A loading system for intelligent vehicle type recognition and dynamic regulation

Abstract

The present invention provides a loading system for intelligent vehicle type identification and dynamic regulation. Compared with the prior art, the present invention includes an arrangement module, an identification module, a loading control module, a dynamic regulation module, and a real-time monitoring platform. The arrangement module intelligently schedules and matches vehicles according to transportation requirements; the identification module accurately identifies vehicle information through image recognition algorithms; the loading control module automatically completes material loading by controlling the loading device through PLC; the dynamic regulation module adjusts the loading speed according to the real-time loading status to avoid overloading or slow loading; the real-time monitoring platform provides monitoring of the progress of transportation tasks and abnormal alarms to ensure the smooth progress of the loading process. The system of the present invention can effectively improve the utilization efficiency of transportation resources, reduce transportation costs, and enhance the automation and intelligence levels of loading operations. Through intelligent scheduling and dynamic regulation, the present invention ensures that the material loading process is more efficient and accurate.

Description

Technical Field

[0001] The present invention relates to the field of vehicle loading and transportation, and particularly to a loading system for intelligent vehicle type identification and dynamic regulation. Background Art

[0002] In the industrial scenario of bulk material loading, due to the wide variety of vehicle types and obvious differences in load-carrying capacities, traditional loading methods often struggle to balance efficiency and accuracy, resulting in problems such as overloading or underloading. This not only affects the timely completion of material transportation tasks but also may bring a series of issues such as vehicle safety hazards and resource waste. For example, overloading may cause the vehicle to operate overloaded, increasing transportation costs and safety risks, while underloading may lead to a high vehicle empty load rate and low transportation efficiency. In addition, since the loading process relies on manual judgment, there are significant subjectivity and error rates, which are not suitable for the efficient loading requirements of large-scale and diverse materials.

[0003] This experimental team has long browsed and studied a large amount of relevant record materials regarding related technologies. At the same time, relying on relevant resources, a large number of relevant experiments have been carried out. After extensive searching, it is found that the existing technologies such as CN116142829A, CN117963563A, CN113401676B, and CN113401676A disclosed in the prior art, such as an intelligent high-speed unmanned operation shipping assembly line disclosed in the prior art, including a transfer conveyor arranged between the workshop and the transport vehicle. An automatic palletizing system and an automatic feeding system are installed at the inner end of the transfer conveyor, and an automatic loading system is installed at the outer end of the transfer conveyor. The automatic feeding system transfers the material pallet into the automatic palletizing system and recovers and sorts the carriers carrying the materials. The automatic palletizing system automatically disassembles the material pallet and transports the materials one by one to the inner end of the transfer conveyor. However, the automatic loading and transportation system in the prior art cannot effectively arrange and monitor the existing vehicles in the garage according to the transportation tasks, resulting in inaccurate vehicle matching, resource allocation, and loading process.

[0004] In order to solve the problems commonly existing in this field, such as low transportation efficiency, resource waste, and safety hazards of overloaded operation caused by overloading or underloading; lack of real-time monitoring and dynamic adjustment mechanisms, resulting in inaccurate vehicle matching, resource allocation, and loading process, etc., the present invention is made. Summary of the Invention

[0005] The purpose of the present invention is to propose a loading system for intelligent vehicle type identification and dynamic regulation in view of the current deficiencies in this field.

[0006] In order to overcome the deficiencies of the prior art, the present invention adopts the following technical solutions:

[0007] An intelligent vehicle type recognition and dynamic regulation loading system, the loading system includes an arrangement module for intelligently scheduling and matching vehicles in the garage according to the transportation requirements of materials, an identification module for identifying and determining the identity of vehicles entering the material loading area, a loading control module for automatically loading the vehicles with determined identities by using a PLC to control the loading device, a dynamic regulation module for dynamically adjusting the material loading speed according to the real-time loading state of the vehicles, and a real-time monitoring platform that can support remote management and data analysis and can provide an abnormal alarm function. Among them, a weight sensor for real-time monitoring of the loading weight of vehicles is arranged on the ground of the material loading area.

