ratio distribution patterns of different biomass, and is the basic data support to ensure that the biomass image recognition model has the ability to identify species and analyze ratios.

[0057] Furthermore, the convergence condition can be understood as the termination criterion in the training process of the biomass image recognition model. It can be reflected in the fact that the model's prediction error (such as the loss function value) remains stable within a certain threshold range, or that the model's recognition accuracy and generalization performance do not significantly improve after multiple iterations of training. This is used to ensure that the model fully learns the features of the training dataset during the training process, while avoiding overfitting or underfitting problems, so that the trained model has a stable and reliable ability to identify biomass species and perform proportional analysis.

[0058] In actual implementation, this application embodiment constructs a training dataset containing images of multiple types of biomass fuels and various proportions to provide rich learning samples for the biomass image recognition model. This enables the model to fully learn the visual features (such as shape, texture, and color) of different biomass fuels and the distribution patterns of image features under different proportion combinations. Then, the model is iteratively trained using this training dataset. By continuously adjusting the model parameters to minimize the prediction error, the model's output results tend to stabilize (reaching the convergence condition), thereby constructing a biomass image recognition model.

[0059] This application embodiment trains the model using a training dataset, which enhances the model's generalization ability and then constructs a biomass image recognition model. This model can accurately identify various types of biomass in the image and precisely analyze their proportions, adapting to the image recognition needs of different types and mixing ratios of biomass, and providing reliable data support for subsequent biomass calorific value detection.

[0060] Optionally, in one embodiment of this application, the biomass image recognition model includes: a convolutional neural network (CNN) model and a U-shaped network (Unet) model, wherein the Unet model is used to capture the contextual semantic information of the biomass image by encoding, restore the feature map to the original image size by decoding and perform pixel classification, and fuse the encoded shallow details and the decoded deep semantics through skip connections to output a segmentation map; the CNN model is used to extract the type and proportion of biomass from the segmentation map through low-level feature extraction, mid-level feature combination and high-level feature recognition and decision-making.

[0061] In actual implementation, the embodiments of this application can construct a biomass image recognition model through the collaboration of the Unet model and the CNN model to achieve hierarchical processing of biomass fuel images.

[0062] This application embodiment first utilizes the encoding / decoding structure and skip connection mechanism of the Unet model to perform pixel-level segmentation on the input material image. Specifically, this application embodiment captures the contextual semantic information of the image through the encoding process, restores the feature map to the original image size through the decoding process and completes pixel classification, and simultaneously fuses the shallow detail features from the encoding process with the deep semantic features from the decoding process through the skip connection mechanism to output a segmentation map that accurately divides the biomass region and the background region.

[0063] Furthermore, in this embodiment of the application, the segmentation map is used as input, and the hierarchical feature processing capability of the CNN model is used to sequentially complete the extraction of low-level features (such as the edges and color blocks of biomass), the combination of mid-level features (such as the texture and component shape of biomass), and the identification and decision of high-level features (such as the overall category and proportional relationship of biomass), thereby extracting the types and corresponding proportions of biomass.

[0064] This application embodiment constructs a biomass image recognition model through the collaborative construction of the Unet model and the CNN model. It leverages the pixel-level segmentation capability of the Unet model to effectively separate the target region from the background interference region in the biomass fuel image, ensuring the targeting and accuracy of subsequent feature extraction. It also utilizes the hierarchical feature extraction capability of the CNN model to accurately identify the type and proportion of biomass from the clean segmented image. The combination of the two gives the model strong feature extraction accuracy and generalization ability.

[0065] Optionally, in one embodiment of this application, before inputting the type of biomass into a pre-constructed biomass database, the method further includes: obtaining at least one of the bulk density, calorific value, ash content, volatile matter, and fixed carbon of a specific type of biomass based on industrial analysis and elemental analysis; and constructing a biomass database based on at least one of the bulk density, calorific value, ash content, volatile matter, and fixed carbon of the specific type of biomass.

[0066] In the embodiments of this application, industrial analysis can be understood as a means of evaluating the quality of biomass as fuel or feedstock, mainly used to determine the main components of biomass, namely moisture, ash, volatile matter, and fixed carbon. Industrial analysis can group components based on mass fraction and thermal behavior, enabling rapid evaluation of fuel process characteristics.

[0067] In addition, elemental analysis can be understood as a means of determining the chemical composition of biomass. It is mainly used to determine the mass percentage of the five major elements, carbon (C), hydrogen (H), oxygen (O), nitrogen (N), and sulfur (S), in biomass. The main analytical methods may include, but are not limited to, ICP-MS (Inductively Coupled Plasma-Mass Spectrometry), XRF (X-ray Fluorescence Spectrometry), and AAS (Atomic Absorption Spectrometry).

