Multi-parameter combined control method and system for key nodes in sea cucumber processing process

Abstract

The invention provides a multi-parameter combined control method and system for key nodes in a sea cucumber processing process, and relates to the technical field of automatic control. Executing drying control in a first drying stage according to preset parameters, monitoring to obtain a first sea cucumber image set, extracting a first real-time drying feature, and then calculating a drying feature deviation; and setting a second-stage drying target according to the second-stage drying index and the drying characteristic deviation, performing drying parameter optimization based on the target, determining an optimal second drying parameter to execute second-stage drying control, and performing iterative deviation analysis and drying parameter optimization until a plurality of drying stages are completed. The technical problems that in the prior art, due to the fact that the sea cucumber state cannot be monitored in real time and drying parameters cannot be dynamically adjusted, drying deviation accumulation is caused, and drying uniformity is poor are solved, and the technical effect of improving the overall drying uniformity and quality stability of sea cucumbers is achieved.

Description

Technical Field

[0001] The present invention relates to the field of automatic control technology, and in particular to a multi-parameter joint control method and system for key nodes in a sea cucumber processing process. Background Art

[0002] As a high-value seafood, sea cucumber processing, especially the drying process, has a crucial impact on the quality of the final product. Traditional sea cucumber processing methods rely primarily on equipment such as multi-layer belt dryers, which remove moisture through staged heating and air supply. The process uses more traditional control methods, performing drying operations based on preset fixed parameters such as temperature, humidity, and time. This makes it impossible to monitor the actual state changes of the sea cucumber during the drying process in real time, and lacks dynamic feedback on key characteristics such as the sea cucumber's appearance and texture. This makes it difficult to make timely and effective adjustments when deviations occur during the drying process, resulting in accumulated drying deviations, poor drying uniformity, and unstable texture of the finished sea cucumber, affecting the quality of the final product. Summary of the Invention

[0003] The present invention provides a multi-parameter joint control method and system for key nodes in the sea cucumber processing process, which solves the technical problem in the prior art that the sea cucumber status cannot be monitored in real time and the drying parameters cannot be dynamically adjusted during the sea cucumber drying process, resulting in accumulated deviations and poor drying uniformity during the sea cucumber drying process, thereby affecting the sea cucumber drying quality. It achieves the technical effect of realizing efficient closed-loop regulation of the drying process at each stage, thereby improving the overall drying uniformity and quality stability of the sea cucumbers.

[0004] In view of the above problems, on the one hand, the present invention provides a multi-parameter joint control method for key nodes of the sea cucumber processing process, the method comprising: dividing the sea cucumber drying process into several drying stages, and determining several standard drying characteristics; executing the drying control of the first drying stage according to the preset drying parameters, monitoring and obtaining the first sea cucumber image set of the first drying stage; performing drying feature extraction based on the first sea cucumber image set, obtaining the first real-time drying feature, and calculating the first drying feature deviation in combination with the first standard drying feature; setting the second stage drying target according to the second stage drying index and the first drying feature deviation, and optimizing the drying parameters of the second drying stage with the expectation of approaching the second stage drying target, and determining the optimal second drying parameters; executing the sea cucumber drying control of the second drying stage according to the optimal second drying parameters, and performing iterative deviation analysis and drying parameter optimization until all the operations in the several drying stages are completed.

[0005] Preferably, the drying characteristics include size reduction rate, surface grayscale mean and texture density.

[0006] Preferably, the drying control of the first drying stage is performed according to preset drying parameters, and a first sea cucumber image set of the first drying stage is monitored and obtained, including: performing the drying control of the first drying stage according to the preset drying parameters, where the drying parameters at least include drying temperature, drying wind speed, and relative humidity; at the end of the first drying stage, multi-position image acquisition of the sea cucumbers on the belt dryer is performed through an industrial camera to obtain the first sea cucumber image set.

[0007] Preferably, drying features are extracted from the first sea cucumber image set to obtain first real-time drying features, including: according to the historical drying records of sea cucumbers, collecting a sample sea cucumber image set, and respectively extracting features from the sample sea cucumber images according to the drying features to obtain a sample drying feature set; using the sample sea cucumber image set and the sample drying feature set to train a convolutional neural network until convergence to obtain a drying feature recognizer; performing single sea cucumber image cropping on the first sea cucumber image set, and selecting complete sea cucumber images to form a first standard single sea cucumber image set; using the drying feature recognizer to respectively extract features from the first standard single sea cucumber image set, and obtaining the first real-time drying features after mean calculation.

[0008] Preferably, performing single sea cucumber image cropping on the first sea cucumber image set, and selecting complete sea cucumber images to form a first standard single sea cucumber image set, including: performing single sea cucumber image cropping on the first sea cucumber image set, and selecting complete sea cucumber images to form a first single sea cucumber image set; performing high-frequency difference feature extraction on the first single sea cucumber image set to obtain the first standard single sea cucumber image set, where if the number of similarities between a first single sea cucumber image and other sea cucumber images in the first single sea cucumber image set is less than a preset similarity threshold and greater than a preset number threshold, it is set as the first standard single sea cucumber image.

[0009] Preferably, the first drying feature deviation is calculated by combining the first standard drying features, including: obtaining the first standard drying features of the first drying stage; subtracting the first real-time drying features from the first standard drying features to obtain the first drying feature deviation.

[0010] Preferably, the second-stage drying target is set according to the second-stage drying index and the first drying feature deviation, and the drying parameter optimization of the second drying stage is performed with the expectation of approaching the second-stage drying target to determine the optimal second drying parameters, including: obtaining the second standard drying features of the second drying stage, subtracting the first standard drying features of the first drying stage to obtain the second-stage drying index; summing the second-stage drying index and the first drying feature deviation to obtain the second-stage drying target; based on the drying parameter adjustment space, performing the drying parameter optimization of the second drying stage with the expectation of approaching the second-stage drying target to determine the optimal second drying parameters.

[0011] Preferably, based on the drying parameter adjustment space, the drying parameter optimization for the second drying stage is carried out with the expectation of approaching the drying target of the second stage, and the optimal second drying parameter is determined, including: collecting a sample drying parameter set and a sample drying feature set according to the historical sea cucumber drying logs of similar belt dryers, training a generative adversarial network, and constructing a drying feature prediction plug-in; randomly generating a number of drying parameters based on the drying parameter adjustment space, and analyzing a number of predicted drying features by using the drying feature prediction plug-in; taking the drying target of the second stage as a benchmark, performing an overall deviation analysis on the number of predicted drying features to obtain a number of feature deviation values; based on the drying parameter adjustment space, performing drying parameter optimization for the second drying stage according to the number of feature deviation values, and outputting the optimal second drying parameter.