[0008] Further, the arrangement module implements the following operation steps:

[0009] S101: Vehicle information in the garage, the vehicle information includes a vehicle number ID for distinguishing each vehicle, a vehicle load weight C max , a carriage volume V max , the material transportation arrangement state Si of the vehicle, the service life Y of the vehicle age , a vehicle maintenance coefficient M reflecting the vehicle maintenance state, and the maximum single transportation distance D that the vehicle can complete in the current state max , M ∈ [0, 1], when M = 1, it means the vehicle maintenance state is the best, and when M = 0, it means the vehicle maintenance state is the worst;

[0010] S102: Obtain the transportation requirement information of the transportation task, the transportation requirement information includes the total weight G of the material to be transported total , the total volume V of the material to be transported total and the total transportation distance D of the material to be transported tota ;

[0011] S103: Calculate the actual load weight C of each vehicle respectively ac :

[0012]

[0013] Among them, k is a non-linear adjustment coefficient reflecting the non-linear influence of the vehicle service life on the load capacity, and n is an exponential parameter of the annual decay;

[0014] S104: Screen the vehicles: Use the vehicles with Si = 1 and η ≥ 1 as alternative vehicles,

[0015] Among them, η is the vehicle transportation efficiency factor, and

[0016] S105: Combine the alternative vehicles to generate all vehicle combinations N that meet the first condition, the first condition is: C acNn≥G total Meanwhile, VNn≥V total ,

[0017] Among them, C ac Nn is the total actual load weight of all vehicles in vehicle combination N, and VNn is the total compartment volume of all vehicles in vehicle combination N.

[0018] All vehicle combinations that meet the first condition will be numbered in sequence as N1, N2…Nm, where m is the number of all eligible combinations;

[0019] S106: Calculate the priority index of each combination:

[0020]

[0021] Among them, Nj∈{N1, N2, N3…Nm}, Cost Nj is the total material transportation cost of all vehicles in the jth vehicle combination, Num Nj is the total number of vehicles in the jth vehicle combination, Value Nj is the priority index of the jth vehicle combination, AvgC is the comparison cost, and AvgN is the comparison quantity;

[0022] S107: Sort the priority indices of all vehicle combinations, select the vehicle combination with the smallest priority index among all vehicle combinations as the final arrangement combination, and use the vehicle combination with the second smallest priority index as the alternative arrangement combination;

[0023] S108: Archive the final arrangement combination and the alternative arrangement combination matched by each transportation task into the system database to provide support for subsequent transportation task scheduling optimization.

[0024] Furthermore, the recognition module includes a camera device for taking pictures of vehicles entering the material loading area, an identification unit for analyzing and processing the pictures taken by the camera device through an image recognition algorithm to identify the license plate information of the vehicles in the pictures and the lengths of the length h, width w, and height g of the vehicle compartments, and a verification unit for verifying and checking the actual information of the vehicles based on the pictures.

[0025] Furthermore, the verification unit completes the following steps:

[0026] S201: Obtain the recorded number, compartment volume V max of the vehicle based on the license plate signal,

[0027] and the matched transportation task;

[0028] At When it is time, send a job instruction to the loading control module to drive and control the loading device to transport materials to the vehicle. △path is the phase difference threshold, and △path ∈ (5%, 15%).

[0029] At it is time, judge the vehicle entering the logistics loading area as an incorrect vehicle, calculate the matching value Vmatd of the incorrect vehicle and the vehicle with Si = 1 in the garage respectively, screen out the vehicle with the smallest difference in the matching value Vmat from the garage and replace it with the incorrect vehicle, and upload to the database to change the final arrangement combination of the transportation task. Among them, Vmatd = C ac ×w1 + V total ×w2 + D tota ×w3, where w1, w2, and w3 are weighting coefficients, and w1 + w2 + w3 = 1, w1 ≥ w2 ≥ w3.

[0030] Furthermore, the loading control module implements the following steps:

[0031] S301: Receive the job instruction sent by the recognition module, and obtain the actual load capacity C ac of the vehicle located in the material loading area, max the compartment volume V

[0032] and the density ρ of the materials transported by the vehicle.