[0068] In actual implementation, the embodiments of this application can obtain the first result through industrial analysis, elemental analysis, and other means. i Specific types of biomass Bi Bulk density Calorific value H Ash content A d volatile matter V d and fixed carbon C d Furthermore, its biomass database format is constructed as follows: B i { , H , A d , V d , C d}, where subscript d This represents dry-based industrial analysis data for biomass.

[0069] Furthermore, in this embodiment of the application, after testing and calibrating the biomass database through industrial analysis, elemental analysis and other means, a query method with biomass type adaptability is developed: after the software obtains biomass type data, it automatically triggers the classification verification mechanism built into the biomass database, locates the target type through structured data index, and outputs the bulk density, calorific value, ash content, volatile matter and fixed carbon of the target type.

[0070] This application embodiment obtains the bulk density, calorific value, ash content, volatile matter, and fixed carbon of specific types of biomass through industrial analysis and elemental analysis. This ensures the scientific nature, accuracy, and comparability of the collected data, thereby constructing a biomass database. This allows for the precise establishment of the correlation between biomass types and corresponding parameters, providing accurate data support for the subsequent rapid matching of biomass types and output of corresponding parameters, and improving the reliability of biomass calorific value detection.

[0071] In step S203, the received basis of moisture and impurities in the biomass fuel is calculated based on the first density and the second density, and the second calorific value of the biomass fuel is calculated based on the received basis and the first calorific value.

[0072] In the embodiments of this application, the received base can be understood as the biomass fuel in its actual state (including the natural state of moisture and impurities). The mass ratio parameter of moisture and impurities is used to provide a basis for the composition ratio for subsequent correction of the first calorific value of dry biomass and to obtain the second calorific value of biomass fuel in its actual state. It is a key intermediate parameter connecting the density parameter and the calorific value parameter.

[0073] Furthermore, the second calorific value can be understood as the heat parameter released by the complete combustion of biomass fuel under actual conditions (including moisture and impurities). It is calculated based on the first calorific value of dry biomass (dry basis calorific value) and corrected by combining the received basis of moisture and impurities. It is the final indicator reflecting the heat release capacity of biomass fuel under actual use conditions and is also the core output result of the biomass calorific value detection method of this application, which can directly reflect the actual energy utilization value of the biomass fuel.

[0074] The embodiments of this application are described in detail below. The received basis of the biomass fuel is calculated based on the first density and the second density, so as to calculate the second calorific value of the biomass fuel based on the received basis and the first calorific value.

[0075] Specifically, in one embodiment of this application, the formula for calculating the received basis may be, but is not limited to, the following: , in, The basis for the removal of moisture and impurities in biomass fuel. The first density of biomass fuel, It is the second density of dry biomass.

[0076] In actual implementation, the embodiments of this application indirectly quantify the received basis of moisture and impurities by using the ratio of the difference between the actual density of state (such as the first density of biomass fuel) and the dry matter density (such as the second density of dry biomass) to the actual density of state.

[0077] This application embodiment indirectly quantifies the received basis of moisture and impurities, which differs from the method of directly weighing to measure mass difference. It effectively connects the previous detection steps, simplifies the operation process, improves the convenience of component ratio detection, provides an accurate basis for the subsequent second calorific value calculation, and improves the accuracy of biomass calorific value detection.

[0078] Furthermore, in this embodiment of the application, after obtaining the received basis containing moisture and impurities, the second calorific value of the biomass fuel can be calculated based on the received basis and the first calorific value, thus completing the calorific value detection of the biomass. The formula for calculating the second calorific value can be, but is not limited to, the following: , in, The second calorific value of biomass fuel, The basis for the removal of moisture and impurities in biomass fuel. It is the first calorific value of dry biomass.

[0079] The principle of the biomass calorific value detection method proposed in this application is illustrated below with reference to a specific embodiment.

[0080] This application embodiment can obtain the total weight of this batch of biomass fuel at weighbridge 1, and then use 3D scans to obtain... Corresponding to the volume of the material pile at any time V 0、 Corresponding to the volume of the material pile at any time V 1. Simultaneously consider the discharge velocity from the silo, and calculate the volume change of this batch of biomass fuel over a certain period of time. Then, based on the total weight of this batch of biomass fuel and the volume change of this batch of biomass fuel over a certain period of time, the first density of this batch of biomass fuel is calculated.

[0081] Furthermore, in this embodiment of the application, an image acquisition device can be used to acquire a material image of the biomass fuel within the silo. The material image is then input into a pre-trained biomass image recognition model to output the type and proportion of biomass in the biomass fuel. Subsequently, in this embodiment of the application, the type of biomass is input into a pre-constructed biomass database to generate the corresponding second density and first calorific value of the dry biomass.

