Digital loading and unloading control system for port logistics container

Abstract

The invention discloses a digital loading and unloading control system for port logistics containers, and relates to the related field of transportation devices, and the system comprises the steps: reading the transportation information of a target cargo ship, predicting the arrival time, and determining a predicted arrival node. And based on the predicted arrival node, the loading layout and the cargo list, performing simulation in the port loading and unloading twin platform, and determining an unloading equipment demand set. And calling the equipment resource library to carry out idle equipment matching, and generating a first unloading equipment matching scheme. A remaining device demand set is determined, a job end node is predicted, and a plurality of predicted end node sets are determined. And outputting a second unloading equipment matching scheme by taking the condition that the predicted end node is earlier than the predicted demand node as a limit. And unloading operation is executed based on the first or second unloading equipment matching scheme. The technical problems that in the prior art, port container loading and unloading operation is difficult to adapt to dynamically-changing logistics requirements, operation efficiency is low, the equipment utilization rate is low, and port operation efficiency is difficult to improve are solved.

Description

Technical Field

[0001] The present application relates to the field of transport equipment, and in particular to a digital loading and unloading control system for port logistics containers. Background Art

[0002] The loading and unloading of port logistics containers is an extremely important part of port management. With the growth of global trade volume, the logistics pressure faced by ports is also increasing. Traditional port container loading and unloading operations usually rely on manual management, which is difficult to adapt to the dynamically changing logistics needs, resulting in low operating efficiency and low equipment utilization, making it difficult to improve the operating efficiency of ports.

[0003] Therefore, in the existing technology, port container loading and unloading operations are difficult to adapt to the dynamically changing logistics needs, resulting in low operating efficiency and low equipment utilization, which makes it difficult to improve the port's operating efficiency. Summary of the invention

[0004] This application provides a digital loading and unloading control system for port logistics containers, which solves the technical problem in the prior art that port container loading and unloading operations are difficult to adapt to dynamically changing logistics needs, resulting in low operating efficiency, low equipment utilization, and difficulty in improving port operating efficiency. By combining weather forecast information and real-time transportation information, the arrival time of cargo ships is accurately predicted, and based on the loading layout and cargo list, combined with unloading priority analysis and simulation, the equipment requirements are accurately determined, which improves operating efficiency and equipment utilization, and further improves the port's operating efficiency.

[0005] The present application provides a digital loading and unloading control system for port logistics containers, the system comprising: an arrival time prediction module, which is used to read the transportation information of the target cargo ship, predict the arrival time based on the weather forecast information and the transportation information, and determine the predicted arrival node, wherein the transportation information includes the container loading data, and the container loading data includes the loading layout and the cargo list; an unloading equipment demand analysis module, which is used to perform simulation in the port loading and unloading twin platform based on the predicted arrival node, loading layout and cargo list, with the expected unloading demand as a constraint, to determine the unloading equipment demand set, wherein the unloading equipment demand set includes a predicted demand node set, multiple equipment type sets and multiple equipment quantity sets; an idle equipment matching module, which is used to call the equipment resource library for idle equipment matching based on the multiple equipment type sets and the multiple equipment quantity sets. , generate a first unloading equipment matching plan; an equipment end node prediction module, used to determine the remaining equipment demand set if the first unloading equipment matching plan does not fully meet the unloading equipment demand set, obtain multiple real-time operation data sets of multiple adapted working equipment sets of the remaining equipment demand set through the equipment monitoring platform, predict the operation end node according to the multiple real-time operation data sets, and determine multiple predicted end node sets; a working equipment matching module, used to determine the initial second unloading equipment matching plan of the remaining equipment demand set with the predicted end node being earlier than the predicted demand node as the restriction, optimize and analyze the initial second unloading equipment matching plan, and output the second unloading equipment matching plan; an unloading operation scheduling module, used to execute the arrival unloading operation of the target cargo ship based on the first unloading equipment matching plan or the second unloading equipment matching plan.

[0006] In a possible implementation, the arrival time prediction module is also used to: read the transportation information of the target cargo ship, wherein the transportation information includes the type of cargo ship, the sailing route, the remaining sailing distance and the container loading capacity; collect weather forecast information, wherein the weather forecast information includes at least wind direction and wind speed; input the wind direction, wind speed and remaining sailing distance into the navigation predictor to predict the arrival time, and output the predicted arrival node, wherein the navigation predictor includes multiple prediction units, and the output is the average of the output results of the multiple prediction units.

[0007] In a possible implementation, the arrival time prediction module is also used to: perform positive sample retrieval based on big data with cargo ship type, sailing route and container loading as constraints to obtain a retrieval data set, wherein the retrieval data includes sample wind direction, sample wind speed, sample sailing distance and sample sailing time; perform differential screening on the retrieval data set to obtain a training data set, and use the training data set to perform supervised training and cross-validation on multiple prediction units respectively to generate the navigation predictor, wherein the prediction unit and the prediction operator correspond one to one, and the prediction operator includes at least BP neural network, random decision forest and support vector machine.