[0033] S302: Calculate the transportation loading weight Gend of the vehicle in the material loading area:

[0033] When the upper limit volume V Cac ≤ V max of the vehicle, Gend = C ac

[0034] On the contrary, when the upper limit volume V Cac > V max of the vehicle, Gend = V max

[0035]

[0036]

[0037]

[0038] Furthermore, the dynamic regulation module implements the following operation steps:

[0038] S401: During the operation of the loading device, the current loading weight Wreal of the vehicle is collected in real time through a weight sensor and continuously updated;

[0039] S402: According to the current real-time loading weight Wreal of the vehicle, dynamically adjust the conveying rate of the loading device to avoid overloading or slow loading of materials:

[0040]

[0041] Fmax is the preset initial loading rate of the loading device, and Fadj is the adjusted loading rate of the loading device.

[0042] λ is the first control coefficient. By controlling the sensitivity of the change in the loading rate to Gend, adjust the change speed of the loading rate when approaching the target loading weight. λ ∈ [0.01, 1].

[0043] σ is the second control coefficient. σ adjusts the reaction sensitivity of the loading rate to the change in the real-time loading weight by controlling the influence of the increase in the loading weight on the change in the loading rate. б ∈ [0.01, 1].

[0044] The beneficial effects achieved by the present invention are:

[0045] 1. Improve loading accuracy and efficiency: Through the intelligent vehicle type recognition technology, accurately identify the vehicle type and load capacity, achieve precise matching with the transportation task, effectively avoid overloading or underloading, and improve the loading efficiency and accuracy.

[0046] 2. Optimize resource allocation: Based on the real-time status and transportation requirements of the vehicle, dynamically adjust the loading speed and loading process, avoid resource waste, improve the utilization rate of transportation resources, and at the same time reduce the phenomena of empty load and overloading.

[0047] 3. Enhance system automation and intelligence: Through the PLC to control the loading device and the dynamic regulation module, realize the automation and intelligence of the loading process, reduce manual intervention, improve the overall stability of the system, reduce human operation errors, and ensure the smooth completion of the loading task. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The present invention can be further understood from the following description in conjunction with the drawings. The components in the drawings are not necessarily drawn to scale, but the emphasis is placed on showing the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0049] Figure 1 It is a modular schematic diagram of the loading system for intelligent vehicle type recognition and dynamic regulation of the present invention.

[0050] Figure 2 It is a modular schematic diagram of the verification unit of the present invention. Detailed implementation manners

[0051] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with its embodiments. It should be noted that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present case. For those skilled in the art, after consulting the following detailed description, other systems, methods and / or features of this embodiment will become obvious. And the terms used to describe the positional relationship in the drawings are only for illustrative purposes and cannot be construed as a limitation of this patent. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to specific circumstances.

[0052] Embodiment 1: Combining the attached Figure 1 and the attached Figure 2 , this embodiment constructs a loading system for intelligent vehicle type recognition and dynamic regulation. The loading system includes an arrangement module that intelligently schedules and matches vehicles in the garage according to the transportation requirements of materials, an identification module that identifies and determines the identity of the vehicles entering the material loading area, a loading control module that uses a PLC to control the loading device to automatically load the vehicles whose identities have been determined, a dynamic regulation module that dynamically adjusts the material loading speed according to the real-time loading status of the vehicles, and a real-time monitoring platform that can support remote management and data analysis and can provide an abnormal alarm function.

[0053] The arrangement module implements the following operation steps:

[0054] S101: Vehicle information in the garage. The vehicle information includes a vehicle number ID for distinguishing each vehicle, a vehicle load weight C max , a carriage volume V max , the material transportation arrangement status Si of the vehicle, the number of years of use Y of the vehicle age , a vehicle maintenance coefficient M reflecting the vehicle maintenance status, and the maximum single transportation distance D that the vehicle can complete in the current state max , M ∈ [0, 1]. When M = 1, it means that the vehicle maintenance status is the best, and when M = 0, it means that the vehicle maintenance status is the worst;

[0055] S102: Obtain the transportation requirement information of the transportation task. The transportation requirement information includes the total weight G of the material to be transported total , the total volume V of the material to be transported total and the total transportation distance D of the material to be transported tota ;

[0056] S103: Calculate the actual load weight C of each vehicle ac :

[0057]

[0058] Among them, k is a non - linear adjustment coefficient reflecting the non - linear influence of the vehicle's service life on its load - carrying capacity, and n is an exponential parameter for annual attenuation.

