Marine crane and net washing machine collaborative operation management method and system

Abstract

The invention relates to the technical field of fishing boat equipment operation management, in particular to a cooperative operation management method and system for a marine crane and a net washing machine. According to the dirt attachment feature information of the to-be-cleaned fishing net, feature pairing is conducted on all available net washing machines in the fishing boat, and a target net washing machine for cleaning the to-be-cleaned fishing net is obtained through pairing; the position of a target net washing machine and the position of the fishing net to be cleaned are obtained, simulation analysis is conducted on all cranes in the fishing boat according to the position of the target net washing machine and the position of the fishing net to be cleaned, and the optimal hoisting and rotating path of the target crane and the target crane is obtained; and acquiring a real-time hoisting and transferring path of the target crane, comparing the real-time hoisting and transferring path with the optimal hoisting and transferring path, and correspondingly regulating and controlling the real-time hoisting and transferring parameters of the target crane according to a comparison result. All the cranes and the net washing machines in the fishing boat are distributed in a coordinated mode through a simple and effective algorithm, intelligent control is achieved, the working efficiency can be effectively improved, and the conflict and delay phenomena in the operation process are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of fishing vessel equipment operation management, and particularly to a collaborative operation management method and system for a marine crane and a net washer. Background Art

[0002] Fishing vessel cranes and net washers are two common pieces of equipment used for the hoisting and cleaning operations of fishing nets. Multiple cranes and net washers are usually equipped on fishing vessels to work together simultaneously. There are some technical deficiencies in the current collaborative operation method of fishing vessel cranes and net washers, which limit the efficiency and reliability of the operation. The following are some of the main deficiencies in the existing technologies: (1) Most marine cranes and net washers lack the application of intelligent control and automation technologies, which makes the operation process rely on manual experience and skills and there is a risk of human misoperation; (2) There is a lack of an effective coordination and communication mechanism between fishing vessel cranes and net washers during the operation process, resulting in improper coordination between the hoisting and net washing operations, which may lead to conflicts and delays during the operation process, reducing the efficiency and quality of the operation. To solve these problems, a collaborative operation management method and system for a marine crane and a net washer are proposed in this paper, aiming to improve the efficiency and reliability of fishing vessel operations. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a collaborative operation management method and system for a marine crane and a net washer.

[0004] The technical solution adopted by the present invention to achieve the above object is as follows:

[0005] In the first aspect of the present invention, a collaborative operation management method for a marine crane and a net washer is disclosed, including the following steps:

[0006] Obtain the image information of the fishing net to be cleaned, perform recognition processing on the image information of the fishing net to be cleaned, and obtain the fouling characteristic information of the fishing net to be cleaned;

[0007] Perform feature matching on each available net washer in the fishing vessel according to the fouling characteristic information of the fishing net to be cleaned, and match the target net washer for cleaning the fishing net to be cleaned;

[0008] Obtain the position of the target net washer and the position of the fishing net to be cleaned, perform simulation analysis on each crane in the fishing vessel according to the position of the target net washer and the position of the fishing net to be cleaned, and obtain the best hoisting path of the target crane and the target net washer;

[0009] Generate the preset hoisting parameters of the target crane based on the best hoisting path, and control the target crane to move along the best hoisting path based on the preset hoisting parameters to hoist the fishing net to be cleaned into the target net washer;

[0010] Obtain the real-time hoisting path of the target crane, compare the real-time hoisting path with the optimal hoisting path, and perform corresponding regulation and control processing on the real-time hoisting parameters of the target crane according to the comparison result.

[0011] Further, in a preferred embodiment of the present invention, obtain the image information of the fishing net to be cleaned, perform recognition processing on the image information of the fishing net to be cleaned, and obtain the fouling characteristic information of the fishing net to be cleaned, specifically:

[0012] Based on the big data network, retrieve the characteristic image information corresponding to the fishing nets with various fouling characteristic information during the historical operation of the fishing boat, construct a knowledge graph, import the characteristic image information corresponding to the fishing nets with various fouling characteristic information into the knowledge graph, and regularly update the knowledge graph; wherein, the fouling characteristic information includes the degree of attachment and the type of fouling.

[0013] Obtain the image information of the fishing net to be cleaned, introduce the perceptual hashing algorithm, and calculate the hash values between the image information of the fishing net to be cleaned and each characteristic image information in the knowledge graph based on the perceptual hashing algorithm to obtain a plurality of hash values.

