A smart control method, system, and storage medium for drying materials.
By using intelligent control methods based on material images and humidity parameters, and by adjusting the parameters of the drying device using neural networks and fuzzy logic, the problem of inaccurate drying in existing technologies has been solved, and intelligent and high-quality control of the material drying process has been achieved.
Patent Information
- Application Number
- CN202411770511.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-04
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2044-12-04
AI Technical Summary
Existing drying technologies cannot detect the drying status of materials in real time, which can easily lead to over-drying or under-drying, reducing the quality of materials.
By acquiring the original images and humidity parameters of the materials, a neural network model is used to classify the materials, extract the feature parameters of the regions of interest, and combine fuzzy logic control to adjust the operating parameters of the drying device, thereby achieving prediction and intelligent control of material state changes.
It enables precise control of the material drying process, avoids over-drying or under-drying, ensures material quality, and improves the intelligence and accuracy of the drying process.
Smart Images

Figure CN119554857B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of intelligent control technology, specifically to an intelligent control method, system, and storage medium for drying materials. Background Technology
[0002] With the continuous advancement of dryer development, intelligent development of dryers has become a trend. During the drying process, material dehydration mainly occurs in the slow heating and constant temperature stages. In the rapid heating stage, the drying rate decreases while the temperature rises rapidly. Inappropriate drying parameters can lead to a decline in material quality or even carbonization. Material drying is a complex, dynamic, and highly nonlinear process, often requiring the control of multiple indicators such as moisture content, color, degree of deformation, antioxidant properties, and various nutrients. Changes in moisture and nutrients during drying are often uncorrelated, making it difficult for a single mathematical or kinetic model to accurately characterize the changes in multiple indicators.
[0003] Currently, drying technologies include traditional natural sun-drying, hot air drying, heat pump drying, solar drying, microwave drying, infrared drying, and combined drying technologies. Most traditional drying technologies employ PLC automated control, incorporating fuzzy PID algorithms to create material drying control algorithms that ensure the material reaches the required dryness. However, existing drying methods cannot detect the material's dryness status in real time, resulting in slow detection speeds. During the drying process, over-drying leading to carbonization or under-drying can easily occur, reducing material quality. Summary of the Invention
[0004] This application addresses the aforementioned technical problems in the existing technology. The purpose of this application is to provide an intelligent control method, system, and storage medium for drying materials, which can predict future changes in the state of the materials and adjust the operating parameters of the drying device based on the prediction results to avoid over-drying or under-drying during the material drying process, thereby reducing material quality.
[0005] According to a first aspect of this application, an intelligent control method for drying materials is provided. The intelligent control method includes: acquiring, via a processor, an original material image containing the material of interest, along with the humidity parameters and a detected temperature of the material of interest; obtaining a region of interest (ROI) based on the original material image; obtaining feature parameters characterizing changes in the state of the material of interest based on the image of the ROI; performing material state change analysis on the image of the ROI; and, if the material state change is determined to meet preset requirements based on the feature parameters, performing fuzzy logic control based on the feature parameters and the humidity parameters to obtain a predicted temperature of the material of interest; and adjusting the operating parameters of a drying device for drying the material of interest based on a comparison between the detected temperature and the predicted temperature, such that the deviation between the predicted temperature obtained based on the current fuzzy logic control and the predicted temperature obtained based on the previous fuzzy logic control meets a threshold range.
[0006] According to a second aspect of this application, an intelligent control system for drying materials is provided. The intelligent control system includes: a data acquisition module configured to acquire original material images, humidity parameters, and temperature of the material of interest; a data processing module configured to execute the intelligent control method for drying materials as described in various embodiments of this application; and a drying module configured to dry the material of interest based on pre-set operating parameters.
[0007] According to a third aspect of this application, a computer-readable storage medium is provided, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the intelligent control method for drying materials described in various embodiments of this application are implemented.
[0008] Compared with the prior art, the beneficial effects of the embodiments of this application are as follows:
[0009] The intelligent control method provided in this application obtains a region of interest based on an original material image and characteristic parameters based on the region of interest. When the material state changes determined by the characteristic parameters meet preset requirements, fuzzy logic control is performed based on the characteristic parameters and humidity parameters to obtain the predicted temperature of the material of interest. Thus, by integrating humidity information and image information of the material of interest for fuzzy logic control, the obtained predicted temperature can reflect future changes in the material of interest in advance.
[0010] In this embodiment, the operating parameters of the drying device used to dry the material of interest are adjusted based on the comparison between the detected temperature and the predicted temperature. This ensures that the deviation between the predicted temperature obtained from the current fuzzy logic control and the predicted temperature obtained from the previous fuzzy logic control meets a threshold range. This achieves intelligent control of the drying process of the material of interest. By adjusting the operating parameters of the drying device based on the comparison between the predicted and detected temperatures, the drying process can be pre-adjusted. This allows for more accurate control of the drying process by adjusting the operating parameters, avoiding over-drying or under-drying, and ensuring the high quality of the material of interest.
