Hoisting object control method, device and equipment based on crane ship and storage medium

Abstract

The invention provides a hoisting object control method, device and equipment based on a crane ship and a storage medium. Real-time environment parameters, real-time hoisting object parameters and real-time operation parameters of the crane ship are obtained through a sensor; inputting the parameters into a parameter generation model to obtain initial control parameters; optimizing the initial control parameter through a fitness function to obtain a target control parameter; and according to the target control parameters, the crane ship is controlled to move the hoisted object to the target position. According to the method, the environment parameters, the hoisting object parameters and the crane ship operation parameters are collected in real time, the parameter generation model and the fitness function are introduced to optimize the control parameters, the position error in the hoisting object operation process is effectively reduced, and the hoisting object control precision is remarkably improved. Moreover, the control parameters are evaluated through the fitness function, and the ship stability, the hoisting object operation precision and the task completion degree are taken into optimization objectives, so that the hoisting object moving efficiency is effectively improved, the operation time is shortened, and the operation quality is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of crane vessels, and in particular to a method, device, equipment and storage medium for controlling a hanging object based on a crane vessel. Background Art

[0002] As a commonly used equipment in marine engineering, crane vessels are widely used in tasks such as lifting and transportation. In actual operation, crane vessel operations face complex marine environments, including the influence of factors such as wind, waves, and currents, resulting in low control accuracy of the lifting objects, affecting task efficiency and safety. At the same time, the stability and accuracy of the lifting objects of the crane vessel are directly related to the smooth progress of the project. Traditional lifting control methods rely on manual operation and simple feedback control, which is difficult to effectively cope with complex dynamic environments and has defects such as low accuracy and poor adaptability.

[0003] In summary, the problems existing in the prior art need to be solved urgently. Summary of the invention

[0004] The present invention provides a method, device, equipment and storage medium for controlling a hanging object based on a crane ship, so as to solve the defects in the prior art and improve the accuracy of the hanging object control.

[0005] The present invention provides a method for controlling a hanging object based on a crane ship, comprising:

[0006] Obtain real-time environmental parameters, real-time load parameters, and real-time operation parameters of the crane vessel through sensors;

[0007] Inputting the real-time environmental parameters, the real-time hanging object parameters and the real-time operation parameters into a parameter generation model to obtain initial control parameters;

[0008] Optimizing the initial control parameters through a fitness function to obtain target control parameters;

[0009] According to the target control parameters, the crane vessel is controlled to move the suspended object to the target position.

[0010] According to a method for controlling a suspended object based on a crane vessel provided by the present invention, a parameter generation model is trained by the following steps:

[0011] Obtaining a training data set, including crane vessel operation parameters, load motion parameters, and operation environment parameters;

[0012] Setting a weight function of the parameter generation model, wherein the value of the weight function is determined according to the iteration result;

[0013] According to the weight function, a parameter generation model is constructed based on a particle swarm algorithm;

[0014] The parameter generation model is trained according to the training data set until a preset number of iterations is reached.

[0015] According to a method for controlling a suspended object based on a crane vessel provided by the present invention, the step of setting a weight function of a parameter generation model, wherein the value of the weight function is determined according to an iteration result, specifically comprises:

[0016] Construct an adaptive adjustment function for inertia weight;

[0017] The inertia weight adaptive adjustment function is converted into a nonlinear inertia weight function, and the nonlinear inertia weight function is used as a weight function of the parameter generation model.

[0018] According to a method for controlling a suspended object based on a crane vessel provided by the present invention, the step of converting the inertia weight adaptive adjustment function into a nonlinear inertia weight function is implemented by:

[0019]

[0020] Among them, ω start is the initial inertia weight, ω end is the termination inertia weight, t is the current iteration number; t max is the maximum number of iterations set initially, and k is the control factor.

