Kelp drying moisture dynamic balance regulation and control method and system based on multi-source perception

Abstract

The invention discloses a kelp drying moisture dynamic balance regulation and control method and system based on multi-source sensing. The method comprises the steps that data are collected in real time through a multi-source sensor in drying equipment; identifying a drying stage in real time based on the obtained temperature and humidity time sequence data, and dynamically adjusting process parameters according to data difference; performing space-time calibration compensation on the kelp surface temperature distribution data and the kelp surface image data; constructing a moisture distribution prediction model, and obtaining kelp moisture distribution gradient data; a local area with the moisture content higher than the global average value is recognized as a high-moisture area, and targeted intensified drying is conducted on the high-moisture area by controlling a subarea heating unit; and water distribution gradient data are obtained, and if the whole-region water gradient difference is smaller than a threshold value and the global average water content is smaller than the threshold value, drying is completed. The kelp drying device has the advantages that the drying process is monitored in real time and dynamically adjusted through the sensor, kelp moisture distribution is accurately controlled, the drying efficiency and quality are improved, and uniform drying of kelp is ensured.

Description

Technical Field

[0001] The present invention relates to a moisture control technology, and in particular to a method and system for controlling the dynamic balance of moisture in kelp drying based on multi-source sensing. Background Art

[0002] Kelp is a nutritious seaweed that contains iodine, calcium, iron, dietary fiber and multiple vitamins. Due to its good health function and edible value, it is widely used in food processing, health products and medicine. However, in the storage and processing of kelp, the moisture content plays a vital role. Kelp has a high moisture content after harvesting. If it is not handled in time, it is very easy to rot and deteriorate, affecting its nutritional content and commercial value.

[0003] The current methods and systems for dynamic balance control of kelp drying moisture on the market usually rely on a single temperature and humidity sensor and fixed drying process parameters, lacking real-time monitoring and adjustment of kelp surface temperature distribution and morphological changes. These traditional methods are difficult to deal with the uneven moisture distribution of kelp caused by deformation, curling and other factors during the drying process, and are prone to local overdrying or overwetting, affecting product quality and production efficiency. At the same time, due to the lack of spatiotemporal calibration and compensation technology, these methods have a relatively slow response to temperature and humidity changes, and may not be able to adjust process parameters in time at different stages of drying, resulting in unstable drying effects and even energy waste. Compared with the dynamic control method based on multi-source perception, the traditional method does not make full use of historical data and intelligent algorithms to predict moisture distribution and accurately identify high-moisture areas, resulting in low accuracy of the drying process. In addition, these traditional methods often ignore the refined control of targeted and enhanced drying, and cannot effectively optimize the drying process in each area, limiting the improvement of drying efficiency. Summary of the invention

[0004] In order to improve the existing methods and systems, a method and system for dynamic balance control of kelp drying moisture based on multi-source sensing is provided. The method uses multi-source sensors to monitor and dynamically adjust the drying process in real time, accurately controls the moisture distribution of kelp, optimizes the process at each stage, improves the drying efficiency and quality, ensures uniform drying of the kelp and reduces energy waste.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] The method for regulating the dynamic balance of moisture in kelp drying based on multi-source perception includes:

[0007] The multi-source sensors inside the drying equipment collect data in real time, including temperature and humidity time series data, kelp surface temperature distribution data, and kelp surface image data;

[0008] Based on the acquired time-series temperature and humidity data, the drying stage is identified in real time, and the process parameters are dynamically adjusted according to the data differences between the real-time data of each stage and the standard data. The drying stage includes a heating-up stage, a constant-rate drying and moisture-removing stage, and a falling-rate shaping stage;

[0009] Based on each drying stage, spatio-temporal calibration and compensation are performed on the kelp surface temperature distribution data and the kelp surface image data;

[0010] Based on the historical kelp drying data, a moisture distribution prediction model is constructed, and the calibrated and compensated data is input into the moisture distribution prediction model to generate the obtained kelp moisture distribution gradient data;

[0011] Based on the kelp moisture distribution gradient data, the local area with a moisture content higher than the global average value is identified as the high-moisture area, and the high-moisture area is subjected to targeted enhanced drying by controlling the partition heating unit;

[0012] Based on the kelp after targeted enhanced drying, its moisture distribution gradient data is obtained. If the moisture gradient difference in the whole area is less than the threshold and the global average moisture content is less than the threshold, the drying is completed.