[0012] Preferably, based on the drying parameter adjustment space, the drying parameter optimization for the second drying stage is carried out according to the number of feature deviation values, and the optimal second drying parameter is output, including: taking the drying parameter as the initial solution, sorting according to the feature deviation value from small to large, and mapping to generate a number of initial solution sequences according to the number of feature deviation values; dividing the number of initial solution sequences into optimal solutions and inferior solutions according to a predetermined ratio, where the number of inferior solutions is N times that of the optimal solutions, and N is greater than or equal to 10; clustering the inferior solutions with the optimal solution as the center to obtain a number of solution sets, and within each solution set, taking the optimal solution as the direction, adjusting the inferior solutions within the solution set according to a preset optimization step length to obtain a number of updated solution sets, where if the adjusted inferior solution exceeds the drying parameter adjustment space, a drying parameter is randomly selected within the drying parameter adjustment space for replacement, and if the feature deviation value of the adjusted inferior solution is less than the feature deviation value of the optimal solution within the same solution set, the inferior solution is used to replace the optimal solution; performing iterative optimization until a preset convergence number is reached, and outputting the drying parameter with the smallest feature deviation value within all solution sets as the optimal second drying parameter.

[0013] On the other hand, the present invention also provides a multi-parameter joint control system for key nodes in the sea cucumber processing process. The system includes: a drying stage division module for dividing the sea cucumber drying process into several drying stages and determining several standard drying characteristics; a first drying control module for performing drying control of the first drying stage according to preset drying parameters and monitoring and obtaining a first sea cucumber image set of the first drying stage; a feature deviation calculation module for extracting drying features based on the first sea cucumber image set to obtain first real-time drying features, and calculating a first drying feature deviation by combining the first standard drying features; a drying parameter optimization module for setting a second-stage drying target according to the second-stage drying index and the first drying feature deviation, and optimizing the drying parameters of the second drying stage with the approximation of the second-stage drying target as the expectation to determine the optimal second drying parameters; a second drying control module for performing sea cucumber drying control of the second drying stage according to the optimal second drying parameters, and performing iterative deviation analysis and drying parameter optimization until all the several drying stages are completed.

[0014] One or more technical solutions provided in the present invention have at least the following beneficial effects: By dividing the sea cucumber drying process into several drying stages and determining several standard drying characteristics, a phased division of the drying process and an ideal drying feature reference value are provided, providing a reference for subsequent deviation detection and parameter correction. Performing drying control of the first drying stage according to preset drying parameters, monitoring and obtaining a first sea cucumber image set of the first drying stage, realizing the perception of the sea cucumber state, extracting drying features based on the first sea cucumber image set to obtain first real-time drying features, and calculating a first drying feature deviation by combining the first standard drying features, quantifying the gap between the actual drying result and the standard features, and clarifying the processing deviation. Setting a second-stage drying target according to the second-stage drying index and the first drying feature deviation, and optimizing the drying parameters of the second drying stage with the approximation of the second-stage drying target as the expectation to determine the optimal second drying parameters, feeding back the actual deviation of the first stage to the second stage, and realizing dynamic deviation correction by adjusting the target and parameters of the second stage to ensure that the subsequent processing stage can effectively correct the deviation. Performing sea cucumber drying control of the second drying stage according to the optimal second drying parameters, and performing iterative deviation analysis and drying parameter optimization until all the several drying stages are completed, forming a multi-stage closed-loop adjustment process: each stage performs parameter optimization and correction based on the deviation of the previous stage, continuously iterating to avoid deviation accumulation.

[0015] In summary, the present invention divides the sea cucumber drying process into several stages, and obtains the sea cucumber drying characteristics in each stage in combination with real-time visual images, thereby realizing stage-by-stage deviation analysis and dynamic parameter optimization, forming a closed-loop control system of multi-parameter joint control and continuous feedback optimization, significantly improving the uniformity and overall processing quality of the sea cucumber drying process, and realizing efficient, precise and intelligent sea cucumber drying control.

[0016] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flow chart of a multi-parameter joint control method for key nodes in a sea cucumber processing process provided by an embodiment of the present invention.

[0018] Figure 2 A schematic flow chart of obtaining the first real-time drying feature in the multi-parameter joint control method for key nodes in the sea cucumber processing process provided by an embodiment of the present invention.

[0019] Figure 3 A schematic diagram of the structure of a multi-parameter joint control system for key nodes in the sea cucumber processing process provided by an embodiment of the present invention.

[0020] Description of the reference numerals: drying stage division module 10 , first drying control module 20 , characteristic deviation calculation module 30 , drying parameter optimization module 40 , second drying control module 50 . DETAILED DESCRIPTION

[0021] The embodiment of the present invention provides a multi-parameter joint control method and system for key nodes in the sea cucumber processing process, thereby solving the technical problem in the prior art that, due to the inability to monitor the sea cucumber status in real time and dynamically adjust the drying parameters during the sea cucumber drying process, deviations accumulate during the sea cucumber drying process, drying uniformity is poor, and the drying quality of the sea cucumber is affected. The embodiment of the present invention achieves the technical effect of realizing efficient closed-loop regulation of the drying process at each stage, thereby improving the overall drying uniformity and quality stability of the sea cucumber.

[0022] Example 1, as Figure 1 As shown, an embodiment of the present invention provides a multi-parameter joint control method for key nodes in a sea cucumber processing process, the method comprising: Step S100: Divide the sea cucumber drying process into several drying stages, and determine several standard drying characteristics.

[0023] Furthermore, the drying characteristics include size reduction rate, surface grayscale mean and texture density.

[0024] Specifically, the sea cucumber drying stage refers to several consecutive or distinguishable stages divided during the entire sea cucumber drying process based on factors such as the moisture content, tissue structure changes, and appearance characteristics of the sea cucumber material at different time nodes. The standard drying characteristics refer to the set of drying characteristic values determined for each drying stage based on historical data or ideal process results, serving as the target comparison benchmark. Among them, the drying characteristics are physical or visual characteristic parameters used to quantitatively evaluate the processing state of sea cucumbers at each drying stage, including three key indicators: the size reduction rate, the average surface gray value, and the texture density. The size reduction rate represents the degree of reduction in the volume or length of the sea cucumber during the drying process and is an important indicator reflecting the dehydration rate and texture changes; the average surface gray value represents the average brightness of the sea cucumber surface image after grayscale conversion, reflecting the drying color change and uniformity; the texture density represents the fineness of the sea cucumber surface texture, which can be obtained through the texture feature extraction method of the image and reflects the surface drying quality and product appearance consistency.