[0008] In a possible implementation, the arrival time prediction module is further used to: randomly extract first retrieval data from the retrieval data set, wherein the first retrieval data includes a first sample wind direction, a first sample wind speed, and a first sample sailing distance; perform deviation calculation on the first sample wind direction and other sample wind directions in the retrieval data set, and count the number of wind direction deviations greater than a predetermined wind direction threshold, which is set as a first difference; if the first difference is greater than the predetermined difference threshold, perform deviation calculation on the first sample wind speed and other sample wind speeds in the retrieval data set to determine a second difference; if the second difference is greater than the predetermined difference threshold, perform deviation calculation on the first sample sailing distance and other sample sailing distances in the retrieval data set to obtain a third difference, and if the third difference is greater than the predetermined difference threshold, add the first retrieval data to the training data set.

[0009] In a possible implementation, the unloading equipment demand analysis module is also used to: perform unloading priority analysis based on the loading layout and cargo list, and determine the container unloading sequence, wherein the cargo list includes multiple container types; in the port loading and unloading twin platform, according to the container unloading sequence, with the expected unloading demand as a constraint, perform unloading simulation according to the predicted arrival node and cargo list, and determine the unloading start node corresponding to each container type, set it as the demand prediction node, and obtain the unloading equipment demand set, wherein the unloading equipment demand set includes a predicted demand node set, multiple equipment type sets, and multiple equipment quantity sets.

[0010] In a possible implementation, the equipment end node prediction module is also used to: obtain multiple working equipment through the equipment monitoring platform, match the remaining equipment demand set with the multiple working equipment, and determine multiple adaptive working equipment sets; randomly select a first adaptive working equipment set from the multiple adaptive working equipment sets, and select the first adaptive working equipment; collect real-time operation data of the first adaptive working equipment to obtain first real-time operation data, wherein the first real-time operation data includes a first remaining workload, a first operation type, and a first equipment location coordinate; perform operation end prediction based on the first remaining workload and the first operation type to obtain a first initial end node, compensate the first initial end node based on the first equipment location coordinate, output the first predicted end node, add it to the first predicted end node set, and obtain multiple predicted end node sets.

[0011] In a possible implementation, the equipment end node prediction module is also used to: obtain the predicted operating position coordinates of the target cargo ship, calculate the equipment scheduling distance based on the predicted operating position coordinates and the first equipment position coordinates, and determine the first equipment scheduling distance; obtain the first unit distance scheduling time of the first adaptive working equipment, calculate the first equipment scheduling time based on the first equipment scheduling distance and the first unit distance scheduling time, and compensate the first initial end node according to the first equipment scheduling time.

[0012] In a possible implementation, the working equipment matching module is further used to: identify the initial second unloading equipment matching scheme, and if the number of second matching equipment is greater than the remaining equipment number requirement, determine multiple redundant matching equipment; obtain multiple equipment characteristics and multiple equipment scheduling distances of the multiple redundant matching equipment, wherein the equipment characteristics at least include the remaining oil volume and equipment performance; perform performance evaluation on the multiple redundant matching equipment based on the remaining oil volume and equipment performance to obtain multiple performance evaluation coefficients; perform equipment fitness analysis based on the multiple performance evaluation coefficients and multiple equipment scheduling distances to determine multiple equipment fitness, wherein the equipment fitness calculation function is: ;in, For device adaptability, is the distance weight, is the performance weight, Distance for device scheduling, is a performance evaluation coefficient; based on the adaptability of the multiple devices, multiple redundant matching devices are screened to determine the optimal matching device; according to the optimal matching device, the initial second unloading device matching scheme is optimized and updated, and the second unloading device matching scheme is output.

