Quay crane operation queue intelligent scheduling data processing method

Abstract

The invention discloses a quay crane operation queue intelligent scheduling data processing method, and belongs to the technical field of intelligent scheduling, and the method comprises the steps: 1, preparing data, processing the data including ship information, equipment information, queue information and rule configuration, and then setting constraint conditions including a preset limiting condition and a target constraint condition; 2, building a CWP algorithm framework; 3, initializing parameters, carrying out data preprocessing, initializing parameters and variables required by an algorithm, and executing scheduling; step 4, constructing a neural network, establishing a neural network model of reinforcement learning, and realizing data progressive extraction from an input layer, a processing layer, a feature fusion layer, a decision layer to an output layer; and 5, training the network and updating parameters. The defects of a traditional scheduling algorithm are overcome, scheduling mode diversification is achieved, global optimization of intelligent scheduling is achieved, and a more flexible, efficient and intelligent job scheduling solution is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent scheduling, and in particular to a data processing method for intelligent scheduling of a quay crane operation queue. Background Art

[0002] Intelligent dispatching of port terminals will use the achievements of Internet of Things technology, artificial intelligence, etc., combined with real-time data on the status of machinery and equipment on the production site, berths, vehicle transportation, etc., and interact with the ship's driving status in real time. Through prediction, the best decision-making plan can be formulated to achieve seamless connection between information system instructions and terminal machinery and equipment control functions, improve operational efficiency and accuracy, ensure the continuity, coordination, balance and economic operation of the production process, and maximize production benefits. This is the future development trend.

[0003] In view of the above-mentioned related technologies, the applicant found that in the current intelligent scheduling algorithm for terminals, the scheduling strategy based on the principle of shortest distance is generally adopted. However, with the continuous emergence of complex factors in practical applications and the growing demand for efficient operation, traditional scheduling algorithms have gradually exposed their inherent defects, that is, the scheduling method is single, mainly relying on distance optimization, ignoring factors such as the actual operation progress of the terminal and the urgency of different operation lines. These algorithms may balance factors such as distance and time to a certain extent, but there may be problems of local optimality rather than global optimality. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a data processing method for intelligent scheduling of quay crane operation queues, which solves the defects of traditional scheduling algorithms, realizes diversified scheduling methods, achieves global optimization of intelligent scheduling, and provides a more flexible, efficient and intelligent operation scheduling solution.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: A method for processing data of intelligent scheduling of a quay crane operation queue comprises the following steps: Step 1: Prepare data, process data including ship information, equipment information, queue information and rule configuration, and then set constraints, including preset constraints and target constraints; Step 2: Build the CWP algorithm framework and input the data into the CWP algorithm framework. The general process of the CWP algorithm framework is data preprocessing. Each job queue is divided into groups of different priorities according to the bay position, loading and unloading type, and position information in the cabin. The job queues of each group are traversed for allocation. The queue allocation strategy is determined by the neural network. During the allocation, whenever a quay crane completes the current queue, that is, it is in an idle state, it needs to be assigned a new task. After the allocation, the current quay crane information and the surrounding operational queue status change accordingly. The updated new quay crane and queue status are input into the neural network to solve the best allocable queue until all grouped queues are allocated. Step 3: Initialize parameters, perform data preprocessing, initialize parameters and variables required by the algorithm, and execute scheduling; Step 4: Construct a neural network and establish a neural network model for reinforcement learning to achieve progressive data extraction from the input layer, processing layer, feature fusion layer, decision layer to the output layer; Step 5: Train the network and update the parameters. The method of allocating first and then training is adopted. In each training, the unupdated neural network is first called to execute the CWP algorithm to provide an allocation and scheduling plan for the quay crane and the queue. After obtaining the output results of the current neural network under different inputs, the reward values ​​and evaluation values ​​corresponding to the different quay crane queue states at each time are calculated as the basis for strategy updating.

