Unattended refrigeration control method and system for fishing transport vessels

Abstract

The present invention provides an unattended refrigeration control method and system for a fishing transport vessel, which relates to the field of fishery refrigeration control technology, including obtaining the structural information, usage information and product information of the refrigerated compartment of the fishing transport vessel; constructing a three-dimensional space model based on the refrigerated compartment structural information, and performing product transportation simulation to obtain a transportation simulation model; using image recognition to determine the product category, and performing refrigerated compartment allocation simulation; analyzing the product quality changes at different transportation times and refrigeration temperatures based on historical product information; sending the above information to a multi-objective optimization model, predicting the optimal refrigeration temperature, and adjusting the refrigeration equipment in real time. The present invention realizes unattended refrigeration control of fishing transport vessels, optimizes refrigerated compartment allocation, improves product quality, and reduces transportation costs.

Description

Technical Field

[0001] The present invention relates to the technical field of fishery refrigeration control, and in particular to an unattended refrigeration control method and system for a fishery transport vessel. Background Art

[0002] Maintaining the freshness and quality of fish products is a key issue during fishery transportation. Traditional fishery transport vessels usually rely on manual monitoring and operation of refrigeration equipment to ensure that the temperature in the cabin is kept within an appropriate range. However, due to the complexity of the marine environment and the technical requirements for the operation of refrigeration equipment, manual monitoring often fails to achieve the desired refrigeration effect, which can easily lead to temperature fluctuations in the refrigerated cabin, thus affecting the quality of the product. In addition, manual operation has a high labor intensity and the risk of misoperation, which is not conducive to the efficient management of fishery transportation.

[0003] The existing technology usually uses simple temperature sensors and manual adjustment to control the temperature of the refrigerated compartment. This method has problems such as slow response speed and low accuracy, and it is difficult to adapt to the personalized refrigeration needs of different products. For example, although some fishing transport ships are equipped with advanced refrigeration equipment, they still need to rely on experienced operators to adjust the temperature due to the lack of intelligent control systems. This not only increases operating costs, but also makes it difficult to ensure that all products maintain the expected quality during transportation. Therefore, there is an urgent need for an unmanned refrigeration control method and system that can solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide an unattended refrigeration control method and system for a fishing transport vessel to improve the above-mentioned problem. In order to achieve the above-mentioned purpose, the technical solution adopted by the present invention is as follows:

[0005] In a first aspect, the present application provides an unattended refrigeration control method for a fishing transport vessel, comprising:

[0006] Obtaining the refrigerated tank structure information of the fishing transport vessel, the purpose information of each refrigerated tank structure, and the product information transported by the fishing transport vessel;

[0007] Constructing a three-dimensional space model of the fishing transport ship based on the structural information of the refrigerated tank of the fishing transport ship, and performing product transportation simulation based on the three-dimensional space model to obtain a transportation simulation model of the transport ship;

[0008] Perform image recognition based on the image information in the product information transported by the fishing transport ship to determine the category of the product transported by the fishing transport ship, and send the category of the product and the use information of each refrigerated tank structure to the transport simulation model of the transport ship to perform refrigerated tank allocation simulation to obtain the transport refrigerated tank information corresponding to each category of products;

[0009] Perform product analysis on the preset historical product information according to its corresponding transportation time and refrigeration temperature to determine the quality change information of products at different transportation times and different refrigeration temperatures;

[0010] The transport refrigerated compartment information corresponding to each category of products and the product quality change information are sent to a preset multi-objective optimization model to predict the optimal refrigeration temperature, and the optimal refrigeration temperature is predicted in real time and the refrigeration equipment is adjusted in real time according to the optimal refrigeration temperature for refrigeration.

[0011] In a second aspect, the present application also provides an unattended refrigeration control system for a fishing transport vessel, comprising:

[0012] An acquisition unit, used to acquire the refrigerated tank structure information of the fishery transport vessel, the use information of each refrigerated tank structure and the product information transported by the fishery transport vessel;

[0013] A first processing unit is used to construct a three-dimensional space model of the fishery transport ship based on the structural information of the refrigerated tank of the fishery transport ship, and to perform product transportation simulation based on the three-dimensional space model to obtain a transportation simulation model of the transport ship;

[0014] The second processing unit is used to perform image recognition based on the image information in the product information transported by the fishery transport ship, determine the category of the product transported by the fishery transport ship, and send the category of the product and the use information of each refrigerated tank structure to the transport simulation model of the transport ship to perform refrigerated tank allocation simulation, so as to obtain the transport refrigerated tank information corresponding to each category of the product;

[0015] The third processing unit is used to analyze the preset historical product information according to its corresponding transportation time and refrigeration temperature, and determine the quality change information of the products at different transportation times and different refrigeration temperatures;

[0016] The fourth processing unit is used to send the transport refrigerated compartment information corresponding to each category of products and the product quality change information to a preset multi-objective optimization model to predict the optimal refrigeration temperature, and to predict the optimal refrigeration temperature in real time and adjust the refrigeration equipment in real time according to the optimal refrigeration temperature for refrigeration.