[0013] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present application provides a digital loading and unloading control system for port logistics containers, including: an arrival time prediction module, which is used to read the transportation information of the target cargo ship, predict the arrival time based on the weather forecast information and the transportation information, and determine the predicted arrival node, wherein the transportation information includes the container loading data, and the container loading data includes the loading layout and the cargo list; an unloading equipment demand analysis module, which is used to perform simulation in the port loading and unloading twin platform based on the predicted arrival node, loading layout and cargo list, with the expected unloading demand as a constraint, to determine the unloading equipment demand set, wherein the unloading equipment demand set includes the predicted demand node set, multiple equipment type sets and multiple equipment quantity sets; an idle equipment matching module, which is used to call the equipment resource library to match idle equipment based on the multiple equipment type sets and the multiple equipment quantity sets, and generate The first unloading equipment matching scheme is formed; the equipment end node prediction module is used to determine the remaining equipment demand set if the first unloading equipment matching scheme does not fully meet the unloading equipment demand set, obtain multiple real-time operation data sets of multiple adaptive working equipment sets of the remaining equipment demand set through the equipment monitoring platform, predict the operation end node according to the multiple real-time operation data sets, and determine multiple predicted end node sets; the working equipment matching module is used to determine the initial second unloading equipment matching scheme of the remaining equipment demand set with the predicted end node earlier than the predicted demand node as the restriction, optimize and analyze the initial second unloading equipment matching scheme, and output the second unloading equipment matching scheme; the unloading operation scheduling module is used to execute the unloading operation of the target cargo ship at the port based on the first unloading equipment matching scheme or the second unloading equipment matching scheme. The technical problem that the port container loading and unloading operation is difficult to adapt to the dynamically changing logistics demand in the prior art is solved, resulting in low operation efficiency, low equipment utilization, and difficulty in improving the port's operating efficiency. By combining weather forecast information and real-time transportation information, the arrival time of cargo ships can be accurately predicted, and based on the loading layout and cargo list, combined with unloading priority analysis and simulation, equipment requirements can be accurately determined, thereby improving operational efficiency and equipment utilization, and further improving the port's operational efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic diagram of the structure of a digital loading and unloading control system for port logistics containers provided in an embodiment of the present application; Figure 2 This is a flow chart of outputting predicted arrival nodes by an arrival time prediction module in a digital loading and unloading control system for port logistics containers in the present application.

[0016] Explanation of the reference numerals: arrival time prediction module 11, unloading equipment demand analysis module 12, idle equipment matching module 13, equipment end node prediction module 14, working equipment matching module 15, unloading operation scheduling module 16. DETAILED DESCRIPTION

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0018] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0019] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, systems, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0020] The present application embodiment provides a digital loading and unloading control system for port logistics containers, such as Figure 1 As shown, the system comprises: An arrival time prediction module is used to read the transportation information of the target cargo ship, predict the arrival time based on the weather forecast information and the transportation information, and determine the predicted arrival node, wherein the transportation information includes container loading data, and the container loading data includes loading layout and cargo list; an unloading equipment demand analysis module is used to perform simulation in the port loading and unloading twin platform based on the predicted arrival node, loading layout and cargo list, with the expected unloading demand as a constraint, to determine the unloading equipment demand set, wherein the unloading equipment demand set includes a predicted demand node set, multiple equipment type sets and multiple equipment quantity sets; an idle equipment matching module is used to call the equipment resource library to match idle equipment based on the multiple equipment type sets and multiple equipment quantity sets, and generate a first unloading equipment matching solution; The arrival time prediction module reads the transportation information of the target cargo ship from the port management system or the cargo ship company. The transportation information includes container loading data, and the container loading data includes loading layout and cargo list. The meteorological service interface is called to obtain the weather forecast information on the ship's sailing route. The arrival time is predicted based on the weather forecast information and the transportation information to determine the predicted arrival node. The transportation information also includes the type of cargo ship, sailing route, remaining sailing distance and container loading information.

[0021] Subsequently, the unloading equipment demand analysis module is based on the predicted port arrival node, loading layout and cargo list, and is constrained by meeting the expected unloading demand, which is the expected unloading time. A simulation is performed in the port loading and unloading twin platform to determine the unloading equipment demand set, wherein the unloading equipment demand set includes a predicted demand node set, multiple equipment type sets and multiple equipment quantity sets. The predicted demand node set refers to the specific time point when each container type starts unloading. Further, through the idle equipment matching module, based on the multiple equipment type sets and multiple equipment quantity sets, the multiple equipment type sets are equipment type schemes for completing unloading tasks, and the multiple equipment quantity sets are the required quantities of each device for the corresponding schemes, the equipment resource library is called to obtain the operating status of each device, and idle equipment matching is performed to generate a first unloading equipment matching scheme, which is one of the schemes in the multiple equipment type sets and multiple equipment quantity sets that meets the equipment idleness.

[0022] Further, such as Figure 2 As shown, the arrival time prediction module 11 is also used to: read the transportation information of the target cargo ship, wherein the transportation information includes the type of cargo ship, the sailing route, the remaining sailing distance and the container loading capacity; collect weather forecast information, wherein the weather forecast information includes at least wind direction and wind speed; input the wind direction, wind speed and remaining sailing distance into the navigation predictor to predict the arrival time, and output the predicted arrival node, wherein the navigation predictor includes multiple prediction units, and the output is the average of the output results of the multiple prediction units.

