A complete set of storage and transportation methods and systems for the entire grain process

Abstract

The present invention relates to the field of grain storage and transportation, and particularly to a complete set of grain storage and transportation methods and systems for the entire process. The method includes the following steps: obtaining information on the type, quality, and weight of the grain to be warehoused; adjusting the warehousing process and equipment parameters of the grain to be warehoused; classifying and removing impurities from the grain to be warehoused; regulating the humidity of the grain to be warehoused; implementing the grain warehousing process; continuously monitoring the storage environment and the warehoused grain; adjusting the storage environment parameters; and planning the optimal outbound unit and transportation route by constructing a deep learning outbound unit planning model and a transportation route planning model. The present invention optimizes the configuration of the warehousing process and equipment parameters through an intelligent adjustment mechanism; adopts the optimal monitoring and regulation technology to ensure the optimal storage environment and guarantee the grain quality; and effectively reduces the losses of grain and equipment by constructing a deep learning outbound unit planning model and a transportation route planning model, realizing the complete set of efficient storage and transportation of grain for the entire process.

Description

Technical Field

[0001] The present invention relates to the field of grain storage and transportation, and specifically relates to a complete set of grain storage and transportation methods and systems for the entire process. Background Art

[0002] In the grain storage and transportation industry, ensuring the safety of grain, improving storage and transportation efficiency, and maintaining its original quality have always been the key concerns of the industry. However, the existing complete set of grain storage and transportation methods for the entire process still have many deficiencies in practical applications, which are specifically manifested in the following aspects:

[0003] (1) Lack of intelligent and personalized adjustment capabilities. Traditional storage and transportation methods often operate based on fixed processes and parameters, and it is difficult to make flexible adjustments according to differences in grain types, qualities, and weights. This results in unnecessary losses for different qualities of grain during the processes of warehousing, processing, and storage, such as excessive drying, residue of impurities, etc., affecting the final quality and nutritional value of the grain. In addition, the fixed operation mode also cannot fully utilize the performance potential of existing equipment, leading to low storage and transportation efficiency.

[0004] (2) Imprecise regulation of the storage environment. Most of the existing means for regulating the storage environment rely on manual experience and simple sensor data, lacking real-time and precise environmental monitoring and regulation mechanisms. This not only makes it difficult to keep key parameters such as temperature, humidity, and gas concentration in the storage environment within the optimal range, but also may cause problems such as mildew and insect pests in the grain due to environmental changes, seriously affecting the storage quality and safety of the grain.

[0005] (3) Lack of intelligence and efficiency in the outbound planning. In the grain outbound link, traditional planning methods often rely on manual experience and simple path planning algorithms, and it is difficult to achieve the optimal planning of outbound units and transportation paths. This not only increases the complexity and time cost of outbound operations, but also may lead to low transportation efficiency and increased costs due to unreasonable paths. At the same time, the lack of intelligent outbound planning also makes it difficult to effectively control the losses and wastes during the grain outbound process.

[0006] Currently, there are not many research works on the complete set of grain storage and transportation methods for the entire process, and there is no specific systematic, efficient, and quality-oriented complete set of grain storage and transportation methods for the entire process. Summary of the Invention

[0007] Aiming at the defects in the prior art, the present invention provides a complete set of grain storage and transportation methods and systems for the entire process.

[0008] In a first aspect, a complete set of storage and transportation methods for the whole process of grains provided by the present invention includes the following steps: obtaining information on the types, qualities, and weights of grains to be stored in the warehouse; adjusting the storage process and equipment parameters of the grains to be stored in the warehouse according to the information to obtain an optimal adjustment result; performing grading and impurity removal on the grains to be stored in the warehouse through the optimal adjustment result to obtain an optimal treatment result; controlling the humidity of the grains to be stored in the warehouse based on the optimal treatment result to obtain an optimal control parameter; executing the grain storage process according to the optimal control parameter to obtain stored grains; obtaining a monitoring result by continuously monitoring the storage environment and the stored grains; adjusting the storage environment parameters according to the monitoring result to obtain an optimal adjustment result; planning an optimal storage unit and an optimal transportation path based on the optimal adjustment result by constructing a deep learning storage unit planning model and a transportation path planning model. By accurately collecting information on the types, qualities, and weights of grains to be stored in the warehouse, the present invention intelligently adjusts the storage process and equipment parameters to achieve precise grading of grains and efficient removal of impurities; by introducing a humidity control mechanism for grains to be stored in the warehouse and a storage environment adjustment mechanism, it is beneficial to maintain the quality of the complete set of storage and transportation for the whole process of grains and reduce storage losses; by constructing a deep learning storage unit planning model and an intelligent loading implementation model, it dynamically predicts and plans the optimal storage unit and transportation path, significantly improving the storage and transportation efficiency and the intelligent level.

[0009] Optionally, the adjusting the transportation process and equipment parameters of the grains to be stored in the warehouse according to the information to obtain an optimal adjustment result includes: constructing a grain storage process efficiency model and an equipment efficiency model according to the information; adjusting the storage process of the grains to be stored in the warehouse based on the grain storage process efficiency model to obtain an optimal adjustment result of the storage process; adjusting the equipment parameters based on the equipment efficiency model to obtain an optimal adjustment result of the equipment parameters. By constructing a grain storage process efficiency model, the present invention accurately predicts the efficiency performance under different storage processes, thereby intelligently adjusting the storage process to achieve process optimization and efficiency maximization; by constructing an equipment efficiency model, based on the equipment performance and grain characteristics, it dynamically adjusts the equipment parameters to ensure that the equipment operates in an optimal state, not only improving the equipment utilization rate but also significantly reducing energy consumption; through the optimal adjustment result, the dual optimization of the storage process and equipment parameters is realized, bringing great efficiency improvement and cost control capabilities to the grain storage and transportation industry.