[0025] Based on factors such as the physical state of the sea cucumber (such as weight, appearance) and the operating characteristics of the drying equipment (such as temperature curve, wind speed curve), the entire sea cucumber drying process is divided into several drying stages. For each stage, several standard drying characteristics related to the process quality of that stage are determined, including the size reduction rate, the average surface gray value, and the texture density. These standard drying characteristics can be extracted based on historical high-quality drying sample data, and their means are statistically analyzed to form a benchmark data set. Subsequently, in the process monitoring of each stage, the standard drying characteristics corresponding to each stage are used as the target indicators for drying quality for comparison and correction. Exemplarily, several drying stages divided in the sea cucumber drying process are shown in Table 1: Table 1 - Examples of Sea Cucumber Drying Stages and Standard Drying Characteristics By dividing the sea cucumber drying process into stages and determining standard drying characteristics such as the size reduction rate, the average surface gray value, and the texture density, precise quality target management for different stages is achieved, providing a clear reference and deviation correction direction for the subsequent dynamic adjustment of process parameters, thereby improving the drying uniformity and the consistency and stability of the final product.

[0026] Step S200: Execute the drying control of the first drying stage according to the preset drying parameters, and monitor and obtain the first sea cucumber image set of the first drying stage.

[0027] Specifically, the preset drying parameters refer to the control variable parameters such as temperature, wind speed, and humidity that are set in advance based on historical experience and equipment capabilities during the first-stage drying. The first sea cucumber image set refers to a collection of multiple sea cucumber images after the end of the first drying stage, which are collected from multiple positions and angles using industrial cameras and are used for subsequent feature extraction and quality assessment. The drying equipment (such as a multi-layer belt dryer) is controlled according to the preset drying parameters to perform the drying operation in the first stage. After the end of the first stage, industrial cameras arranged at different positions of the drying equipment are used to image the sea cucumbers at multiple positions and angles, and the first sea cucumber image set of the first drying stage is collected. The collected images not only cover the products on different levels of the dryer but also take into account the multi-view features of individual sea cucumbers, so as to comprehensively reflect the state characteristics of the sea cucumbers at this stage and ensure the comprehensiveness and accuracy of subsequent feature extraction.

[0028] By performing multi-position image acquisition after the end of the first stage, a comprehensive and objective first sea cucumber image set is obtained, providing a reliable data basis for subsequent drying feature extraction and real-time deviation analysis, and ensuring the scientificity and accuracy of the adjustment and optimization in the next drying stage.

[0029] Step S300: Extract drying features based on the first sea cucumber image set to obtain the first real-time drying features, and calculate the first drying feature deviation by combining with the first standard drying features.

[0030] Specifically, the first real-time drying features refer to the shrinkage rate of the sea cucumber size, the average surface gray value, and the texture density calculated in real time through image processing algorithms based on the first sea cucumber image set. The first drying feature deviation refers to the deviation value between the first real-time drying features and the standard drying features in the first stage, which is used to quantify the gap between the processing quality in the first stage and the ideal state. First, based on the constructed sample sea cucumber image set and standard drying features, using the pre-trained convolutional neural network drying feature recognizer, the first sea cucumber image set is identified and segmented for individual sea cucumbers to extract the first real-time drying features: shrinkage rate of the sea cucumber size, the average surface gray value, and the texture density. After completing the real-time feature extraction, combine with the standard drying features (the first standard drying features) obtained in step S100, and calculate the deviation value between the real-time features and the standard features, that is, subtract the first standard drying features from the first real-time drying features to obtain the first drying feature deviation, providing data support for the target adjustment and parameter optimization in the next stage.

[0031] By analyzing the real-time images of the sea cucumber drying state, extracting real-time drying features, and comparing and analyzing them with the standard drying features, the deviation of the sea cucumber drying quality in the first stage can be intuitively quantified, providing real-time and accurate basis for the target correction and parameter adjustment in the second stage.

[0032] Step S400: Set the second-stage drying target according to the second-stage drying index and the deviation of the first drying feature, and optimize the drying parameters in the second drying stage with the approximation of the second-stage drying target as the expectation to determine the optimal second drying parameters.

[0033] Specifically, the second-stage drying index is the initial processing target of the second stage determined according to the difference between the standard drying feature of the second stage and the first standard drying feature. The second-stage drying target refers to the second-stage drying feature value determined according to the second-stage drying index and the first drying feature deviation, which is used as the target for optimizing the second-stage drying parameters.

[0034] First, obtain the second-stage drying index (such as a 30% reduction in the size reduction rate, a 20 reduction in surface gray scale, etc.) according to the difference between the standard drying feature of the second stage and the standard feature of the first stage in historical samples. Then, combine the deviation of the first drying feature and accumulate to obtain the second-stage drying target. Subsequently, based on the adjustable range of the drying parameters, use the drying feature prediction plug-in trained by the generative adversarial network to randomly generate multiple parameter combinations including temperature, wind speed, and humidity in the parameter space and predict the corresponding drying features. Finally, perform deviation analysis on the predicted drying features and the second-stage target features, and use the iterative clustering evolution optimization algorithm to minimize the deviation value as the goal to determine the optimal second drying parameters.

[0035] By combining the second-stage index with the real-time deviation, intelligently analyzing and dynamically determining the optimal second-stage drying parameters, precise process correction and dynamic process control are achieved, ensuring high-quality and stable operation in the second stage.

[0036] Step S500: Execute the sea cucumber drying control in the second drying stage according to the optimal second drying parameters, and perform iterative deviation analysis and drying parameter optimization until all the several drying stages are completed.

[0037] Specifically, perform the drying operation in the second stage according to the determined optimal second drying parameters. As the second stage progresses, continuously collect sea cucumber images, extract real-time drying features, and perform deviation analysis to determine the drying target for the next stage and optimize the parameters. This process is an iterative closed loop. After each stage ends, based on the real-time deviation results, dynamically adjust the drying target and parameters for the next stage until all drying stages are completed, ultimately achieving precise control of the entire process and high-quality product output.

[0038] By combining process control with image analysis to form real-time closed-loop regulation inside and outside the stage, it is possible to suppress the accumulation of deviations in each stage, achieve multi-stage collaborative optimization, and ultimately significantly improve the consistency, uniformity, and overall quality of sea cucumber drying.

[0039] Further, step S200 includes: Step S210: Perform drying control in the first drying stage according to preset drying parameters, where the drying parameters at least include drying temperature, drying wind speed, and relative humidity.

[0040] Step S220: At the end of the first drying stage, use an industrial camera to collect multi-position images of the sea cucumbers on the belt dryer to obtain a first sea cucumber image set.