[0082] Subsequently, in this embodiment of the application, the ratio of the difference between the first density of biomass fuel and the second density of dry biomass to the first density is used to indirectly quantify the received basis of moisture and impurities. Thus, after obtaining the received basis of moisture and impurities, this embodiment of the application can calculate the second calorific value of biomass fuel based on the received basis and the first calorific value, thereby completing the calorific value detection of biomass.

[0083] According to the biomass calorific value detection method proposed in this application, the first density is obtained by collecting the total weight and calculating the volume change over a certain period of time, providing accurate physical parameters for subsequent component ratio analysis and avoiding single parameter measurement errors. In addition, the second density and the first calorific value are obtained by acquiring material images, model recognition output, and database matching, realizing automated and rapid identification and parameter matching, improving efficiency and adaptability. Furthermore, the second calorific value is obtained by calculating the received basis through density difference and correcting it, simplifying the component detection operation and making the density and calorific value parameters closely correlated. The output heat release capacity data that fits the actual use conditions is output, which improves the overall continuity, convenience and reliability of the detection, meets the actual rapid evaluation needs, and can accurately and quickly detect the power generation of biomass fuel. This not only helps the application of biomass co-firing power generation technology, but also enables effective supervision of power plants. This solves the problems in related technologies, such as the difficulty in balancing accuracy and efficiency when conducting initial testing of large batches of samples using rapid calorific value analyzers, and the difficulty in accurately and quickly detecting the calorific value of biomass and accurately and quickly assessing the power generation of biomass fuels. These problems limit the application of biomass co-firing power generation technology and make it impossible to effectively supervise power plants.

[0084] Next, the biomass calorific value detection device according to the embodiments of this application is described with reference to the accompanying drawings.

[0085] Figure 3 This is a block diagram of a biomass calorific value detection device provided according to an embodiment of this application.

[0086] like Figure 3 As shown, the biomass calorific value detection device 30 includes: a calculation module 100, a generation module 200, and a detection module 300.

[0087] The calculation module 100 is used to collect the total weight of biomass fuel, calculate the volume change of biomass fuel at preset intervals, and calculate the first density of biomass fuel based on the total weight and volume change.

[0088] The generation module 200 is used to acquire a material image of biomass fuel and input the material image into a pre-trained biomass image recognition model to output the types and proportions of biomass in the biomass fuel. The types of biomass are then input into a pre-built biomass database to generate the corresponding second density and first calorific value of dry biomass.

[0089] The detection module 300 is used to calculate the received basis of moisture and impurities in biomass fuel based on the first density and the second density, so as to calculate the second calorific value of biomass fuel based on the received basis and the first calorific value.

[0090] Optionally, in one embodiment of this application, it further includes: a first acquisition module and a first construction module.

[0091] The first acquisition module is used to acquire a training dataset containing images of various types of biomass fuels and in various proportions.

[0092] The first building module is used to train the model using the training dataset until the convergence condition is met, thus building a biomass image recognition model.

[0093] Optionally, in one embodiment of this application, it further includes: a second acquisition module and a second construction module.

[0094] The second acquisition module is used to acquire at least one of the bulk density, calorific value, ash content, volatile matter, and fixed carbon of a specific type of biomass based on industrial analysis and elemental analysis.

[0095] The second building module is used to construct a biomass database based on at least one of the bulk density, calorific value, ash content, volatile matter, and fixed carbon of a specific type of biomass.

[0096] Optionally, in one embodiment of this application, the biomass image recognition model includes: a convolutional neural network (CNN) model and a U-shaped network (Unet) model. The Unet model is used to capture the contextual semantic information of the biomass image through encoding, restore the feature map to the original image size through decoding and perform pixel classification, and fuse the encoded shallow details with the decoded deep semantics through skip connections to output a segmentation map. The CNN model is used to extract the type and proportion of biomass from the segmentation map through low-level feature extraction, mid-level feature combination, and high-level feature recognition and decision-making.

[0097] Optionally, in one embodiment of this application, the formula for calculating the received basis may be, but is not limited to, the following: , in, The basis for the removal of moisture and impurities in biomass fuel. The first density of biomass fuel, It is the second density of dry biomass.

[0098] It should be noted that the foregoing explanation of the embodiment of the biomass calorific value detection method also applies to the biomass calorific value detection device of this embodiment, and will not be repeated here.