[0010] Optionally, the grain storage process efficiency model satisfies the following expression:

[0011] ,

[0012] where, represents that the grain type is , the quality is and the weight is The effective efficiency of the warehousing process at represents the maximum efficiency of the warehousing process when the grain type is ; represents the number of adjustable steps in the warehousing process when the grain type is ; represents the th step weight when the grain quality is and the weight is ; represents the efficiency of the th step when the grain type is ; represents the total efficiency of all steps when the grain type is ; The equipment efficiency model satisfies the following expression:

[0013] ,

[0014] where represents the equipment efficiency when the grain type is , the quality is and the weight is ; represents the optimal equipment efficiency when the grain type is ; represents the change in quality loss when the grain type is , the quality is and the weight is ; represents the gain factor when the grain type is ; represents the equipment parameter adjustment amount when the grain type is . The present invention accurately calculates the effective efficiency of the warehousing process through grain type, quality, and weight information, achieving the maximization of the warehousing process efficiency; by innovatively combining the change in quality loss with the equipment parameter adjustment amount, dynamically evaluating the equipment efficiency, ensuring that the equipment operates in the optimal state, effectively reducing the quality loss of grain during the warehousing process, and improving the overall storage and transportation quality; through a highly parameterized design, flexibly adapting to different grain types and storage and transportation requirements, providing strong customization and scalability for the grain storage and transportation industry, and promoting the development of this field towards a more efficient and intelligent direction.

[0015] Optionally, the step of grading and removing impurities from the grain to be warehoused according to the optimal adjustment result to obtain the optimal treatment result includes: when the effective efficiency of the warehousing process and the equipment efficiency are both maximized, using multi-layer vibration screening and magnetic separation technologies, combined with high-definition cameras and deep learning algorithms, to construct a grading accuracy model; grading the grain according to the grading accuracy model to obtain a grading result; based on the grading result, constructing an impurity removal rate model; accurately identifying and efficiently removing various impurities according to the impurity removal rate model; using the grading accuracy model and the impurity removal rate model to construct an overall effect evaluation model for grading and impurity removal; and obtaining the optimal treatment result according to the overall effect evaluation model. By combining multi-layer vibration screening and magnetic separation technologies, the present invention effectively improves the accuracy and efficiency of grain grading and impurity removal. Especially when the effective efficiency of the warehousing process and the equipment efficiency reach the maximum, it can maximize the effectiveness, ensuring the high efficiency and accuracy of the treatment process; by introducing high-definition cameras and deep learning algorithms to construct a grading accuracy model, it realizes the intelligentization and automation of grain grading, significantly improves the grading accuracy, and reduces the interference of human factors; by constructing an impurity removal rate model, it accurately identifies and efficiently removes various impurities in the grain, improves the purity and quality of the grain, and ensures the quality and safety of the warehoused grain; by constructing an overall effect evaluation model for grading and impurity removal, it effectively improves the grain purity, guarantees the warehousing quality, and optimizes the overall effectiveness of the storage and transportation process.

[0016] Optionally, the step of regulating the humidity of the grain to be warehoused based on the optimal treatment result to obtain the optimal regulation parameters includes: based on the optimal treatment result, constructing an optimal regulation model for grain humidity; substituting the type of the grain to be warehoused, the initial humidity, and the target humidity into the expression satisfied by the optimal regulation model for grain humidity to obtain the optimal regulation objective function value; and determining the optimal regulation parameters through the optimal regulation objective function value, where the optimal regulation parameters include the optimal temperature and the optimal wind speed of the dryer. By constructing an optimal regulation model for grain humidity, the present invention realizes precise regulation for the characteristics, initial humidity, and target humidity requirements of different types of grains, avoiding the blindness and inefficiency of traditional regulation methods; by substituting the specific parameters of the grain to be warehoused into the model expression to obtain the optimal regulation objective function value, it not only improves the regulation accuracy but also realizes the personalization and customization of grain humidity regulation; by determining the optimal temperature and the optimal wind speed of the dryer through the optimal regulation objective function value, it ensures the high efficiency and energy saving of the regulation process. At the same time, it also guarantees that the humidity of the warehoused grain reaches the best state, providing strong support for the long-term storage and quality maintenance of the grain.

[0017] Optionally, the optimal regulation model for grain humidity satisfies the following expression:

[0018] ,

[0019] Among them, represents the objective function for optimal regulation of grain moisture, represents the type of grain, represents the initial moisture of the grain, represents the target moisture of the grain, represents the temperature of the dryer, represents the wind speed of the dryer, represents the energy consumption function, represents the grain state monitoring function, represents the time variable, represents the time when the drying process ends, represents the weight coefficient, represents the efficiency function of the drying process. Through constructing an optimal regulation model for grain moisture, the present invention realizes the comprehensive optimization of the grain moisture regulation process, significantly improves the accuracy and efficiency of regulation; by introducing the time variable and the time when the drying process ends, the regulation process can dynamically adapt to the change of grain moisture, ensuring the stability and reliability of the drying effect; this model realizes the flexible adjustment of the trade-off between energy consumption and drying efficiency, not only meets the requirements of grain moisture regulation, but also takes into account the efficient utilization of energy, demonstrating the innovation and practicality of the model in the field of grain storage management, and providing strong support for the sustainable development of the grain industry.

[0020] Optionally, the adjusting the storage environment parameters according to the monitoring results to obtain the optimal adjustment result includes: constructing an optimal adjustment model for storage environment parameters according to the monitoring results of the storage environment and the incoming grain; by adjusting the temperature, humidity and concentration in the storage environment, combining with the optimal adjustment model for storage environment parameters, obtaining the optimal adjustment objective function value; according to the optimal adjustment objective function value, determining the optimal temperature, optimal humidity and optimal concentration in the storage environment. By integrating the monitoring data of the storage environment and the incoming grain, the present invention constructs an optimal adjustment model for storage environment parameters, accurately reflecting the influence of the storage environment on the storage quality of grain, and providing a scientific basis for the adjustment of environmental parameters; by adjusting the temperature, humidity and concentration parameters in the environment, the refined control of the storage environment is realized, improving the safety and stability of grain storage; the environmental parameters determined according to the optimal adjustment objective function value not only meet the specific requirements of grain storage, but also realize the efficient utilization of energy and the sustainable development of the environment.