[0041] Specifically, the drying temperature refers to the temperature control parameter inside the belt dryer, in °C; the drying wind speed refers to the flow rate of the air flow inside the dryer, in m / s; the relative humidity refers to the humidity level of the air in the drying environment, in %RH. Control the operation of the belt dryer according to the preset drying temperature, drying wind speed, and relative humidity parameters to start the operation of the first drying stage. At the end of the first drying stage, use an industrial camera arranged inside or outside the dryer to collect images of the sea cucumbers during the drying process from multiple positions (e.g., above, front side, diagonal) to obtain sea cucumber image data covering different perspectives and generate a first sea cucumber image set. The first sea cucumber image set contains a large amount of visual feature information and can be used as the input data source for subsequent feature extraction and real-time deviation calculation. For example, in the first drying stage, set the drying temperature to 55 °C, the wind speed to 1.5 m / s, and the humidity to 28%RH; after the first stage ends, 3 industrial cameras located at the outlet of the belt dryer collect images of the dried sea cucumbers from directly above, the left side, and the upper right diagonal respectively, and each camera collects 50 high-resolution images to obtain a first sea cucumber image set containing 150 images.

[0042] By performing the above steps, a complete and rich visual data set for the first drying stage is obtained, providing high-quality input data for subsequent feature extraction and dynamic control, and promoting the intelligent and refined management of the sea cucumber drying process.

[0043] Further, as Figure 2 shown, the drying feature extraction according to the first sea cucumber image set in step S300 to obtain the first real-time drying feature includes: Step S310: According to the historical drying records of the sea cucumbers, collect a sample sea cucumber image set, and perform feature extraction on the sample sea cucumber images respectively according to the drying features to obtain a sample drying feature set.

[0044] Step S320: Use the sample sea cucumber image set and the sample drying feature set to train a convolutional neural network until convergence to obtain a drying feature recognizer.

[0045] Step S330: Crop the single sea cucumber images in the first sea cucumber image set, and select the complete sea cucumber images to form a first standard single sea cucumber image set.

[0046] Step S340: Using the drying feature recognizer, perform feature extraction on the first standard single sea cucumber image set respectively, and obtain the first real-time drying feature after mean calculation.

[0047] Specifically, the sample sea cucumber image set refers to a multi-batch and multi-stage sea cucumber image set with representativeness collected during the historical sea cucumber drying process; the sample drying feature set is a feature data set extracted from the sample sea cucumber image set, including the size reduction rate, surface gray mean value, texture density, etc.; the drying feature recognizer is a convolutional neural network model trained based on the sample sea cucumber image set and the sample drying feature set, used to automatically extract the drying features of the input sea cucumber image; the first standard single sea cucumber image set is a complete and standardized single sea cucumber image set cropped and screened from the first sea cucumber image set; the first real-time drying feature is a comprehensive feature extracted and averaged from the first standard single sea cucumber image set, used to represent the overall drying state of the sea cucumber at the current stage.

[0048] First, select the sea cucumber drying processes under different batches and different temperature and humidity combinations from the historical drying records, and collect the sample sea cucumber image set. Each group of sample sea cucumber images includes multi-angle sea cucumber images taken at different positions and different time points in the belt dryer. Then, use image processing software to perform size normalization on each image (such as unifying to 512×512 pixels), and use threshold segmentation, contour detection or GrabCut algorithm to separate the single sea cucumber area. Then, for each single sea cucumber area, calculate the ratio of the length of the sea cucumber in the image (pixel measurement) to the initial length (recorded in the database) to obtain the size reduction rate; use the cv2.cvtColor() function to convert the image to a grayscale image, and use the cv2.mean() function to obtain the pixel average value. Analyze the sample sea cucumber image using the gray level co-occurrence matrix (GLCM) to generate a co-occurrence matrix, extract texture metrics such as contrast, entropy or ASM from it, and finally map them to texture density values. The drying features extracted from each sample sea cucumber image form a group of three-dimensional feature vectors, which are summarized into the sample drying feature set.

[0049] The above sample sea cucumber image set and its corresponding sample drying characteristics set are combined to form a supervised learning data set. A convolutional neural network is built using the TensorFlow or PyTorch framework, and the network structure can adopt the classic ResNet or VGGNet architecture as the backbone. The input image is 512×512×3 (color image). The network extracts multi-scale features layer by layer through convolutional and pooling layers, and finally the fully connected layer outputs the predicted values of the size reduction rate, surface gray mean, and texture density. The loss function uses the mean squared error (MSE) function, and the optimizer can be Adam or SGD. The learning rate can be initially set to 0.001, and the training batch size is set to 64. Monitor the loss function curve through the validation set. When the loss function value converges and the validation set error reaches the expected threshold (such as MSE < 0.01), it is considered that the model training converges, and finally the model weights are saved to form a drying characteristics recognizer.

[0050] For the first sea cucumber image set, through image cropping and screening, images that are occluded, blurred, or incomplete are removed, and complete and standard single sea cucumber images are extracted to form the first standard single sea cucumber image set. Using the trained drying characteristics recognizer, feature extraction is performed on each image in the first standard single sea cucumber image set, and then the mean values of the size reduction rate, surface gray mean, and texture density of the sea cucumbers in the first stage are calculated for all the feature extraction results, forming the first real-time drying characteristics in the first stage.

[0051] Furthermore, step S330 includes: Step S331: Crop single sea cucumber images from the first sea cucumber image set, and select complete sea cucumber images to form the first single sea cucumber image set.

[0052] Step S332: Extract high-frequency difference features from the first single sea cucumber image set to obtain the first standard single sea cucumber image set. Among them, if the number of similarities between a first single sea cucumber image and other sea cucumber images in the first single sea cucumber image set that are less than a preset similarity threshold is greater than a preset number threshold, it is set as the first standard single sea cucumber image.

[0053] Specifically, a complete sea cucumber image means that the sea cucumber in the image is in a complete form, not occluded by other objects, without damage or missing parts itself, and the image has high clarity and can accurately reflect the appearance characteristics of the sea cucumber. High-frequency difference feature extraction refers to extracting those features with relatively high change frequencies from the image that can reflect significant differences between individuals, such as texture details and edge features. The preset similarity threshold is a preset similarity threshold used to determine whether two images have similar features. The preset number threshold is a preset number threshold used to screen typical feature images with significant differences.