[0013] Preferably, the real-time identification of the drying stage based on the acquired time-series temperature and humidity data and the dynamic adjustment of the process parameters according to the data differences between the real-time data of each stage and the standard data, and the drying stage including the heating-up stage, the constant-rate drying and moisture-removing stage, and the falling-rate shaping stage specifically include:

[0014] Based on the acquired real-time time-series temperature and humidity data, feature extraction is performed to obtain key change index data, including the temperature change rate, the humidity change rate, and the temperature-humidity correlation;

[0015] Based on the key change index data, the drying stage is identified. In the heating-up stage, the temperature continuously rises. In the constant-rate drying and moisture-removing stage, the temperature change rate is 0 and the humidity change rate is negative. In the falling-rate shaping stage, the absolute value of the humidity change rate decreases;

[0016] Based on the identified drying stage, the standard temperature and humidity target curve for this stage is obtained according to historical data, and the actual temperature and humidity curve is obtained based on the real-time collected time-series temperature and humidity data;

[0017] Based on the standard temperature and humidity target curve and the actual temperature and humidity curve, the deviation values are calculated and obtained, including the temperature deviation, the humidity deviation, and the change rate deviation;

[0018] Based on the obtained deviation values, a targeted adjustment strategy is carried out, and the drying stage data is intervened by adjusting the heating power and the opening degree of the moisture exhaust valve.

[0019] Preferably, the spatio-temporal calibration and compensation of the kelp surface temperature distribution data and the kelp surface image data based on each drying stage specifically include:

[0020] Based on the image with a slow change during the heating-up stage, establish the initial position and approximate contour template of the kelp individual, and record the initial kelp surface temperature distribution data;

[0021] Based on the constant-speed drying and moisture-exhausting stage, calculate the pixel-level displacement field on the kelp surface between adjacent visible-light images through the dense optical flow method, and calculate the local deformation field that has occurred on the kelp surface from the end moment of the heating-up stage to the current frame according to the optical flow field;

[0022] Superimpose the local deformation field onto the kelp surface image data calibrated by the projection transformation space through the basic space mapping model to calibrate the actual shape and position of the deformed kelp;

[0023] Based on the minor deformation in the local curling area of the kelp during the falling-rate shaping stage, perform key compensation to accurately correspond the temperature and image features at the curling edge.

[0024] Preferably, the method of constructing a moisture distribution prediction model based on historical kelp drying data and inputting the calibrated and compensated data into the moisture distribution prediction model to generate and obtain the kelp moisture distribution gradient data specifically includes:

[0025] Extract the characteristic data of humidity time-series data, kelp surface temperature distribution data, and kelp surface image data based on historical kelp drying data, and train through the LSTM neural network model to construct a moisture distribution prediction model;

[0026] Based on the trained moisture distribution prediction model, input the spatio-temporal calibrated and compensated data into the model to predict and obtain the moisture distribution data on the kelp surface;

[0027] Based on the predicted moisture distribution data on the kelp surface, calculate the gradient of the moisture content through spatial difference to obtain the kelp moisture distribution gradient data.

[0028] Preferably, the method of identifying the local area with a moisture content higher than the global average as a high-moisture area based on the kelp moisture distribution gradient data and performing targeted enhanced drying on the high-moisture area by controlling the partition heating unit specifically includes:

[0029] Based on the obtained kelp moisture distribution gradient data, calculate and obtain the global average moisture content;

[0030] By comparing the difference between the moisture content at each position of the kelp and the global average moisture content, mark the part exceeding the threshold as a high-moisture area;

[0031] By adjusting the partition heating unit in the high-moisture area, increase the heating intensity to perform targeted enhanced drying on the high-moisture area.