[0021] Optionally, the expression satisfied by the optimal adjustment model for storage environment parameters is as follows:

[0022] ,

[0023] Among them, represents the objective function for the optimal adjustment of warehouse environment parameters, represents the actual temperature of the warehouse environment, represents the actual humidity of the warehouse environment, represents the concentration of the actual warehouse environment, represents the type of incoming grain, represents the initial humidity of the grain when it is put into storage, represents the total energy consumption function of the warehouse environment, represents the inspection period of the warehouse environment, represents the efficiency function of the warehouse environment, represents the time variable, , represent weight coefficients. By introducing the time variable and the inspection period, the present invention realizes the dynamic monitoring and optimization of warehouse environment parameters, ensures that the environmental adjustment can respond in real time to the changes in the grain storage requirements, and improves the fineness and flexibility of warehouse management; by comprehensively considering the total energy consumption and efficiency of the warehouse environment, the optimal balance between energy consumption and efficiency is achieved, which not only guarantees the quality of grain storage, but also promotes energy conservation and environmental sustainable development; by considering the characteristics of different types of grain and the initial humidity, a personalized environmental parameter adjustment scheme is constructed, which improves the pertinence and effectiveness of the warehouse environment adjustment.

[0024] Optionally, based on the optimal adjustment result, by constructing a deep learning outbound unit planning model and a transportation path planning model, planning the optimal outbound unit and the optimal transportation path includes: based on the optimal adjustment result, constructing a deep learning outbound unit planning model; according to the deep learning outbound unit planning model, planning the optimal outbound unit; based on the optimal outbound unit, constructing an intelligent loading implementation model; according to the intelligent loading implementation model, quickly weighing and efficiently loading the grain; based on the optimal outbound unit, constructing a transportation path planning model; based on the transportation path planning model, using information such as grain type, weight, transportation cost, transportation starting point and ending point, planning the optimal transportation path. By constructing a deep learning outbound unit planning model, the present invention realizes the accurate prediction and planning of the warehouse grain outbound unit, improves the outbound efficiency and accuracy, and reduces the labor cost; by constructing an intelligent loading implementation model, the quick weighing and efficient loading of the grain are realized, further optimizing the outbound process and improving the logistics efficiency; by constructing a transportation path planning model and comprehensively considering information such as grain type, weight, transportation cost, transportation starting point and ending point, the optimal selection of the transportation path is realized, reducing the transportation cost and enhancing the safety and timeliness of grain transportation.

[0025] In a second aspect, a complete set of grain storage and transportation systems for the entire process provided by the present invention includes an input device, a processor, an output device, and a memory. The input device, the processor, the output device, and the memory are interconnected. Among them, the memory is used to store computer programs, and the computer programs include program instructions. The processor is configured to call the program instructions, and the system uses the above-mentioned complete set of grain storage and transportation methods for the entire process. The system realizes high-precision and high-efficiency grain grading and impurity removal by integrating multi-layer vibration screening, magnetic separation technology, high-definition cameras, and deep learning algorithms, providing high-quality guarantee for grain storage; by using the optimal adjustment model of warehouse environment parameters, combined with the deep learning outbound unit planning model and the intelligent loading implementation model, it realizes the intelligence and automation of grain outbound and transportation, not only greatly improving the storage and transportation efficiency, but also reducing energy consumption and costs; by constructing a path planning model and comprehensively considering various factors to plan the optimal transportation path, it ensures the safety, speed, and low cost of grain transportation, providing strong technical support for the sustainable development of the grain industry.

[0026] Compared with the prior art, the beneficial effects of the present invention include: by introducing an intelligent and personalized adjustment mechanism, flexible adjustment is carried out according to different types, qualities, and weights of grains to achieve the optimal inbound process and equipment parameter configuration; by adopting a creative real-time monitoring and control technology, it ensures that the warehouse environment parameters are always kept within the optimal range, effectively guaranteeing the storage quality and safety of grains; by constructing a deep learning outbound unit planning model and a transportation path planning model, it realizes the optimal planning of the outbound unit and the transportation path, improves the efficiency and accuracy of outbound operations, and effectively reduces grain and equipment losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a flowchart of the complete set of grain storage and transportation methods for the entire process of the embodiment of the present invention;

[0028] Figure 2 is a schematic structural diagram of the complete set of grain storage and transportation systems for the entire process of the embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0029] The specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described here are only for illustrative purposes and are not used to limit the present invention. In the following description, in order to provide a thorough understanding of the present invention, a large number of specific details are set forth. However, it is obvious to those of ordinary skill in the art that the present invention does not have to employ these specific details. In other instances, well-known circuits, software, or methods have not been described in detail to avoid obscuring the present invention.

[0030] Throughout the specification, references to "one embodiment", "an embodiment", "one example" or "an example" mean that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment of the present invention. Thus, the phrases "in one embodiment", "in an embodiment", "one example" or "an example" appearing throughout the specification do not necessarily all refer to the same embodiment or example. Additionally, the particular features, structures, or characteristics may be combined in any suitable combination and / or sub-combination in one or more embodiments or examples. Furthermore, those of ordinary skill in the art should understand that the diagrams provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0031] Please refer to Figure 1 , an embodiment of the present invention provides a complete set of methods for storing and transporting grain throughout the process, and the method includes the following steps:

[0032] S1. Obtain information on the type, quality, and weight of the grain to be stored in the warehouse.

[0033] In one embodiment, the information on the type of the grain to be stored in the warehouse is understood through the warehousing notice.