[0006] Furthermore, in step 1, The ship information is the ship information required for loading and unloading operations given by TOS, including ship name, hull length, side-to-side approach, total number of shellfish, bow and stern positions, bow-to-stern distance, and estimated start and end time; Equipment information is the information of each operation line and its affiliated quay crane, including sequence number, current position, operation range, moving speed, single and double hook efficiency of loading and unloading ships, and maximum safety distance; The queue information includes the queue primary key, queue name, ship number, ship number, upper and lower cabin marks, operation type, and MOVE hook number; The rules are configured for other rule conditions that require unified special restrictions, including the average operation time for loading and unloading a hatch cover and the time it takes for the quay crane to pass the bridge.

[0007] Furthermore, in step 1, the preset restriction condition is: Condition a: Keep a safe distance between any quay cranes, and do not allow quay cranes to cross other quay cranes to reach a certain bay to prevent crossing:

[0009] Condition b: the sum of the distances moved by each quay crane during loading and unloading is as small as possible; Condition c: the average efficiency of all quay cranes per hour is as close as possible to the same; The target constraints are: Condition d, minimize the ship's completion time:

[0010] Condition e, minimize the difference between the completion time of each quay crane:

[0011] Where n is the number of quay cranes.

[0012] Furthermore, in step 2, If you find a solution: Execute the allocation results, allocate queues to the quay cranes, update the quay crane information, and update the queue information; If no solution is found: Put the current idle quay crane into a waiting state until there is an idle quay crane in the next completion queue to perform scheduling allocation together with it, and update the completion queue time of all quay cranes; If the queues in the current group are allocated, wait until all the quay cranes are idle and process the scheduling of the queues in the next group.

[0013] Furthermore, in step three, The parameters and variables required to initialize the algorithm are: Ship: Calculate the information of the bay position to which the operation queue belongs based on the side-to-side manner and the relevant information of the bow and stern; Operation line: According to the starting position of the operation range of the operation line, the range of bays where the quay crane can operate the ship is determined, and the initial bay is randomly assigned. The single and double hook efficiency of the loading and unloading ship is uniformly converted into the time required for a move, and the moving speed of the quay crane is converted into the time required to pass one bay; Operation queue: According to the bay position of the container to be operated under the cabin, add the operation queue that needs to open and close the hatch cover to the queue list, assign priority to each queue according to the general principle of first loading and then unloading, first unloading and then loading, and group different queues with priority as the main keyword and bay position data as the secondary keyword.

[0014] Furthermore, in step three, the execution time of each queue is estimated in advance, and the scheduling space can be fitted into a two-dimensional space with bay position and time axis as dimensions respectively.

[0015] Furthermore, in step three, Building the CWP algorithm framework includes the following steps: Step a, first traverse the job queue in each group until the current group is empty; Step b, then searching for all quay cranes with the earliest completion queue time, i.e., in an idle state, and calculating the range of bay positions that can be operated based on the current bay positions; Step c, searching for a job queue available for allocation according to the bay position range of the idle quay crane; Step d, representing the job line information and the current environment queue information as tensors, calling the neural network model, and generating a scheduling plan; Step e: If the neural network finds a solution, it will traverse each queue in the solution and assign it to the corresponding quay crane; Step f, if it involves moving the quay crane to a new bay, a moving queue is generated at the same time, and the status of the quay crane is updated, including the current bay position and completion time, and then the task is assigned to the quay crane, a job queue is generated, and the status of the quay crane is updated, and finally the assigned job queue in the group is deleted; Step g, if the neural network does not find a solution, wait until a new quay crane is free and repeat step dg; Step h, updating the completion time of all quay cranes; Step i: Repeat the above steps until all the grouped job queues are assigned.

[0016] Further, in step 4, the input layer includes quay crane information and environment and queue information; The processing layers include a fully connected feature encoder and a recurrent neural network encoder; The information fusion layer includes concatenation and attention mechanism plus feature extraction layer.

