Scheduling method, system, readable storage medium and device for double-circulation rotation operation of quayside crane

Abstract

The invention discloses a bank crane double-circulation rotation operation scheduling method and system and a readable storage medium and device, and belongs to the technical field of bank crane hoisting operation. The method comprises the steps that crane bank operation is divided into ship side operation and vehicle side operation; crane state information is obtained and preprocessed; respectively establishing a ship-side operation time prediction model and a vehicle-side operation time prediction model based on a BP neural network, and respectively inputting the crane state information into the ship-side operation time prediction model and the vehicle-side operation time prediction model to obtain ship-side operation time and vehicle-side operation time; and calculating the load time of the lifting appliance according to the ship-side operation time and the vehicle-side operation time, and controlling the ship-side operation end and the vehicle-side operation end to operate according to the principle that the load time of the lifting appliance is shortest. By adopting the double-circulation rotation operation scheduling method, simultaneous operation of the ship end operation part and the vehicle end operation part can be realized, so that the whole operation process is cooperatively completed, and the operation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of shore crane lifting operations, and particularly to a double-cycle rotation operation scheduling method, system, readable storage medium and device for shore cranes. Background Art

[0002] Nowadays, the container throughput of ports is extremely large and growing rapidly. During the operation process, shore cranes and horizontal transportation systems are mainly used in combination to complete relevant ship loading and unloading tasks. In recent years, with the launch of automated and efficient scheduling systems, especially the application of driverless container trucks, the efficiency of horizontal transportation in ports has been greatly improved. Therefore, how to efficiently complete ship unloading and loading operations within the port to further improve port operation efficiency has become crucial.

[0003] Currently, the ship unloading and loading efficiency of shore cranes has become a key factor restricting the container throughput of ports. During the ship unloading or loading operation process of shore cranes, it is mainly a single-cycle operation, and its efficiency is relatively low. In the current ship unloading operation, a single-cycle operation process includes a series of operations such as grabbing containers on the ship, lifting height, horizontal movement, lowering height, and placing containers on the vehicle. This process is a single-cycle sequential operation process. It is difficult to improve the overall efficiency by enhancing the efficiency of a certain operation link. During the entire operation process, it is necessary to concentrate on docking containers to lift and lower the containers to dock with the vehicle. The operator needs to constantly switch roles to adjust the operation form, which is very time-consuming and laborious, and it is difficult to efficiently complete the entire operation process. Moreover, during the hoisting and transportation process of the hoisting tool, since the lifted goods cannot be loaded and unloaded in a timely manner, the use and wear of the tool will also increase due to the long-time hoisting of goods, reducing its service life. Summary of the Invention

[0004] Aiming at the problems existing in the prior art, the present invention provides a double-cycle rotation operation scheduling method, system, readable storage medium and device for shore cranes. By setting up a ship-side operation department, a transportation operation department and a vehicle-side operation department, and adopting a double-cycle rotation operation scheduling method, the ship-side operation department and the vehicle-side operation department are allowed to operate separately. Different from the single-cycle operation, the operator does not need to constantly switch roles according to the operation process. Two operators can simultaneously operate in the ship-side operation department and the vehicle-side operation department, thereby collaborating to complete the overall operation process and improving the overall operation efficiency.

[0005] The technical solution of the present invention is as follows:

[0006] In the first aspect of the present invention, a double-cycle rotation operation scheduling method for shore cranes is provided, including:

[0007] Obtaining the status information of the ship-side operation-end crane and the vehicle-side operation-end crane and performing preprocessing;

[0008] Based on the BP neural network, a prediction model for the ship-side operation time and a prediction model for the vehicle-side operation time are respectively established. The crane status information is input into the ship-side operation time prediction model and the vehicle-side operation time prediction model respectively to obtain the ship-side operation time and the vehicle-side operation time;

[0009] Calculate the spreader loading time according to the ship-side operation time and the vehicle-side operation time, and control the ship-side operation end and the vehicle-side operation end to operate according to the principle of the shortest spreader loading time.

[0010] In some embodiments of the present invention, the crane status information includes wind speed information, weather information, seawater flow velocity information, crane trolley speed information, crane trolley acceleration information, spreader pose information, and weight information of the lifted object.