[0034] In another embodiment, according to the type and quantity of the grain, a reasonable sampling plan is formulated, and the sampling plan should specify the sampling quantity, sampling location, and sampling time.

[0035] Furthermore, according to the sampling plan, samples are drawn from the grain to be stored in the warehouse, and the samples should be representative and able to reflect the quality status of the entire set of grain.

[0036] Furthermore, the samples drawn are subjected to quality inspections, including appearance, impurity content, moisture content, and mildew condition.

[0037] Furthermore, the quality inspection information is recorded as the basis for subsequent evaluation and processing.

[0038] In yet another embodiment, a modern grain management system, such as an automatic weighing device for underground weighbridge, is used to accurately measure the grain to be stored in the warehouse to obtain the information on the weight of the grain to be stored in the warehouse.

[0039] S2. According to the information, adjust the warehousing process and equipment parameters of the grain to be stored in the warehouse to obtain an adjustment result.

[0040] Among them, S2 further includes the following steps:

[0041] S21. According to the information, construct a grain warehousing process efficiency model and an equipment efficiency model.

[0042] In one embodiment, first, the existing grain warehousing process is comprehensively sorted out to identify the bottleneck links and redundant steps therein.

[0043] Furthermore, by removing bottleneck links and redundant steps, the grain warehousing process is optimized, and the grain storage area is effectively allocated, thereby achieving high-efficiency grain warehousing. According to this idea, an efficiency model of the grain warehousing process is constructed, and the efficiency model of the grain warehousing process satisfies the following expression:

[0044] ,

[0045] wherein, represents the effective efficiency of the warehousing process when the grain type is , the quality is and the weight is ; represents the maximum efficiency of the warehousing process when the grain type is ; represents the number of adjustable steps in the warehousing process when the grain type is ; represents the weight of the th step when the grain quality is and the weight is ; represents the efficiency of the th step when the grain type is ; represents the sum of the efficiencies of all steps when the grain type is .

[0046] In another embodiment, an equipment efficiency model is constructed to solve the problem of target optimization of equipment parameters. The equipment parameters include, but are not limited to, the conveying speed, which will have a certain impact on the quality of the grain. The equipment efficiency model satisfies the following expression:

[0047] ,

[0048] wherein, represents the equipment efficiency when the grain type is , the quality is and the weight is ; represents the optimal equipment efficiency when the grain type is ; represents the change in quality loss when the grain type is , the quality is and the weight is ; represents the gain factor when the grain type is ; represents the adjustment amount of the equipment parameters when the grain type is .

[0049] S22. Adjust the grain receiving process for the to-be-received grain based on the grain receiving process efficiency model and obtain the optimal adjustment result.

[0050] In one embodiment, based on the grain receiving process efficiency model constructed in step S21, by adjusting the grain receiving process for the to-be-received grain, the maximum effective efficiency of the grain receiving process is obtained, thereby determining the optimal receiving steps.

[0051] Specifically, first, set the maximum effective target efficiency , which is obtained by training the grain receiving process efficiency model using historical data.

[0052] Further, based on the information on the type, quality, and weight of the to-be-received grain obtained in step S1.

[0053] Further, adjust the receiving steps and use the grain receiving process efficiency model to solve for the effective efficiency of the receiving process .

[0054] Further, when the condition is met, that is, when the difference between the effective efficiency of the receiving process and the maximum effective target efficiency is minimized, the corresponding receiving steps are the optimal receiving steps and also the optimal adjustment result of the receiving steps.

[0055] S23. Adjust the equipment parameters based on the equipment efficiency model and obtain the optimal adjustment result.

[0056] In one embodiment, based on the equipment efficiency model constructed in step S21, by adjusting the equipment parameters, the maximum efficiency of the equipment is obtained, thereby determining the optimal equipment parameters.

[0057] Specifically, first, set the maximum target efficiency of the equipment , which is obtained by training the equipment efficiency model using historical data.

[0058] Further, based on the information on the type, quality, and weight of the to-be-received grain obtained in step S1, adjust the equipment parameters, and the change amount of the adjustment is , and use the equipment efficiency model to solve for the equipment efficiency .

[0059] Further, when the condition is met, that is, when the difference between the maximum target efficiency and the equipment efficiency is minimized, the corresponding equipment parameters are the optimal equipment parameters and also the optimal adjustment result of the equipment parameters.

[0060] S3. Through the adjustment result, perform grading and impurity removal processing on the to-be-received grain to obtain the optimal processing result.

[0061] Among them, S3 further includes the following steps:

[0062] S31. Classify the grains to be warehoused according to the adjustment result.

[0063] In one embodiment, when both the effective efficiency of the warehousing process and the equipment efficiency are maximized, the multi-layer vibration screening and magnetic separation technology is used, combined with high-definition cameras and deep learning algorithms, to classify the grains to be warehoused and obtain the classification result.

[0064] Specifically, the grains to be warehoused first enter the multi-layer vibration screening machine, and each layer of sieve mesh is screened according to the preset particle size range; during the screening process, by adjusting the vibration frequency and sieve mesh aperture, it is ensured that grains of different particle sizes can be effectively separated; after each layer of screening, the grains meeting the particle size range are collected and enter the next processing stage.

[0065] Furthermore, the grains pass through the magnetic separation device to remove metal impurities therein; the magnetic separation device uses a strong permanent magnet drum to ensure that metal impurities are effectively adsorbed and removed.

[0066] Furthermore, after the grains are screened and magnetically separated, they enter the shooting area of the high-definition camera; the high-definition camera captures the image data of the grain particles and transmits it to the deep learning algorithm system for analysis; the deep learning algorithm automatically classifies the grains according to the color, shape and texture characteristics of the grains; the classification result is used to guide the subsequent grain storage or packaging process to ensure that each batch of grains can be accurately classified.