[0021] According to a method for controlling a suspended object based on a crane vessel provided by the present invention, the step of constructing a parameter generation model based on a particle swarm algorithm according to the weight function is implemented in the following manner:

[0022] v i (t+1)=ω·v i (t)+c1r1(t)[p i (t)-x i (t)]+c2r2(t)[p g -x i (t)]+α·δ(t)

[0023] Among them, v i (t+1) is the velocity of particle i at time t+1, ω is the inertia weight, which controls the inertial effect of the particle velocity, and v i (t) is the speed of particle i at time t, c1 is the first learning factor, which is used to adjust the speed of the particle moving to its own optimal position, c2 is the second learning factor, which is used to adjust the speed of the particle moving to the global optimal position, r1 and r2 are random numbers with a value range of [0, 1], which are used to introduce randomness to increase the diversity of the search, and p i (t) is the best historical position of particle i at time t, p gis the optimal position of the group, x i (t) is the position of particle i at time t, α is the adjustment coefficient of the escape factor, which usually increases after the local optimal solution is identified to enhance randomness, δ(t) is a random perturbation term used to enhance the exploratory nature of the particle, r3 is a random number between [0, 1], and x max and x min are the upper and lower boundaries of the particle search space respectively.

[0024] According to a method for controlling a suspended object based on a crane vessel provided by the present invention, the step of optimizing the initial control parameters by a fitness function to obtain the target control parameters is implemented by:

[0025] S(x i )=ω1·S stability (V wind , H wave , T wave , V flow ,θ flow ,θ pitch ,θ roll ,θ heave )+ω2·S operation (V wind , H wave , T wave , V flow ,θ flow ,h lifting )+ω3·S task (x lifting , x horizontal , x target )

[0026] Among them, S stability is the impact of the marine environment on the stability of the ship, S operation S is the operating accuracy of the hoisted object, target is the task completion degree of the lifting object, V wind is wind speed, H wave is the wave height, T wave is the cycle, V flow is the flow rate, θ flow is the flow direction, θ pitc h is the pitch angle of the ship, θ roll is the ship roll angle and θ Heave is the heave angle of the ship, h lifting is the lifting height of the object, (x lifting ,y lifting ) is the current position of the hanging object and (x target ,y target ) is the target position of the hanging object.

[0027] According to a method for controlling a hanging object based on a crane vessel provided by the present invention, after the step of controlling the crane vessel to move the hanging object to a target position according to the target control parameter, the method further comprises:

[0028] Get the actual position of the hanging object;

[0029] Determining error information between the actual position of the hanging object and the target position;

[0030] Feedback information is generated according to the error information, and the feedback information is used to adjust the parameter generation accuracy of the parameter generation model.

[0031] The present invention also provides a lifting object control device based on a crane ship, comprising:

[0032] A data acquisition module is used to obtain real-time environmental parameters, real-time lifting object parameters and real-time operation parameters of the crane vessel through sensors;

[0033] A parameter generation module, used for inputting the real-time environmental parameters, the real-time hanging object parameters and the real-time operation parameters into a parameter generation model to obtain initial control parameters;

[0034] A parameter optimization module, used to optimize the initial control parameters through a fitness function to obtain target control parameters;

[0035] The hanging object moving module is used to control the crane ship to move the hanging object to the target position according to the target control parameters.

[0036] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for controlling a hanging object based on a crane vessel as described above is implemented.

[0037] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for controlling a hanging object based on a crane vessel as described above is implemented.

[0038] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned methods for controlling hanging objects based on a crane vessel.

[0039] The crane-based object control method, device, equipment and storage medium provided by the present invention obtain real-time environmental parameters, real-time object parameters and real-time operation parameters of the crane through sensors; input the real-time environmental parameters, the real-time object parameters and the real-time operation parameters into the parameter generation model to obtain initial control parameters; optimize the initial control parameters through the fitness function to obtain the target control parameters; according to the target control parameters, control the crane to move the object to the target position. The present invention collects environmental parameters, object parameters and crane operation parameters in real time, and introduces the parameter generation model and the fitness function to optimize the control parameters, effectively reducing the position error during the operation of the object, and significantly improving the accuracy of the control of the object. In addition, the control parameters are evaluated through the fitness function, and the ship stability, object operation accuracy and task completion are included in the optimization target, which effectively improves the efficiency of the object movement, shortens the operation time and improves the operation quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 It is a flow chart of a method for controlling a hanging object based on a crane vessel provided by the present invention;