[0011] In some embodiments of the present invention, specifically obtaining the ship-side operation time is as follows:

[0012] Perform outlier removal and data normalization processing on the wind speed information, weather information, seawater flow velocity information, crane trolley speed, crane trolley acceleration information, spreader pose information, and weight information of the lifted object. The processed data is input into the ship-side operation time prediction model for training, and the current crane status information is input into the ship-side operation time prediction model to obtain the predicted value of the operation time under the current ship-side working conditions.

[0013] In some embodiments of the present invention, specifically obtaining the vehicle-side operation time is as follows:

[0014] Perform outlier removal and data normalization processing on the wind speed information, weather information, seawater flow velocity information, crane trolley speed, crane trolley acceleration information, spreader pose information, and weight information of the lifted object. The processed data is input into the vehicle-side operation time prediction model for training, and the current crane status information is input into the vehicle-side operation time prediction model to obtain the predicted value of the operation time under the current vehicle-side working conditions.

[0015] In some embodiments of the present invention, the principle of the shortest spreader loading time is specifically as follows:

[0016] When performing ship-side container grabbing operation, the vehicle-side container grabbing spreader can arrive at the ship-side in advance when not grabbing the container. When the ship-side container grabbing spreader performs the container discharging operation at the vehicle-side, during the process of the ship-side container grabbing spreader grabbing the container at the ship-side and discharging it at the vehicle-side, it arrives at the vehicle-side on time after the ship-side container grabbing spreader finishes discharging the container;

[0017] When performing vehicle-side container grabbing operation, the ship-side container grabbing spreader can arrive at the vehicle-side in advance when not grabbing the container. When the vehicle-side container grabbing spreader performs the container discharging operation at the ship-side, during the process of the vehicle-side container grabbing spreader grabbing the container at the vehicle-side and discharging it at the ship-side, it arrives at the ship-side on time after the vehicle-side container grabbing spreader finishes discharging the container.

[0018] In a second aspect of the present invention, there is provided a system for a double-cycle rotation operation scheduling method of a shore crane, including:

[0019] A ship-end operation module, configured to receive instructions from the intelligent control module and independently complete the loading or unloading operation at the ship end;

[0020] A vehicle-end control module, configured to dock with the horizontal transportation module for vehicle arrival and departure messages, receive instructions from the intelligent control module, and independently complete the loading and unloading operations;

[0021] An intelligent control module, configured to respectively establish a ship-side operation time prediction model and a vehicle-side operation time prediction model based on the BP neural network according to the obtained crane status information, and predict the ship-side operation time and the vehicle-side operation time under different working conditions; calculate the spreader load time according to the ship-side operation time and the vehicle-side operation time, and control the ship-side operation end and the vehicle-side operation end to perform operations according to the principle of the shortest spreader load time.

[0022] In some embodiments of the present invention, it further includes:

[0023] A transportation control module, configured to transport the two spreaders from the vehicle end to the ship end or from the ship end to the vehicle end. When receiving the transportation instruction from the intelligent control module, it transports the specified spreader and transmits the information back to the intelligent control module after the transportation ends.

[0024] In some embodiments of the present invention, it further includes:

[0025] An information acquisition and processing module, configured to acquire the crane status information and perform preprocessing to obtain the processed wind speed information, seawater flow velocity information, trolley speed, trolley acceleration information, spreader pose information, and weight information of the lifted object;

[0026] A motor scheduling module, receiving instructions from the intelligent control module, and completing the switching and scheduling work of the cranes motors at the ship-side operation end and the vehicle-side operation end.

[0027] In a third aspect of the present invention, there is provided a readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the above-mentioned double-cycle rotation operation scheduling method of a shore crane.

[0028] In a fourth aspect of the present invention, there is provided a processing device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the above-mentioned double-cycle rotation operation scheduling method of a shore crane.