[0067] Furthermore, a classification accuracy model is constructed, and according to the feedback of the classification accuracy, the parameters and training data of the deep learning algorithm are adjusted to improve the classification accuracy; the classification accuracy model satisfies the following expression:

[0068] ,

[0069] Among them, represents the classification accuracy, represents the weight of correctly classified grains, represents the total weight of classified grains. The weight of correctly classified grains is the weight of grains correctly identified by the high-definition camera and the deep learning algorithm, and the total weight of classified grains is the total weight of all grains entering the classification process.

[0070] Furthermore, the maximum warehousing efficiency and the maximum equipment efficiency are obtained through monitoring, so as to realize the parameter setting of the multi-layer vibration screening and magnetic separation device and improve the overall processing efficiency.

[0071] S32. Remove impurities from the grains to be warehoused based on the classification result.

[0072] In one embodiment, based on the hierarchical processing results, various impurities are accurately identified and efficiently removed to obtain the optimal processing results.

[0073] Specifically, during the multi-layer vibration screening process, grains and impurities of different particle sizes are separated according to a preset particle size range. Larger impurities, such as stones and straws, are removed during the preliminary screening. The magnetic separation device removes metal impurities in the grains, such as iron nails and iron wires.

[0074] Furthermore, a high-definition camera captures the image data of the grain particles, and a deep learning algorithm analyzes the images to identify impurities that do not match the grain shape and color characteristics. According to the recognition results, mechanical removal devices, such as pneumatic nozzles and robotic arms, precisely separate the impurities from the grains.

[0075] Furthermore, air separation uses the difference in wind resistance of different substances to blow out light impurities, such as dust and wheat husks, from the grains. Specific gravity separation separates impurities with different densities from the grains according to the density difference of substances through the action of vibration or air flow.

[0076] Furthermore, for particularly important grain batches or cases where it is difficult to remove impurities, manual re-inspection is carried out to ensure that the impurities are completely removed.

[0077] Furthermore, an impurity removal rate model is constructed, and according to the feedback of the impurity removal results, the parameters and strategies of the impurity removal method are continuously adjusted. The impurity removal rate model satisfies the following expression:

[0078] ,

[0079] where, represents the impurity removal rate, represents the total amount of removed impurities, represents the impurity content in the initial total amount of grains. The total amount of removed impurities is the weight of the impurities successfully removed through the impurity removal process, and the impurity content in the initial total amount of grains is the percentage of impurities in the grains before entering the hierarchical processing.

[0080] S33. According to the hierarchical accuracy rate model and the impurity removal rate model, obtain the optimal processing results.

[0081] In one embodiment, using the hierarchical accuracy rate model and the impurity removal rate model, an effect evaluation model for hierarchical processing and impurity removal processing is constructed, and the effect evaluation model satisfies the following expression:

[0082] ,

[0083] where, represents the evaluation index of the processing effect, represents the classification accuracy rate, represents the impurity removal rate, represents the total weight of pure grains, represents the total weight of the grains to be stored in the warehouse. The total weight of pure grains is the weight of the grains that meet the quality standards after classification and impurity removal. The evaluation index comprehensively considers the classification accuracy, impurity removal efficiency, and the yield of pure grains.

[0084] Furthermore, set the threshold of the evaluation index , where satisfies the following conditions:

[0085]

[0086] When , the classification and impurity removal treatments do not meet the standards;

[0087] When , the classification and impurity removal treatments meet the standards.

[0088] Furthermore, in the case where the classification and impurity removal treatments meet the standards, take the treatment result closest to 1 as the optimal treatment result.

[0089] S4. Based on the optimal treatment result, regulate the humidity of the grains to be stored in the warehouse to obtain the optimal regulation parameters.

[0090] Among them, S4 further includes the following steps:

[0091] S41. Based on the optimal treatment result, construct an optimal regulation model for grain humidity;

[0092] In one embodiment, based on step S3, after the optimal treatment of classifying and removing impurities from the grains to be stored in the warehouse, an optimal regulation model for grain humidity is constructed. The optimal regulation model for grain humidity satisfies the following expression:

[0093] ,

[0094] where represents the objective function of the optimal regulation of grain humidity, represents the type of grain, represents the initial humidity of the grain, represents the target humidity of the grain, represents the temperature of the dryer, represents the wind speed of the dryer, represents the energy consumption function, represents the grain status monitoring function, represents the time variable, Indicates the time when the drying process ends. Indicates the weight coefficient. Indicates the efficiency function of the drying process.

[0095] S42. Substitute the type of grain to be stored in the warehouse, the initial humidity, and the target humidity into the expression satisfied by the optimal grain humidity regulation model to obtain the optimal regulation target value.

[0096] In one embodiment, using MATLAB numerical software, substitute the type of grain to be stored in the warehouse, the initial humidity, and the target humidity into the expression satisfied by the optimal grain humidity regulation model for solution to obtain the optimal regulation target value.

[0097] S43. Determine the optimal regulation parameters through the optimal regulation target value, where the optimal regulation parameters include the optimal temperature and the optimal wind speed of the dryer.

[0098] In one embodiment, based on the optimal regulation target value obtained in step S42 and combined with the optimal grain humidity regulation model constructed in step S41, inversely deduce the optimal regulation parameters, where the optimal regulation parameters include the optimal temperature and the optimal wind speed of the dryer.

[0099] S5. Execute the grain storage process according to the optimal regulation parameters to obtain the stored grain.

[0100] In one embodiment, according to the optimal regulation parameters obtained in step S43 and combined with the optimal adjustment result obtained in step S2, execute the grain storage process on the grain.

[0101] Specifically, first, prepare storage containers, such as grain bags, for complete set storage; the storage containers are clean, without damage, and meet the storage requirements, and a moisture-proof layer is laid inside to prevent the grain from getting damp.

[0102] Further, put the regulated grain into the warehouse in sequence according to the type and batch, and allocate the storage area; during the storage process, pay attention to maintaining the looseness of the grain to avoid uneven humidity caused by compaction.