[0017] The beneficial effects of the present invention are:

[0018] The present invention obtains the refrigerated compartment structure information, usage information and transport product information, constructs a three-dimensional space model, performs product transportation simulation, and realizes the automation and intelligent control of the transportation process. Image recognition technology is used to classify the transport products, and the refrigerated compartment allocation simulation is performed based on the product category and refrigerated compartment usage information to ensure that each type of product obtains the expected storage conditions. By analyzing the quality changes in historical product information, combining the multi-objective optimization model to predict the optimal refrigeration temperature, and adjusting the refrigeration equipment in real time, accurate temperature control is achieved, which not only improves the refrigeration efficiency, but also significantly improves the product quality maintenance effect. The intelligent control system improves transportation efficiency, reduces human operation errors and labor intensity, and reduces operating costs. At the same time, through optimized refrigeration temperature control, it effectively reduces energy consumption and further saves costs. Combining these beneficial effects, this method significantly improves the management efficiency of fishing transport ships and the quality of product transportation.

[0019] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 It is a schematic flow chart of an unattended refrigeration control method for a fishing transport vessel described in an embodiment of the present invention;

[0022] Figure 2 It is a schematic diagram of the topological structure of an unattended refrigeration control system for a fishing transport vessel described in an embodiment of the present invention.

[0023] In the figure: 701, acquisition unit; 702, first processing unit; 703, second processing unit; 704, third processing unit; 705, fourth processing unit. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0025] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0026] Embodiment 1:

[0027] This embodiment provides an unattended refrigeration control method for a fishing transport vessel.

[0028] See also Figure 1 , the figure shows that the method includes step S1, step S2, step S3, step S4 and step S5.

[0029] Step S1, obtaining the refrigerated tank structure information of the fishing transport ship, the use information of each refrigerated tank structure and the product information transported by the fishing transport ship;

[0030] It can be understood that the refrigerated tank structure information in this step refers to the specific structural data of each refrigerated tank on the fishing transport ship, including the size, location, insulation thickness, door location and number of the refrigerated tank, etc. The purpose information of the refrigerated tank structure refers to the specific function or intended purpose of the refrigerated tank. For example, some refrigerated tanks may be used to store different types of seafood, such as fish, shrimp or shellfish. Refrigerated tanks for different purposes have different temperature and humidity requirements: the product information transported by the fishing transport ship includes the type, quantity, packaging method, storage temperature requirements, etc. of the transported products. This step provides a solid data foundation, laying the foundation for subsequent optimization control and intelligent management.

[0031] Step S2, constructing a three-dimensional space model of the fishing transport ship based on the refrigerated compartment structure information of the fishing transport ship, and performing product transportation simulation based on the three-dimensional space model to obtain a transportation simulation model of the transport ship;

[0032] It can be understood that the three-dimensional space model in this step truly reflects the internal structure of the transport ship, providing a reliable basis for the simulation and optimization of product transportation. Secondly, through detailed product transportation simulation, potential problems can be discovered in advance, the product allocation and temperature control strategy of the refrigerated compartment can be optimized, and the transportation efficiency and product quality can be improved. In this step, step S2 includes step S21, step S22, step S23 and step S24.

[0033] Step S21, converting the format of the refrigerated tank structure data and the refrigeration equipment pipeline data in the refrigerated tank structure information of the fishing transport vessel, performing XOY plane frame selection processing on the converted refrigerated tank structure data and the refrigeration equipment pipeline data, and obtaining the framed refrigerated tank structure diagram and the refrigeration equipment pipeline structure diagram;

[0034] It can be understood that this step unifies and clarifies the data format, allowing the 3D modeling software to accurately identify and process all data, thereby improving the accuracy and efficiency of modeling.

[0035] Step S22, sending the preset discrete elevation data of the refrigerated tank structure of the fishing transport ship, the selected refrigerated tank structure diagram and the refrigeration equipment pipeline structure diagram to the three-dimensional modeling software for processing, and obtaining the three-dimensional model of the refrigerated tank structure and the refrigeration equipment pipeline of the fishing transport ship;

[0036] It can be understood that this step can accurately construct the 3D model of the refrigerated compartment and refrigeration equipment pipeline of the fishing transport ship by using 3D modeling software, which can truly and intuitively reflect the internal structure of the transport ship. Secondly, this process ensures the integration and consistency of various data, and the generated 3D model can provide a reliable basis for subsequent transportation simulation and optimization.

[0037] Step S23, discretizing the three-dimensional model of the refrigerated tank structure and the refrigeration equipment pipeline of the fishing transport ship to obtain at least one refrigerated tank structure unit, and performing linear interpolation processing on each of the refrigerated tank structure units based on a linear interpolation method to obtain a three-dimensional model with the refrigerated tank as a structure unit;

[0038] It can be understood that this step decomposes the complex structure of the entire refrigerated compartment into multiple small units through discretization processing, which improves the calculation accuracy and processing efficiency of the model. The linear interpolation method smoothly interpolates between known data points, ensuring the continuity and accuracy of the model data and enhancing the authenticity of the simulation results.

[0039] Step S24: Send the historical product information of the preset fishing transport ship to the three-dimensional modeling software for transport simulation to obtain a transport simulation model of the transport ship.