[0014] Construct a sorting table, input the plurality of hash values into the sorting table for size sorting, and after the sorting is completed, extract the maximum hash value and obtain the characteristic image information corresponding to the maximum hash value.

[0015] According to the characteristic image information corresponding to the maximum hash value, pair and identify in the knowledge graph to obtain the fouling characteristic information of the fishing net to be cleaned.

[0016] Further, in a preferred embodiment of the present invention, perform feature pairing on each available net washer in the fishing boat according to the fouling characteristic information of the fishing net to be cleaned, and pair and obtain the target net washer for cleaning the fishing net to be cleaned, specifically:

[0017] Obtain the real-time working status of each net washer in the fishing boat, and calibrate the net washer with the real-time working status of the idle working status as the available net washer.

[0018] Obtain the functional characteristic information of each available net washer, introduce the multi-head attention mechanism algorithm, analyze the attention weights between the fouling characteristic information of the fishing net to be cleaned and the functional characteristic information of each available net washer based on the multi-head attention mechanism algorithm to obtain a number of attention weights; and compare each attention weight with the preset weight one by one.

[0019] If there is only one case where the attention weight is greater than the preset weight, then calibrate the available net washer corresponding to the attention weight greater than the preset weight as the target net washer.

[0020] If there are multiple cases where the attention weights are greater than the preset weight, obtain the energy consumption information of the available net washing machines corresponding to each attention weight greater than the preset weight, sort the energy consumption information of each available net washing machine, extract the available net washing machine with the minimum energy consumption information, and designate the available net washing machine with the minimum energy consumption information as the target net washing machine;

[0021] If all attention weights are not greater than the preset weight, sort the several attention weights, extract the maximum attention weight, and designate the available net washing machine corresponding to the maximum attention weight as the target net washing machine;

[0022] Transport the target net washing machine to the cloud platform.

[0023] Further, in a preferred embodiment of the present invention, obtain the position of the target net washing machine and the position of the fishing net to be cleaned, and perform a simulation analysis on each crane in the fishing boat according to the position of the target net washing machine and the position of the fishing net to be cleaned to obtain the best hoisting and turning path of the target crane and the target crane, specifically:

[0024] Obtain the real-time working status of each crane in the fishing boat, and designate the crane with the real-time working status as the idle working status as a type I crane; and obtain the working range information of each type I crane;

[0025] Obtain the position of the target net washing machine and the position of the fishing net to be cleaned; judge one by one whether the working range of each type I crane can cover the position of the target net washing machine and the position of the fishing net to be cleaned at the same time;

[0026] If it can, further designate the corresponding type I crane as an available crane, and obtain the position of each available crane; if not, designate the corresponding type I crane as an invalid crane;

[0027] Determine a target area according to the position of the target net washing machine, the position of the fishing net to be cleaned, and the position of the available crane, obtain a real-time scene image of the target area, and construct a real-time scene three-dimensional model diagram of the target area according to the real-time scene image;

[0028] In the real-time scene three-dimensional model diagram, designate the position of the available crane as the path starting point, the position of the fishing net to be cleaned as the path transfer point, and the position of the target net washing machine as the path end point;

[0029] Introduce the particle swarm optimization algorithm, and based on the particle swarm optimization algorithm, plan several hoisting and turning paths in the real-time scene three-dimensional model diagram according to each path starting point, path transfer point, and path end point; and obtain the path length values of each hoisting and turning path;

[0030] Screen out the hoisting path with the shortest path length value, obtain the available crane corresponding to the hoisting path with the shortest path length value, and label the available crane corresponding to the hoisting path with the shortest path length value as the target crane; and label the hoisting path with the shortest path length value as the optimal hoisting path;

[0031] Transmit the target crane and the optimal hoisting path to the cloud platform.

[0032] Further, in a preferred embodiment of the present invention, obtain the real-time hoisting path of the target crane, compare the real-time hoisting path with the optimal hoisting path, and perform corresponding regulation processing on the real-time hoisting parameters of the target crane according to the comparison result. Specifically:

[0033] Collect the real-time position information of the target crane at multiple preset time nodes, and construct the real-time hoisting path of the target crane according to the real-time position information of the target crane collected at multiple preset time nodes;

[0034] Obtain the optimal hoisting path of the target crane, integrate the optimal hoisting path into the real-time scene three-dimensional model diagram to obtain a three-dimensional model diagram of the hoisting path;

[0035] Input the real-time hoisting path into the three-dimensional model diagram of the hoisting path, and calculate the coincidence degree between the real-time hoisting path and the optimal hoisting path in the three-dimensional model diagram of the hoisting path based on the Euclidean distance algorithm; and compare the coincidence degree with the preset coincidence;

[0036] If the coincidence degree is greater than the preset coincidence degree, no regulation processing is performed on the real-time hoisting parameters of the target crane;

[0037] If the coincidence degree is not greater than the preset coincidence degree, regulation processing is performed on the real-time hoisting parameters of the target crane.