[0103] Further, record the storage time, quantity, and humidity information of each batch of grain; paste an identification plate on the storage container to indicate the grain type, batch, and storage time information.

[0104] Further, obtain the complete set of stored grain.

[0105] S6. Obtain the monitoring result by monitoring the storage environment and the stored grain.

[0106] In one embodiment, first, set the parameters of the monitoring equipment, such as the sampling frequency and the alarm threshold, to ensure that the monitoring parameters can accurately reflect the actual situation of the storage environment and the grain.

[0107] Further, start the monitoring system, begin to collect and transmit monitoring data in real time, ensure the normal operation of the monitoring equipment, and record and process the monitoring data in a timely manner; the monitoring data includes the temperature, humidity, and concentration data of the storage environment.

[0108] Further, analyze and process the collected monitoring data, extract useful information, and judge whether the status of the storage environment and the grain is normal.

[0109] S7. According to the monitoring results, adjust the storage environment parameters to obtain the optimal adjustment result.

[0110] Among them, S7 further includes the following steps:

[0111] S71. Based on the monitoring results of the storage environment and the incoming grain, construct an optimal adjustment model for the storage environment parameters.

[0112] In one embodiment, based on the monitoring results of the storage environment and the incoming grain, combined with the environmental target requirements most suitable for grain storage, construct an optimal adjustment model for the storage environment parameters. The expression satisfied by the optimal adjustment model for the storage environment parameters is as follows:

[0113] ,

[0114] Among them, represents the objective function for the optimal adjustment of the storage environment parameters, represents the actual temperature of the storage environment, represents the actual humidity of the storage environment, represents the concentration of the storage environment, represents the type of incoming grain, represents the initial humidity when the grain is put into storage, represents the total energy consumption function of the storage environment, represents the inspection period of the storage environment, represents the efficiency function of the storage environment, represents the time variable, 、 represent the weight coefficients.

[0115] S72. By adjusting the temperature, humidity, and concentration in the storage environment, combined with the optimal adjustment model for the storage environment parameters, obtain the optimal adjustment objective function value.

[0116] In one embodiment, according to the scale and adjustment requirements of the storage environment, select appropriate temperature, humidity, and concentration adjustment equipment.

[0117] Specifically, devices such as air conditioners, dehumidifiers, humidifiers, and generators are used to adjust the parameters of the storage environment.

[0118] Furthermore, the adjustment devices are reasonably arranged in the storage environment to ensure that the parameters of the storage environment can be adjusted evenly and effectively. Among them, the operating noise and energy consumption factors of the devices are fully considered to optimize the device layout plan.

[0119] Furthermore, according to the optimal adjustment model and the target value, the parameters of the adjustment devices are set, including setting the control range of temperature and humidity, and the replenishment or emission rate of the concentration.

[0120] Furthermore, the adjustment devices are started to start adjusting the temperature, humidity, and concentration parameters in the storage environment, and the operating status of the devices is monitored to ensure that the devices operate normally and achieve the expected effect. During the adjustment process, when the minimum optimization condition of the optimal adjustment model of the storage environment parameters is met, the optimal adjustment objective function value is obtained. It should be noted that the optimal adjustment objective function value refers to the objective function in the optimal adjustment model of the storage environment parameters constructed in step S71 value.

[0121] S73. According to the optimal adjustment objective function value, determine the optimal temperature, optimal humidity, and optimal concentration in the storage environment.

[0122] In one embodiment, during the process of adjusting the storage environment parameters, the adjusted temperature, humidity, and concentration corresponding to the optimal adjustment objective function value are determined as the optimal temperature, optimal humidity, and optimal concentration in the storage environment.

[0123] S8. Based on the optimal adjustment result, by constructing a deep learning outbound unit planning model and a transportation path planning model, plan the optimal outbound unit and the optimal transportation path.

[0124] Among them, S8 further includes the following steps:

[0125] S81. Based on the optimal adjustment result, use the deep learning outbound unit planning algorithm to plan the optimal outbound unit.

[0126] In one embodiment, first, obtain the grain location, inventory, warehouse layout diagram, aisle width, and obstacle location information in the warehouse management system.

[0127] Furthermore, convert the warehouse layout diagram into a format suitable for processing by the deep learning model, and perform normalization and feature engineering processing on other data.

[0128] Furthermore, according to the characteristics of the warehouse layout and path planning problems, a convolutional neural network is selected to process image data.

[0129] Furthermore, a deep learning outbound unit planning model is constructed.

[0130] Specifically, the model architecture is designed, including an input layer, a hidden layer, and an output layer. The input layer receives the preprocessed inventory, warehouse layout, and grain position information; the hidden layer extracts features through a multi-layer neural network; the output layer outputs the position of the optimal outbound unit.

[0131] Furthermore, for the input layer, assume the size of the warehouse layout map is , and the grain position information is represented as a two-dimensional coordinate . Among them, represents the width, represents the height.

[0132] Furthermore, for the hidden layer, it includes a convolutional layer, a pooling layer, and a fully connected layer.

[0133] Specifically, the hidden layer is used to extract the local features of the warehouse layout map and is designed as multiple convolutional layers, each using different convolutional kernel sizes and numbers. The expression of the convolutional operation is as follows:

[0134]

[0135] Among them, represents the result of the convolutional operation, represents the input, represents the convolutional kernel weight, represents the bias term, represents the activation function.

[0136] The pooling layer is used to reduce the dimension of the feature map, reduce the computational amount, and retain important features at the same time.

[0137] The fully connected layer flattens the output of the convolutional layer or the pooling layer and then performs feature fusion and classification through the fully connected layer. The expression of the fully connected operation is as follows:

[0138]

[0139] Among them, represents the result of the fully connected operation, represents the weight matrix, represents the output of the hidden layer, represents the activation function, represents the bias term.