[0040] It can be understood that this step can comprehensively analyze various influencing factors in the transportation process and optimize the product placement and temperature control in the refrigerated compartment by using historical data combined with a three-dimensional model for transportation simulation. The transportation simulation model can predict the state changes of products under different transportation conditions, improving the controllability and predictability of the transportation process. And through the analysis and optimization of the simulation results, the management level and economic benefits of fishery transport ships can be significantly improved, ensuring the quality of products during transportation and reducing losses and waste.

[0041] Step S3, performing image recognition based on the image information in the product information transported by the fishing transport ship, determining the category of the product transported by the fishing transport ship, and sending the category of the product and the use information of each refrigerated compartment structure to the transport simulation model of the transport ship to perform refrigerated compartment allocation simulation, and obtain the transport refrigerated compartment information corresponding to each category of the product;

[0042] It can be understood that this step can automatically and efficiently determine the product category transported by the fishing transport vessel by performing image recognition based on the image in the product information, thereby reducing the error and workload of manual classification. Using image recognition technology, the texture, contour and color features of the product can be quickly and accurately extracted to achieve accurate classification. Combined with the use information of the refrigerated compartment structure, the refrigerated compartment allocation simulation is performed through the particle swarm optimization algorithm, which can optimize the utilization rate of the refrigerated compartment, ensure that each type of product is stored in the most suitable compartment, and ensure the quality of the product and the efficiency of the transportation process. In this step, step S3 includes step S31, step S32, step S33, step S34 and step S35.

[0043] Step S31, identifying the image information in the product information transported by the fishing transport vessel, wherein each frame of the image containing the product is extracted to obtain at least two frames of product image information;

[0044] It can be understood that this step automatically extracts each frame of the image and filters out the key frames containing product information, which helps the subsequent image processing and feature extraction, ensuring the validity and accuracy of the extracted image data. The automated processing of frame extraction and screening reduces manual intervention, improves processing efficiency and image recognition accuracy. This step provides high-quality input data for subsequent image processing, thereby ensuring the efficient and accurate operation of the entire unattended refrigeration control system.

[0045] Step S32, grayscale conversion is performed on all product image information, and pixel points with the same grayscale value in the grayscale image obtained by the grayscale conversion are connected by lines, wherein the lines are interpolated by a linear interpolation method to obtain texture features of the product;

[0046] It can be understood that this step can effectively reduce the complexity of image data by grayscale conversion of all product image information, making subsequent processing more efficient. By connecting pixels with the same grayscale value, the texture features in the image can be highlighted, making the detailed features of the image more obvious. Using linear interpolation to interpolate the lines can make the lines more continuous and smooth, further enhancing the expression of texture features. This step provides high-quality feature data for subsequent image recognition and product classification by refining and enhancing the texture information in the image, thereby improving the recognition accuracy and efficiency of the entire system.

[0047] Step S33, performing edge detection on the product image information to obtain the contour edge of the product in the product image information, and converting the image outside the contour edge of the product into white to obtain the contour feature of the product;

[0048] It can be understood that this step can accurately extract the contour edges in the product image by applying the edge detection algorithm, so that the key features in the image are effectively highlighted. Converting the image area outside the contour edge to white not only simplifies the complexity of the image, but also further enhances the contrast of the product contour, making the contour features clearer and easier to identify. This step provides high-quality input data for subsequent feature extraction and product classification, significantly improving the accuracy and efficiency of recognition.

[0049] Step S34, clustering the three components R, G, and B of all pixels within the contour edge of the product, and calculating the square differences of all clusters obtained by clustering, and using the calculated square differences as the color features of the product;

[0050] It can be understood that this step can effectively capture the color distribution characteristics of the product by extracting all the pixels within the edge of the product outline and clustering the RGB color components of these pixels. Clustering helps to simplify a large amount of color data into several representative color clusters, making the color features more concise and easier to analyze. By calculating the square difference of the clusters, the degree of dispersion within the color cluster can be quantified, thereby extracting unique color features for each product. This process enhances the accuracy of the system in identifying different product categories, especially in the classification of products with significant color features, providing higher recognition.

[0051] Step S35: Identify and classify the products based on the texture features, contour features and color features of the products to determine the category of each product.

[0052] It can be understood that this step can greatly improve the accuracy and robustness of product classification by combining the texture features, contour features and color features of the product for comprehensive classification. This multi-feature fusion method makes full use of the information of each feature and improves the system's ability to identify product categories.

[0053] It can be understood that step S35 also includes step S36, step S37, step S38 and step S39.

[0054] Step S36, initializing the category of the product and the use information of each refrigerated compartment structure, and using the category of the product and the use information of the refrigerated compartment structure after the initialization as a particle swarm parameter;

[0055] It can be understood that this step ensures that the format and content of the input data meet the algorithm requirements through initialization processing, thereby ensuring the effectiveness and accuracy of the particle swarm optimization process.

[0056] Step S37, calculating the fitness of particles in each particle group based on a preset fitness function, obtaining the individual optimal position and the global optimal position of the particle, wherein the fitness function of the particle;

[0057] It can be understood that this step can effectively evaluate the pros and cons of each product and refrigerated compartment usage allocation scheme by calculating the fitness of the particles in each particle swarm based on the preset fitness function, thereby determining the individual optimal position and global optimal position of the particle. This step guides the particle swarm to converge to the optimal solution by continuously updating the individual optimal and global optimal positions, ensuring that the system achieves the highest efficiency and optimal performance in refrigerated compartment allocation.