[0032] Preferably, based on the kelp after targeted enhanced drying, obtaining its moisture distribution gradient data, if the moisture gradient difference in the entire region is less than the threshold and the global average moisture content is less than the threshold, the drying is completed, specifically including:

[0033] Based on the kelp after targeted enhanced drying, use a sensor to collect data again and input it into the moisture distribution prediction model to obtain the moisture distribution gradient data of the kelp;

[0034] Calculate the global average moisture content based on the moisture distribution gradient data of the kelp. If the moisture gradient difference in the entire region is less than the threshold and the global average moisture content is less than the threshold, the drying is completed.

[0035] Furthermore, a dynamic balance control system for kelp drying based on multi-source perception is proposed, including:

[0036] Data acquisition module: The data acquisition module is used to collect the temperature and humidity time-series data, kelp surface temperature distribution data, and kelp surface image data during the drying process in real time, providing a basis for subsequent data analysis;

[0037] Drying stage identification module: The drying stage identification module identifies the current drying stage through the real-time acquired temperature and humidity time-series data, and dynamically adjusts the process parameters according to the differences in stages;

[0038] Spatio-temporal calibration and compensation module: The spatio-temporal calibration and compensation module performs spatio-temporal calibration and compensation on the kelp surface data based on the temperature distribution and image data of each drying stage to ensure accuracy;

[0039] Moisture distribution prediction module: The moisture distribution prediction module uses historical drying data to construct a moisture distribution prediction model, and generates the moisture distribution gradient data of the kelp by inputting the compensated data;

[0040] High-moisture area identification module: The high-moisture area identification module identifies local high-moisture areas based on the moisture distribution gradient data, and performs targeted enhanced drying by adjusting the partition heating unit;

[0041] Drying determination module: The drying determination module determines the moisture gradient difference in the entire region and the global average moisture content according to the moisture distribution data after enhanced drying. If the standard is met, the drying is completed;

[0042] Processor: The processor is used to process the calculation process of each formula and the construction calculation process of each model.

[0043] Compared with the prior art, the advantages of the present invention are:

[0044] By collecting temperature and humidity, temperature distribution and surface image data in real time through multi-source sensors, and combining advanced spatiotemporal calibration and compensation technology, it is possible to accurately identify changes in different drying stages and dynamically adjust process parameters to ensure the optimal drying effect at each stage. Especially when dealing with high-moisture areas, the system can accurately analyze the moisture distribution gradient and strengthen heating in a targeted manner to avoid overdrying or local over-humidification, thereby ensuring the overall quality of the kelp. In addition, the moisture distribution prediction model built based on historical data can further optimize moisture control, avoid waste and improve production efficiency. Ultimately, by determining the moisture differences in the entire area in real time, it is ensured that the kelp reaches an ideal uniform drying state at the end of drying. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A schematic diagram of the method proposed by the present invention;

[0046] Figure 2 This is a schematic diagram of drying stage identification proposed by the present invention;

[0047] Figure 3 A schematic diagram of the time-space calibration compensation proposed by the present invention;

[0048] Figure 4 This is a schematic diagram of the moisture distribution prediction model proposed by the present invention;

[0049] Figure 5 A schematic diagram for drying proposed by the present invention;

[0050] Figure 6 This is a schematic diagram of drying completion determination proposed by the present invention;

[0051] Figure 7 This is a schematic diagram of the electronic device in this solution;

[0052] Figure 8 This is a schematic diagram of the computer-readable storage medium structure in this solution. DETAILED DESCRIPTION

[0053] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0054] The dynamic balance control system of kelp drying moisture based on multi-source perception includes:

[0055] Data acquisition module: The data acquisition module is used to collect temperature and humidity time series data, kelp surface temperature distribution data and kelp surface image data in real time during the drying process, providing a basis for subsequent data analysis;

[0056] Drying stage identification module: The drying stage identification module identifies the current drying stage through the temperature and humidity time series data obtained in real time, and dynamically adjusts the process parameters according to the differences in stages.