[0042] Figure 2 It is a structural schematic diagram of a lifting object control device based on a crane vessel provided by the present invention;

[0043] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] In order to solve the problems in the prior art, the present invention proposes a method for controlling a hanging object based on a crane ship to improve the accuracy of the hanging object control. The following is a description of the method for controlling a hanging object based on a crane ship. Figure 1 As shown, including but not limited to the following steps:

[0046] Step 110: Acquire real-time environmental parameters, real-time hanging object parameters, and real-time operation parameters of the crane vessel through sensors.

[0047] In step 110, the sensors may include but are not limited to environmental monitoring sensors, hanging object position sensors, and hull motion sensors.

[0048] Environmental monitoring sensors are used to collect real-time ocean environmental parameters, such as wind speed, wave height, wave period, current speed, current direction, etc.

[0049] The load position sensor is used to detect the real-time position coordinates of the load, load height and other parameters.

[0050] The hull motion sensor is used to monitor the real-time motion status of the crane vessel, such as the pitch angle, roll angle, heave angle, etc.

[0051] Step 120: input the real-time environmental parameters, the real-time hanging object parameters and the real-time operation parameters into a parameter generation model to obtain initial control parameters.

[0052] In this step, the parameter generation model is constructed in the following way:

[0053] The training data set includes crane vessel operation parameters, load motion parameters and operation environment parameters.

[0054] The particle swarm algorithm is used to train the parameter generation model and set the weight function, where the weight function is adjusted by the adaptive inertia weight function to improve the optimization ability and convergence speed of the model.

[0055] The model is generated by trained parameters, and the real-time environmental parameters, hanging object parameters and operation parameters are input into the model to obtain the initial control parameters.

[0056] Step 130: Optimize the initial control parameters by using a fitness function to obtain target control parameters.

[0057] In this step, the fitness function is used to evaluate the quality of the initial control parameters, which is specifically implemented by the following formula:

[0058] F fitness =w1S stability +w2S operation +w3S target

[0059] Among them, S stability is the impact of the marine environment on the stability of the ship, S operation S is the operating accuracy of the hoisted object, target is the completion degree of the lifting task, ω1, ω2, and ω3 are the weight values ​​of each indicator respectively.

[0060] The fitness function takes into account the impact of environmental factors such as wind speed, wave height, and ship motion angle on the stability of the crane vessel, as well as operational accuracy such as the position deviation of the hoisted object, to ensure that the target control parameters can meet the actual operation requirements.

[0061] Step 140: Control the crane vessel to move the load to the target position according to the target control parameters.

[0062] In step 140, the control system sends the optimized target control parameters to the actuator of the crane ship to control the operating device of the crane ship so that the object is moved smoothly to the target position along the set path. Specifically, the control system monitors the current position (x lifting ,y lifting ) and the target position (x target ,y target ) and dynamically adjusts the control instructions of the crane vessel based on the error information to ensure smooth movement and high-precision positioning of the load.

[0063] The present invention obtains operating parameters in real time, establishes a parameter generation model and introduces a fitness function to optimize the control parameters, thereby effectively improving the operating accuracy and operating stability of the crane ship's hoisting objects, and has good robustness and adaptability, especially in complex marine environments.

[0064] As a further optional embodiment, the parameter generation model is trained by the following steps:

[0065] Obtaining a training data set, including crane vessel operation parameters, load motion parameters, and operation environment parameters;

[0066] Setting a weight function of the parameter generation model, wherein the value of the weight function is determined according to the iteration result;

[0067] According to the weight function, a parameter generation model is constructed based on a particle swarm algorithm;

[0068] The parameter generation model is trained according to the training data set until a preset number of iterations is reached.

[0069] In this embodiment, a training data set is obtained from historical job data, and the data set includes the following contents:

[0070] Crane ship operation parameters: the movement status of the crane ship in different marine environments;

[0071] Hoisting object motion parameters: real-time motion status of hoisting objects;

[0072] Working environment parameters: environmental factors such as wind speed, wave height, wave period, current speed and current direction.