[0038] Further, in a preferred embodiment of the present invention, if the coincidence degree is not greater than the preset coincidence degree, regulation processing is performed on the preset hoisting parameters of the target crane. Specifically:

[0039] Obtain the real-time hoisting parameters of the target crane, compare the real-time hoisting parameters of the target crane with the preset hoisting parameters, and obtain the deviation value of the hoisting parameters between the real-time hoisting parameters and the preset hoisting parameters;

[0040] Compare the deviation value of the hoisting parameters between the real-time hoisting parameters and the preset hoisting parameters with the preset deviation value;

[0041] Label the real-time hoisting parameters with the hoisting parameter deviation value greater than the preset deviation value as normal hoisting parameters,

[0042] Calibrate the real-time lifting and turning parameters with deviation values greater than the preset deviation value as abnormal lifting and turning parameters, and perform regulation processing on the abnormal lifting and turning parameters based on the corresponding deviation values of the lifting and turning parameters.

[0043] The second aspect of the present invention discloses a collaborative operation management system for a marine crane and a net washer. The collaborative operation management system for the marine crane and the net washer includes a memory and a processor. A program for the collaborative operation management method of the marine crane and the net washer is stored in the memory. When the program for the collaborative operation management method of the marine crane and the net washer is executed by the processor, the following steps are realized:

[0044] Obtain the image information of the fishing net to be cleaned, perform recognition processing on the image information of the fishing net to be cleaned, and obtain the attached dirt characteristic information of the fishing net to be cleaned;

[0045] Perform feature matching on each available net washer in the fishing boat according to the attached dirt characteristic information of the fishing net to be cleaned, and match the target net washer for cleaning the fishing net to be cleaned;

[0046] Obtain the position of the target net washer and the position of the fishing net to be cleaned, perform simulation analysis on each crane in the fishing boat according to the position of the target net washer and the position of the fishing net to be cleaned, and obtain the best lifting and turning path of the target crane and the target crane;

[0047] Generate the preset lifting and turning parameters of the target crane based on the best lifting and turning path, and control the target crane to move along the best lifting and turning path based on the preset lifting and turning parameters to lift and turn the fishing net to be cleaned into the target net washer;

[0048] Obtain the real-time lifting and turning path of the target crane, compare the real-time lifting and turning path with the best lifting and turning path, and perform corresponding regulation processing on the real-time lifting and turning parameters of the target crane according to the comparison result.

[0049] The present invention solves the technical defects existing in the background technology, and the present invention has the following beneficial effects:

[0050] This method first obtains the information of the fishing net image to be cleaned, performs recognition processing on the information of the fishing net image to be cleaned, and obtains the fouling feature information of the fishing net to be cleaned; pairs the features of each available net washer in the fishing boat according to the fouling feature information of the fishing net to be cleaned, and pairs to obtain the target net washer for cleaning the fishing net to be cleaned; obtains the position of the target net washer and the position of the fishing net to be cleaned, and performs simulation analysis on each crane in the fishing boat according to the position of the target net washer and the position of the fishing net to be cleaned, and obtains the best lifting and turning path of the target crane and the target crane; generates the preset lifting and turning parameters of the target crane based on the best lifting and turning path, and controls the target crane to move along the best lifting and turning path based on the preset lifting and turning parameters to lift and turn the fishing net to be cleaned into the target net washer; obtains the real-time lifting and turning path of the target crane, compares the real-time lifting and turning path with the best lifting and turning path, and performs corresponding regulation and control processing on the real-time lifting and turning parameters of the target crane according to the comparison result. Through a simple and effective algorithm, the cranes and net washers in the fishing boat are coordinated and allocated, thereby improving the coordination of fishing boat operations, realizing intelligent control, effectively improving work efficiency, and avoiding conflicts and delays during operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain the drawings of other embodiments without creative efforts based on these drawings.