[0054] Using the contour detection algorithm in the OpenCV library, detect the boundaries of sea cucumbers in the image to generate circumscribed rectangles or polygon regions. Further, use cv2.boundingRect() or cv2.minAreaRect() to obtain the bounding box coordinate information of a single sea cucumber, and crop the sea cucumber region according to the bounding box to remove the background part. After cropping, uniformly adjust the size of each single sea cucumber image (for example, standardize it to 512×512 pixels), and store it in the first set of single sea cucumber images. Through the above cropping and standardization, it is ensured that each image only contains a complete single sea cucumber, and the surface morphology and texture feature information of the sea cucumber are retained, facilitating subsequent feature extraction processing.

[0055] For each image in the first set of single sea cucumber images, use two-dimensional fast Fourier transform for high-frequency feature extraction. Specifically, call numpy.fft.fft2() or cv2.dft() to perform Fourier transform on each single sea cucumber image to obtain the frequency domain representation; further, use the numpy.fft.fftshift() function to centralize the spectrum, concentrating the high-frequency components on the edge of the spectrum. Then, extract the high-frequency component feature vector. Preferably, the modulus value and phase distribution of the part exceeding the set spectrum radius threshold can be statistically analyzed to form a high-frequency feature vector. Next, use cosine similarity or Euclidean distance to calculate the similarity between each single sea cucumber image and other images in the first set of single sea cucumber images. Preferably, set a similarity threshold (such as 0.8). When the number of times the similarity between a certain single sea cucumber image and other images is less than this threshold is greater than the preset number threshold (such as 3), determine that this image is a typical feature image with a large difference from the whole. Through the above steps, several single sea cucumber images with significant high-frequency feature differences and representativeness are selected to form the first set of standard single sea cucumber images. By analyzing and screening the high-frequency features, the surface features of sea cucumbers in the typical drying stage can be effectively extracted, reducing the redundant calculations of full data processing and improving the accuracy and efficiency of feature extraction.

[0056] Further, the first drying feature deviation calculated in step S300 in combination with the first standard drying feature includes: Step S350: Obtain the first standard drying feature in the first drying stage.

[0057] Step S360: Subtract the first real-time drying feature from the first standard drying feature to obtain the first drying feature deviation.

[0058] Specifically, the first standard drying feature is the reference value of the drying feature formed according to the typical surface features of sea cucumbers under the standard process conditions of the first drying stage. Preferably, the first standard drying feature can be obtained in the following way: through previous multi-batch drying experiments, record the typical process parameters at each stage and their corresponding sea cucumber image features, and combine the quality inspection results of sea cucumbers (such as moisture content, appearance, elasticity, etc.) to screen out the drying images and their extracted features in the optimal state under the first drying stage as the first standard drying feature. In the specific implementation process, based on three-dimensional feature parameters such as the surface texture density, size reduction rate, and surface gray mean value of sea cucumbers, the mean or median of the results of multiple experiments can be taken respectively to form a multi-dimensional vector of the first standard drying feature. Through the above acquisition method, it is ensured that the first standard drying feature can comprehensively reflect the ideal drying state of sea cucumbers in the first drying stage and serve as the reference for subsequent feature deviation analysis.

[0059] Perform a difference operation on the first real-time drying feature vector extracted by the drying feature recognizer and the obtained first standard drying feature vector. Preferably, the element-by-element difference method is adopted. The specific formula is as follows: the first drying feature deviation = the first standard drying feature - the first real-time drying feature. Among them, the three dimensions of the three-dimensional vector correspond to the texture density, size reduction rate, and surface gray mean value respectively. The three-dimensional difference result can directly represent the deviation degree of each feature dimension. The numerical unit of the difference result is the same as that of the original feature. By calculating the first drying feature deviation, the difference between the current drying state and the ideal state can be quantified, providing a basis for subsequent deviation feedback and parameter optimization, and realizing the dynamic adjustment and fine control of the drying process.

[0060] Further, step S400 includes: Step S410: Obtain the second standard drying feature of the second drying stage, subtract the first standard drying feature of the first drying stage to obtain the drying index of the second stage.

[0061] Step S420: Sum the drying index of the second stage and the first drying feature deviation to obtain the drying target of the second stage.

[0062] Step S430: Based on the drying parameter adjustment space, perform optimization of the drying parameters in the second drying stage with the approximation of the drying target of the second stage as the expectation to determine the optimal second drying parameters.

[0063] Specifically, the second standard drying feature is also the optimal drying feature vector (a three-dimensional vector including texture density, size reduction rate, and average surface gray value) in the second drying stage based on the experimental results of multiple batches and quality inspection data. The acquisition method of the second standard drying feature is the same as that of the first standard drying feature. Subtract the first standard drying feature in the first drying stage from the second standard drying feature in the second drying stage to obtain the drying index in the second stage, so as to intuitively reflect the ideal change direction and amplitude of the transition from the first stage to the second stage.

[0064] In order to make the feature evolution in the second drying stage as close as possible to the ideal transition effect, add the drying index in the second stage and the deviation of the first drying feature element by element to form the drying target vector in the second stage. The formula is: Drying target in the second stage = Drying index in the second stage + Deviation of the first drying feature. This drying target in the second stage comprehensively reflects the deviation between the current drying state and the ideal stage, and provides a dynamic target value for the optimization of the next drying parameters.

[0065] The adjustable space of drying parameters refers to the range in which the drying parameters (drying temperature, drying wind speed, relative humidity) can vary within the allowable range of the equipment, providing a feasible range for the optimization of drying parameters. According to the performance of the drying equipment and the drying process specifications, determine the adjustable ranges of the drying temperature, drying wind speed, and relative humidity, and construct the adjustable space of drying parameters. For example, the temperature range is 40°C to 60°C, the wind speed range is 1 m / s to 3 m / s, and the relative humidity range is 50%RH to 70%RH. On this basis, use a target-driven optimization algorithm (such as gradient descent, genetic algorithm, etc.) to iteratively update the parameters, simulate and predict the feature evolution trajectory until the Euclidean distance or weighted deviation value between the predicted drying feature vector and the drying target vector in the second stage is minimized, or a preset deviation threshold is met (such as less than 1% deviation); finally, output the optimal second drying parameters as the actual execution parameters in the second drying stage to achieve intelligent and adaptive dynamic adjustment of drying parameters.

[0066] Furthermore, step S430 includes: Step S431: According to the historical sea cucumber drying logs of similar belt dryers, collect the sample drying parameter set and the sample drying feature set, train a generative adversarial network, and construct a drying feature prediction plug-in.

[0067] Step S432: Randomly generate a number of drying parameters based on the adjustable space of drying parameters, and use the drying feature prediction plug-in to analyze and obtain a number of predicted drying features.

[0068] Step S433: Based on the drying target in the second stage, conduct an overall deviation analysis on the number of predicted drying features to obtain a number of feature deviation values.