[0017] Furthermore, in step five, in terms of the evaluation strategy, for the short-term return of the allocation result, in the process of each model calling the allocation queue, the input of the algorithm is the state of the quay crane and the current environment queue state information, and the output is the selected queue information. The current bay position of the model, the bay position of the target queue and the number of MOVEs are comprehensively considered for evaluation. For the future return of the model allocation, after each calculation of the allocation plan for all queues, the future return of the allocation plan can be comprehensively evaluated based on the difference between the estimated completion time of the ship and the end time of all quay cranes, the sum of the moving distances of all quay cranes, and the sum of waiting times.

[0018] In summary, compared with the prior art, the above technical solution has the following beneficial effects: (1) By combining multiple factors such as real-time location information, operable range, demand for operating lines, and busyness, the algorithm can realize reasonable and efficient intelligent scheduling of the operation queue instructions issued by the Terminal Operating System (TOS) and the quay crane equipment. This algorithm can not only provide a reasonable and efficient queue scheduling plan, effectively reduce equipment congestion and idle waiting, but also dynamically adjust the operation queue under the premise of complying with a series of constraints. Even if new container trucks are added or the position changes during the execution process, it can respond quickly to achieve more reasonable resource allocation; (2) The present invention realizes the independence and non-interference between the operating quay cranes, ensuring that each quay crane can execute the queue safely and efficiently even in a complex operating environment, greatly improving the stability and reliability of the system; (3) The present invention provides a general CWP algorithm framework that quantifies the time dimension of the queue as the height in a two-dimensional space. Other algorithms can also be applied in this framework to calculate efficient and feasible scheduling plans; (4) The present invention can not only provide a scheduling plan for the operation of the quay crane in advance, but also respond quickly even when a new quay crane is added during the operation or when resource changes occur in the time and space dimensions, thereby achieving more reasonable resource allocation; (5) An intelligent scheduling algorithm for job queues was designed by introducing a deep reinforcement learning algorithm. The scheduling plan provided by the algorithm optimized the problem of low utilization of quay crane resources, reduced traffic congestion in a certain operation area, and made the scheduling process more reasonable and efficient. At the same time, the algorithm quickly responded to idle quay crane resources and balanced the progress of each job queue, which not only improved the operation efficiency, but also reduced the workload of operators and saved terminal costs. In addition, the process of allocating queues also reduced the ineffective waiting time of the quay cranes and minimized the latest end time between quay cranes, thereby significantly improving the overall operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of intelligent scheduling logic in an embodiment of the present invention; Figure 2 A schematic diagram of a neural network structure in an embodiment of the present invention; Figure 3 This is a visualization allocation result diagram of the six quay cranes on board a ship in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The principles and features of the present invention are described below in conjunction with all the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0021] The embodiment of the invention discloses a method for processing data of intelligent scheduling of a quay crane operation queue.

[0022] The present invention mainly relates to a Crane Workqueue Planning (CWP) algorithm for port and wharf operations in the field of logistics scheduling. In the current scheduling algorithm, the scheduling strategy based on the shortest distance principle is generally adopted. However, with the continuous emergence of complex factors in practical applications and the growing demand for efficient operation, the traditional scheduling algorithm has gradually exposed its inherent defects as follows: 1. Single dispatching method: mainly relying on distance optimization, ignoring factors such as the actual operation progress of the terminal and the urgency of different operation lines; these methods may balance factors such as distance and time to a certain extent, but there may be problems of local optimality rather than global optimality.

[0023] 2. Poor utilization of quay cranes: Scheduling that only considers a single factor often leads to large-scale congestion of some quay cranes in certain areas, while there is a shortage of quay cranes in other areas. This not only affects the utilization of equipment, but also greatly reduces the overall scheduling effect.

[0024] 3. Lack of dynamic adjustment: Once a scheduling plan is formulated, it is difficult to adjust. Tasks can only be executed based on pre-allocated quay crane resources and operation queues. If new resources are added in the middle, the scheduling algorithm cannot dynamically adjust the allocation, which can easily lead to problems such as unreasonable resource allocation and slow response speed.