[0057] Space-time calibration and compensation module: The space-time calibration and compensation module performs space-time calibration and compensation on the kelp surface data based on the temperature distribution and image data of each drying stage to ensure accuracy.

[0058] Moisture distribution prediction module: The moisture distribution prediction module constructs a moisture distribution prediction model using historical drying data, and generates kelp moisture distribution gradient data by inputting the compensated data.

[0059] High moisture area identification module: The high moisture area identification module identifies local high moisture areas based on the moisture distribution gradient data, and performs targeted enhanced drying by adjusting the partition heating unit.

[0060] Drying determination module: The drying determination module determines the moisture gradient difference in the whole area and the global average moisture content according to the moisture distribution data after enhanced drying. If the standard is met, the drying is completed.

[0061] Processor: The processor is used to process the calculation processes of each formula and the construction calculation processes of each model.

[0062] Refer to Figure 1 As shown, the dynamic balance control method for kelp drying moisture based on multi-source perception includes:

[0063] Step 1: Collect data in real time through multi-source sensors inside the drying equipment, including temperature and humidity time series data, kelp surface temperature distribution data, and kelp surface image data.

[0064] Step 2: Based on the obtained temperature and humidity time series data, identify the drying stage in real time, and dynamically adjust the process parameters according to the data differences between the real-time data and the standard data of each stage. The drying stages include the heating-up stage, the constant-rate drying and moisture-removing stage, and the falling-rate shaping stage.

[0065] Step 3: Based on each drying stage, perform space-time calibration and compensation on the kelp surface temperature distribution data and the kelp surface image data.

[0066] Step 4: Based on historical kelp drying data, construct a moisture distribution prediction model, and input the calibrated and compensated data into the moisture distribution prediction model to generate the obtained kelp moisture distribution gradient data.

[0067] Step 5: Based on the kelp moisture distribution gradient data, identify the local areas with moisture content higher than the global average as high moisture areas, and perform targeted enhanced drying on the high moisture areas by controlling the partition heating unit.

[0068] Step Six: Based on the targeted enhanced dried kelp, obtain its moisture distribution gradient data. If the moisture gradient difference in the entire area is less than the threshold and the global average moisture content is less than the threshold, the drying is completed.

[0069] Refer to Figure 2 As shown, based on the obtained temperature and humidity time-series data, identify the drying stage in real time, and dynamically adjust the process parameters according to the data differences between the real-time data and the standard data in each stage. The drying stage includes a heating-up stage, a constant-rate drying and moisture-removing stage, and a falling-rate shaping stage, which specifically include:

[0070] Based on the obtained real-time temperature and humidity time-series data, perform feature extraction to obtain key change index data, including the temperature change rate, the humidity change rate, and the temperature-humidity correlation;

[0071] Based on the key change index data, identify the drying stage. In the heating-up stage, the temperature continuously rises; in the constant-rate drying and moisture-removing stage, the temperature change rate is 0 and the humidity change rate is negative; in the falling-rate shaping stage, the absolute value of the humidity change rate decreases;

[0072] Based on the identified drying stage, obtain the standard temperature and humidity target curve for this stage according to historical data, and obtain the actual temperature and humidity curve based on the real-time collected temperature and humidity time-series data;

[0073] Based on the standard temperature and humidity target curve and the actual temperature and humidity curve, calculate and obtain the deviation values, including the temperature deviation, the humidity deviation, and the change rate deviation;

[0074] Based on the obtained deviation values, implement a targeted adjustment strategy to intervene in the drying stage data by adjusting the heating power and the opening degree of the moisture exhaust valve.