[0140] Furthermore, for the output layer, with a two-dimensional coordinate Indicates the location of the optimal outbound unit. To ensure that the output is within the boundaries of the warehouse, the sigmoid function is used to map the output to the interval (0, 1), and then multiplied by the size of the warehouse.

[0141] Furthermore, historical data is used as the training set, and the model parameters are adjusted through the backpropagation algorithm to enable the model to accurately predict the optimal outbound unit.

[0142] Furthermore, the latest inventory quantity, grain location, and warehouse layout information are input into the trained deep learning outbound unit planning model. Based on the input information, the model predicts the optimal outbound unit location.

[0143] S82. Based on the optimal outbound unit, intelligent loading technology is used to quickly weigh and efficiently load the grain.

[0144] In one embodiment, based on the optimal outbound unit determined in step S81, intelligent loading technology is used to quickly weigh and efficiently load the grain.

[0145] Specifically, a grasping device is installed above the location of the optimal outbound unit, and an appropriate grasping method is selected according to the type and shape of the grain.

[0146] Furthermore, a high-precision weighing sensor is installed below the grasping device. When the grasping device touches the grain and starts to lift, the weighing sensor will record the weight of the grain in real time.

[0147] Furthermore, by calculating the difference of the weighing sensor before and after grasping, the accurate weight of the grasped grain is obtained.

[0148] Furthermore, the grasped grain is quickly loaded into the transportation equipment.

[0149] Furthermore, during the loading process, barcodes and RFID technology are used to identify and track the grain to ensure that the source, weight, and destination of each batch of grain are clearly traceable. At the same time, the weighing results and loading information are recorded in the database in real time for subsequent data analysis and report generation.

[0150] Furthermore, an intelligent loading implementation model is constructed, and the intelligent loading implementation model is used to judge the situation of grain loading. The intelligent loading implementation model satisfies the following expression:

[0151]

[0152] where, represents the implementation result, represents the implementation function, represents the location of the optimal outbound unit, represents the total weight of the loaded grain, Indicates the type and status of the transportation equipment, and indicates the loading time. The optimal outbound unit location refers to the two-dimensional coordinates mentioned in step S81 . The types of the transportation equipment include AGV carts and robotic arms, and the status of the transportation equipment includes the current position, speed, and load capacity. The specific implementation details of this implementation model are as follows: At the optimal outbound unit location , by judging the type and status of the transportation equipment , the transportation equipment is reasonably allocated. When the loading time is , the grain with a total weight of is loaded.

[0153] S83. Based on the optimal outbound unit, plan the optimal transportation path according to the grain type, weight, transportation cost, starting point, and ending point information.

[0154] In one embodiment, first, according to the grain type, weight, transportation starting point, and ending point information, a transportation path planning model is constructed. The transportation path planning model satisfies the following expression:

[0155] ,

[0156] where, represents the objective function value, also called the comprehensive transportation cost per unit weight, represents the unit cost of the th type of grain, represents the weight of the th type of grain, represents the total weight of all grains, represents the set of transportation paths from the starting point to the ending point, represents the weight of the th transportation path.

[0157] Furthermore, using the transportation path planning model, an optimal transportation path from the warehouse to the destination is found. This path minimizes the comprehensive transportation cost per unit weight after considering factors such as grain type, weight, and transportation cost.

[0158] Please refer to Figure 2 , Figure 2 , which is a schematic structural diagram of the complete set of grain storage and transportation systems in the embodiments of the present invention. The system includes an input device, a processor, an output device, and a memory. The input device, the processor, the output device, and the memory are interconnected. Among them, the memory is used to store computer programs. The computer programs include program instructions. The processor is configured to call the program instructions. The system uses the described method for a complete set of grain storage and transportation processes.

[0159] In this embodiment, the input device includes a collection module and an input module;

[0160] Specifically, the collection module employs a variety of instruments, including a temperature monitor, a humidity monitor, and a gas concentration monitor, for real-time acquisition of the temperature, humidity, and concentration data of the warehouse environment; the input module includes a display screen for inputting the storage and transportation information of the grain, including information on the type, quality, and weight of the grain.

[0161] The processor, being the core of the system, includes a calculation module and an analysis module;

[0162] Specifically, the calculation module incorporates a variety of calculation models, including an effect evaluation model for grading and impurity removal processing, a grain warehousing process efficiency model, a device efficiency model, an optimal grain humidity regulation model, an optimal storage environment parameter adjustment model, a deep learning outbound unit planning model, an intelligent loading implementation model, and a transportation route planning model; the analysis module is used to analyze the situation of grain inbound, storage, and outbound.

[0163] The output device includes a display screen for displaying the processing results of the processor and the actual situation of the entire process of grain storage and transportation.

[0164] The memory uses a high-speed solid-state drive, which features fast read and write speeds, large capacity, and high reliability. It is mainly used to store the original data obtained by the input device and the acquisition device, as well as the result data processed by the processor, and can meet the requirements of large data volume storage.

[0165] In summary, a method for the entire process of grain storage and transportation provided by the present invention, by utilizing an intelligent adjustment mechanism and processing measures, optimally configures the warehousing process and equipment parameters according to different types, qualities, and weights of grains, realizing precise grading of grains and efficient removal of impurities; by adopting a creative real-time monitoring and control technology, ensuring that the storage environment parameters are always maintained within the optimal range, effectively guaranteeing the storage quality and safety of grains; by constructing a deep learning outbound unit planning model and a transportation route planning model, achieving optimal planning of the outbound unit and transportation route, improving the efficiency and accuracy of outbound operations, and effectively reducing grain and equipment losses.