[0029] One or more technical solutions of the present invention have the following beneficial effects:

[0030] The present invention is applicable to the field of task scheduling for ship loading and unloading operations of shore cranes. It can make full use of the lifting operation ability of the machine. After dividing a single-cycle operation into three independent operation modules, a double-cycle rotation operation scheduling method is adopted to separate the operation of the ship-side operation department and the vehicle-side operation department. Different from the single-cycle operation, the operations of two single-cycles can be transformed into two independent ship-side operations, two vehicle-side operations, and one transportation control operation. Two lifting drivers can work separately in the ship-side operation department and the vehicle-side operation department. The operator does not need to constantly switch roles according to the operation process. Two operators can perform operations in the ship-side operation department and the vehicle-side operation department simultaneously. Each operator focuses on their own unique ship-side tasks or vehicle-side tasks, thus collaborating to complete the overall operation process and improving the overall operation efficiency.

[0031] In addition, during the single-cycle operation process of container grabbing on the ship, lifting height, horizontal movement, lowering height, and placing the container on the vehicle, the lifting tool needs to lift the container throughout the operation process. At the same time, due to the low transfer efficiency of each operation process, there is a situation where the lifting tool waits for lifting goods during the operation. Over time, this will increase the wear and tear of the lifting tool and increase the subsequent maintenance cost. However, in the double-cycle rotation operation scheduling method proposed by the present invention, since the ship-side operation department and the vehicle-side operation department operate separately, the situation where the lifting tool waits for lifting goods is greatly reduced, improving the operation efficiency while reducing the use loss of the lifting tool and increasing its service life. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic flow chart of a double-cycle rotation operation scheduling method for a shore crane provided in Embodiment 1 of the present invention;

[0033] Figure 2 It is a schematic diagram of the intelligent control module provided in Embodiment 1 of the present invention;

[0034] Figure 3 It is a schematic diagram of the ship-side operation time prediction model provided in Embodiment 1 of the present invention;

[0035] Figure 4 It is a schematic diagram of the BP neural network structure provided in Embodiment 1 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0036] The present invention will be further described below in conjunction with the drawings and embodiments.

[0037] Embodiment 1

[0038] In a typical implementation manner of the present invention, a double-cycle rotation operation scheduling method for a shore crane is proposed, including:

[0039] Obtain the status information of the ship-side operation end crane and the vehicle-side operation end crane and perform preprocessing;

[0040] Based on the BP neural network, a prediction model for the ship-side operation time and a prediction model for the vehicle-side operation time are respectively established. The crane status information is input into the prediction model for the ship-side operation time and the prediction model for the vehicle-side operation time respectively to obtain the ship-side operation time and the vehicle-side operation time;

[0041] Calculate the spreader loading time according to the ship-side operation time and the vehicle-side operation time, and control the ship-side operation end and the vehicle-side operation end to operate according to the principle of the shortest spreader loading time.

[0042] In some embodiments of the present invention, the crane status information includes wind speed information, weather information, seawater flow velocity information, crane trolley speed information, crane trolley acceleration information, spreader pose information, and weight information of the lifted object.

[0043] In some embodiments of the present invention, the specific method for obtaining the ship-side operation time is as follows:

[0044] Perform outlier rejection and data normalization processing on the wind speed information, weather information, seawater flow velocity information, crane trolley speed, crane trolley acceleration information, spreader pose information, and weight information of the lifted object. The processed data is input into the prediction model for the ship-side operation time for training, and the current crane status information is input into the prediction model for the ship-side operation time to obtain the predicted value of the operation time under the current ship-side working conditions.

[0045] In some embodiments of the present invention, the specific method for obtaining the vehicle-side operation time is as follows:

[0046] Perform outlier rejection and data normalization processing on the wind speed information, weather information, seawater flow velocity information, crane trolley speed, crane trolley acceleration information, spreader pose information, and weight information of the lifted object. The processed data is input into the prediction model for the vehicle-side operation time for training, and the current crane status information is input into the prediction model for the vehicle-side operation time to obtain the predicted value of the operation time under the current vehicle-side working conditions.