[0069] Step S434: Based on the drying parameter adjustment space, optimize the drying parameters for the second drying stage according to the several feature deviation values, and output the optimal second drying parameters.

[0070] Specifically, according to the historical sea cucumber drying logs of similar belt dryers, collect sample drying parameter sets (including temperature, wind speed, humidity, etc.) and corresponding sample drying feature sets (size reduction rate, average surface gray value, texture density, etc.) under multiple batches and different drying parameters. Use a generative adversarial network for training, and utilize the mutual game optimization of the generator and discriminator to construct a drying feature prediction plugin with strong generalization ability. This drying feature prediction plugin can quickly generate the corresponding drying feature vector prediction results under given drying parameters, and realize the rapid estimation of the feature evolution during the drying process under different parameter configurations.

[0071] Within the drying parameter adjustment space, randomly generate several drying parameter combinations. For each generated set of parameters, call the drying feature prediction plugin to obtain the corresponding predicted drying features. The prediction result is also a three-dimensional vector, which can be directly compared and analyzed with the drying target in the second stage.

[0072] Taking the drying target in the second stage as the benchmark, calculate the Euclidean distance or weighted absolute deviation between each predicted drying feature and the target vector to obtain several feature deviation values. The smaller this deviation value is, the closer the predicted feature is to the drying target in the second stage. According to the above several feature deviation values, optimize the drying parameters within the drying parameter adjustment space, select the parameter combination with the smallest deviation value, and output it as the optimal second drying parameters.

[0073] Furthermore, step S434 includes: Step S434-1: Taking the drying parameters as the initial solution, sort them in ascending order according to the feature deviation values, and map and generate several initial solution sequences according to the several feature deviation values.

[0074] Step S434-2: Divide the several initial solution sequences into excellent solutions and inferior solutions according to a predetermined ratio, where the number of inferior solutions is N times that of excellent solutions, and N is greater than or equal to 10.

[0075] Step S434-3: Centering on the excellent solutions, cluster the inferior solutions to obtain multiple solution sets, and within each solution set, taking the excellent solutions as the direction, adjust the inferior solutions within the solution set according to the preset optimization step size to obtain multiple updated solution sets. Among them, if the adjusted inferior solutions exceed the drying parameter adjustment space, randomly select a drying parameter within the drying parameter adjustment space for replacement. If the feature deviation value of the adjusted inferior solutions is smaller than that of the excellent solutions within the same solution set, use the inferior solutions to replace the excellent solutions.

[0076] Step S434-4: Perform iterative optimization until the preset convergence times are reached, and set the drying parameters with the minimum feature deviation value in all solution sets as the optimal second drying parameters.

[0077] Specifically, based on the several drying parameters obtained in step S433 and their corresponding feature deviation values, sort them in ascending order of the feature deviation values. According to the sorting result, map and generate several initial solution sequences. Each initial solution sequence represents a set of initial drying parameter combinations and serves as the starting point for subsequent iterative optimization. Divide the several initial solution sequences into an excellent solution set and a poor solution set according to a predetermined ratio. Among them, the excellent solution set is a part of the initial solutions with smaller feature deviation values. The poor solution set is the remaining initial solutions after removing the excellent solution set from the several initial solution sequences, and the number is N times that of the excellent solution set, N≥10 (for example, 10 excellent solutions and 100 poor solutions).

[0078] Centering on each excellent solution, cluster the poor solutions respectively to form multiple solution sets. Within each solution set, adjust according to the following steps: Taking the excellent solution as the direction, fine-tune the poor solutions in the solution set according to the preset optimization step size (for example, a normalized ratio of 0.01 to 0.1) to generate an updated solution set. If the adjusted poor solution exceeds the drying parameter adjustment space (that is, the temperature, wind speed, and humidity range allowed physically or technically), then randomly select a new set of feasible drying parameters within this drying parameter adjustment space for replacement to ensure the physical feasibility of the solution. Compare the feature deviation value of the updated poor solution with the feature deviation value of the excellent solution in the same solution set. If the poor solution performs better than the original excellent solution (that is, the feature deviation value is smaller), then replace the current excellent solution with this poor solution. By continuously adjusting and updating the excellent solution, ensure that each iteration advances towards the solution space with a smaller feature deviation value.

[0079] Repeat the above adjustment-replacement process to perform multiple rounds of iterative optimization until the preset convergence times are reached. Finally, within all solution sets, extract the drying parameters corresponding to the minimum feature deviation value as the optimal second drying parameters in the second drying stage.

[0080] In summary, the multi-parameter joint control method for key nodes in the sea cucumber processing process provided by the embodiments of the present invention has the following beneficial effects: By dividing the sea cucumber drying process into several drying stages and determining several standard drying characteristics, the present invention provides a phased division of the drying process and the reference values of ideal drying characteristic benchmarks, providing a reference for subsequent deviation detection and parameter correction. Execute the drying control of the first drying stage according to the preset drying parameters, monitor and obtain the first sea cucumber image set of the first drying stage, realize the perception of the sea cucumber state, extract the drying characteristics according to the first sea cucumber image set, obtain the first real-time drying characteristics, calculate the first drying characteristic deviation by combining the first standard drying characteristics, quantify the gap between the actual drying result and the standard characteristics, and clarify the processing deviation. Set the drying target of the second stage according to the drying index of the second stage and the first drying characteristic deviation, and optimize the drying parameters of the second drying stage with the approximation of the second stage drying target as the expectation, determine the optimal second drying parameters, feedback the actual deviation of the first stage to the second stage, and realize dynamic deviation correction by adjusting the target and parameters of the second stage, ensuring that the subsequent processing stage can effectively correct the deviation. Execute the sea cucumber drying control of the second drying stage according to the optimal second drying parameters, and perform iterative deviation analysis and drying parameter optimization until all the several drying stages are completed, forming a multi-stage closed-loop adjustment process: each stage optimizes and corrects the parameters based on the deviation of the previous stage, continuously iterates, and avoids the accumulation of deviations.

[0081] Generally speaking, in the embodiment of the present invention, by dividing the sea cucumber drying process into several stages and obtaining the sea cucumber drying characteristics by combining real-time visual images in each stage, the phased deviation is realized. At the same time, based on the adaptive iterative optimization of multi-solution clustering, the local optimal trap is effectively overcome, the optimal parameter dynamic adjustment and global quality balance of each stage in the drying process are realized, a closed-loop control system of multi-parameter joint control and continuous feedback optimization is formed, the uniformity and overall processing quality of the sea cucumber drying process are significantly improved, and the efficient, accurate and intelligent sea cucumber drying control is realized.