[0052] Figure 1 It is the overall method flow chart of a management method for collaborative operation of a marine crane and a net washer;

[0053] Figure 2 It is a partial method flow chart of a management method for collaborative operation of a marine crane and a net washer;

[0054] Figure 3 It is the system block diagram of a management system for collaborative operation of a marine crane and a net washer. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] In order to be able to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0056] Many specific details are set forth in the following description in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0057] As Figure 1 shown, the first aspect of the present invention discloses a collaborative operation management method for a marine crane and a net washing machine, including the following steps:

[0058] S102: Obtain the image information of the fishing net to be cleaned, perform identification processing on the image information of the fishing net to be cleaned, and obtain the fouling characteristic information of the fishing net to be cleaned;

[0059] S104: Perform feature matching on each available net washing machine in the fishing boat according to the fouling characteristic information of the fishing net to be cleaned, and match to obtain the target net washing machine for cleaning the fishing net to be cleaned;

[0060] S106: Obtain the position of the target net washing machine and the position of the fishing net to be cleaned, perform simulation analysis on each crane in the fishing boat according to the position of the target net washing machine and the position of the fishing net to be cleaned, and obtain the best lifting and turning path of the target crane and the target crane;

[0061] S108: Generate preset lifting and turning parameters of the target crane based on the best lifting and turning path, and control the target crane to move along the best lifting and turning path based on the preset lifting and turning parameters to lift and turn the fishing net to be cleaned into the target net washing machine;

[0062] S110: Obtain the real-time lifting and turning path of the target crane, compare the real-time lifting and turning path with the best lifting and turning path, and perform corresponding regulation and control processing on the real-time lifting and turning parameters of the target crane according to the comparison result.

[0063] As Figure 2 shown, further, in a preferred embodiment of the present invention, obtaining the image information of the fishing net to be cleaned and performing identification processing on the image information of the fishing net to be cleaned to obtain the fouling characteristic information of the fishing net to be cleaned specifically includes:

[0064] S202: Retrieve, based on the big data network, the characteristic image information corresponding to the fishing nets with various fouling characteristic information during the historical operation of the fishing boat, construct a knowledge graph, and import the characteristic image information corresponding to the fishing nets with various fouling characteristic information into the knowledge graph, and regularly update the knowledge graph; wherein, the fouling characteristic information includes the degree of attachment and the type of fouling;

[0065] S204: Obtain the image information of the fishing net to be cleaned, introduce the perceptual hashing algorithm, and calculate the hash values between the image information of the fishing net to be cleaned and each characteristic image information in the knowledge graph based on the perceptual hashing algorithm to obtain a plurality of hash values;

[0066] S206: Construct a sorting table, input the plurality of hash values into the sorting table for size sorting, and after the sorting is completed, extract the maximum hash value and obtain the characteristic image information corresponding to the maximum hash value;

[0067] S208: Identify the fouling feature information of the fishing net to be cleaned by pairing in the knowledge graph according to the feature image information corresponding to the maximum hash value.

[0068] It should be noted that the image information of the fishing net to be cleaned is captured by a camera, and then the hash values between the image information of the fishing net to be cleaned and the feature image information in the knowledge graph are calculated by the perceptual hash algorithm. The larger the hash value, the higher the similarity between the images. By obtaining the feature image information with the highest similarity, the fouling feature information of the fishing net to be cleaned can be identified by pairing in the knowledge graph. Through this method, the fouling degree and fouling type of the fishing net to be cleaned can be quickly obtained according to the captured image.

[0069] Further, in a preferred embodiment of the present invention, the feature pairing of each available net washer in the fishing boat is performed according to the fouling feature information of the fishing net to be cleaned, and the target net washer for cleaning the fishing net to be cleaned is obtained by pairing. Specifically:

[0070] Obtain the real-time working status of each net washer in the fishing boat, and calibrate the net washer with the real-time working status of the idle working status as the available net washer;

[0071] Obtain the functional feature information of each available net washer, introduce the multi-head attention mechanism algorithm, analyze the attention weights between the fouling feature information of the fishing net to be cleaned and the functional feature information of each available net washer based on the multi-head attention mechanism algorithm, and obtain a number of attention weights; and compare each attention weight with the preset weight one by one;

[0072] If there is only one case where the attention weight is greater than the preset weight, then calibrate the available net washer corresponding to the attention weight greater than the preset weight as the target net washer;

[0073] If there are multiple cases where the attention weight is greater than the preset weight, then obtain the energy consumption information of the available net washers corresponding to each attention weight greater than the preset weight, sort the energy consumption information of each available net washer, extract the available net washer with the minimum energy consumption information, and set the available net washer with the minimum energy consumption information as the target net washer;

[0074] If all attention weights are not greater than the preset weight, then sort the several attention weights, extract the maximum attention weight, and calibrate the available net washer corresponding to the maximum attention weight as the target net washer;

[0075] Transport the target net washer to the cloud platform.