[0073] Next, a weight function is introduced into the parameter generation model to balance the importance of different parameters in the model. The initial value of the weight function is determined by empirical data and dynamically adjusted according to subsequent iteration results.

[0074] The weight function is defined as:

[0075] w k =f(ΔE k )

[0076] ω1 is the weight of the kth parameter, ΔE k represents the error contribution of the k-th parameter to the model performance, and f(·) is the weight update function, which is optimized by the error gradient descent algorithm.

[0077] Subsequently, the particle swarm algorithm is used to optimize the structure and weights of the parameter generation model. The algorithm is implemented by the following steps:

[0078] Set the initial position x for each particle i (0) and the initial velocity y i (0), randomly distributed in parameter space;

[0079] Using the training data set, calculate the fitness function of each particle;

[0080] According to the particle's historical best position p i and the global optimal position p g , adjust the position and velocity of the particle, and the update formula is

[0081] v i (t+1)=ω·v i (t)+c1r1(t)[p i (t)-x i (t)]+c2r2(t)[p g -x i (t)]

[0082] x i (t+1)=x i (t)+v i (t+1)

[0083] Among them, v i (t+1) is the velocity of particle i at time t+1, ω is the inertia weight, which controls the inertial effect of the particle velocity, and v i (t) is the speed of particle i at time t, c1 is the first learning factor, which is used to adjust the speed of the particle moving to its own optimal position, c2 is the second learning factor, which is used to adjust the speed of the particle moving to the global optimal position, r1 and r2 are random numbers with a value range of [0, 1], which are used to introduce randomness to increase the diversity of the search, and pi (t) is the best historical position of particle i at time t, p g is the optimal position of the group, x i (t) is the position of particle i at time t, α is the adjustment coefficient of the escape factor, which usually increases after the local optimal solution is identified to enhance randomness, δ(t) is a random perturbation term used to enhance the exploratory nature of the particle, r3 is a random number between [0, 1], and x max and x min are the upper and lower boundaries of the particle search space respectively.

[0084] When the fitness function reaches the preset threshold or the number of iterations reaches the upper limit, the particle swarm optimization process is stopped. Through the optimization of the parameter generation model by the particle swarm algorithm, the model can quickly converge to the global optimal solution in a complex parameter space.

[0085] The parameter generation model is trained according to the training data set.

[0086] The obtained training data set is input into the parameter generation model, and the model parameters are gradually optimized by batch training. During the model training process, the error is calculated by the following objective function:

[0087]

[0088] Where: L is the loss function; y i is the true value; is the model prediction value; N is the total number of samples.

[0089] During the training process, the model parameters are continuously optimized until the preset number of iterations is reached or the loss function value is less than the set threshold.

[0090] The parameter generation model trained through the above steps can generate initial control parameters more efficiently, significantly improve the accuracy and stability of hanging object control, and provide a solid foundation for subsequent optimization and operation.

[0091] This embodiment combines the particle swarm algorithm and the weight dynamic adjustment mechanism to make the construction of the parameter generation model more efficient and accurate, and significantly improve the model's adaptability to complex operating environments. In practical applications, it can quickly generate control parameters that meet operating requirements and improve the operating efficiency and operational safety of the crane ship.

[0092] As a further optional embodiment, the step of setting a weight function of the parameter generation model, wherein the value of the weight function is determined according to an iteration result, specifically includes:

[0093] Construct an adaptive adjustment function for inertia weight;

[0094] The inertia weight adaptive adjustment function is converted into a nonlinear inertia weight function, and the nonlinear inertia weight function is used as a weight function of the parameter generation model.

[0095] In this embodiment, the inertia weight is an important parameter in the particle swarm algorithm, which is used to balance the global search capability and the local search capability. In order to enable the inertia weight to dynamically adapt to different stages of the optimization process, this embodiment constructs an inertia weight adaptive adjustment function, which is expressed as:

[0096]

[0097] Among them, T max represents the maximum evolutionary generation; ω max represents the maximum inertia weight; ω min represents the minimum inertia weight; t represents the current iteration number.