[0011] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above description and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description
[0012] In drawings that are not necessarily drawn to scale, the same reference numerals may describe similar parts in different views. Similar reference numerals with different letter suffixes may indicate different examples of similar components. The drawings generally illustrate various embodiments by way of example rather than limitation, and are used together with the specification and claims to illustrate the disclosed embodiments. Such embodiments are illustrative and exemplary, and are not intended to be exhaustive or exclusive embodiments of the method, apparatus, system, or non-transitory computer-readable medium having instructions for implementing the method.
[0013] Figure 1 A flowchart of an intelligent control method for drying materials according to an embodiment of this application is shown.
[0014] Figure 2 A further flowchart of an intelligent control method for drying materials according to an embodiment of this application is shown.
[0015] Figure 3 A schematic diagram of a membership function according to an embodiment of this application is shown.
[0016] Figure 4 An example of a fuzzy rule according to an embodiment of this application is shown.
[0017] Figure 5 A schematic diagram of an intelligent control system for drying materials according to an embodiment of this application is shown. Detailed Implementation
[0018] To enable those skilled in the art to better understand the technical solutions of this application, the application will be described in detail below with reference to the accompanying drawings and specific embodiments. The embodiments of this application will be further described in detail below with reference to the accompanying drawings and specific examples, but these are not intended to limit the scope of this application.
[0019] The terms "first," "second," and similar words used in this application do not indicate any order, quantity, or importance, but are merely used for distinction. The terms "including" or "comprising," etc., used in this application mean that the element preceding the word encompasses the elements listed after the word, and do not exclude the possibility of encompassing other elements. In this application, the arrows shown in the figures for each step are merely examples of the execution order, not limitations. The technical solution of this application is not limited to the execution order described in the embodiments. The steps in the execution order can be combined, broken down, or rearranged, as long as the logical relationship of the executed content is not affected.
[0020] All terms used in this application (including technical or scientific terms) have the same meaning as understood by one of ordinary skill in the art to which this application pertains, unless otherwise specifically defined. It should also be understood that terms defined in general dictionaries should be interpreted as having meanings consistent with their meanings in the context of the relevant art, and not as idealized or highly formalized, unless expressly defined herein. Technologies and equipment known to one of ordinary skill in the art may not be discussed in detail, but where appropriate, such technologies and equipment should be considered part of the specification.
[0021] In this application, the arrows shown in the figures for each step are merely examples of the execution order and not limitations. The technical solution of this application is not limited to the execution order described in the embodiments. The steps in the execution order can be combined, decomposed, or their order can be changed, as long as the logical relationship of the execution content is not affected.
[0022] Figure 1 A flowchart of an intelligent control method for drying materials according to an embodiment of this application is shown. The intelligent control method executes the steps shown in steps S101-S104 via a processor. In this embodiment, the arrows shown in the figure for each step are merely examples of the execution order and not limitations. The technical solution of this application is not limited to the execution order described in the embodiment. The steps in the execution order can be combined, decomposed, or rearranged, as long as the logical relationship of the execution content is not affected.
[0023] In step S101, an original material image containing the material of interest, along with the humidity parameters and detection temperature of the material of interest, is acquired, and a region of interest is obtained based on the original material image. Specifically, a camera device can be used to acquire the original material image in real time, and a humidity sensor and a temperature sensor can be used to acquire the humidity parameters and detection temperature of the material of interest, respectively. The humidity parameter can be the relative humidity of the material of interest, and the detection temperature is the temperature of the material of interest acquired in real time.
[0024] The acquired raw material images, along with the humidity parameters and detected temperature of the materials of interest, are uploaded to the data storage space for subsequent processing and verification.
[0025] Specifically, the embodiments of this application can be applied to drying multiple types of herbs. For example, for mixed materials, the materials can be classified by variety first.
[0026] In other embodiments of this application, a neural network model is used to classify the mixture to be dried to obtain various material categories, wherein the materials in each material category have the same characteristic attributes. Taking the mixture including licorice, wolfberry, astragalus, and lily as an example, a transfer learning method can be used, employing a pre-trained VGG16 model as the base model, with its classifier part fine-tuned to adapt to the herbal medicine classification task.
[0027] For example, within deep learning frameworks (such as TensorFlow or PyTorch), you can call the corresponding function to load a pre-trained VGG16 model. Taking PyTorch as an example, you can use `torchvision.models.vgg16(pretrained=True)` to load a pre-trained VGG16 model. This model has been trained on large-scale image datasets (such as ImageNet) and has good image feature extraction capabilities. After loading, the parameters of the VGG16 model will be initialized, containing feature representation information learned from a large number of images, such as the weights of the convolutional kernels.