[0059] Among them, k is the non - linear influence coefficient of the load - carrying capacity according to the vehicle's service life Y age The specific value of k is obtained by technical personnel through fitting calculation by repeating training and optimizing the performance of vehicles of different ages based on historical data and design goals. k describes how the increase in the vehicle's service life affects its maximum load - carrying capacity. Technical personnel calculate the change trend of k by using the historical performance of a large number of vehicles and repeated training data, and adjust it in combination with the actual use situation and design goals of the vehicle, so as to determine the value of k that can accurately reflect the actual change of the vehicle's load - carrying capacity.

[0060] n is used to control the sensitivity of k to the vehicle age in the calculation. The value of n is initially determined by technical personnel through fitting calculation and model optimization of historical data on actual loading capacity and vehicle age changes, and finally determines the optimal value of n through repeated training and optimization to ensure that the influence degree of vehicle age on load - carrying capacity conforms to the actual situation.

[0061] S104: Screen the vehicles: Select the vehicles with Si = 1 and η≥1 as alternative vehicles.

[0062] Among them, η is the vehicle transportation efficiency factor, and

[0063] S105: Combine the alternative vehicles to generate all vehicle combinations N that meet the first condition. The first condition is: C ac Nn≥G total , and at the same time VNn≥V total ,

[0064] Among them, C ac Nn is the total actual load - carrying weight of all vehicles in the vehicle combination N, and VNn is the total volume of the carriages of all vehicles in the vehicle combination N.

[0065] All vehicle combinations that meet the first condition will be numbered in order as N1, N2…Nm, where m is the number of all eligible combinations.

[0066] S106: Calculate the priority index of each combination:

[0067]

[0068] Among them, Nj∈{N1, N2, N3…Nm}, Cost Njis the total material transportation cost of all vehicles within the j-th vehicle combination, Num Nj is the total number of vehicles within the j-th vehicle combination, Value Nj is the priority index of the j-th vehicle combination. AvgC is the comparison cost, AvgN is the comparison quantity. The material transportation cost is determined based on the fuel consumption and highway tolls of the vehicles. AvgC is determined by those skilled in the art through historical experience data and cost records of actual transportation tasks, which is used to reflect the cost performance of the vehicle combination in the transportation task and is calculated and determined by those skilled in the art based on the average number of vehicles within the vehicle combination in the historical experience data. AvgN is used to reflect the number of vehicles required during a specific transportation task;

[0069] S107: Sort the priority indices of all vehicle combinations, select the vehicle combination with the smallest priority index among all vehicle combinations as the final arrangement combination, and use the vehicle combination with the second-to-last priority index as the alternative arrangement combination;

[0070] S108: Archive the final arrangement combination and the alternative arrangement combination matched for each transportation task into the system database to provide support for subsequent transportation task scheduling optimization.

[0071] The arrangement module matches vehicles to complete each transportation task according to each transportation task. The design of the arrangement module ensures that each transportation task can be completed by the most suitable vehicle combination through intelligent matching and optimized scheduling. By considering multiple factors such as load capacity, volume, transportation efficiency, and distance, and combining vehicle priority, task time limit, etc., it greatly improves the utilization efficiency of transportation resources and the accuracy of task execution. This not only reduces unnecessary resource waste but also reduces transportation costs and improves the efficiency of the overall transportation system.

[0072] Embodiment 2: Combining attached Figure 1 and attached Figure 2 , in addition to including the content of the above embodiment, it further lies in that the recognition module includes a camera device for taking pictures of vehicles entering the material loading area, an identification unit for analyzing and processing the pictures taken by the camera device through an image recognition algorithm to identify the license plate information of the vehicle in the pictures and the lengths of the length h, width w, and height g of the vehicle carriage, and a verification unit for checking and verifying the actual information of the vehicle based on the pictures.

[0073] Among them, the image recognition algorithm includes a feature-based license plate recognition algorithm, deep learning methods, and object detection algorithms and 3D reconstruction techniques for carriage size recognition. The deep learning methods include CNN, YOLO, FasterR-CNN, and CRNN models. The image recognition algorithm can achieve a comprehensive analysis of vehicle images, thereby accurately identifying the key information of license plates and the length, width, and height of carriages.