[0058] It can be understood that in this step, the calculation formula of the fitness function is as follows:

[0059]

[0060] Among them, x represents the current position of the particle, that is, the allocation plan of product categories and refrigerated compartment uses, n is the number of product types, m is the number of refrigerated compartments, represents the energy consumption of product i stored in refrigerated compartment j, represents the distribution amount of product i in refrigerated compartment j; represents the quality change of product i stored in refrigerated compartment j, i represents the i-th product, j represents the j-th refrigerated compartment, and is a non-negative weight parameter that reflects the relative importance of product category and refrigerated compartment usage in the overall fitness.

[0061] Step S38, continuously updating the speed and position of all particles based on the particle update speed formula and the particle update position formula in the particle swarm optimization algorithm until the particle swarm optimization algorithm reaches a preset number of iterations, and obtaining parameter information after iteration, wherein the parameter information after iteration is the refrigerated compartment with the highest category fitness value for the product;

[0062] It can be understood that this step can efficiently search for the optimal product category and refrigerated compartment usage allocation scheme by using the particle swarm optimization algorithm. The particle swarm optimization algorithm can quickly converge to the global optimal solution in the multi-dimensional search space by simulating the collaborative search behavior of the particle group. By continuously updating the speed and position of the particles and iteratively optimizing the fitness function, the utilization efficiency of the refrigerated compartment can be effectively improved, energy consumption can be reduced, and the products can be stored under the expected conditions, thereby improving the intelligence and automation level of the unattended refrigeration control system.

[0063] Step S39: Allocate the refrigerated compartments according to the iterated parameter information to obtain an allocation result for each refrigerated compartment.

[0064] It can be understood that this step can ensure the maximum utilization efficiency of each refrigerated compartment by allocating the refrigerated compartment according to the iterated parameter information, while meeting the storage requirements and quality maintenance requirements of the product. This step not only improves the utilization rate of the refrigerated compartment and reduces energy consumption, but also effectively maintains the quality of the product, reduces losses, and improves the overall operational efficiency of the fishing transport ship.

[0065] Step S4, analyzing the preset historical product information according to its corresponding transportation time and refrigeration temperature, and determining the quality change information of the products at different transportation times and different refrigeration temperatures;

[0066] It can be understood that in this step, step S4 includes step S41, step S42, step S43 and step S44.

[0067] Step S41, performing image recognition on preset historical product information to obtain feature information of products at multiple transportation times and multiple refrigeration temperatures, wherein the feature information of the products includes product texture features, product contour features, and product color features;

[0068] It can be understood that this step analyzes the preset historical product information according to its corresponding transportation time and refrigeration temperature, and can predict the quality changes under various transportation conditions based on the historical data of different products, and take measures in advance to ensure the quality of the product during transportation.

[0069] Step S42: compare the characteristic information of all products in pairs to obtain characteristic variation data of each product at different transportation times and different refrigeration temperatures;

[0070] It can be understood that this step can accurately quantify the changes in product characteristics under different transportation times and refrigeration temperatures by comparing the characteristic information of all products in pairs. Then, by understanding the changes in product characteristics under different conditions, it can assist in formulating a more reasonable refrigeration control strategy to ensure the quality of the product during transportation.

[0071] Step S43: Perform vibration detection on products at different transportation times and different refrigeration temperatures based on a preset vibration detection strategy to obtain the quality variation of all products;

[0072] It can be understood that this step can accurately evaluate the quality changes of products under different conditions through vibration detection, and provide data support for subsequent quality control. Based on the vibration detection results, the transportation strategy is optimized to reduce the negative impact of vibration on product quality. By optimizing the refrigeration and transportation strategies, the quality of the product during transportation is ensured to be stable, and the market competitiveness and consumer satisfaction of the product are improved. In this step, step S43 includes step S431, step S432 and step S433.

[0073] Step S431, using the least square method to fit the signal information generated by the vibration detection strategy, to obtain the amplitude signal of each order of harmonics and the phase signal of each order of harmonics in the initial state and at any vibration time;

[0074] It can be understood that the amplitude and phase information of each order of harmonics obtained by fitting in this step can more accurately describe the characteristics of the vibration signal and improve the accuracy of signal analysis. Each order of harmonic signals can reflect the state changes of the product during different vibration times, which is helpful for real-time monitoring of the transportation status of the product. According to the analysis results of the harmonic signal, the transportation conditions can be optimized and the impact of vibration on product quality can be reduced, thereby improving the transportation quality of the product.

[0075] Step S432: calculating the amplitude difference between the harmonic amplitude signal in the initial state and the amplitude difference between each order of harmonic amplitude signals in each vibration time based on a preset amplitude difference calculation formula, and calculating the phase difference between the harmonic phase signal in the initial state and the phase difference between each order of harmonic phase signals in each vibration time based on a preset phase difference calculation formula;

[0076] It can be understood that the preset amplitude difference calculation formula in this step is as follows;

[0077]

[0078] in, is the amplitude difference, T is any time, is the amplitude signal of each order harmonic in the initial state, It is the amplitude signal of each order harmonic within any vibration time.