[0028] Accurate classification of mixed materials allows for the setting of optimal drying parameters for different types of herbs, ensuring that each herb achieves the best drying effect. It's possible to freeze certain layers of the VGG16 model, for example, freezing the parameters of the first 10 convolutional layers. These layers have already learned common image features such as texture and shape, allowing the trained first 10 layers to serve as feature extractors. Only three layers are retained for training, making the model more closely fit the dataset generated from the mixed materials. For example, in PyTorch, setting `requires_grad=False` can freeze the parameters of corresponding layers, preventing these parameters from being updated during backpropagation.
[0029] In this embodiment, material classification is performed for four mixtures. The final linear layer sets the output 4096-dimensional features to four-dimensional features. For example, with some parameter settings: batch_size=32, Dropout(p=0.5), Linear(4096,4), epochs=5, the classification results show an average loss of 0.0047 and an accuracy of 97.6%. The VGG16 model, when transferred to four different herbs (licorice, lily, wolfberry, and astragalus), exhibits excellent material classification performance.
[0030] The trained VGG16 model can then be used as a prediction model for classifying mixed materials. The model directly uses the trained parameters to predict the mixed materials captured by the camera. First, image preprocessing is performed: the image is centered and cropped to 224x224 pixels, then converted to a tensor and normalized to the range [-1, 1]. Next, the VGG16 prediction model is loaded and its classifier is replaced to adapt to the four-class classification task. The new classifier contains three fully connected layers, each with 4096 nodes, and applies ReLU activation and Dropout regularization. The availability of a GPU is checked; if so, the model is moved to the GPU and set to evaluation mode to disable training-specific operations such as Dropout. Four classification labels are defined, corresponding to lily, licorice, goji berries, and astragalus. Finally, the images are loaded and preprocessed, and then a prediction model is used to make predictions. The prediction result is determined by taking the index of the highest probability value and matching it with predefined category labels. Finally, the prediction results and corresponding images are displayed, thus classifying the mixed materials into four categories of interest: lily bulb, licorice root, goji berry, and astragalus root. In this way, a good classification accuracy can be achieved with only a small amount of herbal data and general computing power.
[0031] The materials of interest in each category share the same characteristic attributes, including color, outline, texture, and shape. The materials of interest are distinguished based on these same characteristic attributes, and the mixture is classified into licorice, lily, wolfberry, and astragalus, so that material state change analysis can be performed based on the material of interest category.
[0032] This is merely one example and does not constitute a limitation on any specific solution. For example, the neural network model could also be LeNet5, AlexNet, or GoogLeNet.
[0033] Returning to the embodiments of this application, the region where the material of interest is located can be extracted as the region of interest based on the original material image. Specifically, the region of interest can be extracted using existing functions in OpenCV, such as threshold segmentation, edge detection, morphological operations, and other different methods. No limitation is made in this regard.
[0034] In step S102, feature parameters for characterizing the state changes of the material of interest are obtained based on the image of the region of interest. These feature parameters may be, for example, color difference parameters, deformation parameters, viscosity parameters, browning index, etc., and are not limited thereto. Preferably, the feature parameters include color difference parameters and browning index.
[0035] The following explanation uses color difference parameter and browning index as examples of characteristic parameters.
[0036] Specifically, color features can be extracted from the image of the region of interest using methods such as color histograms and color moments, the color image can be converted into a grayscale image, and then a binarization algorithm can be used to obtain a binarized image to highlight the difference between the material of interest and the background in the image.
[0037] The binarized image is masked over the region of interest (ROI) image, thus removing background interference and other relevant information about the material of interest. The average values of the R, G, and B channels are extracted from the masked ROI image, and the color difference (ΔE) and browning index (BI) are obtained based on these average values.
[0038] Taking the CIELAB color space as an example, the CIELAB color space is a three-dimensional color space, consisting of a lightness coefficient (L). * ), red-green axis (a * ) and yellow-blue axis (b * Color is described using three coordinates. Where L... * The range is 0-100 (0 represents black, 100 represents white), a * Positive values indicate the red direction, and negative values indicate the green direction. * Positive values indicate the yellow direction, and negative values indicate the blue direction.
[0039] The CIE76 color difference formula is the most basic formula for calculating color difference. Assuming there are two colors in the CIELAB color space, their coordinates are (L1...) * a1 * b1 * ) and (L2 * a2 * b2 * ),
[0040]
[0041] Suppose that color A has coordinates (50, 20, 30) and color B has coordinates (60, 25, 35).
[0042] First, calculate the brightness difference ΔL. * =60-50=10;
[0043] Next, calculate a. * The difference Δa on the axis * =25-20=5;
[0044] Calculate b again * The difference Δb on the axis * =35-30=5;
[0045] Finally, substituting these values into the formula, we get: ΔE ab * =12.25.
[0046] The browning index is an important indicator for measuring the degree of color change (transition to brown) of a substance. In the CIELAB color space, it mainly utilizes the lightness index (L). * ), red-green axis (a * ) and yellow-blue axis (b * These three parameters are used for calculation. A commonly used formula is: Here
[0047]
[0048] Suppose that there exists a color coordinate (50, 10, 20) in the CIELAB color space. First, calculate X = 0.42, and then substitute the X value into the browning index formula to calculate the BI value, BI = 64.71.