[0023] Read the transportation information of the target cargo ship, wherein the transportation information includes the type of cargo ship, the sailing route, the remaining sailing distance and the container loading capacity. The cargo ship type is the specific model category of the cargo ship, and the sailing route includes detailed information on the starting port, the end port and the intermediate port of call. The remaining sailing distance is the remaining sailing distance from the current location of the target cargo ship to the destination port. The container loading capacity is the loading information such as the number and weight of containers currently loaded on the cargo ship. Call the meteorological service interface to collect and obtain the weather forecast information on the current and future sailing routes of the target cargo ship, wherein the weather forecast information includes at least wind direction and wind speed. Finally, the wind direction, wind speed and remaining sailing distance are input into the sailing predictor to predict the arrival time, and the predicted arrival node is output, wherein the sailing predictor includes multiple prediction units, and the output is the average of the output results of multiple prediction units.

[0024] Furthermore, the arrival time prediction module 11 is also used to: perform positive sample retrieval based on big data with cargo ship type, sailing route and container loading as constraints to obtain a retrieval data set, wherein the retrieval data includes sample wind direction, sample wind speed, sample sailing distance and sample sailing time; perform differential screening on the retrieval data set to obtain a training data set, and use the training data set to perform supervised training and cross-validation on multiple prediction units respectively to generate the navigation predictor, wherein the prediction unit and the prediction operator correspond one to one, and the prediction operator includes at least BP neural network, random decision forest and support vector machine.

[0025] Based on the constraints of cargo ship type, navigation route and container loading, relevant navigation sample data is retrieved from big data. The retrieval data includes the wind direction, wind speed, navigation distance and navigation duration information of the sample, and a retrieval data set is obtained based on the retrieval data. Subsequently, the retrieval data set is differentially screened to obtain a training data set, thereby saving training time, improving model training efficiency and improving the accuracy and robustness of model training. Using the screened training data set, supervised training is performed on the BP neural network, random decision forest and support vector machine models respectively, until the output accuracy of the cross-validation of the training model based on the training data meets the requirements, and multiple prediction units that have been trained are obtained, and multiple prediction units are integrated to generate the navigation predictor. Among them, the prediction unit and the prediction operator correspond one to one, and the prediction operator includes at least BP neural network, random decision forest and support vector machine. The navigation predictor is used to analyze the wind direction, wind speed and navigation distance to obtain the predicted navigation duration data, and the predicted navigation duration data is obtained after the average value calculation based on the output results of multiple prediction units.

[0026] Furthermore, the arrival time prediction module 11 is also used to: randomly extract first retrieval data from the retrieval data set, wherein the first retrieval data includes a first sample wind direction, a first sample wind speed and a first sample sailing distance; perform deviation calculation on the first sample wind direction and other sample wind directions in the retrieval data set, and count the number of wind direction deviations greater than a predetermined wind direction threshold, which is set as a first difference; if the first difference is greater than the predetermined difference threshold, perform deviation calculation on the first sample wind speed and other sample wind speeds in the retrieval data set to determine a second difference; if the second difference is greater than the predetermined difference threshold, perform deviation calculation on the first sample sailing distance and other sample sailing distances in the retrieval data set to obtain a third difference, and if the third difference is greater than the predetermined difference threshold, add the first retrieval data to the training data set.

[0027] The first retrieval data is randomly extracted from the retrieval data set, wherein the first retrieval data includes a first sample wind direction, a first sample wind speed and a first sample sailing distance. Subsequently, the deviation calculation is performed on the first sample wind direction and other sample wind directions in the retrieval data set, the wind direction deviation of the first sample wind direction and other sample wind directions is obtained, and the number of wind direction deviations greater than a predetermined wind direction threshold is counted, which is set as a first difference degree, and the predetermined wind direction threshold is a preset wind direction deviation parameter. When it is greater than the threshold, the corresponding wind direction deviation is larger. If the first difference degree is greater than the predetermined difference threshold, that is, the amount of difference data is greater than the threshold, the deviation calculation is performed on the first sample wind speed and other sample wind speeds in the retrieval data set, and the number of wind speed deviations greater than the predetermined wind speed threshold is counted, which is set to determine the second difference degree. On the contrary, if the first difference degree is less than or equal to the predetermined difference threshold, the corresponding data is discarded. If the second difference degree is greater than the predetermined difference threshold, the deviation calculation is performed on the first sample sailing distance and other sample sailing distances in the retrieval data set, and the number of sailing distance deviations greater than the predetermined sailing distance threshold is counted to obtain a third difference degree. If the third difference degree is greater than the predetermined difference threshold, the first retrieval data is added to the training data set. Otherwise, the corresponding data will be eliminated to ensure data diversity and improve the accuracy and robustness of the final model training.