[0099] According to the biomass calorific value detection device proposed in this application, the first density is obtained by collecting the total weight and calculating the volume change over a certain period of time, providing accurate physical parameters for subsequent component ratio analysis and avoiding single parameter measurement errors. In addition, the second density and the first calorific value are obtained by acquiring material images, model recognition output, and database matching, realizing automated and rapid identification and parameter matching, improving efficiency and adaptability. Furthermore, the second calorific value is obtained by calculating the received basis through density difference and correcting it, simplifying the component detection operation, making the density and calorific value parameters closely related, and outputting heat release capacity data that fits the actual use conditions. Overall, the continuity, convenience, and reliability of the detection are improved, meeting the actual rapid evaluation needs. In this way, the power generation of biomass fuel can be accurately and quickly detected, which not only helps the application of biomass co-firing power generation technology, but also enables effective supervision of power plants. This solves the problems in related technologies, such as the difficulty in balancing accuracy and efficiency when conducting initial testing of large batches of samples using rapid calorific value analyzers, and the difficulty in accurately and quickly detecting the calorific value of biomass and accurately and quickly assessing the power generation of biomass fuels. These problems limit the application of biomass co-firing power generation technology and make it impossible to effectively supervise power plants.

[0100] Figure 4 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. The electronic device may include: The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0101] When the processor 402 executes the program, it implements the biomass calorific value detection method provided in the above embodiments.

[0102] Furthermore, electronic devices also include: Communication interface 403 is used for communication between memory 401 and processor 402.

[0103] The memory 401 is used to store computer programs that can run on the processor 402.

[0104] Memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0105] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0106] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0107] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0108] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described biomass calorific value detection method.

[0109] This application also provides a computer program product, including a computer program that, when executed, implements the above-described method for detecting the calorific value of biomass.

[0110] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0111] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0112] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0113] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0114] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0115] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0116] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0117] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for determining the calorific value of biomass, characterized in that, Includes the following steps: The total weight of the biomass fuel is collected, and the volume change of the biomass fuel is calculated at preset intervals. Based on the total weight and the volume change, the first density of the biomass fuel is calculated. The material image of the biomass fuel is obtained and input into a pre-trained biomass image recognition model to output the types and proportions of biomass in the biomass fuel. The types of biomass are then input into a pre-constructed biomass database to generate the corresponding second density and first calorific value of dry biomass. The received basis of moisture and impurities in the biomass fuel is calculated based on the first density and the second density, and the second calorific value of the biomass fuel is calculated based on the received basis and the first calorific value.

2. The method according to claim 1, characterized in that, Before inputting the material image into a pre-trained biomass image recognition model, the method further includes: Obtain a training dataset containing images of various types of biomass fuels and in various proportions; The model is trained using the training dataset until the convergence condition is met, thus constructing the biomass image recognition model.

3. The method according to claim 1, characterized in that, Before inputting the types of biomass into a pre-constructed biomass database, the process also includes: Based on industrial analysis and elemental analysis, obtain at least one of the following: bulk density, calorific value, ash content, volatile matter, and fixed carbon of a specific type of biomass; The biomass database is constructed based on at least one of the bulk density, calorific value, ash content, volatile matter, and fixed carbon of the specific type of biomass.

4. The method according to claim 2, characterized in that, The biomass image recognition model includes a convolutional neural network (CNN) model and a U-shaped network (Unet) model. The Unet model is used to capture the contextual semantic information of the biomass image through encoding, restore the feature map to the original image size through decoding and perform pixel classification, and fuse the encoded shallow details and the decoded deep semantics through skip connections to output a segmentation map. The CNN model is used to extract the type and proportion of biomass from the segmentation map through low-level feature extraction, mid-level feature combination and high-level feature recognition and decision-making.

5. The method according to claim 1, characterized in that, The formula for calculating the received base is: ， in, The received basis is for the moisture and impurities in the biomass fuel. The first density of the biomass fuel is... The second density of the dry biomass is given.

6. A biomass calorific value detection device, characterized in that, include: The calculation module is used to collect the total weight of the biomass fuel, calculate the volume change of the biomass fuel at preset intervals, and calculate the first density of the biomass fuel based on the total weight and the volume change. The generation module is used to acquire a material image of the biomass fuel and input the material image into a pre-trained biomass image recognition model to output the types and proportions of biomass in the biomass fuel, and input the types of biomass into a pre-constructed biomass database to generate the corresponding second density and first calorific value of dry biomass. The detection module is used to calculate the received basis of moisture and impurities in the biomass fuel based on the first density and the second density, and to calculate the second calorific value of the biomass fuel based on the received basis and the first calorific value.

7. The apparatus according to claim 6, characterized in that, Also includes: The acquisition module is used to acquire a training dataset containing images of various types of biomass fuels and in various proportions. A construction module is used to train the model using the training dataset until the convergence condition is met, thereby constructing the biomass image recognition model.

8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the biomass calorific value detection method as described in any one of claims 1-5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the biomass calorific value detection method as described in any one of claims 1-5.

10. A computer program product, comprising a computer program, characterized in that, The computer program is executed to implement the method for detecting the calorific value of biomass as described in any one of claims 1-5.

Images