[0049] The above is just one way to calculate color difference parameters and browning index. It can be adjusted according to specific needs, and there are no limitations on this.
[0050] In other words, in some other embodiments of this application, the color features of the material of interest are extracted based on the image of the region of interest, and the image of the region of interest is converted into a grayscale image, and a binarized image is obtained based on the grayscale image; the binarized image is masked on the image of the region of interest, and the average values of the R, G, and B channels are obtained based on the color features; the color difference parameter and browning index are obtained based on the average values of the R, G, and B channels.
[0051] In step S103, material state change analysis is performed based on the image of the region of interest. If the material state change meets preset requirements based on the feature parameters, fuzzy logic control is performed based on the feature parameters and the humidity parameter to obtain the predicted temperature of the material of interest. Specifically, during the drying process of the material of interest, its temperature, humidity, and morphology will all change. The feature parameters, such as color difference parameters and browning index, can be used to reflect the state changes of the material of interest, such as whether the color difference change is too large or the browning is too large during the drying process.
[0052] Based on feature parameters and humidity parameters, fuzzy logic control is used to obtain the predicted temperature of the material of interest. This predicted temperature is obtained by combining the humidity information and image information of the material of interest through fuzzy logic control, and can reflect the future changes of the material of interest in advance.
[0053] Specifically, such as Figure 2 The following explanation uses color difference and browning index as characteristic parameters. In step S201, the intelligent control system is activated. The computer vision processing program, sensors, and other related equipment within the intelligent control system are all started. Based on computer vision technology, it monitors changes in the material of interest, offering good real-time performance and fast detection speed. In step S206, for example, a humidity sensor can be used to collect the relative humidity of the material. In step S207, for example, a temperature sensor can be used to collect the detection temperature T of the material, which is the real-time temperature of the material of interest. In step S202, image processing is performed on the acquired raw material image. This image processing includes identifying the region of interest, extracting color features from the image of the region of interest, and grayscale and image binarization processing, etc. These processes are not limited; for example, they may also include image preprocessing to remove interfering background elements other than the material of interest from the image. In step S203, color difference parameters and browning index are extracted based on the processed image. That is, for example, the average values of the R, G, and B channels can be extracted based on the image of the region of interest after masking, and then the color difference and browning index are obtained based on the average values of the R, G, and B channels.
[0054] In step S204, it is determined whether the color difference parameter and browning index meet the preset requirements. Specifically, the color difference parameter can be compared with a preset color difference range, and the browning index can be compared with a preset browning range. If the color difference parameter is within the preset color difference range and the browning index is within the preset browning range, it indicates that the material change processing of the material of concern is within the normal range, and the material state change meets the preset requirements.
[0055] The preset color difference range and preset browning range are not specifically limited. Users can set them themselves based on the type of material they are interested in or their existing experience, or the processor can automatically configure them by default based on the type of material they are interested in.
[0056] If the judgment result in step S204 is negative, step S205 is executed to issue an alarm and urgently stop the equipment, thereby ensuring the safe operation of the drying process. In other words, in some embodiments of this application, when the material state change does not meet preset requirements, a warning message is issued to indicate an abnormality. The warning message may be, for example, an alarm sound, text, or a warning symbol; there is no limitation on these, as long as they can be used to alert staff to a drying abnormality.
[0057] If the judgment result in step S204 is yes, step S208 is executed, using the color difference parameter, browning index, and relative humidity as inputs, fuzzy logic control is performed, and the predicted temperature Ts is output. In some other embodiments of this application, based on the values of the color difference parameter, browning index, and humidity parameter, a membership function is used to determine the fuzzy sets to which the values of the color difference parameter, browning index, and humidity parameter belong, respectively. The fuzzy sets include negative large (NB), negative small (NS), positive small (PS), and positive large (PB). That is, the specific values of the color difference parameter, browning index, and humidity parameter are converted into fuzzy sets. The membership function determines the relationship between the precise value of the input quantity and the fuzzy variable after fuzzy transformation. It is a mapping from the precise value to the membership degree of the fuzzy set. The membership degree represents the degree to which a precise value belongs in a certain fuzzy set (such as NB, NS, PS, PB).
[0058] Suppose we use a triangular membership function to describe the fuzzy set of color difference. For the fuzzy set Negative Large (NB), when the color difference is 2, its membership degree in Negative Large (NB) is 0.8, so it is more likely to belong to Negative Large (NB); when the color difference is 6, its membership degree in Negative Large (NB) is 0, and its membership degree in Negative Small (NS) is 1, so it belongs to Negative Small (NS). This is only an example and does not constitute a limitation on any specific solution.
[0059] In this embodiment, the initial settings for color difference, browning index, and humidity range are 0-18, 0.9-1.8, and 10-50, respectively, and can be adjusted according to the corresponding experiments of different materials of interest. Membership functions can have various shapes, such as triangles, trapezoids, Gaussian shapes, etc., and there is no limitation on them, as long as the membership function can be used to convert precise values into fuzzy sets.