[0079] The preset phase difference calculation formula in this step is as follows;

[0080]

[0081] in, is the phase difference, T is any time, is the phase signal of each order harmonic in the initial state, It is the phase signal of each order harmonic in any vibration time.

[0082] Step S433: Compare the amplitude difference and the phase difference with preset thresholds respectively, and based on the comparison results obtained by comparison, determine the quality change degree of the product at different transportation times and different refrigeration temperatures.

[0083] It can be understood that this step can accurately determine the quality change degree of the product by real-time monitoring of the quality change of the product during transportation and by comparing the harmonic amplitude difference and phase difference. According to the judgment result of the quality change degree, the transportation conditions and refrigeration temperature can be adjusted, the transportation strategy can be optimized, and the adverse effect on product quality can be reduced. Among them, this step combines the amplitude difference and phase difference of each order of harmonics by adopting a weighted method to calculate the total quality change degree. For example, if the preset threshold is 0.05, the harmonic amplitude difference and phase difference are divided by the preset threshold respectively, and then the results of the two are added to obtain the quality change degree of the product.

[0084] Step S44: weight the characteristic change data and quality change degree of each product according to the minimum discrimination principle, and calculate the quality change score of the product at different transportation times and different refrigeration temperatures.

[0085] It can be understood that the quality change score calculated by comprehensively considering the characteristic change and the quality change degree in this step can more accurately reflect the quality change of the product under different conditions. Based on the quality change score, a more accurate transportation and refrigeration strategy can be formulated to ensure the stability of the product quality during transportation to the greatest extent. In this step, step S44 includes step S441, step S442 and step S443.

[0086] Step S441, establishing an objective function according to the minimum discriminant information principle, solving the objective function to construct a Lagrangian function;

[0087] It can be understood that in this step, the objective function is as follows:

[0088]

[0089] in, is the characteristic change data of the cth product, is the quality variation of the cth product, is the combined weight vector of the characteristic change data and quality change degree of the cth product, and n is the total number of products;

[0090] It can be understood that the Lagrangian function is constructed as follows:

[0091]

[0092]

[0093] Where L is the Lagrangian function, Lagrange constant, is the characteristic change data of the cth product, is the quality variation of the cth product, is the combined weight of the characteristic change data and quality change degree of the cth product, and n is the total number of products.

[0094] Step S442: Substitute the characteristic change data and quality change degree of each product into the Lagrangian function for solution to obtain the combined weight of the characteristic change data and quality change degree of each product;

[0095] It can be understood that the Lagrangian function solution formula in this step is as follows:

[0096]

[0097] in, is the characteristic change data of the cth product, is the quality variation of the cth product, is the combined weight of the characteristic change data and quality change degree of the cth product, and n is the total number of products.

[0098] Step S443: Calculate the characteristic change data and quality change degree of each product according to the combined weight to obtain the quality change scores of the products at different transportation times and different refrigeration temperatures.

[0099] It can be understood that this step can quantify the quality changes of products under different conditions by calculating the quality change score, making quality monitoring more accurate and quantitative. The quality change score provides quantitative data support for subsequent refrigeration control strategies, making the decision-making process more scientific and data-driven.

[0100] Step S5: Send the transport refrigerated compartment information corresponding to each category of products and the product quality change information to a preset multi-objective optimization model to predict the optimal refrigeration temperature, and predict the optimal refrigeration temperature in real time and adjust the refrigeration equipment in real time according to the optimal refrigeration temperature for refrigeration.

[0101] It can be understood that this step ensures that the quality of the product is maintained during transportation by predicting and adjusting the optimal refrigeration temperature in real time, and reduces the quality loss caused by improper temperature. By optimizing the refrigeration temperature, unnecessary refrigeration energy consumption is reduced, and efficient use of energy is achieved. In this step, step S5 includes step S51, step S52, step S53, step S54 and step S55.

[0102] Step S51, taking the transportation time, refrigeration temperature and refrigerated compartment area of ​​each category of products as decision variables;

[0103] It can be understood that the decision variables clearly defined in this step provide accurate data input for multi-objective optimization, so that the optimization model can accurately calculate the optimal transportation plan, taking into account the transportation time, refrigeration temperature and refrigerated compartment area, and can comprehensively evaluate and optimize the resource utilization of each link to improve transportation efficiency.

[0104] Step S52, calculating the refrigerated compartment cost and quality change degree based on the transport refrigerated compartment information corresponding to each category of products and the product quality change information, and obtaining an objective function set by setting a specific cost function and quality change target;

[0105] It can be understood that the objective function set in this step is as follows:

[0106]

[0107] in, represents the cost function, represents the transportation time cost, The cost corresponding to the cooling temperature, Represents the refrigerated compartment area cost. , and Both are cost coefficients.

[0108]

[0109] in, represents the quality change objective function, where represents the degree of change corresponding to the transportation time, Indicates the quality change corresponding to the refrigeration temperature, and All are quality variation coefficients.