[0098] Through this adjustment function, the inertia weight can be dynamically adjusted according to the changes in the current fitness function. In the early stage of optimization, a larger weight value is maintained to enhance the global search capability; in the later stage of optimization, the weight value is reduced to improve the accuracy and stability of local search.

[0099] In practical applications, the adjustment of linear inertia weight may not meet the optimization requirements of complex parameter space, so the inertia weight adaptive adjustment function is further transformed into a nonlinear inertia weight function to improve the flexibility and efficiency of the optimization process. The expression of the nonlinear inertia weight function is:

[0100]

[0101] Among them, ω start is the initial inertia weight, ω end is the termination inertia weight, t is the current iteration number; t max is the maximum number of iterations set initially, and k is the control factor.

[0102] Through this nonlinear function, the inertia weight decreases slowly in the early stage of optimization, which can explore the global search space more fully; the inertia weight decreases faster in the later stage of optimization, thus focusing on local search.

[0103] As a further optional embodiment, the step of converting the inertia weight adaptive adjustment function into a nonlinear inertia weight function is implemented by:

[0104]

[0105] Among them, ω start is the initial inertia weight, ω end is the termination inertia weight, t is the current iteration number; tmax is the maximum number of iterations set initially, and k is the control factor.

[0106] This embodiment achieves refined control of dynamic weight adjustment by converting the inertia weight adaptive adjustment function into a nonlinear inertia weight function and applying it to the parameter generation model. During the optimization process, the model can dynamically adjust the weight ratio of global search and local search according to the needs of different stages, thereby significantly improving the convergence speed and final accuracy of the model. In practical applications, this embodiment can improve the generation efficiency of crane operation control parameters and further enhance the safety and stability of crane operations.

[0107] As a further optional embodiment, the step of constructing a parameter generation model based on the particle swarm algorithm according to the weight function is implemented in the following manner:

[0108] v i (t+1)=ω·v i (t)+c1r1(t)[p i (t)-x i (t)]+c2r2(t)[p g -x i (t)]+α·δ(t)

[0109] Among them, v i (t+1) is the velocity of particle i at time t+1, ω is the inertia weight, which controls the inertial effect of the particle velocity, and v i (t) is the speed of particle i at time t, c1 is the first learning factor, which is used to adjust the speed of the particle moving to its own optimal position, c2 is the second learning factor, which is used to adjust the speed of the particle moving to the global optimal position, r1 and r2 are random numbers with a value range of [0, 1], which are used to introduce randomness to increase the diversity of the search, and p i (t) is the best historical position of particle i at time t, p g is the optimal position of the group, x i (t) is the position of particle i at time t, α is the adjustment coefficient of the escape factor, which usually increases after the local optimal solution is identified to enhance randomness, δ(t) is a random perturbation term used to enhance the exploratory nature of the particle, r3 is a random number between [0, 1], and x max and x min are the upper and lower boundaries of the particle search space respectively.

[0110] In this embodiment, when the particle swarm is judged to be trapped in a local optimal solution, the particle speed update formula is adjusted to increase its escape possibility. The escape mechanism is achieved by enhancing the random factor. Therefore, an escape factor α is added to the particle swarm algorithm, where α is the adjustment coefficient of the escape factor, which usually increases after the local optimal solution is identified to enhance randomness. δ(t) is a random perturbation term used to enhance the exploration of particles. It can be generated with random numbers. r3 is a random number between [0, 1], and x max and x min are the upper and lower boundaries of the particle search space respectively.

[0111] As a further optional embodiment, the step of optimizing the initial control parameters by using a fitness function to obtain target control parameters is implemented in the following manner:

[0112] S(x i )=ω1·S stability (V wind , H wave , T wave , V flow ,θ flow ,θ pitch ,θ roll ,θ heave )+ω2·S operation (V wind , H wave , T wave , V flow ,θ flow ,h lifting )+ω3·S task (x lifting , x horizontal , x target )

[0113] Among them, S stability is the impact of the marine environment on the stability of the ship, S operation S is the operating accuracy of the hoisted object, target is the task completion degree of the lifting object, V wind is wind speed, H wave is the wave height, T wave is the cycle, V flow is the flow rate, θ flow is the flow direction, θ pitch is the ship pitch angle, θ roll is the ship roll angle and θ Heave is the heave angle of the ship, h lifting is the lifting height of the object, (x lifting ,y lifting ) is the current position of the hanging object and (x target ,y target) is the target position of the hanging object.