[0060] In other embodiments of this application, temperature prediction is performed based on fuzzy rules according to the fuzzy sets to which the values of the color difference parameter, browning index, and humidity parameter belong, to obtain the predicted temperature of the material of interest. Figure 3 This diagram illustrates how fuzzy logic control based on color difference, browning index, and humidity is used to obtain predicted temperature. Specifically, a fuzzy function editing tool can be used to design fuzzy sets and membership functions, where the inputs are color difference, browning index, and humidity, and the output is the predicted temperature. According to preset fuzzy rules, the membership function for the predicted temperature is determined based on color difference, browning index, and humidity. Then, the membership function is converted into a numerical value to obtain the predicted temperature.
[0061] Specifically, the fuzzy rules can be user-defined, and fuzzy rules can be, for example, as follows: Figure 4 As shown, where secha represents color difference, hebian represents browning index, H represents humidity, and T represents predicted temperature. For example, if (secha is NB) and (hebian is NB) and (H is NB) then (T is NB), it means that when color difference, browning index, and humidity are all negatively large, the predicted temperature will also be negatively large. Similarly, if (secha is NS) and (hebian is NB) and (H is NB) then (T is NB), it means that when color difference is negatively small, browning index, and humidity are all negatively large, the predicted temperature will also be negatively large. Finally, if (secha is PS) and (hebian is NB) and (H is NB) then (T is... Taking NS as an example, it explains that when color difference is small positive, browning index is large negative, and humidity is large negative, the predicted temperature is small negative; when color difference is large positive, browning index is large negative, and humidity is large negative, the predicted temperature is small positive; when color difference is large negative, browning index is large negative, and humidity is small negative, the predicted temperature is small negative, and so on. All the fuzzy rules will not be elaborated further; please refer to [link to relevant documentation]. Figure 4 The 64 fuzzy rules shown.
[0062] The fuzzy rules provided above are merely illustrative and do not constitute a specific limitation on fuzzy rules. Users can set fuzzy rules themselves according to different materials of interest, so that the predicted temperature obtained based on the fuzzy rules can be used in advance to accurately characterize the state changes of the materials of interest. For the same material of interest, differences in fuzzy rules may lead to different prediction results, but these prediction results are feasible as long as they are within a reasonable range. Different fuzzy rules are based on different experiences or settings to make decisions, and the differences between them reflect different processing strategies or different material characteristics. Due to the differences in predicted temperatures, the adjustment of the operating parameters of the drying device may also be different, but again, it is within a reasonable range.
[0063] The precise intelligent control capabilities of this application's embodiments are reflected in the pre-defined, reasonable fuzzy rules. In dynamic and complex environments, the operating parameters of the drying device can be accurately adjusted based on the real-time feedback provided by this application's embodiments, thereby achieving intelligent adjustment of the drying temperature. In this application's embodiments, "precise" refers to the precise adjustment of the drying device's operating parameters under reasonable fuzzy rules. Different fuzzy rules will have different adjustment strategies, but ultimately they all tend to focus on the appropriate drying temperature for the material, rather than producing the same fixed parameter under different rules.
[0064] In other embodiments of this application, material state change analysis is performed based on the original material image at preset time intervals to determine whether the current material state change meets preset requirements. Specifically, for example, the image acquisition device caches the acquired image information in the data storage space, and then acquires the original material image at the current moment every preset time interval (e.g., every 30 seconds). Based on the acquired original material image at the current moment, image processing is performed, including determining the region of interest, grayscale processing, binarization processing, and masking, to remove background and other interference from the image of the region of interest of the material of interest. Feature parameters are obtained based on the processed image, and then the material state change analysis continues. If the current material change of interest meets the preset requirements, fuzzy logic control is performed to obtain the predicted temperature. In this way, the material state change of the material of interest during the drying process can be quickly updated and monitored, and in particular, the predicted temperature of the material of interest can be obtained to predict the future temperature of the material of interest during the drying process.
[0065] Returning to the embodiments of this application, in step S104, based on the comparison result of the detected temperature and the predicted temperature, the operating parameters of the drying device used to dry the material of interest are adjusted so that the deviation between the predicted temperature obtained based on the current fuzzy logic control and the predicted temperature obtained based on the previous fuzzy logic control meets a threshold range. Here, "previous" refers to the time preceding the current moment. For example, the processor acquires the latest raw material image every 30 seconds and performs subsequent processing based on the latest acquired raw material image. Assuming the current moment is 210 seconds, then "previous" refers to 180 seconds. Based on the comparison result of the detected temperature and the predicted temperature, the operating parameters of the drying device are adjusted, for example, by reducing or increasing the power of the drying device, so that the deviation between the predicted temperature obtained by analyzing the raw material image acquired at 210 seconds and the predicted temperature obtained by analyzing the raw material image acquired at 180 seconds meets a threshold range. If the deviation meets the threshold range, it indicates that the change state of the material of interest tends to stabilize, and drying can be stopped, thereby ensuring the high quality of the material of interest.