[0110] Step S53: Obtain constraint conditions according to preset product transportation rules, wherein the constraint conditions include refrigerated compartment storage restrictions and transportation time windows;

[0111] It can be understood that this step ensures that there is enough storage space for the product in the refrigerated compartment to avoid product damage or poor refrigeration due to overloading, and sets a reasonable transportation time window according to the characteristics and needs of the product to ensure that the product arrives at the destination in the expected state and maintains product quality. Through reasonable constraints, the transportation process is optimized, transportation costs are reduced, transportation efficiency is improved, and efficient operation of the logistics system is ensured. Among them, the constraint formulas of the refrigerated compartment storage limit and the transportation time window are as follows:

[0112]

[0113]

[0114]

[0115]

[0116] in, represents the volume of product i, represents the capacity of refrigerated compartment j, represents the weight of product i, The load capacity of the refrigerated compartment j, Indicates the start time of the transportation time window, Indicates the shipping start time of product i, The shipping end time of product i, Indicates the end time of the transportation time window.

[0117] Step S54: performing genetic operations on the decision variable representations using a multi-objective evolutionary algorithm according to the objective function set and the constraint conditions to obtain an optimized solution set;

[0118] The multi-objective evolutionary algorithm performs genetic operations on the decision variable representation, including first calculating the objective function value of each individual based on the objective function set, including the refrigerated compartment cost and quality variability. And ensure that each individual meets the constraints of the transportation time window and the refrigerated compartment capacity. Then, the population is non-dominated sorted, and the crowding distance of each individual is calculated. A new population is generated through tournament selection, crossover and mutation operations. Further, by merging the parent and child populations, and selecting the first preset number of individuals as the new population. Finally, the above steps are repeated until the preset number of iterations is reached to obtain the optimal solution set. In addition, the multi-objective evolutionary algorithm in the present invention is the NSGA-II (Non-dominated Sorting Genetic Algorithm II) evolutionary algorithm in the prior art. The present invention can obtain the optimal real-time refrigeration temperature mentioned in the present application through the evolutionary algorithm and the decision variables, objective function set and constraint condition formulas mentioned above, and then monitor the temperature changes in the refrigerated compartment in real time through the temperature sensor. If the temperature in the controlled refrigerated compartment is not in the refrigerated compartment, the system controls the refrigeration equipment to adjust the temperature value to predict the optimal refrigeration temperature, thereby ensuring that the temperature of each refrigerated compartment is always in the optimal range.

[0119] It can be understood that this step ensures both cost reduction and product quality improvement by finding a balance between the cost of the refrigerated compartment and the quality of the product. The target evolution algorithm improves the computational efficiency of solving complex multi-objective problems through intelligent search and optimization. Through iterative optimization, it gradually approaches the optimal solution, enhancing the stability and reliability of the system in practical applications.

[0120] Step S55: Evaluate and screen the set of optimized solutions, compare the performance of each solution in terms of refrigerated compartment cost and quality variability, and use Pareto front analysis to screen out the optimal solution, which is the optimal real-time refrigeration temperature of each transport refrigerated compartment.

[0121] It is understandable that this step can consider multiple objectives at the same time through the Pareto frontier method, find a solution that performs balanced on each objective, and improve the optimization effect of the overall system. Through scientific methods to select the optimal solution, improve the rationality and scientificity of decision-making, and ensure the optimal balance between the cost and quality variability of the refrigerated compartment. Through the screening and evaluation of the optimal solution set, the stability and reliability of the system in practical applications are improved, ensuring the efficient operation of the system under different conditions.

[0122] Embodiment 2:

[0123] like Figure 2 As shown, this embodiment provides an unattended refrigeration control system for a fishing transport vessel, see Figure 2The system includes an acquisition unit 701 , a first processing unit 702 , a second processing unit 703 , a third processing unit 704 and a fourth processing unit 705 .

[0124] An acquisition unit 701 is used to acquire the refrigerated tank structure information of the fishing transport ship, the use information of each refrigerated tank structure and the product information transported by the fishing transport ship;

[0125] The first processing unit 702 is used to construct a three-dimensional space model of the fishing transport ship based on the refrigerated tank structure information of the fishing transport ship, and perform product transportation simulation based on the three-dimensional space model to obtain a transportation simulation model of the transport ship;

[0126] The second processing unit 703 is used to perform image recognition based on the image information in the product information transported by the fishing transport ship, determine the category of the product transported by the fishing transport ship, and send the category of the product and the use information of each refrigerated compartment structure to the transport simulation model of the transport ship to perform refrigerated compartment allocation simulation, so as to obtain the transport refrigerated compartment information corresponding to each category of products;

[0127] The third processing unit 704 is used to analyze the preset historical product information according to its corresponding transportation time and refrigeration temperature, and determine the quality change information of the products at different transportation times and different refrigeration temperatures;

[0128] The fourth processing unit 705 is used to send the transport refrigerated compartment information corresponding to each category of products and the product quality change information to a preset multi-objective optimization model to predict the optimal refrigeration temperature, and to predict the optimal refrigeration temperature in real time and adjust the refrigeration equipment in real time according to the optimal refrigeration temperature for refrigeration.