[0076] It should be noted that by obtaining the real-time working status of each net washer in the fishing boat, and calibrating the net washers with the real-time working status of the idle working status as available net washers, and further, obtaining the functional characteristic information of each available net washer, such as including the net washing method, decontamination type, maximum water spray flow rate, rotation speed of the maximum rotating brush, maximum capacity, etc. of each available net washer. Analyze the attention weights between the fouling characteristic information of the fishing net to be cleaned and the functional characteristic information of each available net washer based on the multi-head attention mechanism algorithm. If the attention weight between the fouling characteristic information of the fishing net to be cleaned and the functional characteristic information of a certain available net washer is greater, it means that the fishing net is more suitable to be cleaned by this net washer. Therefore, by extracting and setting a preset weight, compare each attention weight with the preset weight one by one; if there is only one attention weight greater than the preset weight, then calibrate the available net washer corresponding to the attention weight greater than the preset weight as the target net washer; if there are multiple attention weights greater than the preset weight, then obtain the energy consumption information of the available net washers corresponding to each attention weight greater than the preset weight, sort the energy consumption information of each available net washer, extract the available net washer with the minimum energy consumption information, and set the available net washer with the minimum energy consumption information as the target net washer; if all attention weights are not greater than the preset weight, then sort several attention weights, extract the maximum attention weight, and calibrate the available net washer corresponding to the maximum attention weight as the target net washer. Through this step, the best cleaning machine for cleaning the fishing net to be cleaned can be automatically matched according to the fouling degree and fouling type of the fishing net to be cleaned.

[0077] Furthermore, in a preferred embodiment of the present invention, obtain the position of the target net washer and the position of the fishing net to be cleaned, and perform simulation analysis on each crane in the fishing boat according to the position of the target net washer and the position of the fishing net to be cleaned to obtain the best lifting and rotating path of the target crane, specifically:

[0078] Obtain the real-time working status of each crane in the fishing boat, and calibrate the crane with the real-time working status of the idle working status as a type-I crane; and obtain the working range information of each type-I crane;

[0079] Obtain the position of the target net washer and the position of the fishing net to be cleaned; judge one by one whether the working range of each type-I crane can cover the position of the target net washer and the position of the fishing net to be cleaned at the same time;

[0080] If it can, then further calibrate the corresponding type-I crane as an available crane, and obtain the position of each available crane; if not, then calibrate the corresponding type-I crane as an invalid crane;

[0081] Determine a target area based on the position of the target net washer, the position of the fishing net to be cleaned, and the position of the available crane, and obtain a real-time scene image of the target area. Construct a real-time scene three-dimensional model diagram of the target area according to the real-time scene image;

[0082] In the real-time scene three-dimensional model diagram, mark the position of the available crane as the path starting point, the position of the fishing net to be cleaned as the path transfer point, and the position of the target net washer as the path ending point;

[0083] Introduce the particle swarm optimization algorithm, and based on the particle swarm optimization algorithm, plan several hoisting and turning paths in the real-time scene three-dimensional model diagram according to each path starting point, path transfer point, and path ending point; and obtain the path length values of each hoisting and turning path;

[0084] Select the hoisting and turning path with the shortest path length value, and obtain the available crane corresponding to the hoisting and turning path with the shortest path length value, and mark the available crane corresponding to the hoisting and turning path with the shortest path length value as the target crane; and mark the hoisting and turning path with the shortest path length value as the optimal hoisting and turning path;

[0085] Transmit the target crane and the optimal hoisting and turning path to the cloud platform.