[0114] In the formal lifting operation, the IPSO algorithm calculates the appropriate steering angle and lifting operation instructions through the real-time collection of marine environmental parameters and the attitude information of the crane ship. The input marine environmental parameters include wind speed V wind , wave height H wave , period T wave , flow rate V flow and the flow direction θ flow etc. The ship data consists of the ship position P location and attitude including pitch angle θ pitc h, roll angle θ roll and the heave angle θ Heave The lifting height of the object is h. lifting 、Current position of the object (x lifting ,y lifting ) and the target position of the object (x target ,y target )composition.

[0115] Design the fitness function. The fitness function needs to comprehensively consider the stability of the ship, the accuracy of the lifting operation, and the completion of the task. The ocean environment and ship posture information are used as input, and the optimization results are calculated through the following fitness function.

[0116] S(x i )=ω1·S stability (V wind , H wave , T wave , V flow ,θ flow ,θ pitch ,θ roll ,θ heave )+ω2·S operation (V wind , H wave , T wave , V flow ,θ flow ,h lifting )+ω3·S task (x lifting , x horizontal , x target )

[0117] Among them, S stability Based on the ship's attitude (pitch angle, roll angle), wind speed, wave height, wave period, flow speed and flow direction, the impact of the marine environment on the ship's stability is considered. operation The lifting speed and lateral speed of the load are optimized according to the wind speed, flow speed, wave period, wave height and load height to optimize the operation accuracy of the load. targetThe task completion degree of the hoisted object is calculated based on the error between the current position and the target position of the hoisted object.

[0118] In the particle swarm algorithm, the position of the hanging particle is expressed as:

[0119] x i =[θ rudder , v lifting , v horizontal ]

[0120] where θ rudder is the steering angle; v lifting is the lifting speed of the object; v horizontal is the lateral velocity of the load.

[0121] Then, the particle speed is updated by improving the particle swarm formula, and the particle position is updated by the position update formula. The optimal particle position obtained after optimization is used to calculate the steering angle, lifting and lowering instructions, and lateral speed according to the position value of each particle. Assume that the position of the optimal particle is:

[0122]

[0123] Thus, the calculation of the steering angle, the lifting speed of the suspended object and the lateral speed is updated, and the calculation formula is as follows:

[0124]

[0125] By converting the ocean environment parameters from wind speed V wind , wave height H wave , period T wave , flow rate V flow and the flow direction θ flow Incorporating them into the IPSO algorithm can effectively optimize the control parameters of the crane vessel according to these marine environmental parameters, and then calculate the appropriate steering angle and hoisting operation instructions, thereby achieving efficient operation under complex sea conditions.

[0126] This embodiment constructs a multi-factor fitness function, comprehensively considers the impact of the marine environment, the accuracy of the hoisting operation and the degree of task completion, and significantly improves the optimization effect of the control parameters of the crane ship operation. The dynamic optimization of the fitness function can ensure that the target control parameters can adapt to the complex and changeable marine environment and meet the precise positioning requirements of the hoisting objects, thereby improving the safety and efficiency of the crane ship operation.

[0127] As a further optional embodiment, after the step of controlling the crane vessel to move the suspended object to the target position according to the target control parameter, the method further includes:

[0128] Get the actual position of the hanging object;

[0129] Determining error information between the actual position of the hanging object and the target position;

[0130] Feedback information is generated according to the error information, and the feedback information is used to adjust the parameter generation accuracy of the parameter generation model.

[0131] After the load is moved to the target position, the actual position (x actual ,y actual ).