[0025] 4. Dynamic bay allocation: Traditional algorithms can often only operate within the range of bays planned in advance, and cannot dynamically adjust the bays according to the urgency of actual work needs and other conditions during execution. This limitation is more obvious in complex and changing working environments.

[0026] The present invention aims to provide a CWP algorithm based on deep reinforcement learning, which realizes reasonable and efficient intelligent scheduling of the operation queue instructions issued by TOS and the quay crane equipment by combining multiple factors such as real-time location information, operable range, demand for the operation line, and busyness. It can not only provide a reasonable and efficient queue scheduling plan, effectively reduce equipment congestion and idle waiting, but also dynamically adjust the operation queue under the premise of complying with a series of constraints. Even if a new container truck is added or the position changes during the execution process, it can respond quickly to achieve more reasonable resource allocation.

[0027] In summary, the present invention provides a more flexible, efficient and intelligent operation scheduling solution, which helps to improve the overall operational efficiency of ports and terminals, reduce operating costs and improve service quality.

[0028] A data processing method for intelligent scheduling of quay crane operation queues. The idea of ​​the present invention is mainly to assign the pending operation instructions issued by TOS to different quay cranes, and guide the quay cranes to automatically load and unload containers on board. In the scheduling process, the target constraints are to minimize the estimated completion time of the ship and minimize the difference in the end time between all quay cranes. Combined with the current position of the quay crane, the matching degree between the quay crane and the operation position, and under the premise of strictly complying with a series of preset constraints, the intelligent algorithm automatically calculates the optimal allocation relationship between the quay crane and the queue through comprehensive optimization and deployment.

[0029] refer to Figure 1 A method for processing data of intelligent scheduling of a quay crane operation queue is provided. The method of the present invention comprises the following steps: Step 1: Prepare data Processing data including vessel information, equipment information, queue information and rule configuration, and then setting constraints, including preset constraints and target constraints; (1) Data processing The ship information is the ship information required for loading and unloading operations given by TOS, including ship name, hull length, side-to-side approach, total number of shells, bow and stern positions, bow-to-stern distance, estimated start and end time, etc. Please refer to the following Table 1: Table 1 Comparison table of variable information of ship number Data Objects Remark vslVisitGkey Vessel number primary key vslId Vessel Code / ID vslName Vessel Name vslLoa Length Over All bayNum Total number of shells bethingSide Side-to-side mode, PS: port side; SS: starboard side bowPos Bow position sternPos Stern position bowToBay Bow distance, the distance from the bow to the first shell sternToBay The distance from the stern to the last 1cm bowToBridge Number of shells in front of cab 1 sternToBridge Number of shells in front of cab 2 visitPhase Vessel berthing status etbTime Estimated berthing time etwTime Estimated start time etcTime Estimated completion time etdTime Estimated time of departure rtbTime Actual berthing time The equipment information is the information of each operation line and its affiliated quay crane, including sequence number, current position, operation range, moving speed, single and double hook efficiency of loading and unloading ships, maximum safety distance, etc. Please refer to the following Table 2: Table 2 Variable information comparison table of quay crane operation line Data Objects Remark lineGkey Job line primary key vslVisitGkey Vessel number primary key powId Operation point, quay crane number linearSeq Sequence number of the quay crane on the shoreline, EQP_SET startPos Quay crane operating range - starting position, unit: meter endPos Quay crane operation range - end position, unit: meter avgGantryVelocity Average moving speed of the trolley (m / min) vslJobSpace Operation interval - liner operation interval (BAY) eqpWidth Width of shore equipment (m) deadSafeDist Maximum safety distance DISTANCE etwTime Estimated start time etcTime Estimated end time prodt11 Expected efficiency, unloading - single hook prodt12 Expected efficiency, unloading - double hook prodt21 Expected efficiency, loading - single hook prodt21 Expected efficiency, loading - double hook The queue information includes the queue primary key, queue name, corresponding ship number, ship number, upper and lower cabin marks, operation type, number of MOVE hooks, etc. Please refer to the following Table 3: Table 3 Job queue variable information comparison table Data Representation Remark queueGkey Job queue primary key queueName Job Queue Name lineGkey Job line primary key vslVisitGkey Vessel number primary key moveKind Task type, value: DSCH, LOAD vslBayNbr Ship No. deckHold Deck / hold sign moveQty MOVE number powId Operation point, quay crane number queueSeq Queue Order The rules are configured as other rule conditions that require unified special restrictions, including the average operation time for loading and unloading a hatch cover, the time it takes for the quay crane to pass the bridge, etc.