[0047] In some embodiments of the present invention, the principle of the shortest spreader loading time is specifically as follows:

[0048] When performing ship-side container grabbing operations, the vehicle-side container grabbing spreader can arrive at the ship-side in advance when not grabbing containers. When the ship-side container grabbing spreader performs container discharging operations on the vehicle-side, during the process of the ship-side container grabbing spreader grabbing a container at the ship-side and discharging it at the vehicle-side, the vehicle-side container grabbing spreader arrives at the vehicle-side on time after the ship-side container grabbing spreader finishes discharging the container;

[0049] When performing the operation of grasping containers on the vehicle side, the container-grabbing spreader on the ship side can arrive at the vehicle side in advance to wait when it is not grasping containers. When the container-grabbing spreader on the vehicle side is performing the operation of discharging containers on the ship side, during the process of the container-grabbing spreader on the vehicle side grasping the container at the vehicle side and discharging it at the ship side, it arrives at the ship side on time after the container-grabbing spreader on the vehicle side finishes discharging the container.

[0050] It can be understood that when one end of the spreader on the ship side or the vehicle side is operating, the spreader at the other end can arrive at one side in advance to wait without load. If the spreader at the other end needs to perform the operation of grasping containers, it cannot arrive in advance because the energy consumption is relatively large under load. In order to achieve the optimal benefit, it is necessary to wait for the instruction to perform the operation of grasping containers, so that the waiting time of the other spreader under load is the shortest.

[0051] In this embodiment, training the BP neural network model includes the following steps:

[0052] S1: Input nodes x 1 , x 2 , …, x i , weight matrix w 1 , w 2 , …, w i , bias matrix b, output y 1 , y 2 , …y m , activation function f = 1 / (1 + e -x);

[0053] S2: Forward propagation process:

[0054] The input of the neurons in the hidden layer is the weighted sum of all inputs, that is:

[0055] The output of the neurons in the hidden layer is obtained by exciting with the S function: Then

[0056]

[0057] The output of the output layer of the neural network is: y n (k) = ∑w jo x j ′ ;

[0058] The error between the network output and the ideal output is: e(k) = y(k) - y n (k);

[0059] Then the performance index function of the network is defined as:

[0060] S3: Backward propagation process:

[0061] According to the gradient descent method, the learning adjustment algorithm of the weights is as follows:

[0062] The training process of the weights from the network output layer to the hidden layer is as follows:

[0063] In the formula,

[0064] At the (k + 1)-th moment, the weight update from the output layer to the hidden layer is: w jo (k + 1) = w jo (k) + Δw jo ;

[0065] The learning process of the weights from the hidden layer to the input layer is as follows:

[0066] At the (k + 1)-th moment, the weight update from the network hidden layer to the input layer is: w ij (k + 1) = w ij (k) + Δw ij ;

[0067] S4: The prediction model continuously iterates in the forward calculation and weight back-adjustment of the neural network until the network prediction error meets the requirements.

[0068] In the second aspect of the present invention, a system for the double-cycle rotation operation scheduling method of a shore crane is provided, including:

[0069] A ship-end operation module, configured to receive instructions from the intelligent control module and independently complete the loading or unloading operation at the ship end;

[0070] A vehicle-end control module, configured to dock with the horizontal transportation module for vehicle arrival and departure messages, receive instructions from the intelligent control module, and independently complete the loading and unloading operations; in this embodiment, the vehicle-end control module docks with the transportation control module for vehicle arrival and departure messages, receives instructions from the intelligent control module, and independently completes the loading and unloading operations.

[0071] An intelligent control module, configured to respectively establish a ship-side operation time prediction model and a vehicle-side operation time prediction model based on the BP neural network according to the obtained crane state information, and predict the ship-side operation time and the vehicle-side operation time under different working conditions; calculate the spreader load time according to the ship-side operation time and the vehicle-side operation time, and control the ship-side operation end and the vehicle-side operation end to operate according to the principle of the shortest spreader load time.

[0072] In this embodiment, the main functions of the intelligent control module are divided into two: one is to establish operation time prediction models for the ship side and the vehicle side respectively through a BP neural network based on the obtained crane status information and environmental information, and predict the operation time of the ship side and the vehicle side under different working conditions; the other is to send operation instructions to the ship side and the vehicle side in a timely manner according to the predicted operation time, and scientifically schedule the two hoisting motors to work respectively, so that the crane can perform double-cycle operations efficiently.