[0082] Embodiment 2, as Figure 3 shown, based on the same inventive concept as the foregoing Embodiment 1, the embodiment of the present invention provides a multi-parameter joint control system for key nodes in the sea cucumber processing process, and the system includes: A drying stage division module 10, configured to divide the sea cucumber drying process into several drying stages and determine several standard drying characteristics.

[0083] A first drying control module 20, configured to execute the drying control of the first drying stage according to the preset drying parameters, and monitor and obtain the first sea cucumber image set of the first drying stage.

[0084] A feature deviation calculation module 30, configured to extract the drying characteristics according to the first sea cucumber image set, obtain the first real-time drying characteristics, and calculate the first drying characteristic deviation by combining the first standard drying characteristics.

[0085] The drying parameter optimization module 40 is used to set the second-stage drying target according to the second-stage drying index and the first drying feature deviation, and optimize the drying parameters in the second drying stage with the approximation of the second-stage drying target as the expectation to determine the optimal second drying parameters.

[0086] The second drying control module 50 is used to execute the sea cucumber drying control in the second drying stage according to the optimal second drying parameters, and perform iterative deviation analysis and drying parameter optimization until all the several drying stages are completed.

[0087] Further, the drying features include the size reduction rate, the average surface gray value, and the texture density.

[0088] Further, the first drying control module 20 in the embodiment of the present invention is further used to execute the following steps: Execute the drying control in the first drying stage according to the preset drying parameters, where the drying parameters at least include the drying temperature, the drying wind speed, and the relative humidity; at the end of the first drying stage, perform multi-position image acquisition on the sea cucumbers on the belt dryer through an industrial camera to obtain the first sea cucumber image set.

[0089] Further, the feature deviation calculation module 30 in the embodiment of the present invention is further used to execute the following steps: According to the historical drying records of the sea cucumbers, collect the sample sea cucumber image set, and respectively extract the features of the sample sea cucumber images according to the drying features to obtain the sample drying feature set; use the sample sea cucumber image set and the sample drying feature set to train the convolutional neural network until convergence to obtain the drying feature recognizer; perform single sea cucumber image cropping on the first sea cucumber image set, and select the complete sea cucumber images to form the first standard single sea cucumber image set; use the drying feature recognizer to respectively extract the features of the first standard single sea cucumber image set, and obtain the first real-time drying feature after average value calculation.

[0090] Further, the feature deviation calculation module 30 in the embodiment of the present invention is further used to execute the following steps: Perform single sea cucumber image cropping on the first sea cucumber image set, and select the complete sea cucumber images to form the first single sea cucumber image set; perform high-frequency difference feature extraction on the first single sea cucumber image set to obtain the first standard single sea cucumber image set, where if the number of similarities between the first single sea cucumber image and other sea cucumber images in the first single sea cucumber image set is less than the preset similarity threshold and greater than the preset number threshold, it is set as the first standard single sea cucumber image.

[0091] Further, the feature deviation calculation module 30 in the embodiment of the present invention is further used to execute the following steps: Obtain the first standard drying feature of the first drying stage; subtract the first real-time drying feature from the first standard drying feature to obtain the first drying feature deviation.

[0092] Further, the drying parameter optimization module 40 in the embodiment of the present invention is further configured to perform the following steps: Obtain the second standard drying feature of the second drying stage, subtract the first standard drying feature of the first drying stage to obtain the drying index of the second stage; sum the drying index of the second stage and the first drying feature deviation to obtain the drying target of the second stage; based on the drying parameter adjustment space, optimize the drying parameters of the second drying stage with the approximation of the drying target of the second stage as the expectation, and determine the optimal second drying parameters.

[0093] Further, the drying parameter optimization module 40 in the embodiment of the present invention is further configured to perform the following steps: According to the historical sea cucumber drying logs of similar belt dryers, collect the sample drying parameter set and the sample drying feature set, train a generative adversarial network, and construct a drying feature prediction plug-in; randomly generate a number of drying parameters based on the drying parameter adjustment space, and use the drying feature prediction plug-in to analyze and obtain a number of predicted drying features; based on the drying target of the second stage, perform an overall deviation analysis on the number of predicted drying features to obtain a number of feature deviation values; based on the drying parameter adjustment space, optimize the drying parameters of the second drying stage according to the number of feature deviation values, and output the optimal second drying parameters.

[0094] Further, the drying parameter optimization module 40 in the embodiment of the present invention is further configured to perform the following steps: Take the drying parameters as the initial solution, sort them in ascending order according to the feature deviation values, and map a number of initial solution sequences according to the number of feature deviation values; divide the number of initial solution sequences into optimal solutions and inferior solutions according to a predetermined ratio, where the number of inferior solutions is N times that of the optimal solutions, and N is greater than or equal to 10; take the optimal solution as the center, cluster the inferior solutions to obtain multiple solution sets, and within each solution set, take the optimal solution as the direction and adjust the inferior solutions within the solution set according to a preset optimization step size to obtain multiple updated solution sets. If the adjusted inferior solution exceeds the drying parameter adjustment space, randomly select a drying parameter within the drying parameter adjustment space for replacement. If the feature deviation value of the adjusted inferior solution is less than the feature deviation value of the optimal solution within the same solution set, use the inferior solution to replace the optimal solution; perform iterative optimization until the preset convergence number of times is reached, and output the drying parameters with the smallest feature deviation value in all solution sets as the optimal second drying parameters.

[0095] Through the foregoing detailed description of the multi-parameter joint control method for key nodes in the sea cucumber processing process, those skilled in the art can clearly know the multi-parameter joint control system for key nodes in the sea cucumber processing process in this embodiment. For the system disclosed in Embodiment 2, since it corresponds to the method disclosed in Embodiment 1, it has corresponding functional modules and beneficial effects. For the relevant parts, reference can be made to the description in the method part.

[0096] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A multi-parameter joint control method for key nodes in the sea cucumber processing process, characterized in that, The method includes: Dividing the sea cucumber drying process into several drying stages and determining several standard drying characteristics; Performing drying control for the first drying stage according to preset drying parameters, and monitoring and obtaining the first sea cucumber image set of the first drying stage; Performing drying characteristic extraction based on the first sea cucumber image set to obtain the first real-time drying characteristics, and calculating the first drying characteristic deviation by combining the first standard drying characteristics; Obtaining the second standard drying characteristics of the second drying stage, subtracting the first standard drying characteristics of the first drying stage to obtain the drying index of the second stage, setting the drying target of the second stage according to the drying index of the second stage and the first drying characteristic deviation, and performing optimization of the drying parameters for the second drying stage with the approximation of the drying target of the second stage as the expectation to determine the optimal second drying parameters; Performing sea cucumber drying control for the second drying stage according to the optimal second drying parameters, and performing iterative deviation analysis and drying parameter optimization until all the several drying stages are completed.