[0132] According to the target position and actual position of the hanging object, the error information between the two is calculated. The error formula is:

[0133] Δx=x actual -x target

[0134] Δy=y actual -y target

[0135]

[0136] Among them, Δx and Δy are the errors between the actual position and the target position in the horizontal and vertical directions, respectively, and Δd is the Euclidean distance error between the actual position and the target position.

[0137] Based on the above error information Δx, Δy and Δd, feedback information is generated for dynamically adjusting the generation accuracy of the parameter generation model. The specific steps of generating feedback information include:

[0138] If the error Δd is less than a preset threshold (e.g., 5 cm), it is considered that the accuracy of the parameter generation model has met the requirements and no adjustment is required;

[0139] If the error Δd exceeds the preset threshold, the error information is recorded and the parameter adjustment step is entered.

[0140] According to the error information, the generation accuracy of the parameter generation model is adjusted, specifically including the following methods:

[0141] Adjust the weight function: fine-tune the weight coefficient (such as inertia weight) of the weight function in the parameter generation model to enhance the model's optimization ability for specific parameters;

[0142] Optimize the training data set: Use the current error information and actual position data as new training data and add them to the training data set of the parameter generation model to improve the model's adaptability to similar environmental conditions;

[0143] Increase the number of iterations: Appropriately increase the number of iterations of model training to improve the generalization ability of the model.

[0144] Based on the generated feedback information, the parameter generation model is dynamically updated to enable it to generate more accurate control parameters. The updated parameter generation model can be used for the next lifting operation to achieve adaptive optimization of the system.

[0145] The following is a description of the object control device based on a crane vessel provided by the present invention. Figure 2 As shown, the crane vessel-based hanging object control device described below and the crane vessel-based hanging object control method described above can correspond to each other.

[0146] A lifting object control device based on a crane ship, comprising:

[0147] The data acquisition module 210 is used to acquire real-time environmental parameters, real-time hanging object parameters and real-time operation parameters of the crane vessel through sensors;

[0148] A parameter generation module 220 is used to input the real-time environmental parameters, the real-time hanging object parameters and the real-time operation parameters into a parameter generation model to obtain initial control parameters;

[0149] A parameter optimization module 230 is used to optimize the initial control parameters through a fitness function to obtain target control parameters;

[0150] The load moving module 240 is used to control the crane vessel to move the load to a target position according to the target control parameters.

[0151] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the crane-based object control method, which includes:

[0152] Obtain real-time environmental parameters, real-time load parameters, and real-time operation parameters of the crane vessel through sensors;

[0153] Inputting the real-time environmental parameters, the real-time hanging object parameters and the real-time operation parameters into a parameter generation model to obtain initial control parameters;

[0154] Optimizing the initial control parameters through a fitness function to obtain target control parameters;

[0155] According to the target control parameters, the crane vessel is controlled to move the suspended object to the target position.

[0156] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0157] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the crane vessel-based hanging object control method provided by the above methods, the method includes:

[0158] Obtain real-time environmental parameters, real-time load parameters, and real-time operation parameters of the crane vessel through sensors;

[0159] Inputting the real-time environmental parameters, the real-time hanging object parameters and the real-time operation parameters into a parameter generation model to obtain initial control parameters;

[0160] Optimizing the initial control parameters through a fitness function to obtain target control parameters;

[0161] According to the target control parameters, the crane vessel is controlled to move the suspended object to the target position.

[0162] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the method for controlling a suspended object based on a crane vessel provided by the above methods, the method comprising:

[0163] Obtain real-time environmental parameters, real-time load parameters, and real-time operation parameters of the crane vessel through sensors;

[0164] Inputting the real-time environmental parameters, the real-time hanging object parameters and the real-time operation parameters into a parameter generation model to obtain initial control parameters;

[0165] Optimizing the initial control parameters through a fitness function to obtain target control parameters;

[0166] According to the target control parameters, the crane vessel is controlled to move the suspended object to the target position.

[0167] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0168] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0169] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for controlling a suspended object based on a crane vessel, characterized in that: include: Obtain real-time environmental parameters, real-time load parameters, and real-time operation parameters of the crane vessel through sensors; Inputting the real-time environmental parameters, the real-time hanging object parameters and the real-time operation parameters into a parameter generation model to obtain initial control parameters; Optimizing the initial control parameters through a fitness function to obtain target control parameters; According to the target control parameters, the crane vessel is controlled to move the suspended object to the target position.