[0129] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0130] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0131] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An unattended refrigeration control method for a fishing transport vessel, characterized in that: include: Obtaining the refrigerated tank structure information of the fishing transport vessel, the purpose information of each refrigerated tank structure, and the product information transported by the fishing transport vessel; Constructing a three-dimensional space model of the fishing transport ship based on the structural information of the refrigerated tank of the fishing transport ship, and performing product transportation simulation based on the three-dimensional space model to obtain a transportation simulation model of the transport ship; Perform image recognition based on the image information in the product information transported by the fishing transport ship to determine the category of the product transported by the fishing transport ship, and send the category of the product and the use information of each refrigerated tank structure to the transport simulation model of the transport ship to perform refrigerated tank allocation simulation to obtain the transport refrigerated tank information corresponding to each category of products; Perform product analysis on the preset historical product information according to its corresponding transportation time and refrigeration temperature to determine the quality change information of products at different transportation times and different refrigeration temperatures; The transport refrigerated compartment information corresponding to each category of products and the product quality change information are sent to a preset multi-objective optimization model to predict the optimal refrigeration temperature, and the optimal refrigeration temperature is predicted in real time and the refrigeration equipment is adjusted in real time according to the optimal refrigeration temperature for refrigeration.

2. The unattended refrigeration control method for a fishing transport vessel according to claim 1, characterized in that: A three-dimensional space model of a fishery transport ship is constructed based on the structural information of the refrigerated tank of the fishery transport ship, and a product transportation simulation is performed based on the three-dimensional space model to obtain a transportation simulation model of the transport ship, including: The refrigerated tank structure data and refrigeration equipment pipeline data in the refrigerated tank structure information of the fishing transport ship are formatted, and the converted refrigerated tank structure data and refrigeration equipment pipeline data are processed by XOY plane frame selection to obtain the refrigerated tank structure diagram and refrigeration equipment pipeline structure diagram after frame selection; Send the preset discrete elevation data of the refrigerated tank structure of the fishing transport ship, the refrigerated tank structure diagram after the box selection, and the refrigeration equipment pipeline structure diagram to the 3D modeling software for processing, and obtain the 3D model of the refrigerated tank structure and refrigeration equipment pipeline of the fishing transport ship; Discretizing the three-dimensional model of the refrigerated tank structure and the refrigeration equipment pipeline of the fishing transport ship to obtain at least one refrigerated tank structure unit, and performing linear interpolation processing on each of the refrigerated tank structure units based on a linear interpolation method to obtain a three-dimensional model with the refrigerated tank as a structure unit; The historical product information of the preset fishing transport ship is sent to the 3D modeling software for transportation simulation to obtain the transportation simulation model of the transport ship.

3. The unattended refrigeration control method for a fishing transport vessel according to claim 1, characterized in that: The performing of image recognition based on the image information in the product information transported by the fishing transport vessel to determine the category of the product transported by the fishing transport vessel includes: Identifying image information in the product information transported by the fishing transport vessel, wherein each frame of image containing the product is extracted to obtain at least two frames of product image information; All product image information is gray-scale transformed, and pixel points of the same gray-scale value in the gray-scale image obtained by the gray-scale transformation are connected, wherein the connection is interpolated by a linear interpolation method to obtain the texture features of the product; Performing edge detection on the product image information to obtain the contour edge of the product in the product image information, and converting the image outside the contour edge of the product into white to obtain the contour feature of the product; Clustering the three components of R, G, and B of all pixels within the contour edge of the product, respectively, and calculating the square differences of all clustering clusters obtained by clustering, and using the calculated square differences as the color features of the product; The products are identified and classified based on the texture features, contour features and color features of the products to determine the category of each product.

4. The unattended refrigeration control method for a fishing transport vessel according to claim 1, characterized in that: The product category and the usage information of each refrigerated tank structure are sent to the transport simulation model of the transport ship for refrigerated tank allocation simulation, including: Initializing the product category and the usage information of each refrigerated compartment structure, and using the initialized product category and the usage information of the refrigerated compartment structure as particle swarm parameters; The fitness of each particle in the particle group is calculated based on the preset fitness function to obtain the individual optimal position and the global optimal position of the particle, where the fitness function of the particle; Based on the particle update speed formula and the particle update position formula in the particle swarm optimization algorithm, the speed and position of all particles are continuously updated until the particle swarm optimization algorithm reaches a preset number of iterations, and the parameter information after the iteration is obtained, and the parameter information after the iteration is the refrigerated compartment with the highest category fitness value of the product; The refrigerated compartments are allocated according to the iterated parameter information to obtain an allocation result for each refrigerated compartment.

5. The unattended refrigeration control method for a fishing transport vessel according to claim 1, characterized in that: Perform product analysis based on the preset historical product information according to its corresponding transportation time and refrigeration temperature to determine the quality change information of products at different transportation times and different refrigeration temperatures, including: Perform image recognition on preset historical product information to obtain feature information of products at multiple transportation times and multiple refrigeration temperatures, wherein the feature information of the products includes product texture features, product contour features, and product color features; The characteristic information of all products is compared in pairs to obtain the characteristic change data of each product at different transportation time and different refrigeration temperature; Based on the preset vibration detection strategy, vibration detection is performed on products at different transportation times and different refrigeration temperatures to obtain the quality variation of all products; The characteristic change data and quality change degree of each product are weighted according to the minimum discrimination principle, and the quality change scores of products at different transportation times and different refrigeration temperatures are calculated.