[0066] Specifically, the drying device can be, for example, a solar collector, a heat pump dryer, etc., without limitation. The operating parameters can be the power of the solar collector, the wind speed of the dryer, or other relevant operating parameters that can be used to change the drying effect of the solar collector. There are no specific limitations, as long as the drying temperature of the drying device can be adjusted by adjusting the operating parameters.
[0067] In other embodiments of this application, when the deviation between the detected temperature and the predicted temperature is greater than or equal to a threshold deviation, the operating parameters of the drying apparatus are adjusted by reducing the temperature of the material of interest. The threshold deviation can be zero. Specifically, for example, the drying temperature of the material of interest can be reduced by decreasing the power of the drying apparatus, thereby lowering the detected temperature of the material of interest.
[0068] like Figure 2 In step S209, it is determined whether the difference between the material detection temperature T and the predicted temperature Ts is greater than or equal to 0. If the result of step S209 is yes, it indicates that the current material detection temperature T is too high, and step S210 is continued to reduce the power of the solar collector, thereby reducing the temperature of the material of interest and avoiding over-drying. If the result of step S209 is no, it indicates that the current material detection temperature T is too low, and step S211 is continued to increase the power of the solar collector, thereby increasing the drying temperature of the material of interest. In other words, when the deviation between the detection temperature and the predicted temperature is less than a threshold deviation, the operating parameters of the drying device are adjusted by increasing the temperature of the material of interest.
[0069] In this embodiment, fuzzy logic control is used to predict the temperature of the material of interest at future times based on color difference parameters, browning index, and humidity parameters. Based on the prediction results, the operating parameters of the drying device are intelligently adjusted, which can effectively avoid the problems of over-drying or poor drying effect of the material of interest, thereby improving the drying quality of the material.
[0070] After step S210, step S212 is executed to determine whether the difference between the predicted temperature Ts obtained based on the current fuzzy logic control and the predicted temperature T0 obtained from the previous fuzzy logic control is less than or equal to 0.1. In this embodiment, the threshold range is 0-0.1, or it could be 0-0.05; there is no limitation on this range. That is, if Ts-T0≤0, it indicates that the material of interest has been dried to its optimal state, and the changes in the material of interest after drying are minimal, so drying can be terminated. This achieves intelligent drying control of the material of interest.
[0071] If the judgment result of step S212 is negative, the humidity parameters and detection temperature of the material of interest are collected again, the material state change analysis of the material of interest is performed, and the operating parameters of the drying device used to dry the material of interest are adjusted based on the comparison result of the predicted temperature and the detection temperature, so that the deviation between the predicted temperature obtained based on the current fuzzy logic control and the predicted temperature obtained in the previous fuzzy logic control meets the threshold range.
[0072] In this way, intelligent control of the drying process of the material of interest can be achieved. The operating parameters of the drying device can be adjusted based on the comparison between the predicted temperature and the detected temperature. The drying process can be pre-adjusted, and the drying process of the drying device can be accurately controlled by adjusting the operating parameters. This avoids the problems of over-drying or under-drying, and helps to ensure that the material of interest maintains a high quality.
[0073] While the operating parameters of the drying device can be adjusted directly based on the real-time temperature of the material detected by sensors, this method lacks a comprehensive analysis of the complex dynamic characteristics of the material drying process. Real-time temperature only reflects the current temperature state of the material and cannot be used for intelligent drying adjustments based on this single temperature state. For example, during the drying of medicinal herbs, the temperature sensor may measure a low real-time drying temperature, but the humidity and image information of the herbs at this time indicate that the material requires a higher drying temperature. In this case, there is no basis for adjustment based on the single real-time temperature, and it is impossible to predict the future trend of the herbs.
[0074] The intelligent control method of this application embodiment can obtain the predicted temperature based on characteristic parameters and humidity parameters using fuzzy logic control. This predicted temperature, obtained based on fuzzy logic control, can better reflect the drying pattern of the material and the future temperature trend, enabling proactive adjustment of the material drying process. By comparing the predicted temperature and the detected temperature, the operating parameters of the drying device can be adjusted more accurately, thereby achieving proactive intelligent control, avoiding over-drying or under-drying, and improving material quality.
[0075] In other embodiments of this application, the color difference parameters, browning index, humidity parameters, and predicted temperature are all stored in a storage space to facilitate user access to historical data. This storage space can be located in the cloud, allowing users to remotely control the drying process via mobile phones or other portable smart devices. For example, if an abnormal alarm occurs during the drying process, the user can retrieve relevant data from the storage space for tracing and analysis.
[0076] In other embodiments of this application, the original material image containing the material of interest and the dried target material image are displayed side-by-side on the display interface, allowing the user to intuitively observe the state of the dried material. During the drying process, image acquisition devices such as cameras collect image information of the material of interest in real time. The image information acquired by the processor at preset time intervals is the original material image, while the image information obtained after the entire intelligent drying process is completed is the target material image. Furthermore, the initial material image and the target material image can be displayed simultaneously on the display interface to facilitate comparison of the target material image and the initial material image to observe the quality of the dried material of interest.