[0074] The checking unit completes the following steps:

[0075] S201: Obtain the vehicle number and vehicle compartment volume V based on the license plate signal max , and the matching transportation tasks;

[0076] S202: Check whether the size of the carriage in the picture matches the recorded carriage volume:

[0077] exist When , the operation instruction is sent to the loading control module to drive the loading device to transport materials to the vehicle. △path is the difference threshold, △path∈(5%, 15%),

[0078] exist When the vehicle entering the logistics loading area is judged as an error vehicle, the matching value Vmatd of the error vehicle and the vehicle with Si=1 in the garage is calculated respectively, and the vehicle with the smallest difference in matching value Vmat from the error vehicle is selected from the garage and replaced with the error vehicle, and the database is uploaded to change the final arrangement combination of the transportation task, where Vmatd=C ac ×w1+V total ×w2+D tota ×w3, w1, w2, w3 are weight coefficients, and w1+w2+w3=1, w1≥w2≥w3.

[0079] By combining image processing technology and deep learning algorithms, the recognition module can extract key information such as the vehicle's license plate information and compartment size with high precision, ensure the accuracy of the data, and avoid scheduling problems caused by recognition errors. Its automated processing flow significantly reduces manual intervention, improves operational efficiency, and speeds up vehicle entry and loading. In addition, the module has a flexible exception handling mechanism, which selects the most suitable replacement vehicle through similarity calculation and comprehensive matching to ensure the smooth completion of the task. At the same time, the recognition module provides precise support for subsequent vehicle scheduling and resource allocation, effectively optimizes the loading task process, reduces the situation of empty or overloaded vehicles, and significantly improves overall transportation efficiency and resource utilization.

[0080] Embodiment 3: Combining with Figure 1 and attached Figure 2 In addition to the contents of the above embodiments, the loading control module controls the loading device through PLC to quantitatively transport materials of the transport loading weight of the vehicle into the vehicle compartment after the identification module completes the identification. The loading device is a belt conveyor or a screw conveyor that transports materials from the material storage area to the vehicle compartment. A weight sensor for real-time monitoring of the vehicle's loading weight is provided on the ground of the material loading area.

[0081] The loading control module implements the following steps:

[0082] S301: Receive the operation instruction sent by the recognition module, and obtain the actual load capacity C of the vehicle located in the material loading area ac , the compartment volume V max and the density ρ of the material transported by the vehicle;

[0083] S302: Calculate the transport loading weight Gend of the vehicle in the material loading area:

[0084] When the upper limit volume V of the vehicle Cac ≤V max , Gend = C ac ,

[0085] On the contrary, when the upper limit volume V of the vehicle Cac >V max , Gend = V max , where ρ is the density of the material,

[0086] S303: Start the conveying equipment to transfer materials to the vehicle compartment;

[0087] S304: Real-time monitor the loading weight of the vehicle through the weight sensor. When the cumulative loading weight of the vehicle reaches Gac, stop the operation of the loading device and send a loading completion signal to remind the vehicle to leave the material loading area.

[0088] The dynamic regulation module implements the following operation steps:

[0089] S401: During the operation of the loading device, real-time collect the current loading weight Wreal of the vehicle through the weight sensor and continuously update it;

[0090] S402: Dynamically adjust the conveying rate of the loading device according to the current real-time loading weight Wreal of the vehicle to avoid material overload or too slow loading:

[0091]

[0092] Among them, Fmax is the preset initial loading rate of the loading device, Fadj is the adjusted loading rate of the loading device,

[0093] λ is the first control coefficient. By controlling the sensitivity of the change in the loading rate to Gend, adjust the change speed of the loading rate when approaching the target loading weight. Specifically, a larger λ value will cause the loading rate to slow down rapidly when approaching the target weight, while a smaller λ value will make the rate slow down more gently, which is suitable for scenarios with a more stable requirement for the change in the loading rate. λ ∈ [0.01, 1],

[0094] σ is the second control coefficient. By controlling the influence of the increase in the loading weight on the change rate of the loading rate, σ adjusts the sensitivity of the loading rate to the change in the real-time loading weight. Specifically, a larger σ value will make the loading rate respond more quickly to the weight change, which is suitable for scenarios where the rate needs to be adjusted quickly. While a smaller σ value makes the rate adjustment smoother, thus avoiding sudden changes during the loading process. б ∈ [0.01, 1].