[0030] (2) Constraints The default constraints are: Condition a: Keep a safe distance between any quay cranes, and do not allow quay cranes to cross other quay cranes to reach a certain bay to prevent crossing:

[0031] Condition b: the sum of the distances moved by each quay crane during loading and unloading is as small as possible; Condition c: the average efficiency of all quay cranes per hour is as close as possible to the same; The target constraints are: Condition d, minimize the ship's completion time:

[0032] Condition e, minimize the difference between the completion time of each quay crane:

[0033] Where n is the number of quay cranes.

[0034] Step 2: Build the CWP algorithm framework Build the CWP algorithm framework and input the data into the CWP algorithm framework. The general process of the CWP algorithm framework is data preprocessing. Each job queue is divided into groups of different priorities according to information such as bay position, loading and unloading type, and position in the cabin. The job queues of each group are traversed for allocation. The queue allocation strategy is determined by the neural network. During the allocation, whenever a quay crane completes the current queue, that is, it is in an idle state, it needs to be assigned a new task. After the allocation, the current quay crane information and the surrounding operational queue status change accordingly. The updated new quay crane and queue status are input into the neural network to solve the best allocable queue until all grouped queues are allocated.

[0035] Input data: ship information, equipment information, queue information and rule configuration Algorithm flow: Data preprocessing Group queues into groups with different priorities Traverse the job queue of each group: Find all idle gantry cranes that complete the queue time earliest Update the status information of idle quay cranes and surrounding operational queues Call the neural network, input the quay crane and queue data, and output the solution: If you find a solution: Execute the allocation result and allocate a queue to the quay crane Update information of quay crane Update queue information If no solution is found: Put the current idle quay crane into a waiting state until the next idle quay crane that completes the queue is dispatched and allocated together with it Update the completion queue time of all quay cranes If the queues in the current group are allocated, wait until all the quay cranes are idle, process the scheduling of the queues in the next group, and reset the values ​​of some algorithm parameters.

[0036] Output data: Queue allocation list corresponding to each quay crane.

[0037] Step 3: Initialize parameters Perform data preprocessing, initialize the parameters and variables required by the algorithm, and perform scheduling (1) Data preprocessing Initialize the parameters and variables required by the algorithm Ship: Calculate the information of the bay position to which the operation queue belongs based on the side-to-side manner and the relevant information of the bow and stern; Operation line: According to the starting position of the operation range of the operation line, the bay position range of the ship that the quay crane can operate is determined, and the initial bay position is randomly assigned. The single and double hook efficiency of the loading and unloading ship is uniformly converted into the time required to make a MOVE (unit: second), and the moving speed of the quay crane is converted into the time required to pass one bay position (unit: second).

[0038] Operation queue: According to the bay position of the container to be operated under the cabin, add the operation queue that needs to open and close the hatch cover to the queue list, assign priority to each queue according to the principle of first loading and then unloading, first unloading and then loading, and group different queues with priority as the main keyword and other data such as bay position as secondary keywords. Since the process of executing the queue by the quay crane has a certain time sequence, this brings many unpredictable complex situations to the scheduling algorithm, so it is also necessary to estimate the execution time of each queue in advance. The scheduling space can be fitted into a two-dimensional space with bay position and time axis as dimensions (refer to Figure 3 As shown, the length of the column is the time cost of the corresponding queue).