[0077] Figure 4 An intelligent control system for drying materials is illustrated, including a data acquisition module 501 configured to acquire original material images, humidity parameters, and temperature of the material of interest. Specifically, the data acquisition module 501 may include a camera device (not shown) to acquire initial images of the material of interest and images of the material during the drying process in real time. It may also include a humidity sensor (not shown) and a temperature sensor (not shown) to acquire humidity parameters and temperature (real-time temperature of the material of interest) in real time, respectively. The data acquisition module 501 may also include other devices; this is not limited and can be configured by the user according to the drying process.
[0078] The intelligent control system may also include a data storage module 504. Image information data and status information data of the material of interest (including humidity and temperature, which are not limited) acquired by the data acquisition module 501, as well as other data generated during subsequent analysis, can all be stored in the data storage module 504. For example, during the intelligent drying process, if an abnormal alarm occurs, the user can pause the drying process and inspect the drying device or other related equipment. The user can also retrieve relevant data parameters from the data storage module 504 for data verification to identify the cause of the problem. This improves the user's troubleshooting capabilities for the drying system.
[0079] The data processing module 502 is configured to execute the intelligent control method for drying materials as described in the various embodiments of this application, and the drying module 503 is configured to dry the material of interest based on pre-set operating parameters. The drying module 503 includes a solar collector 505. After the user turns on the drying equipment, an air intake fan draws outside air into the solar collector 505, which converts solar energy into heat energy. The internal air temperature of the solar collector 505 rises, and the hot air is blown into the drying chamber 506 to dry the material of interest.
[0080] The power of the solar collector 505 is adjusted based on the comparison between the predicted temperature and the detected temperature obtained by the data processing module 502, thereby realizing intelligent control of the drying process, avoiding problems such as over-drying during the drying process, and ensuring the quality of the materials.
[0081] The processor can be a processing device that includes one or more general-purpose processing devices, such as a microprocessor, a central processing unit (CPU), a graphics processing unit (GPU), etc. More specifically, the processor can be a Complex Instruction Set Computing (CISC) microprocessor, a Reduced Instruction Set Computing (RISC) microprocessor, a Very Long Instruction Word (VLIW) microprocessor, a processor that runs other instruction sets, or a processor that runs a combination of instruction sets. The processor can also be one or more special-purpose processing devices, such as an Application-Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), a System-on-a-Chip (SoC), etc. The processor can cooperate with the near-infrared brain functional imaging device that acquires the first near-infrared data to perform relevant data analysis and processing.
[0082] This application describes various operations or functions that can be implemented as software code or instructions, or defined as software code or instructions. Such content can be directly executable source code or differential code (“incremental” or “patch” code) (“object” or “executable” form). The software code or instructions can be stored in a computer-readable storage medium and, when executed, can cause a machine to perform the described functions or operations, and include any mechanism for storing information in a machine-accessible form, such as recordable or non-recordable media (e.g., read-only memory (ROM), random access memory (RAM), disk storage media, optical storage media, flash memory devices, etc.).
[0083] The exemplary methods described in this application can be implemented, at least in part, by a machine or computer. In some embodiments, a computer-readable storage medium stores computer program instructions that, when executed by a processor, cause the processor to perform the steps of the intelligent control method for drying materials described in the various embodiments of this application. The various steps of the intelligent control method for drying materials described in the foregoing embodiments can be incorporated herein and implemented by a processor executing computer program instructions, and will not be elaborated further here.
[0084] Implementations of such methods may include software code, such as microcode, assembly language code, high-level language code, etc. Various software programming techniques can be used to create various programs or program modules. For example, program parts or program modules can be designed using or with the aid of Java, Python, C, C++, assembly language, or any known programming language. One or more of such software parts or modules can be integrated into a computer system and / or a computer-readable medium. Such software code may include computer-readable instructions for performing various methods. This software code can form part of a computer program product or a computer program module. Furthermore, in the example, the software code may be tangibly stored on one or more volatile, non-transitory, or non-volatile tangible computer-readable media, for example, during execution or at other times. Examples of such tangible computer-readable media may include, but are not limited to, hard disks, removable disks, removable optical discs (e.g., optical discs and digital video discs), magnetic tape cassettes, memory cards or memory sticks, random access memory (RAM), read-only memory (ROM), etc.
[0085] Furthermore, although exemplary embodiments have been described herein, their scope includes any and all embodiments based on this application that have equivalent elements, modifications, omissions, combinations (e.g., schemes involving intersections of various embodiments), adaptations, or alterations. Elements in the claims will be interpreted broadly based on the language used in the claims and are not limited to the examples described in this specification or during the implementation of this application, which will be interpreted as non-exclusive. Therefore, this specification and examples are intended to be considered illustrative only, and the true scope and spirit are indicated by the full scope of the following claims and their equivalents.