[0028] Furthermore, the unloading equipment demand analysis module 12 is also used to: perform unloading priority analysis based on the loading layout and cargo list, and determine the container unloading sequence, wherein the cargo list includes multiple container types; in the port loading and unloading twin platform, according to the container unloading sequence, with the expected unloading demand as a constraint, perform unloading simulation according to the predicted arrival node and cargo list, and determine the unloading start node corresponding to each container type, set it as the demand prediction node, and obtain the unloading equipment demand set, wherein the unloading equipment demand set includes a predicted demand node set, multiple equipment type sets, and multiple equipment quantity sets.

[0029] Read the loading layout and cargo list. The loading layout refers to the specific placement of the container on the cargo ship. The cargo list includes detailed information of each container, such as the container type. Based on the loading layout and cargo list, the unloading priority analysis is performed. The unloading priority is determined by the container type priority and the loading layout. The container type priority is the highest priority for the refrigerated container, followed by the dangerous goods container, then the special container, and finally the standard container. When performing the unloading priority analysis, the container unloading priority is determined mainly based on the container type and supplemented by the loading layout. The specific rule is to first unload the container with a high priority of the container type. When there are other containers on the surface of the container with a high priority, it needs to be unloaded first, and the unloading order is the outer circle container first and the inner circle container later. Exemplarily, the position of each refrigerated container is first determined by the priority of the container type, and then the covering box and the refrigerated container are disassembled in the order from the outer circle to the inner circle to obtain the container unloading sequence.

[0030] Subsequently, in the port loading and unloading twin platform, according to the container unloading sequence, with the expected unloading demand as a constraint, unloading simulation is performed according to the predicted port arrival node and the cargo list. The expected unloading demand is the preset unloading time. The required number of equipment and equipment category are determined based on the unloading time and the number of unloading containers. Different equipment categories correspond to different unloading rates. According to the number of container unloading and the equipment unloading rate, the equipment type and number that meet the requirements are obtained under the condition of meeting the expected unloading demand. The port loading and unloading twin platform is a virtual simulation system, which is used to simulate the port unloading operation according to the specific placement of the container and the container unloading sequence, and determine the corresponding equipment type and equipment number based on the number of container unloading and the expected unloading demand. And determine the corresponding unloading start node of the container. The unloading start node refers to the specific time point when the container starts unloading, which is set as the demand prediction node, and obtain the unloading equipment demand set, wherein the unloading equipment demand set includes the predicted demand node set, multiple equipment type sets and multiple equipment quantity sets.

[0031] An equipment end node prediction module is used to determine the remaining equipment demand set if the first unloading equipment matching scheme does not fully meet the unloading equipment demand set, obtain multiple real-time operation data sets of multiple adapted working equipment sets of the remaining equipment demand set through the equipment monitoring platform, predict the operation end node according to the multiple real-time operation data sets, and determine multiple predicted end node sets; a working equipment matching module is used to determine the initial second unloading equipment matching scheme of the remaining equipment demand set with the restriction that the predicted end node is earlier than the predicted demand node, optimize and analyze the initial second unloading equipment matching scheme, and output the second unloading equipment matching scheme; an unloading operation scheduling module is used to execute the arrival unloading operation of the target cargo ship based on the first unloading equipment matching scheme or the second unloading equipment matching scheme.

[0032] If the first unloading equipment matching scheme does not fully meet the unloading equipment demand set, that is, there is no unloading equipment that meets the requirements in the first unloading equipment matching scheme, then the remaining equipment demand set is determined through the equipment end node prediction module, and the remaining equipment demand set is the unloading equipment scheme in a busy state. Through the equipment monitoring platform, multiple real-time operation data sets of multiple adapted working equipment sets of the remaining equipment demand set are obtained, and the operation end node prediction is performed according to the multiple real-time operation data sets to determine multiple predicted end node sets, and the multiple predicted end node sets contain the end time nodes of the equipment completion scheduling of different equipment schemes. Subsequently, through the working equipment matching module, the equipment scheme whose predicted end node is earlier than the predicted demand node is obtained, and the predicted demand node is the earliest time node in the predicted demand node set, and the initial second unloading equipment matching scheme that meets the above requirements of the remaining equipment demand set is determined. The initial second unloading equipment matching scheme is optimized and analyzed, and the second unloading equipment matching scheme is output. Finally, the unloading operation scheduling module is performed to perform the unloading operation of the target cargo ship at the port based on the first unloading equipment matching scheme or the second unloading equipment matching scheme. The technical problem that the existing technology of port container loading and unloading operations is difficult to adapt to the dynamically changing logistics needs, resulting in low operating efficiency, low equipment utilization, and difficulty in improving the port's operating efficiency has been solved. By combining weather forecast information and real-time transportation information, the arrival time of cargo ships is accurately predicted, and based on the loading layout and cargo list, combined with unloading priority analysis and simulation, the equipment requirements are accurately determined, which improves the operating efficiency and equipment utilization, and further improves the port's operating efficiency.