[0039] (2) Building the CWP algorithm framework The steps include: Step a, first traverse the job queue in each group until the current group is empty; Step b, then searching for all quay cranes with the earliest completion queue time, i.e., in an idle state, and calculating the range of bay positions that can be operated based on the current bay positions; Step c, searching for a job queue available for allocation according to the bay position range of the idle quay crane; Step d, the information of the job line and the current environment queue is represented as a tensor, and the neural network model is called to generate a scheduling plan; Step e: If the neural network finds a solution, it will traverse each queue in the solution and assign it to the corresponding quay crane; Step f, if it involves moving the quay crane to a new bay, a moving queue is generated at the same time, and the status of the quay crane is updated, including the current bay position and completion time, and then the task is assigned to the quay crane, a job queue is generated, and the status of the quay crane is updated, and finally the assigned job queue in the group is deleted; Step g, if the neural network does not find a solution, wait until a new quay crane is free and repeat step dg; Step h, updating the completion time of all quay cranes; Step i: Repeat the above steps until all the grouped job queues are assigned.

[0040] Step 4: Build a neural network Build a neural network and establish a neural network model for reinforcement learning (see Figure 2 ), the network layer includes input layer, processing layer, feature fusion layer, decision layer and output layer. The composition and characteristics of each network layer are shown as follows: (1) The input layer includes quay crane information, environment and queue information Quay crane information: Assuming there are N quay cranes (i.e. N operating lines), the status of each quay crane is represented by a dimensional tensor, then the size of the quay crane tensor is .

[0041] Environment and queue information: Assume that environment information and executable queue information can be encoded into a dimensional vector, and the length of this vector can adapt to different amounts of environmental information input, but the width is fixed. Therefore, the size of this input tensor is , where M is variable.

[0042] (2) The processing layer includes a fully connected feature encoder and a recurrent neural network encoder Fully connected feature encoder: The encoder receives both the shore bridge state tensor and an integer i, where i indicates that this is the input of the i-th shore bridge. The shore bridge tensor uses a mask matrix to highlight the features of the i-th shore bridge while weakening the features of other shore bridges. The shore bridge state tensor is then processed using one or more stacked fully connected layers to extract the features of each shore bridge. The size of the output tensor is still ,in is the feature dimension after encoding.

[0043] Recurrent Neural Network Encoder: For the second input tensor, a recurrent neural network (such as LSTM or GRU) is used to process it because it has a variable length. This can capture the pattern in the sequence. The output tensor is of size The hidden state of the last time step of , or if more context information needs to be retained, the state of all time steps can be output, with a size of .

[0044] (3) Information fusion layer includes concatenation and attention mechanism plus feature extraction layer The outputs of the two encoders are combined in some way. One way is to concatenate the feature vector of each quay crane with the environment queue vector to form a new tensor , or use a multi-head attention mechanism to allow each quay crane to dynamically adjust its state representation based on environmental information.

[0045] (4) Decision-making level After information fusion, further feature extraction is performed through a series of fully connected layers, and finally an action probability distribution is output for the gantry crane. Because the action space is discrete, a softmax layer is used to generate the probability distribution.

[0046] (5) Output layer The size of the final output tensor is ,in Represents the possibility of selecting each action space. For the current pier, the output tensor contains a probability distribution over all possible queues.

[0047] Step 5: Train the network and update parameters Since there is great uncertainty in predicting future rewards based on the current status in each allocation step, the method of allocation first and then training is adopted. In each training, the unupdated neural network is first called to execute the CWP algorithm to provide an allocation scheduling plan for the quay crane and queue. After obtaining the output results of the current neural network under different inputs, the reward values ​​and evaluation values ​​corresponding to the different quay crane queue states at each moment are calculated as the basis for strategy updating.

[0048] In terms of evaluation strategy, for the short-term returns of the allocation results, in each process of the model calling the allocation queue, the input of the algorithm is the status of the quay crane and the current environment queue status information, and the output is the selected queue information. The evaluation is carried out by comprehensively considering the current bay position of the model, the bay position of the target queue, the number of MOVEs and other data through some form of measurement. For the future returns of the model allocation, after each calculation of the allocation plan for all queues, the future returns of the allocation plan can be comprehensively evaluated based on the gap between the estimated completion time of the ship and the end time of all quay cranes, the total moving distance of all quay cranes, the total waiting time and other aspects.