2. The method for controlling hanging objects based on a crane vessel according to claim 1, characterized in that: The parameter generation model is trained through the following steps: Obtaining a training data set, including crane vessel operation parameters, load motion parameters, and operation environment parameters; Setting a weight function of the parameter generation model, wherein the value of the weight function is determined according to the iteration result; According to the weight function, a parameter generation model is constructed based on a particle swarm algorithm; The parameter generation model is trained according to the training data set until a preset number of iterations is reached.

3. The method for controlling hanging objects based on a crane vessel according to claim 2, characterized in that: The step of setting the weight function of the parameter generation model, wherein the value of the weight function is determined according to the iteration result, specifically includes: Construct an adaptive adjustment function for inertia weight; The inertia weight adaptive adjustment function is converted into a nonlinear inertia weight function, and the nonlinear inertia weight function is used as a weight function of the parameter generation model.

4. The method for controlling hanging objects based on a crane vessel according to claim 3, characterized in that: The step of converting the inertia weight adaptive adjustment function into a nonlinear inertia weight function is achieved by: in, is the initial inertia weight, To terminate the inertia weight, is the current iteration number; is the maximum number of iterations set initially, is the control factor.

5. The method for controlling hanging objects based on a crane vessel according to claim 2, characterized in that: The step of constructing a parameter generation model based on the particle swarm algorithm according to the weight function is achieved by: in, is the velocity of particle i at time t+1, is the inertia weight, which controls the inertia effect of particle velocity. is the velocity of particle i at time t, is the first learning factor, which is used to adjust the speed at which particles move to their optimal positions. is the second learning factor, which is used to adjust the speed at which particles move to the global optimal position. , is a random number with a value range of [0,1], which is used to introduce randomness to increase the diversity of the search. is the best historical position of particle i at time t, is the best position of the group globally, is the position of particle i at time t, 𝛼 is the adjustment coefficient of the escape factor, which usually increases after the local optimal solution is identified to enhance randomness. is a random perturbation term used to enhance the exploratory nature of particles, 𝑟3 is a random number between [0,1], and are the upper and lower boundaries of the particle search space respectively.

6. The method for controlling hanging objects based on a crane vessel according to claim 1, characterized in that: The step of optimizing the initial control parameters by the fitness function to obtain the target control parameters is achieved by: in, The impact of the marine environment on ship stability. For the operating accuracy of the hoisted object, is the task completion degree of the lifting object, V wind is wind speed, H wave is the wave height, T wave is the cycle, V flow is the flow rate, For flow direction, is the ship pitch angle, is the ship's roll angle and is the heave angle of the ship, h lifting is the lifting height of the object, (x lifting ,y lifting ) is the current position of the hanging object and (x target ,y target ) is the target position of the hanging object, are the weight values ​​of each indicator respectively.

7. The method for controlling hanging objects based on a crane vessel according to claim 1, characterized in that: After the step of controlling the crane vessel to move the suspended object to the target position according to the target control parameter, the method further comprises: Get the actual position of the hanging object; Determining error information between the actual position of the hanging object and the target position; Feedback information is generated according to the error information, and the feedback information is used to adjust the parameter generation accuracy of the parameter generation model.

8. A lifting object control device based on a crane ship, characterized in that: include: A data acquisition module is used to obtain real-time environmental parameters, real-time lifting object parameters and real-time operation parameters of the crane vessel through sensors; A parameter generation module, used for inputting the real-time environmental parameters, the real-time hanging object parameters and the real-time operation parameters into a parameter generation model to obtain initial control parameters; A parameter optimization module, used to optimize the initial control parameters through a fitness function to obtain target control parameters; The hanging object moving module is used to control the crane ship to move the hanging object to the target position according to the target control parameters.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for controlling hanging objects based on a crane vessel as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for controlling a suspended object based on a crane vessel as claimed in any one of claims 1 to 7 is implemented.

Images