[0033] Furthermore, the equipment end node prediction module 14 is also used to: obtain multiple working equipment through the equipment monitoring platform, match the remaining equipment demand set with the multiple working equipment, and determine multiple adaptive working equipment sets; randomly select a first adaptive working equipment set from the multiple adaptive working equipment sets, and select the first adaptive working equipment; collect real-time operation data of the first adaptive working equipment to obtain first real-time operation data, wherein the first real-time operation data includes a first remaining workload, a first operation type, and a first equipment location coordinate; perform operation end prediction based on the first remaining workload and the first operation type to obtain a first initial end node, compensate the first initial end node based on the first equipment location coordinate, output the first predicted end node, add it to the first predicted end node set, and obtain multiple predicted end node sets.

[0034] A plurality of working devices are obtained through the equipment monitoring platform, and the remaining equipment demand set is matched with the plurality of working devices, wherein the remaining equipment demand set includes equipment solutions in a busy state, and a plurality of adapted working equipment sets are determined. The plurality of adapted working equipment sets include specific equipment solutions and corresponding equipment working states. A first adapted working equipment set is randomly selected from the plurality of adapted working equipment sets, and the first adapted working equipment is selected. Real-time operation data of the first adapted working equipment is collected to obtain first real-time operation data, wherein the first real-time operation data includes a first remaining workload, a first operation type, and a first equipment location coordinate. Finally, the operation end prediction is performed according to the first remaining workload and the first operation type to obtain a first initial end node. The first initial end node is the time node when the first adapted working equipment completes the current unloading work. Subsequently, the first initial end node is compensated according to the first equipment location coordinate, that is, the equipment scheduling time is obtained according to the location coordinate, the first initial end node is compensated based on the equipment scheduling time, the first predicted end node is output, and the first predicted end node is added to the first predicted end node set, and a plurality of predicted end node sets of different equipment solutions are obtained.

[0035] Furthermore, the equipment end node prediction module 14 is also used to: obtain the predicted operating position coordinates of the target cargo ship, calculate the equipment scheduling distance based on the predicted operating position coordinates and the first equipment position coordinates, and determine the first equipment scheduling distance; obtain the first unit distance scheduling time of the first adaptive working equipment, calculate the first equipment scheduling time based on the first equipment scheduling distance and the first unit distance scheduling time, and compensate the first initial end node according to the first equipment scheduling time.

[0036] The predicted operation position coordinates of the target cargo ship, i.e., the coordinates of the target cargo ship for unloading, are obtained, and the equipment scheduling distance is calculated according to the predicted operation position coordinates and the first equipment position coordinates to determine the first equipment scheduling distance. Subsequently, the first unit distance scheduling time of the first adaptable working equipment is obtained, and the first unit distance scheduling time is the time required to move the unit distance. The first equipment scheduling time is calculated according to the first equipment scheduling distance and the first unit distance scheduling time, and the first equipment scheduling time is the ratio of the first equipment scheduling distance to the first unit distance scheduling time. The first initial end node is compensated by summing the first equipment scheduling time with the first initial end node.

[0037] Further, the working equipment matching module 15 is also used to: identify the initial second unloading equipment matching scheme, and if the number of second matching equipment is greater than the number of remaining equipment required, determine multiple redundant matching equipment; obtain multiple equipment characteristics and multiple equipment scheduling distances of the multiple redundant matching equipment, wherein the equipment characteristics at least include the remaining oil volume and equipment performance; perform performance evaluation on multiple redundant matching equipment based on the remaining oil volume and equipment performance to obtain multiple performance evaluation coefficients; perform equipment fitness analysis based on the multiple performance evaluation coefficients and multiple equipment scheduling distances to determine multiple equipment fitness, wherein the equipment fitness calculation function is: ;in, For device adaptability, is the distance weight, is the performance weight, Distance for device scheduling, is a performance evaluation coefficient; based on the adaptability of the multiple devices, multiple redundant matching devices are screened to determine the optimal matching device; according to the optimal matching device, the initial second unloading device matching scheme is optimized and updated, and the second unloading device matching scheme is output.