[0049] Therefore, the strategy update adopts the method of allocation first and then training. First, the unupdated neural network execution algorithm is called to generate a complete allocation scheduling plan for the quay crane and queue. After obtaining the output results of the current neural network under different inputs, various evaluation values ​​are calculated for the output results as the basis for strategy updating.

[0050] refer to Figure 3 , showing the scheduling results calculated by the algorithm for 6 quay cranes on a ship. Different colors represent different quay cranes, and the blank space in the middle of the rectangular box represents the waiting process.

[0051] The implementation effect of a method for intelligent scheduling data processing of a quay crane operation queue according to an embodiment of the present invention is as follows: By introducing a deep reinforcement learning algorithm, an intelligent scheduling method for job queues was designed. The scheduling plan provided optimized the problem of low utilization of quay crane resources, reduced traffic congestion in a certain operation area, and made the scheduling process more reasonable and efficient. At the same time, the algorithm quickly responded to idle quay crane resources and balanced the progress of each job queue, which not only improved the operation efficiency, but also reduced the workload of operators and saved terminal costs. In addition, the process of allocating queues also reduced the ineffective waiting time of the quay cranes and minimized the latest end time between quay cranes, thereby significantly improving the overall operation efficiency.

[0052] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for intelligent scheduling data processing of quay crane operation queues, characterized in that: The steps include: Step 1: Prepare data, process data including ship information, equipment information, queue information and rule configuration, and then set constraints, including preset constraints and target constraints; Step 2: Build the CWP algorithm framework and input the data into the CWP algorithm framework. The general process of the CWP algorithm framework is data preprocessing. Each job queue is divided into groups of different priorities according to the bay position, loading and unloading type, and position information in the cabin. The job queues of each group are traversed for allocation. The queue allocation strategy is determined by the neural network. During the allocation, whenever a quay crane completes the current queue, that is, it is in an idle state, it needs to be assigned a new task. After the allocation, the current quay crane information and the surrounding operational queue status change accordingly. The updated new quay crane and queue status are input into the neural network to solve the best allocable queue until all grouped queues are allocated. Step 3: Initialize parameters, perform data preprocessing, initialize parameters and variables required by the algorithm, and execute scheduling; Step 4: Construct a neural network and establish a neural network model for reinforcement learning to achieve progressive data extraction from the input layer, processing layer, feature fusion layer, decision layer to the output layer; Step 5: Train the network and update the parameters. The method of allocating first and then training is adopted. In each training, the unupdated neural network is first called to execute the CWP algorithm to provide an allocation and scheduling plan for the quay crane and the queue. After obtaining the output results of the current neural network under different inputs, the reward values ​​and evaluation values ​​corresponding to the different quay crane queue states at each time are calculated as the basis for strategy updating.

2. The method for intelligent scheduling data processing of a quay crane operation queue according to claim 1, characterized in that: In step one, The ship information is the ship information required for loading and unloading operations given by TOS, including ship name, hull length, side-to-side approach, total number of shellfish, bow and stern positions, bow-to-stern distance, and estimated start and end time; Equipment information is the information of each operation line and its affiliated quay crane, including sequence number, current position, operation range, moving speed, single and double hook efficiency of loading and unloading ships, and maximum safety distance; The queue information includes the queue primary key, queue name, ship number, ship number, upper and lower cabin marks, operation type, and MOVE hook number; The rules are configured for other rule conditions that require unified special restrictions, including the average operation time for loading and unloading a hatch cover and the time it takes for the quay crane to pass the bridge.

3. The method for intelligent scheduling data processing of quay crane operation queue according to claim 2 is characterized in that: In step 1, the preset constraints are: Condition a: Keep a safe distance between any quay cranes, and do not allow quay cranes to cross other quay cranes to reach a certain bay to prevent crossing: Condition b: the sum of the distances moved by each quay crane during loading and unloading is as small as possible; Condition c: the average efficiency of all quay cranes per hour is as close as possible to the same; The target constraints are: Condition d, minimize the ship's completion time: Condition e, minimize the difference between the completion time of each quay crane: Where n is the number of quay cranes.