[0095] The real-time monitoring platform implements the following operation steps:

[0096] S501: Store the key data of each transportation task, including the loading start time of each transportation task, the remaining loading weight of the material, and the numbers of the loaded vehicles and unloaded vehicles.

[0097] S502: Monitor the execution time Ttask of each transportation task. If the transportation task has not been completed after exceeding the preset maximum time threshold Tmax, an overtime alarm will be automatically triggered and the alarm will be sent through the visual interface, sound prompt, and text message or email to remind the operator to respond in a timely manner.

[0098] S503: All triggered alarm messages will be recorded and stored in the system database for subsequent viewing and analysis. The alarm messages include the time when the alarm is triggered, the transportation task related to the alarm, the vehicle number of the transportation task related to the alarm, and the material loading situation.

[0099] Through the collaborative work of the loading control module, dynamic regulation module, and real-time monitoring platform, the present invention provides intelligent regulation and efficient monitoring for the material loading process. Through precise loading control, dynamic rate adjustment, and real-time task monitoring, the system can ensure that the loading process proceeds efficiently, safely, and smoothly. The alarm function of the real-time monitoring platform provides an immediate response to abnormal situations, reduces potential safety hazards and operation delays, and improves the overall transportation efficiency and management level.

[0100] Although the present invention has been described above with reference to various embodiments, it should be understood that many changes and modifications can be made without departing from the scope of the present invention. That is to say, the methods, systems and devices discussed above are examples. Various configurations can be appropriately omitted, replaced or various processes or components added. For example, in an alternative configuration, the method can be performed in an order different from the described order, and / or various components can be added, omitted and / or combined. Moreover, the features described with respect to certain configurations can be combined in various other configurations, such as different aspects and elements of the configurations can be combined in a similar manner. In addition, as technology develops, the elements therein can be updated, that is, many elements are examples and do not limit the scope of the present disclosure or the claims. And it should be understood that after reading the content of the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent changes and modifications also fall within the scope defined by the claims of the present invention.

Claims

1. An intelligent vehicle type recognition and dynamic regulation loading system, characterized in that, The loading system includes an arrangement module that intelligently schedules and matches vehicles in the garage according to the transportation requirements of materials, an identification module that identifies the identity of vehicles entering the material loading area, a loading control module that uses a PLC to control the loading device to automatically load the vehicles with determined identities, a dynamic regulation module that dynamically adjusts the material loading speed based on the real-time loading status of the vehicles, and a real-time monitoring platform that supports remote management and data analysis and can provide an abnormal alarm function. Among them, weight sensors for real-time monitoring of the loading weight of vehicles are arranged on the ground of the material loading area; The arrangement module implements the following operation steps: S101: Obtain vehicle information in the garage, where the vehicle information includes a vehicle number ID for distinguishing each vehicle, a vehicle load weight C max , a carriage volume V max , a material transportation arrangement status Si of the vehicle, a service life Y of the vehicle age , a vehicle maintenance coefficient M reflecting the vehicle maintenance status, and a maximum single - trip transportation distance D that the vehicle can complete in the current state max , , M ∈ [0, 1]. When M = 1, it indicates that the vehicle maintenance status is the best, and when M = 0, it indicates that the vehicle maintenance status is the worst; S102: Obtain the transportation demand information of the transportation task, where the transportation demand information includes the total weight G of the materials to be transported total , the total volume V of the materials to be transported total and the total transportation distance D of the materials to be transported total ; S103: Calculate the actual load weight C of each vehicle respectively ac : ， where k is a non-linear adjustment coefficient reflecting the non-linear influence of the vehicle's service life on its load capacity, and n is an exponential parameter for annual attenuation; S104: Screen the vehicles: Use the vehicles with Si = 1 and η ≥ 1 as alternative vehicles, where η is the vehicle transportation efficiency factor, and , S105: Combine the alternative vehicles to generate all vehicle combinations N that meet the first condition. The first condition is: C ac Nn ≥ G total and at the same time VNn ≥ V total , Among them, C ac Nn is the total actual load weight of all vehicles in vehicle combination N, and VNn is the total carriage volume of all vehicles in vehicle combination N. Number all vehicle combinations that meet the first condition in sequence as N1, N2…Nm, where m is the number of all eligible combinations; S106: Calculate the priority index Value of each combination Nj : ， where, Nj ∈ {N1, N2, N3…Nm}, Cost Nj is the total material transportation cost of all vehicles within the j-th vehicle combination, Num Nj is the total number of vehicles within the j-th vehicle combination, Value Nj is the priority index of the j-th vehicle combination, AvgC is the comparison cost, and AvgN is the comparison quantity; S107: Sort the priority indices of all vehicle combinations, select the vehicle combination with the smallest priority index among all vehicle combinations as the final arrangement combination, and use the vehicle combination with the second smallest priority index as the alternative arrangement combination; S108: Archive the final arrangement combination and the alternative arrangement combination matched by each transportation task into the system database to support the subsequent optimization of transportation task scheduling.