[0038] Identify the initial second unloading equipment matching scheme. If the number of second matching devices is greater than the remaining number of devices required, determine multiple redundant matching devices. Redundant matching devices refer to the number of devices in the initial matching scheme whose equipment requirements are less than the remaining number of devices. Obtain multiple device characteristics and multiple device scheduling distances of the multiple redundant matching devices, wherein the equipment characteristics at least include the remaining oil volume and equipment performance, and the equipment performance is the unloading rate per unit time. Perform performance evaluation on multiple redundant matching devices based on the remaining oil volume and equipment performance to obtain multiple performance evaluation coefficients, and the performance evaluation coefficient is equal to the remaining oil volume multiplied by the equipment performance. Perform equipment fitness analysis based on the multiple performance evaluation coefficients and multiple equipment scheduling distances to determine the fitness of multiple devices. When determining the fitness of multiple devices, use the equipment fitness calculation function to perform fitness calculation. The equipment fitness calculation function is: ;in, For device adaptability, is the distance weight, is the performance weight, Distance for device scheduling, is the performance evaluation coefficient, and the distance weight and performance weight are both preset weight parameters. When the importance of the distance is high, the corresponding distance weight parameter accounts for a high proportion, otherwise the weight parameter accounts for a low proportion, and the sum of the distance weight and the performance weight is 1. The equipment fitness is equal to the ratio of the performance evaluation coefficient to the equipment scheduling distance. Based on the multiple equipment fitnesses, multiple redundant matching devices are screened, and multiple devices with the largest fitness are obtained to determine the optimized matching device. The initial second unloading equipment matching scheme is optimized and updated according to the optimized matching device, and the second unloading equipment matching scheme is output.

[0039] The embodiment of the present application reads the transportation information of the target cargo ship, predicts the arrival time based on the weather forecast information and the transportation information, and determines the predicted arrival node, wherein the transportation information includes container loading data, and the container loading data includes loading layout and cargo list; based on the predicted arrival node, loading layout and cargo list, with the constraint of meeting the expected unloading demand, simulation is performed in the port loading and unloading twin platform to determine the unloading equipment demand set, wherein the unloading equipment demand set includes the predicted demand node set, multiple equipment type sets and multiple equipment quantity sets; based on the multiple equipment type sets and multiple equipment quantity sets, the equipment resource library is called to match the idle equipment, and the first unloading equipment matching formula is generated. If the first unloading equipment matching scheme does not fully meet the unloading equipment demand set, determine the remaining equipment demand set, obtain multiple real-time operation data sets of multiple adaptive working equipment sets of the remaining equipment demand set through the equipment monitoring platform, predict the operation end node according to the multiple real-time operation data sets, and determine multiple predicted end node sets; with the predicted end node earlier than the predicted demand node as the restriction, determine the initial second unloading equipment matching scheme of the remaining equipment demand set, optimize and analyze the initial second unloading equipment matching scheme, and output the second unloading equipment matching scheme; perform the unloading operation of the target cargo ship at the port based on the first unloading equipment matching scheme or the second unloading equipment matching scheme. The technical problem that the port container loading and unloading operation is difficult to adapt to the dynamically changing logistics demand in the prior art is solved, resulting in low operation efficiency, low equipment utilization rate, and difficulty in improving the operation efficiency of the port. By combining weather forecast information and real-time transportation information, the arrival time of the cargo ship is accurately predicted, and based on the loading layout and cargo list, combined with unloading priority analysis and simulation, the equipment demand is accurately determined, the operation efficiency and equipment utilization rate are improved, and the operation efficiency of the port is further improved.

[0040] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A digital loading and unloading control system for port logistics containers, characterized in that: include: The arrival time prediction module is used to read the transportation information of the target cargo ship, predict the arrival time based on the weather forecast information and the transportation information, and determine the predicted arrival node, wherein the transportation information includes container loading data, and the container loading data includes loading layout and cargo list; The unloading equipment demand analysis module is used to perform simulation in the port loading and unloading twin platform based on the predicted port arrival node, loading layout and cargo list, with the expected unloading demand as a constraint, to determine the unloading equipment demand set, wherein the unloading equipment demand set includes a predicted demand node set, multiple equipment type sets and multiple equipment quantity sets; An idle equipment matching module, configured to call an equipment resource library to match idle equipment based on the multiple equipment type sets and the multiple equipment quantity sets, and generate a first unloading equipment matching solution; An equipment end node prediction module is used to determine the remaining equipment demand set if the first unloading equipment matching solution does not fully meet the unloading equipment demand set, obtain multiple real-time operation data sets of multiple adaptive working equipment sets of the remaining equipment demand set through the equipment monitoring platform, perform operation end node prediction based on the multiple real-time operation data sets, and determine multiple predicted end node sets; A working equipment matching module is used to determine an initial second unloading equipment matching scheme for the remaining equipment demand set with the prediction end node being earlier than the prediction demand node as a restriction, optimize and analyze the initial second unloading equipment matching scheme, and output a second unloading equipment matching scheme; The unloading operation scheduling module is used to execute the unloading operation of the target cargo ship at the port based on the first unloading equipment matching plan or the second unloading equipment matching plan.

2. According to the digital loading and unloading control system of port logistics containers as described in claim 1, it is characterized in that: The arrival time prediction module is also used for: Reading the transport information of the target cargo ship, wherein the transport information includes the cargo ship type, the sailing route, the remaining sailing distance and the container loading amount; Collecting weather forecast information, wherein the weather forecast information includes at least wind direction and wind speed; The wind direction, wind speed and remaining sailing distance are input into the navigation predictor to predict the arrival time, and the predicted arrival node is output, wherein the navigation predictor includes multiple prediction units, and the output is the average of the output results of the multiple prediction units.