4. The method for intelligent scheduling data processing of a quay crane operation queue according to claim 1, characterized in that: In step 2, If you find a solution: Execute the allocation results, allocate queues to the quay cranes, update the quay crane information, and update the queue information; If no solution is found: Put the current idle quay crane into a waiting state until there is an idle quay crane in the next completion queue to perform scheduling allocation together with it, and update the completion queue time of all quay cranes; If the queues in the current group are allocated, wait until all the quay cranes are idle and process the scheduling of the queues in the next group.

5. The method for intelligent scheduling data processing of quay crane operation queue according to claim 1 is characterized by: In step three, The parameters and variables required to initialize the algorithm are: Ship: Calculate the information of the bay position to which the operation queue belongs based on the side-to-side manner and the relevant information of the bow and stern; Operation line: According to the starting position of the operation range of the operation line, the range of bays where the quay crane can operate the ship is determined, and the initial bay is randomly assigned. The single and double hook efficiency of the loading and unloading ship is uniformly converted into the time required for a move, and the moving speed of the quay crane is converted into the time required to pass one bay; Operation queue: According to the bay position of the container to be operated under the cabin, add the operation queue that needs to open and close the hatch cover to the queue list, assign priority to each queue according to the general principle of first loading and then unloading, first unloading and then loading, and group different queues with priority as the main keyword and bay position data as the secondary keyword.

6. The method for intelligent scheduling data processing of quay crane operation queue according to claim 5 is characterized in that: In step three, the execution time of each queue is estimated in advance, and the scheduling space can be fitted into a two-dimensional space with bay position and time axis as dimensions.

7. The method for intelligent scheduling data processing of quay crane operation queue according to claim 1 is characterized by: In step three, Building the CWP algorithm framework includes the following steps: Step a, first traverse the job queue in each group until the current group is empty; Step b, then searching for all quay cranes with the earliest completion queue time, i.e., in an idle state, and calculating the range of bay positions that can be operated based on the current bay positions; Step c, searching for a job queue available for allocation according to the bay position range of the idle quay crane; Step d, representing the job line information and the current environment queue information as tensors, calling the neural network model, and generating a scheduling plan; Step e: If the neural network finds a solution, it will traverse each queue in the solution and assign it to the corresponding quay crane; Step f, if it involves moving the quay crane to a new bay, a moving queue is generated at the same time, and the status of the quay crane is updated, including the current bay position and completion time, and then the task is assigned to the quay crane, a job queue is generated, and the status of the quay crane is updated, and finally the assigned job queue in the group is deleted; Step g, if the neural network does not find a solution, wait until a new quay crane is free and repeat step dg; Step h, updating the completion time of all quay cranes; Step i: Repeat the above steps until all the grouped job queues are assigned.

8. The method for intelligent scheduling data processing of quay crane operation queue according to claim 1, characterized in that: In step 4, the input layer includes quay crane information and environment and queue information; The processing layers include a fully connected feature encoder and a recurrent neural network encoder; The information fusion layer includes concatenation and attention mechanism plus feature extraction layer.

9. The method for intelligent scheduling data processing of quay crane operation queue according to claim 1, characterized in that: In step five, in terms of the evaluation strategy, for the short-term return of the allocation result, in each process of the model calling the allocation queue, the input of the algorithm is the status of the quay crane and the current environment queue status information, and the output is the selected queue information. The current bay position of the model, the bay position of the target queue and the number of MOVEs are comprehensively considered for evaluation. For the future return of the model allocation, after each calculation of the allocation plan for all queues, the future return of the allocation plan can be comprehensively evaluated based on the gap between the estimated completion time of the ship and the end time of all quay cranes, the sum of the moving distances of all quay cranes, and the sum of waiting time.

Images