[0073] In some embodiments of the present invention, it further includes:

[0074] A transportation control module, which is used to transport the two spreaders from the vehicle end to the ship end or from the ship end to the vehicle end. When receiving the transportation instruction from the intelligent control module, it transports the specified spreader, and after the transportation is completed, it transmits the information back to the intelligent control module.

[0075] In this embodiment, the transportation control module controls the transportation of the two spreaders from the vehicle end to the ship end or from the ship end to the vehicle end. When receiving the transportation instruction from the intelligent control module, it transports the specified spreader, and after the transportation is completed, it transmits the information back to the intelligent control module.

[0076] In some embodiments of the present invention, it further includes:

[0077] An information acquisition and processing module, which is used to acquire the crane status information and perform preprocessing to obtain the processed wind speed information, seawater flow velocity information, trolley speed, trolley acceleration information, spreader pose information, and weight information of the lifted object.

[0078] A motor scheduling module, which receives the instruction from the intelligent control module and completes the switching and scheduling work of the motors at the ship side operation end and the vehicle side operation end.

[0079] It can be understood that during the single-cycle rotation operation process, the motor is generally on the trolley. As the crane operates, the motor works alternately at the ship end and the vehicle end. In the double-cycle rotation operation, the newly added working motors and the original working motors both work at the ship end and the vehicle end, but the control signals received by the two newly added working motors and the original working motors are different, and the operation contents are also different.

[0080] In the third aspect of the present invention, a readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, it implements the above-mentioned double-cycle rotation operation scheduling method for a quay crane.

[0081] In the fourth aspect of the present invention, a processing device is provided, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the above-mentioned double-cycle rotation operation scheduling method for a quay crane.

[0082] The present invention is applicable to the field of task scheduling for loading and unloading operations of shore cranes. It can make full use of the lifting operation ability of the machine. After dividing a single-cycle operation into three independent operation modules, a double-cycle rotation operation scheduling method is adopted, allowing the ship-end operation department and the vehicle-end operation department to operate separately. Different from the single-cycle operation, the operations of two single-cycles can be transformed into two independent ship-end operations, two vehicle-end operations, and one transportation control operation. Two lifting drivers can work separately in the ship-end operation department and the vehicle-end operation department respectively. The operator does not need to constantly switch roles according to the operation process. Two operators can perform operations in the ship-end operation department and the vehicle-end operation department simultaneously, and each operator focuses on their own unique ship-end tasks or vehicle-end tasks, thereby collaborating to complete the overall operation process and improving the overall operation efficiency.

[0083] In addition, during the single-cycle operation process of grabbing a container on the ship, lifting height, horizontal movement, lowering height, and placing the container on the vehicle, the lifting tool needs to lift the container throughout the operation process. At the same time, due to the low transfer efficiency of each operation process, there is a situation where the lifting tool waits for lifting the goods during the operation. Over time, this will increase the wear and tear of the lifting tool and the subsequent maintenance cost. However, for the double-cycle rotation operation scheduling method proposed by the present invention, since the ship-end operation department and the vehicle-end operation department operate separately, the situation where the lifting tool waits for lifting the goods is greatly reduced, improving the operation efficiency while reducing the use loss of the lifting tool and increasing its service life.

[0084] Although the specific implementation manners of the present invention are described above in conjunction with the accompanying drawings, it is not a limitation to the protection scope of the present invention. Those skilled in the art should understand that based on the technical solutions of the present invention, various modifications or deformations that can be made by those skilled in the art without creative efforts are still within the protection scope of the present invention.

Claims

1. A dual-cycle rotation operation scheduling method for a shore crane, characterized in that: include: Obtain the status information of the ship-side operation end crane and the vehicle-side operation end crane and perform preprocessing; Based on the BP neural network, a ship side operation time prediction model and a vehicle side operation time prediction model are respectively established, and the crane status information is respectively input into the ship side operation time prediction model and the vehicle side operation time prediction model to obtain the ship side operation time and the vehicle side operation time; The spreader load time is calculated based on the ship side operation time and the vehicle side operation time, and the ship side operation end and the vehicle side operation end are controlled to perform operations based on the principle of shortest spreader load time.