[0075] Specifically, extract key features from the real-time collected temperature and humidity time-series data, mainly including the temperature change rate, the humidity change rate, and the temperature-humidity correlation. The temperature-humidity correlation is measured by calculating the correlation coefficient between temperature and humidity, usually using the Pearson correlation coefficient. The formula is:

[0076]

[0077] Where is the Pearson correlation coefficient between temperature and humidity, , are the temperature and humidity at the i-th time point, , are the means of temperature and humidity, and n is the number of data points;

[0078] The main feature of the heating-up stage is that the temperature change rate is continuously a significant positive value, and the secondary feature is that the relative humidity usually also rises rapidly or begins to decline. When it is detected that the temperature rises continuously and rapidly, and the humidity change conforms to the expected trend, it is determined that the heating-up stage has entered;

[0079] The main feature of the constant-speed drying and moisture-exhausting stage is that the temperature change rate is close to 0 (the temperature is basically stable with small fluctuations near the set drying temperature), and at the same time, the humidity change rate is a significant negative value. The secondary feature is that the surface temperature of the material tends to be stable and slightly lower than the ambient temperature. When it is detected that the temperature reaches the preset drying temperature range and tends to be stable, and the humidity shows a continuous and stable downward trend, it is determined that the constant-speed drying and moisture-exhausting stage has entered, which is the stage with the most intense moisture evaporation;

[0080] The main feature of the falling-rate shaping stage is that the absolute value of the humidity change rate decreases significantly (close to 0 or becomes a very small negative value or even a slight positive value), indicating that the moisture evaporation rate has decreased greatly, and the temperature change rate begins to become negative or remains stable. The secondary feature is that the surface temperature of the material may begin to approach or equal the ambient temperature, and the image data shows that the edges of the kelp begin to curl and the color deepens. When it is detected that the humidity decline rate slows down significantly, tends to be stable or rises slightly (because the evaporation amount is very small and it is difficult for the ambient humidity to continue to decline), and the temperature begins to decline according to the preset curve or remains stable, it is determined that the falling-rate shaping stage has entered;

[0081] Through historical data, calculate and fit the standard temperature and humidity target curve. The interpolation method or the curve fitting method can be used to obtain the target temperature and humidity values of each stage. Extract the temperature and humidity data of the current drying stage from the time-series temperature and humidity data collected in real time, construct the actual temperature and humidity curve, and calculate the deviations between the standard temperature and humidity target curve and the actual temperature and humidity curve, including temperature deviation, humidity deviation, and change rate deviation.

[0082] Refer to Figure 3 As shown, based on each drying stage, the spatio-temporal calibration and compensation of the kelp surface temperature distribution data and the kelp surface image data specifically include:

[0083] Based on the images with slow changes in the heating-up stage, establish the initial position and approximate contour template of the kelp individual, and record the initial kelp surface temperature distribution data;

[0084] Based on the constant-speed drying and moisture-exhausting stage, calculate the pixel-level displacement field on the kelp surface between adjacent visible light images through the dense optical flow method, and calculate the local deformation field that has occurred on the kelp surface from the end moment of the heating-up stage to the current frame according to the optical flow field;

[0085] Superimpose the local deformation field onto the kelp surface image data calibrated by the projection transformation space through the basic space mapping model to calibrate the actual shape and position of the deformed kelp;

[0086] Focus on compensating for the minute deformation in the locally curled area of the kelp during the decelerating and shaping stage, and precisely correspond the temperature and image features at the curled edge.

[0087] Specifically, capture the contour and position of the kelp individual through the image sequence in the heating stage to obtain the preliminary contour of the kelp.

[0088] The dense optical flow method estimates the motion direction and speed of each pixel point by analyzing the pixel brightness change between adjacent frames. The formula is:

[0089]

[0090] Among them, is the spatial gradient of the image, is the displacement vector of the pixel point, is the derivative of the image brightness with respect to time;

[0091] Through the estimated displacement field, the local deformation field that occurs on the kelp surface from the end of the heating stage to the current frame can be calculated. Perform projection transformation space calibration on the image through the basic space mapping model to ensure that the actual shape and position of the deformed kelp are consistent with the image data.

[0092] During the decelerating and shaping stage, minute deformation may occur in the locally curled area of the kelp, and key compensation is required, especially for the temperature and image features at the curled edge. The deformed shape can be compensated by a small displacement field.

[0093] For the minute deformation area, record the temperature of the curled area through a temperature sensor or an infrared imaging device, and precisely correspond it to the image features. The temperature at each position on the compensated image can be calculated by the interpolation method.