6. The unattended refrigeration control method for a fishing transport vessel according to claim 5, characterized in that: Vibration detection is performed on products at different transportation times and different refrigeration temperatures based on preset vibration detection strategies, including: The signal information generated by the vibration detection strategy is fitted using the least squares method to obtain the amplitude signals and phase signals of each order of harmonics in the initial state and at any vibration time. The amplitude difference between the harmonic amplitude signal in the initial state and the amplitude difference between each order of harmonic amplitude signals in each vibration time is calculated based on a preset amplitude difference calculation formula, and the phase difference between the harmonic phase signal in the initial state and the phase difference between each order of harmonic phase signals in each vibration time is calculated based on a preset phase difference calculation formula; The amplitude difference and the phase difference are compared with preset thresholds respectively, and based on the comparison results obtained by comparison, the quality change degree of the product at different transportation times and different refrigeration temperatures is judged.

7. The unattended refrigeration control method for a fishing transport vessel according to claim 5, characterized in that: The characteristic change data and quality change degree of each product are weighted according to the minimum discrimination principle, including: Establishing an objective function according to the minimum discriminant information principle, solving the objective function to construct a Lagrangian function; Substituting the characteristic change data and quality change degree of each product into the Lagrangian function for solution to obtain the combined weight of the characteristic change data and quality change degree of each product; The characteristic change data and quality change degree of each product are scored according to the combined weights to obtain the quality change scores of the products at different transportation times and different refrigeration temperatures.

8. The unattended refrigeration control method for a fishing transport vessel according to claim 1, characterized in that: The transport refrigerated compartment information corresponding to each category of products and the product quality change information are sent to a preset multi-objective optimization model to predict the optimal refrigeration temperature, including: The transportation time, refrigeration temperature and refrigerated compartment area of ​​each category of products are taken as decision variables; The refrigerated compartment cost and quality variation degree are calculated based on the transportation refrigerated compartment information corresponding to each category of products and the product quality variation information, and a target function set is obtained by setting a specific cost function and quality variation target; According to the preset product transportation rules, constraints are formulated, wherein the constraints include refrigerated compartment storage restrictions and transportation time windows; According to the objective function set and the constraint conditions, a multi-objective evolutionary algorithm is used to perform genetic operations on the decision variable representation to obtain an optimized solution set; Evaluation and screening are performed based on the set of optimized solutions. By comparing the performance of each solution in two dimensions, namely, refrigerated compartment cost and quality variability, the optimal solution is screened out using Pareto front analysis. The optimal solution is the optimal real-time refrigeration temperature of each transport refrigerated compartment.

9. An unattended refrigeration control system for a fishing transport vessel, characterized in that: include: An acquisition unit, used to acquire the refrigerated tank structure information of the fishery transport vessel, the use information of each refrigerated tank structure and the product information transported by the fishery transport vessel; A first processing unit is used to construct a three-dimensional space model of the fishery transport ship based on the structural information of the refrigerated tank of the fishery transport ship, and to perform product transportation simulation based on the three-dimensional space model to obtain a transportation simulation model of the transport ship; The second processing unit is used to perform image recognition based on the image information in the product information transported by the fishery transport ship, determine the category of the product transported by the fishery transport ship, and send the category of the product and the use information of each refrigerated tank structure to the transport simulation model of the transport ship to perform refrigerated tank allocation simulation, so as to obtain the transport refrigerated tank information corresponding to each category of the product; The third processing unit is used to analyze the preset historical product information according to its corresponding transportation time and refrigeration temperature, and determine the quality change information of the products at different transportation times and different refrigeration temperatures; The fourth processing unit is used to send the transport refrigerated compartment information corresponding to each category of products and the product quality change information to a preset multi-objective optimization model to predict the optimal refrigeration temperature, and to predict the optimal refrigeration temperature in real time and adjust the refrigeration equipment in real time according to the optimal refrigeration temperature for refrigeration.

10. The unattended refrigeration control system for a fishing transport vessel according to claim 9, characterized in that: The first processing unit comprises: The first modeling subunit is used to convert the format of the refrigerated tank structure data and the refrigeration equipment pipeline data in the refrigerated tank structure information of the fishing transport ship, and perform XOY plane frame selection processing on the converted refrigerated tank structure data and refrigeration equipment pipeline data to obtain the framed refrigerated tank structure diagram and refrigeration equipment pipeline structure diagram; The second modeling subunit is used to send the preset discrete elevation data of the refrigerated tank structure of the fishing transport ship, the selected refrigerated tank structure diagram and the refrigeration equipment pipeline structure diagram to the three-dimensional modeling software for processing, so as to obtain the three-dimensional model of the refrigerated tank structure and the refrigeration equipment pipeline of the fishing transport ship; The third modeling subunit is used to discretize the three-dimensional model of the refrigerated tank structure and the refrigeration equipment pipeline of the fishing transport ship to obtain at least one refrigerated tank structure unit, and perform linear interpolation processing on each of the refrigerated tank structure units based on a linear interpolation method to obtain a three-dimensional model with the refrigerated tank as a structure unit; The fourth modeling subunit is used to send the historical product information of the preset fishing transport ship to the three-dimensional modeling software for transport simulation to obtain the transport simulation model of the transport ship.

Images