2. The loading system for intelligent vehicle type identification and dynamic regulation according to claim 1, characterized in that The identification module includes a camera device that takes pictures of vehicles entering the material loading area, an identification unit that analyzes and processes the pictures taken by the camera device through an image recognition algorithm to identify the license plate information of the vehicle in the picture and the lengths of the length h, width w, and height g of the vehicle compartment, and a verification unit that checks the actual information of the vehicle based on the picture.

3. The loading system for intelligent vehicle type recognition and dynamic regulation according to claim 2, characterized in that The verification unit completes the following steps: S201: Obtain the number recorded by the vehicle, the carriage volume V max , and the matched transportation task; S202: Check whether the size of the compartment in the picture meets the recorded compartment volume: At , send a job instruction to the loading control module to drive and control the loading device to transport materials to the vehicle. △path is the phase difference threshold, and △path ∈ (5%, 15%). At this time, the vehicle entering the logistics loading area is judged as a wrong vehicle, and the matching values Vmatd of the wrong vehicle and the vehicle with Si = 1 in the garage are calculated respectively. The vehicle with the smallest difference in the matching value Vmat from the wrong vehicle is selected from the garage and replaced with the wrong vehicle, and the database is uploaded to change the final arrangement combination of the transportation task, where , w1, w2, and w3 are weight coefficients, and w1 + w2 + w3 = 1, w1 ≥ w2 ≥ w3.

4. The loading system for intelligent vehicle type recognition and dynamic regulation according to claim 3, characterized in that The loading control module implements the following steps: S301: Receive the job instruction sent by the recognition module, and obtain the actual load capacity C of the vehicle located in the material loading area ac , the carriage volume V max and the density ρ of the materials transported by the vehicle. S302: Calculate the transportation loading weight Gend of the vehicles in the material loading area: When the upper limit volume V of the vehicle Cac ≤V max then Gend = C ac , Conversely, at the upper limit volume V of the vehicle Cac > V max when, Gend = V max , where , ρ is the density of the material, and the weight of the material loaded into the vehicle by the loading device is the transportation loading weight of the vehicle S303: Start the conveying equipment to transfer materials to the vehicle compartment, S304: Real-time monitor the loading weight of the vehicle through the weight sensor. When the cumulative loading weight of the vehicle reaches Gac, stop the operation of the loading device and send a loading completion signal to remind the vehicle to drive out of the material loading area.

5. The loading system for intelligent vehicle type recognition and dynamic regulation according to claim 4, wherein The dynamic regulation module implements the following operation steps: S401: During the operation of the loading device, continuously collect the current loading weight 𝑊real of the vehicle through the weight sensor and update it continuously; S402: Dynamically adjust the conveying rate of the loading device according to the current real-time loading weight Wreal of the vehicle to avoid overloading or slow loading of materials: ， Fmax is the preset initial loading rate of the loading device, and Fadj is the adjusted loading rate of the loading device, λ is the first control coefficient. By controlling the sensitivity of the change in the loading rate to Gend, adjust the change speed of the loading rate when approaching the target loading weight, λ ∈ [0.01, 1], σ is the second control coefficient. By controlling the influence intensity of the increase in the loading weight on the change in the loading rate, σ adjusts the response sensitivity of the loading rate to the change in the real-time loading weight, and б ∈ [0.01, 1].

Images