[0094] Refer to Figure 4 As shown, based on the historical kelp drying data, construct a moisture distribution prediction model. Input the calibrated and compensated data into the moisture distribution prediction model to generate and obtain the kelp moisture distribution gradient data, specifically including:

[0095] Based on the historical kelp drying data, extract the characteristic data of the humidity time series data, the kelp surface temperature distribution data, and the kelp surface image data, and train them through the LSTM neural network model to construct a moisture distribution prediction model.

[0096] Based on the trained moisture distribution prediction model, input the spatio-temporal calibrated and compensated data into the model to predict and obtain the moisture distribution data on the kelp surface.

[0097] Based on the predicted moisture distribution data on the kelp surface, calculate the gradient of the moisture content through spatial difference to obtain the kelp moisture distribution gradient data.

[0098] Specifically, based on the extracted feature data: humidity time series data, temperature distribution data, and image data, an LSTM neural network is used for training to construct a moisture distribution prediction model. The LSTM model learns the relationship between features such as humidity, temperature, and images and moisture distribution through the training of time series data, and updates the weights of the model.

[0099] Based on the trained LSTM model, the data after spatio-temporal calibration and compensation is input to predict the moisture distribution data on the surface of the kelp. The gradient of the moisture content is calculated through spatial difference to obtain the change trend of the moisture distribution on the surface of the kelp. The moisture distribution gradient formula is:

[0100]

[0101] Where, is the moisture distribution gradient at the position on the surface of the kelp, are the gradients of the moisture distribution in the and directions respectively.

[0102] Refer to Figure 5 As shown, based on the kelp moisture distribution gradient data, the local area with a moisture content higher than the global average is identified as the high-moisture area. Specifically, targeted enhanced drying of the high-moisture area is carried out by controlling the partition heating unit, including:

[0103] Based on the obtained kelp moisture distribution gradient data, the global average moisture content is calculated.

[0104] By comparing the difference between the moisture content at each position of the kelp and the global average moisture content, the part exceeding the threshold is marked as the high-moisture area.

[0105] By adjusting the partition heating unit in the high-moisture area, the heating intensity is increased to carry out targeted enhanced drying of the high-moisture area.

[0106] Specifically, according to the obtained kelp moisture distribution gradient data, first calculate the global average moisture content of the moisture on the surface of the kelp. The formula is:

[0107]

[0108] Where, is the global average moisture content, is the total number of positions on the surface of the kelp, is the sum of the moisture contents at all positions;

[0109] By comparing the difference between the moisture content at each position and the global average moisture content, the area with a large deviation in moisture is identified. The moisture difference can be represented by the deviation between the moisture content at each position and the global average moisture content.

[0110] Once the high-moisture areas are identified, it is necessary to adjust the heating unit to enhance the drying effect in these areas. The adjustment of the heating unit helps to enhance the drying effect specifically in the high-moisture areas. By increasing the heating intensity in these areas, the moisture can be quickly evaporated, reducing the moisture difference in these areas.

[0111] Refer to Figure 6 As shown, based on the kelp after targeted enhanced drying, obtain its moisture distribution gradient data. If the moisture gradient difference in the whole area is less than the threshold and the global average moisture content is less than the threshold, the drying is completed, specifically including:

[0112] Based on the kelp after targeted enhanced drying, collect data again through the sensor and input it into the moisture distribution prediction model to obtain the moisture distribution gradient data of the kelp;

[0113] Calculate the global average moisture content based on the moisture distribution gradient data of the kelp. If the moisture gradient difference in the whole area is less than the threshold and the global average moisture content is less than the threshold, the drying is completed.

[0114] Furthermore, the method according to the embodiment of the present application can also be implemented by means of Figure 7 the architecture of the electronic device shown. As Figure 7 shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to the network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, can store the method and system for regulating the dynamic balance of the moisture in kelp drying based on multi-source perception provided by the present application. The electronic device 500 may further include a terminal interface 508. Of course, Figure 7 the architecture shown is only exemplary. When implementing different devices, one or more components shown in the Figure 7 electronic device may be omitted according to actual needs.