3. According to claim 2, a digital loading and unloading control system for port logistics containers is characterized in that: The arrival time prediction module is also used for: Taking the cargo ship type, sailing route and container loading as constraints, positive sample retrieval is performed based on big data to obtain a retrieval data set, where the retrieval data includes sample wind direction, sample wind speed, sample sailing distance and sample sailing time; The retrieval data set is differentially screened to obtain a training data set, and the training data set is used to perform supervised training and cross-validation on multiple prediction units to generate the navigation predictor, wherein the prediction units and prediction operators correspond one to one, and the prediction operators include at least BP neural network, random decision forest and support vector machine.

4. According to claim 3, a digital loading and unloading control system for port logistics containers is characterized in that: The arrival time prediction module is also used for: randomly extracting first retrieval data from the retrieval data set, wherein the first retrieval data includes a first sample wind direction, a first sample wind speed, and a first sample sailing distance; Calculate the deviation between the first sample wind direction and other sample wind directions in the retrieved data set, and count the number of wind direction deviations greater than a predetermined wind direction threshold, setting the number as a first difference degree; If the first difference is greater than a predetermined difference threshold, performing deviation calculation on the first sample wind speed and other sample wind speeds in the retrieved data set to determine a second difference; If the second difference is greater than a predetermined difference threshold, a deviation is calculated between the first sample navigation distance and other sample navigation distances in the retrieval data set to obtain a third difference; if the third difference is greater than a predetermined difference threshold, the first retrieval data is added to the training data set.

5. According to the digital loading and unloading control system of port logistics containers as described in claim 1, it is characterized in that: The unloading equipment demand analysis module is also used for: performing an unloading priority analysis based on the loading layout and the cargo list to determine a container unloading sequence, wherein the cargo list includes multiple container types; In the port loading and unloading twin platform, according to the container unloading sequence and subject to the constraint of meeting the expected unloading demand, unloading simulation is performed according to the predicted arrival node and cargo list, and the unloading start node corresponding to each container type is determined and set as the demand prediction node to obtain the unloading equipment demand set, wherein the unloading equipment demand set includes a predicted demand node set, multiple equipment type sets and multiple equipment quantity sets.

6. According to the digital loading and unloading control system of port logistics containers as claimed in claim 1, it is characterized in that: The device end node prediction module is also used for: Acquire multiple working devices through the device monitoring platform, match the remaining device requirement set with the multiple working devices, and determine multiple adapted working device sets; Randomly selecting a first set of adapted working devices from the plurality of sets of adapted working devices, and selecting a first adapted working device; Collecting real-time operation data of a first adaptable working device to obtain first real-time operation data, wherein the first real-time operation data includes a first remaining workload, a first operation type, and a first device position coordinate; The job end prediction is performed according to the first remaining workload and the first job type to obtain a first initial end node, the first initial end node is compensated according to the first device position coordinates, the first predicted end node is output, and the first predicted end node is added to the first predicted end node set to obtain multiple predicted end node sets.

7. According to claim 6, a digital loading and unloading control system for port logistics containers is characterized in that: The device end node prediction module is also used for: Acquire the predicted operating position coordinates of the target cargo ship, calculate the equipment scheduling distance according to the predicted operating position coordinates and the first equipment position coordinates, and determine the first equipment scheduling distance; A first unit distance scheduling time of a first adaptation working device is obtained, a first device scheduling time is calculated according to the first device scheduling distance and the first unit distance scheduling time, and a first initial end node is compensated according to the first device scheduling time.

8. According to claim 1, a digital loading and unloading control system for port logistics containers is characterized in that: The working equipment matching module is also used for: Identifying the initial second unloading equipment matching solution, and if the number of second matching equipment is greater than the number of remaining equipment required, determining a plurality of redundant matching equipment; Acquire multiple device characteristics and multiple device dispatching distances of the multiple redundant matching devices, wherein the device characteristics at least include remaining oil volume and device performance; Based on the remaining oil volume and the equipment performance, a plurality of redundant matching equipment are evaluated for performance to obtain a plurality of performance evaluation coefficients; The device adaptability analysis is performed according to the multiple performance evaluation coefficients and the multiple device scheduling distances to determine multiple device adaptabilities, wherein the device adaptability calculation function is: ; in, For device adaptability, is the distance weight, is the performance weight, Distance for device scheduling, is the performance evaluation coefficient; Based on the multiple device adaptability, multiple redundant matching devices are screened to determine the optimal matching device, and the initial second unloading device matching solution is optimized and updated according to the optimal matching device, and the second unloading device matching solution is output.

Images