2. The multi-parameter joint control method for key nodes in the sea cucumber processing process according to claim 1, characterized in that, The drying characteristics include the size reduction rate, the average surface gray value, and the texture density.

3. The multi-parameter joint control method for key nodes in the sea cucumber processing process according to claim 1, characterized in that, Performing drying control for the first drying stage according to preset drying parameters, and monitoring and obtaining the first sea cucumber image set of the first drying stage, including: Performing drying control for the first drying stage according to preset drying parameters, where the drying parameters at least include the drying temperature, the drying wind speed, and the relative humidity; At the end of the first drying stage, performing multi-position image acquisition on the sea cucumbers on the belt dryer through an industrial camera to obtain the first sea cucumber image set.

4. The multi-parameter joint control method for key nodes in the sea cucumber processing process according to claim 2, characterized in that, Performing drying characteristic extraction based on the first sea cucumber image set to obtain the first real-time drying characteristics, including: According to the historical drying records of the sea cucumbers, collecting a sample sea cucumber image set, and respectively performing characteristic extraction on the sample sea cucumber images according to the drying characteristics to obtain a sample drying characteristic set; Using the sample sea cucumber image set and the sample drying characteristic set to train the convolutional neural network until convergence to obtain a drying characteristic recognizer; Performing cropping of single sea cucumber images on the first sea cucumber image set, and selecting complete sea cucumber images to form the first standard single sea cucumber image set; Using the drying characteristic recognizer to respectively perform characteristic extraction on the first standard single sea cucumber image set, and obtaining the first real-time drying characteristics after mean calculation.

5. The multi-parameter joint control method for key nodes in the sea cucumber processing process according to claim 4, wherein Performing cropping of single sea cucumber images on the first sea cucumber image set, and selecting complete sea cucumber images to form the first standard single sea cucumber image set, including: Performing cropping of single sea cucumber images on the first sea cucumber image set, and selecting complete sea cucumber images to form the first single sea cucumber image set; Performing high-frequency difference feature extraction on the first single sea cucumber image set to obtain the first standard single sea cucumber image set, where if the number of similarities between the first single sea cucumber image and other sea cucumber images in the first single sea cucumber image set is less than the preset similarity threshold and is greater than the preset number threshold, it is set as the first standard single sea cucumber image.

6. The multi-parameter joint control method for key nodes in the sea cucumber processing process according to claim 1, characterized in that, Calculating the first drying characteristic deviation by combining the first standard drying characteristics, including: Obtaining the first standard drying characteristics of the first drying stage; Subtracting the first real-time drying characteristics from the first standard drying characteristics to obtain the first drying characteristic deviation.

7. The multi-parameter joint control method for key nodes in the sea cucumber processing process according to claim 1, characterized in that, Set the second-stage drying target according to the second-stage drying index and the deviation of the first drying characteristics, and optimize the drying parameters in the second drying stage with the expectation of approaching the second-stage drying target to determine the optimal second drying parameters, including: Obtain the second-stage drying target by summing the second-stage drying index and the deviation of the first drying characteristics; Based on the drying parameter adjustment space, optimize the drying parameters in the second drying stage with the expectation of approaching the second-stage drying target to determine the optimal second drying parameters.

8. The multi-parameter joint control method for key nodes in the sea cucumber processing process according to claim 7, characterized in that, Based on the drying parameter adjustment space, optimize the drying parameters in the second drying stage with the expectation of approaching the second-stage drying target to determine the optimal second drying parameters, including: According to the historical sea cucumber drying logs of similar belt dryers, collect the sample drying parameter set and the sample drying characteristics set, train a generative adversarial network, and construct a drying characteristics prediction plugin; Randomly generate a number of drying parameters based on the drying parameter adjustment space, and analyze to obtain a number of predicted drying characteristics using the drying characteristics prediction plugin; Based on the second-stage drying target, conduct an overall deviation analysis of the number of predicted drying characteristics to obtain a number of characteristic deviation values; Based on the drying parameter adjustment space, optimize the drying parameters in the second drying stage according to the number of characteristic deviation values, and output the optimal second drying parameters.

9. The multi-parameter joint control method for key nodes in the sea cucumber processing process according to claim 8, characterized in that, Based on the drying parameter adjustment space, optimize the drying parameters in the second drying stage according to the number of characteristic deviation values, and output the optimal second drying parameters, including: Taking the drying parameters as the initial solution, sort them in ascending order according to the characteristic deviation values, and map to generate a number of initial solution sequences according to the number of characteristic deviation values; Divide the number of initial solution sequences into optimal solutions and inferior solutions according to a predetermined ratio, where the number of inferior solutions is N times that of the optimal solutions, and N is greater than or equal to 10; Centering on the optimal solution, cluster the inferior solutions to obtain multiple solution sets, and within each solution set, adjust the inferior solutions in the solution set in the direction of the optimal solution according to a preset optimization step size to obtain multiple updated solution sets. If the adjusted inferior solution exceeds the drying parameter adjustment space, randomly select a drying parameter within the drying parameter adjustment space for replacement. If the characteristic deviation value of the adjusted inferior solution is smaller than the characteristic deviation value of the optimal solution in the same solution set, use the inferior solution to replace the optimal solution; Perform iterative optimization until the preset convergence number is reached, and output the drying parameter with the smallest characteristic deviation value in all solution sets as the optimal second drying parameter.

10. A multi-parameter joint control system for key nodes in the sea cucumber processing process, characterized in that, The system is used to execute the multi-parameter joint control method for key nodes in the sea cucumber processing process described in any one of claims 1-9, including: A drying stage division module for dividing the sea cucumber drying process into several drying stages and determining several standard drying characteristics; A first drying control module for performing drying control in the first drying stage according to preset drying parameters and monitoring and obtaining the first sea cucumber image set in the first drying stage; A characteristic deviation calculation module for extracting drying characteristics according to the first sea cucumber image set to obtain the first real-time drying characteristics, and calculating the first drying characteristic deviation in combination with the first standard drying characteristics; The drying parameter optimization module is used to obtain the second standard drying characteristics in the second drying stage, subtract the first standard drying characteristics in the first drying stage to obtain the drying index in the second stage, set the drying target in the second stage according to the drying index in the second stage and the deviation of the first drying characteristics, and optimize the drying parameters in the second drying stage with the approximation of the drying target in the second stage as the expectation to determine the optimal second drying parameters; The second drying control module is used to execute the sea cucumber drying control in the second drying stage according to the optimal second drying parameters, and perform iterative deviation analysis and drying parameter optimization until all the several drying stages are completed.

Images