[0115] Figure 8 is a schematic structural diagram of a computer-readable storage medium provided by an embodiment of the present application. As Figure 8As shown, it is a computer-readable storage medium 600 according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are run by a processor, the method and system for dynamically balancing the moisture content in kelp drying based on multi-source perception according to the embodiments of the present application described with reference to the above drawings can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory, etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0116] It should be noted that: the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. And the above specific embodiments of this specification have been described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0117] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments.

[0118] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for regulating the dynamic balance of moisture in kelp drying based on multi-source perception, characterized in that, Including: Collect data in real time through multi-source sensors inside the drying equipment, including temperature and humidity time-series data, kelp surface temperature distribution data, and kelp surface image data; Based on the obtained temperature and humidity time-series data, identify the drying stage in real time, and dynamically adjust the process parameters according to the data differences between the real-time data of each stage and the standard data. The drying stage includes a heating-up stage, a constant-rate drying and moisture-removing stage, and a falling-rate shaping stage; Based on each drying stage, perform spatio-temporal calibration and compensation on the kelp surface temperature distribution data and the kelp surface image data; Based on historical kelp drying data, construct a moisture distribution prediction model, input the calibrated and compensated data into the moisture distribution prediction model, and generate and obtain kelp moisture distribution gradient data; Based on the kelp moisture distribution gradient data, identify the local areas with moisture content higher than the global average as high-moisture areas, and perform targeted enhanced drying on the high-moisture areas by controlling the partition heating unit; Based on the kelp after targeted enhanced drying, obtain its moisture distribution gradient data. If the moisture gradient difference in the whole area is less than the threshold and the global average moisture content is less than the threshold, the drying is completed.

2. The method for regulating the dynamic balance of moisture in kelp drying based on multi-source perception according to claim 1, wherein, The step of based on the obtained temperature and humidity time-series data, identifying the drying stage in real time, and dynamically adjusting the process parameters according to the data differences between the real-time data of each stage and the standard data, where the drying stage includes a heating-up stage, a constant-rate drying and moisture-removing stage, and a falling-rate shaping stage specifically includes: Based on the obtained real-time temperature and humidity time-series data, perform feature extraction to obtain key change index data, including temperature change rate, humidity change rate, and temperature-humidity correlation; Based on the key change index data, identify the drying stage. In the heating-up stage, the temperature continuously rises. In the constant-rate drying and moisture-removing stage, the temperature change rate is 0 and the humidity change rate is negative. In the falling-rate shaping stage, the absolute value of the humidity change rate decreases; Based on the identified drying stage, obtain the standard temperature and humidity target curve for this stage according to historical data, and obtain the actual temperature and humidity curve based on the real-time collected temperature and humidity time-series data; Based on the standard temperature and humidity target curve and the actual temperature and humidity curve, calculate and obtain deviation values, including temperature deviation, humidity deviation, and change rate deviation; Based on the obtained deviation values, perform a targeted adjustment strategy, and intervene in the drying stage data by adjusting the heating power and the opening degree of the moisture exhaust valve.

3. The method for regulating the dynamic balance of moisture in kelp drying based on multi-source perception according to claim 1, characterized in that, The step of based on each drying stage, performing spatio-temporal calibration and compensation on the kelp surface temperature distribution data and the kelp surface image data specifically includes: Based on the images with slow changes in the heating-up stage, establish the initial position and approximate contour template of the kelp individual, and record the initial kelp surface temperature distribution data; Based on the constant-rate drying and moisture-removing stage, calculate the pixel-level displacement field on the kelp surface between adjacent visible light images through the dense optical flow method, and calculate the local deformation field that has occurred on the kelp surface from the end moment of the heating-up stage to the current frame according to the optical flow field; Superimpose the local deformation field on the kelp surface image data calibrated by the projection transformation in the basic space mapping model to calibrate the actual shape and position of the deformed kelp; Based on the minor deformations in the local curling area of the kelp in the falling-rate shaping stage, perform key compensation to accurately correspond the temperature and image features at the curling edge.