[0086] The above description is intended to be illustrative and not restrictive. For example, the above examples (or one or more of them) can be used in combination with each other. Other embodiments may be used by those skilled in the art upon reading the above description. Furthermore, in the above detailed description, various features may be grouped together to simplify the application. This should not be construed as an intention that a disclosed feature not claimed is necessary for any claim. Rather, the subject matter of the application may be less than all the features of a particular disclosed embodiment. Thus, the claims are incorporated herein by reference as examples or embodiments, wherein each claim is an independent, separate embodiment, and these embodiments are contemplated as being combined with each other in various combinations or arrangements. The scope of this application should be determined by reference to the appended claims and the full scope of their equivalents.
[0087] The above embodiments are merely exemplary embodiments of this application and are not intended to limit this application. The scope of protection of this application is defined by the claims. Those skilled in the art can make various modifications or equivalent substitutions to this application within its substance and scope of protection, and such modifications or equivalent substitutions should also be considered to fall within the scope of protection of this application.
Claims
1. A method of intelligent control for drying material, characterized in that, The intelligent control method includes, via a processor, Acquire a raw material image containing the material of interest, along with the humidity parameters and detection temperature of the material of interest, and obtain the region of interest based on the raw material image; Based on the image of the region of interest, feature parameters are obtained to characterize the state changes of the material of interest. Based on the image of the region of interest, material state change analysis is performed. If the material state change meets the preset requirements based on the feature parameters, fuzzy logic control is performed based on the feature parameters and the humidity parameters to obtain the predicted temperature of the material of interest. Based on the comparison results of the detected temperature and the predicted temperature, the operating parameters of the drying device used to dry the material of interest are adjusted so that the deviation between the predicted temperature obtained based on the current fuzzy logic control and the predicted temperature obtained based on the previous fuzzy logic control meets the threshold range. The characteristic parameters include color difference parameters and browning index; Determining whether the material state change meets preset requirements based on the characteristic parameters specifically includes: The color difference parameter is compared with a preset color difference range, and the browning index is compared with a preset browning range. When the color difference parameter is within the preset color difference range and the browning index is within the preset browning range, the material state change meets the preset requirements.
2. The intelligent control method of claim 1, wherein, Based on the comparison between the detected temperature and the predicted temperature, the operating parameters of the drying device used to dry the material of interest are adjusted, specifically including: If the deviation between the detected temperature and the predicted temperature is greater than or equal to a threshold deviation, the operating parameters of the drying device are adjusted by reducing the temperature of the material of interest. If the deviation between the detected temperature and the predicted temperature is less than a threshold deviation, the operating parameters of the drying device are adjusted by increasing the temperature of the material of interest.
3. The intelligent control method of claim 1, wherein, Based on the image of the region of interest, feature parameters are obtained to characterize changes in the state of the material, specifically including: The color features of the material of interest are extracted from the image of the region of interest, and the image of the region of interest is converted into a grayscale image. Then, a binarized image is obtained based on the grayscale image. The binarized image is masked over the image of the region of interest, and the average values of the R, G, and B channels are obtained based on the color features; The color difference parameter and browning index are obtained based on the average values of the R, G, and B channels.
4. The intelligent control method of claim 1, wherein, The intelligent control method further includes: The material state changes are analyzed based on the original material image at preset time intervals to determine whether the current material state changes meet the preset requirements.
5. The intelligent control method according to claim 1, characterized in that, The intelligent control method further includes: issuing a prompt message to indicate an abnormality when the material state change does not meet preset requirements.
6. The intelligent control method according to any one of claims 1-3, characterized in that, The intelligent control method further includes: A neural network model is used to classify the mixed materials to be dried to obtain each category of material of interest, and the material state change analysis is performed based on each category of material of interest. The materials of interest in each category of material of interest have the same characteristic attributes.
7. The intelligent control method according to claim 1, characterized in that, Fuzzy logic control is used based on color difference parameters, browning index, and humidity parameters to obtain the predicted temperature of the material of interest, specifically including: Based on the values of color difference parameter, browning index and humidity parameter, the fuzzy set to which the values of color difference parameter, browning index and humidity parameter belong is determined by the membership function. The fuzzy set includes negative large, negative small, positive small and positive large. Based on the fuzzy sets to which the values of color difference parameter, browning index and humidity parameter belong, temperature prediction is performed according to fuzzy rules to obtain the predicted temperature of the material of interest.
8. An intelligent control system for drying materials, characterized in that, The intelligent control system includes: The data acquisition module is configured to acquire raw material images of the material of interest, humidity parameters of the material of interest, and detect temperature. A data processing module, configured to execute the intelligent control method for drying materials as described in any one of claims 1-7; and The drying module is configured to dry the material of interest based on pre-set operating parameters.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent control method for drying materials as described in any one of claims 1-7.
Citation Information
Patent Citations
Drying temperature control method and system for predicting eutectic point based on convolutional neural network
CN114139456A