[0166] A complete set of grain storage and transportation system provided by the present invention integrates multi-layer vibration screening, magnetic separation technology, high-definition cameras and deep learning algorithms, achieving high precision and high efficiency in grain grading and impurity removal, providing high-quality guarantee for grain storage; by using the optimal adjustment model of warehouse environment parameters, combined with the deep learning outbound unit planning model and the intelligent loading implementation model, it realizes the intelligence and automation of grain outbound and transportation, not only greatly improving the storage and transportation efficiency, but also reducing energy consumption and costs; by planning the optimal transportation path, it ensures the safety, speed and low cost of grain transportation, providing strong technical support for the sustainable development of the grain industry.

[0167] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and the description of the present invention.

Claims

1. A complete set of grain storage and transportation method, characterized in that: The method comprises the following steps: Obtain information on the type, quality and weight of grain to be stored; According to the information, the storage process and equipment parameters of the grain to be stored are adjusted to obtain the optimal adjustment result; Based on the optimal adjustment result, the grain to be stored is graded and impurities are removed to obtain the optimal processing result; Based on the optimal processing result, the humidity of the grain to be stored is adjusted to obtain the optimal adjustment parameters; According to the optimal control parameters, the grain storage process is executed to obtain the stored grain; By continuously monitoring the storage environment and the stored grain, monitoring results are obtained; According to the monitoring results, adjust the storage environment parameters to obtain the optimal adjustment results; Based on the optimal adjustment result, the optimal outbound unit and the optimal transportation route are planned by constructing a deep learning outbound unit planning model and a transportation route planning model; The step of adjusting the storage process and equipment parameters of the grain to be stored according to the information to obtain the optimal adjustment result includes: constructing a grain storage process efficiency model and an equipment efficiency model according to the information; adjusting the storage process of the grain to be stored based on the grain storage process efficiency model to obtain the optimal adjustment result of the storage process; adjusting equipment parameters based on the equipment efficiency model to obtain the optimal adjustment result of the equipment parameters; the grain storage process efficiency model satisfies the following expression: in, Indicates that the food type is , quality is and weight is Effective efficiency of the warehousing process, Indicates that the food type is Maximum efficiency of the warehousing process at the time Indicates that the food type is The number of steps in the warehousing process can be adjusted. Indicates Steps in food quality and weight is The weight of Indicates that the food type is The The efficiency of each step, Indicates that the food type is The equipment efficiency model satisfies the following expression: in, Indicates that the food type is , quality is and weight is Equipment efficiency at Indicates that the food type is Optimal equipment efficiency at the time of Indicates that the food type is , quality is and weight is The change in quality loss when Indicates that the food type is The gain factor when Indicates that the food type is The amount of equipment parameter adjustment when The method of grading and removing impurities from the grain to be stored by the optimal adjustment result to obtain the optimal processing result includes: when the effective efficiency of the storage process and the equipment efficiency are both at the maximum, using multi-layer vibration screening and magnetic separation technology, combined with high-definition cameras and deep learning algorithms, to build a grading accuracy model; grading the grain according to the grading accuracy model to obtain grading results; building an impurity removal rate model based on the grading results; accurately identifying and efficiently removing various types of impurities according to the impurity removal rate model; building an overall effect evaluation model for grading and impurity removal using the grading accuracy model and the impurity removal rate model; and obtaining the optimal processing result through the overall effect evaluation model; The step of adjusting the humidity of the grain to be stored based on the optimal processing result to obtain the optimal control parameters includes: constructing an optimal control model for grain humidity based on the optimal processing result; substituting the type of grain to be stored, the initial humidity and the target humidity into the expression satisfied by the optimal control model for grain humidity to obtain the optimal control objective function value; determining the optimal control parameters through the optimal control objective function value, wherein the optimal control parameters include the optimal temperature and the optimal wind speed of the dryer, and the optimal control model for grain humidity satisfies the following expression: in, represents the objective function for optimal control of grain humidity, Indicates the type of food. Indicates the initial moisture content of grain. Indicates the target moisture content of the grain. Indicates the temperature of the dryer. Indicates the wind speed of the dryer. represents the energy consumption function, represents the food status monitoring function, represents the time variable, Indicates the time when the drying process ends. represents the weight coefficient, represents the efficiency function of the drying process; The step of adjusting the storage environment parameters according to the monitoring results to obtain the optimal adjustment results includes: constructing an optimal adjustment model for storage environment parameters according to the monitoring results of the storage environment and the stored grain; adjusting the temperature, humidity and concentration, combined with the optimal adjustment model of the storage environment parameters, to obtain the optimal adjustment objective function value; according to the optimal adjustment objective function value, determine the optimal temperature, optimal humidity and optimal Concentration, the expression satisfied by the optimal adjustment model of storage environment parameters is as follows: in, represents the objective function for optimal adjustment of storage environment parameters, Indicates the actual storage environment temperature. Indicates the actual storage environment humidity. Represents the actual storage environment concentration, Indicates the type of grain entering the warehouse. Indicates the initial humidity of grain when it enters the warehouse. Represents the total energy consumption function of the storage environment, Indicates the inspection cycle of the storage environment. represents the efficiency function of the storage environment, represents the time variable, , Represents the weight coefficient.

2. A complete set of grain storage and transportation method according to claim 1, characterized in that: Based on the optimal adjustment result, by constructing a deep learning outbound unit planning model and a transportation path planning model, planning the optimal outbound unit and the optimal transportation path includes: Based on the optimal adjustment result, a deep learning outbound unit planning model is constructed; Planning the optimal outbound unit according to the deep learning outbound unit planning model; Based on the optimal outbound unit, an intelligent loading implementation model is constructed; According to the intelligent loading implementation model, the grain is weighed quickly and loaded efficiently; Based on the optimal outbound unit, a transportation path planning model is constructed; Based on the transportation route planning model, the optimal transportation route is planned using the food type, weight, transportation cost, transportation starting point and transportation end point information.

3. A complete set of grain storage and transportation system, the system using a complete set of grain storage and transportation method according to any one of claims 1 to 2, characterized in that: The system includes an input device, a processor, an output device and a memory, wherein the input device, the processor, the output device and the memory are connected to each other, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions.

Images