2. A dual-cycle operation scheduling method for a shore crane according to claim 1, characterized in that: The crane status information includes wind speed information, weather information, seawater flow rate information, crane trolley speed information, crane trolley acceleration information, hoisting device position information, and hoisted object weight information.

3. A dual-cycle rotation operation scheduling method for a shore crane as claimed in claim 2, characterized in that: The ship side operation time is obtained as follows: The wind speed information, weather information, seawater flow rate information, crane trolley speed, crane trolley acceleration information, sling posture information, and hoisted object weight information are processed for outlier elimination and data normalization. The processed data are input into the ship-side operation time prediction model for training, and the current crane status information is input into the ship-side operation time prediction model to obtain the operation time prediction value of the current working conditions on the ship side.

4. A dual-cycle rotation operation scheduling method for a shore crane as claimed in claim 2, characterized in that: The vehicle side operation time is obtained as follows: The wind speed information, weather information, seawater flow rate information, crane trolley speed, crane trolley acceleration information, sling posture information, and hoisted object weight information are processed for outlier elimination and data normalization. The processed data are input into the vehicle-side operation time prediction model for training, and the current crane status information is input into the vehicle-side operation time prediction model to obtain the operation time prediction value of the current working condition on the vehicle side.

5. A dual-cycle rotation operation scheduling method for a shore crane as claimed in claim 1, characterized in that: The principle of shortest load time of the spreader is specifically: When the container grabbing operation is being carried out on the ship side, the container grabbing spreader on the vehicle side can arrive at the ship side in advance to wait when not grabbing containers. When the container grabbing spreader on the ship side is placing containers on the vehicle side, the container grabbing spreader on the vehicle side grabs the container on the ship side and places it on the vehicle side. It will arrive at the vehicle side on time after the container grabbing spreader on the ship side finishes placing the containers. When carrying out container grabbing operations on the vehicle side, the ship side container grabbing spreader can arrive at the vehicle side in advance and wait when not grabbing containers. When the vehicle side container grabbing spreader is performing container placing operations on the ship side, the ship side container grabbing spreader grabs containers from the vehicle side and places them on the ship side, and arrives at the ship side on time after the vehicle side container grabbing spreader finishes placing containers.

6. A system for scheduling dual-cycle operation of a shore crane according to any one of claims 1 to 5, characterized in that: include: The ship-side operation module is used to receive instructions from the intelligent control module and independently complete the loading and unloading operations on the ship side; The vehicle-side control module is used to connect with the horizontal transport module to receive vehicle arrival and departure messages, receive instructions from the intelligent control module, and independently complete vehicle-side loading and unloading operations; An intelligent control module is used to establish a ship side operation time prediction model and a vehicle side operation time prediction model based on a BP neural network according to the obtained crane status information, and to predict the ship side operation time and vehicle side operation time under different working conditions; The spreader load time is calculated based on the ship side operation time and the vehicle side operation time, and the ship side operation end and the vehicle side operation end are controlled to perform operations based on the principle of shortest spreader load time.

7. A system for scheduling a dual-cycle operation of a shore crane according to claim 6, characterized in that: Also includes: The transport control module is used to transport two spreaders from the vehicle end to the ship end or from the ship end to the vehicle end. Upon receiving the transport instruction from the intelligent control module, the designated spreader is transported and the information is transmitted back to the intelligent control module after the transport is completed.

8. The system of the double-cycle rotation operation scheduling method of the shore crane according to claim 6, characterized in that: Also includes: The information collection and processing module is used to obtain the crane status information and perform preprocessing to obtain the processed wind speed information, seawater flow rate information, trolley speed, trolley acceleration information, spreader posture information, and suspended object weight information; The motor scheduling module receives instructions from the intelligent control module and completes the switching scheduling of the crane motors at the ship-side operation end and the vehicle-side operation end.

9. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a dual-cycle rotation operation scheduling method for a shore crane as described in any one of claims 1 to 5 is implemented.

10. A processing device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, a dual-cycle rotation operation scheduling method for a shore crane is implemented as described in any one of claims 1-5.

Images