4. The method for regulating the dynamic balance of moisture in kelp drying based on multi-source perception according to claim 1, wherein Based on the historical kelp drying data, a moisture distribution prediction model is constructed. Inputting the calibrated and compensated data into the moisture distribution prediction model to generate and obtain the kelp moisture distribution gradient data specifically includes: Based on the historical kelp drying data, extract the characteristic data of humidity time series data, kelp surface temperature distribution data, and kelp surface image data, and train through the LSTM neural network model to construct a moisture distribution prediction model; Based on the trained moisture distribution prediction model, input the spatio-temporal calibrated and compensated data into the model to predict and obtain the moisture distribution data on the kelp surface; Based on the predicted moisture distribution data on the kelp surface, calculate the gradient of the moisture content through spatial difference to obtain the kelp moisture distribution gradient data.

5. The method for dynamically regulating the moisture balance of kelp drying based on multi-source perception according to claim 1, characterized in that Based on the kelp moisture distribution gradient data, identify the local area with moisture content higher than the global average as the high-moisture area, and specifically include targeted enhanced drying of the high-moisture area by controlling the partition heating unit: Based on the obtained kelp moisture distribution gradient data, calculate and obtain the global average moisture content; By comparing the difference between the moisture content at each position of the kelp and the global average moisture content, mark the part exceeding the threshold as the high-moisture area; By adjusting the partition heating unit in the high-moisture area, increase the heating intensity to perform targeted enhanced drying on the high-moisture area.

6. The method for regulating the dynamic balance of moisture in kelp drying based on multi-source perception according to claim 1, characterized in that, Based on the kelp after targeted enhanced drying, obtain its moisture distribution gradient data. If the moisture gradient difference in the whole area is less than the threshold and the global average moisture content is less than the threshold, the drying is completed, specifically including: Based on the kelp after targeted enhanced drying, collect data again through the sensor and input it into the moisture distribution prediction model to obtain the kelp moisture distribution gradient data; Calculate the global average moisture content based on the kelp moisture distribution gradient data. If the moisture gradient difference in the whole area is less than the threshold and the global average moisture content is less than the threshold, the drying is completed.

7. A kelp drying moisture dynamic balance control system based on multi-source perception is used to implement the kelp drying moisture dynamic balance control method based on multi-source perception according to any one of claims 1-6, characterized in that, Including: Data acquisition module: The data acquisition module is used to collect the temperature and humidity time series data, kelp surface temperature distribution data, and kelp surface image data in real time during the drying process, providing a basis for subsequent data analysis; Drying stage identification module: The drying stage identification module identifies the current drying stage through the real-time obtained temperature and humidity time series data, and dynamically adjusts the process parameters according to the differences in stages; Spatio-temporal calibration and compensation module: The spatio-temporal calibration and compensation module performs spatio-temporal calibration and compensation on the kelp surface data based on the temperature distribution and image data of each drying stage to ensure accuracy; Moisture distribution prediction module: The moisture distribution prediction module uses historical drying data to construct a moisture distribution prediction model, and generates kelp moisture distribution gradient data by inputting the compensated data; High-moisture area identification module: The high-moisture area identification module identifies local high-moisture areas based on the moisture distribution gradient data, and performs targeted enhanced drying by adjusting the partition heating unit; Drying determination module: The drying determination module determines the moisture gradient difference in the whole area and the global average moisture content according to the moisture distribution data after enhanced drying. If the standard is met, the drying is completed; Processor: The processor is used to process the calculation process of each formula and the construction calculation process of each model.

8. An electronic device, characterized in that, Including: At least one processor; And a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for dynamically balancing and regulating the moisture content of kelp drying based on multi-source perception according to any one of claims 1-6.

9. A computer-readable storage medium storing computer-readable instructions, characterized in that, When the computer-readable instructions are executed by a processor, the method for dynamically balancing and regulating the moisture content of kelp drying based on multi-source perception according to any one of claims 1-6 is implemented.

Images