[0086] It should be noted that the target area is the path area involved in hoisting and turning the fishing net to be cleaned to the net washer by the crane. The real-time scene in the target area changes at a certain time node. For example, goods are stacked at a certain position at a certain time node, resulting in changes in the real-time scene in the target area. Therefore, a real-time scene image of the target area is obtained through the monitoring camera device on the fishing boat, and a real-time scene three-dimensional model diagram of the target area is constructed according to the real-time scene image. In the real-time scene three-dimensional model diagram, mark the position of the available crane as the path starting point, the position of the fishing net to be cleaned as the path transfer point, and the position of the target net washer as the path ending point. Then, combined with the particle swarm optimization algorithm, the optional paths for each available crane to hoist and turn the fishing net to be cleaned are planned and constructed to obtain several hoisting and turning paths. Then, the shortest hoisting and turning path is further selected from the several hoisting and turning paths, so as to finally determine the target crane and the optimal hoisting and turning path. Through this step, the optimal crane and the corresponding hoisting and turning path for hoisting and turning the fishing net to be cleaned can be intelligently selected according to the real-time scene of the fishing boat, improving the coordination of the fishing net cleaning work, improving the work efficiency, and avoiding collision accidents.

[0087] Further, in a preferred embodiment of the present invention, obtain the real-time hoisting and turning path of the target crane, compare the real-time hoisting and turning path with the optimal hoisting and turning path, and perform corresponding regulation and control processing on the real-time hoisting and turning parameters of the target crane according to the comparison result, specifically:

[0088] Collect the real-time position information of the target crane at multiple preset time nodes, and construct the real-time hoisting path of the target crane according to the real-time position information of the target crane collected at the multiple preset time nodes;

[0089] Obtain the optimal hoisting path of the target crane, integrate the optimal hoisting path into the real-time scene three-dimensional model diagram to obtain a three-dimensional model diagram of the hoisting path;

[0090] Input the real-time hoisting path into the three-dimensional model diagram of the hoisting path, and calculate the coincidence degree between the real-time hoisting path and the optimal hoisting path in the three-dimensional model diagram of the hoisting path based on the Euclidean distance algorithm; and compare the coincidence degree with the preset coincidence;

[0091] If the coincidence degree is greater than the preset coincidence degree, no adjustment processing is performed on the real-time hoisting parameters of the target crane;

[0092] If the coincidence degree is not greater than the preset coincidence degree, adjustment processing is performed on the real-time hoisting parameters of the target crane.

[0093] Furthermore, in a preferred embodiment of the present invention, if the coincidence degree is not greater than the preset coincidence degree, adjustment processing is performed on the preset hoisting parameters of the target crane, specifically:

[0094] Obtain the real-time hoisting parameters of the target crane, compare the real-time hoisting parameters of the target crane with the preset hoisting parameters to obtain the hoisting parameter deviation values between the real-time hoisting parameters and the preset hoisting parameters;

[0095] Compare the hoisting parameter deviation values between the real-time hoisting parameters and the preset hoisting parameters with the preset deviation values;

[0096] Calibrate the real-time hoisting parameters with hoisting parameter deviation values greater than the preset deviation values as normal hoisting parameters,

[0097] Calibrate the real-time hoisting parameters with hoisting parameter deviation values greater than the preset deviation values as abnormal hoisting parameters, and perform adjustment processing on the abnormal hoisting parameters based on the corresponding hoisting parameter deviation values.

[0098] It should be noted that during the process of the target crane hoisting and rotating the fishing net, by obtaining the real-time hoisting and rotating path of the target crane, calculating the coincidence degree between the real-time hoisting and rotating path and the optimal hoisting and rotating path in the three-dimensional model diagram of the hoisting path, if the coincidence degree is greater than the preset coincidence degree, it indicates that the moving path of the target crane is normal. If the coincidence degree is not greater than the preset coincidence degree, it indicates that the moving path of the target crane has deviated. At this time, further analyze the reasons for the path deviation, that is, abnormal hoisting and rotating parameters, so as to adjust and control the abnormal hoisting and rotating parameters. Through the above steps, the reliability of the target crane during the hoisting and rotating process can be improved, collisions during operation can be avoided, and the coordination of fishing boat operations can be improved.

[0099] In addition, the method further includes the following steps:

[0100] Obtain the real-time net washing parameters of the target net washing machine during the process of washing the target fishing net, introduce the random forest algorithm, and initialize several decision trees, and calculate the Manhattan distance between each real-time net washing parameter and each decision tree;

[0101] Allocate the real-time net washing parameter with the shortest Manhattan distance to the corresponding decision tree, calculate the Euclidean distance between each real-time net washing parameter within each decision tree, and perform an averaging process on the Euclidean distances between each real-time net washing parameter within each decision tree to obtain the average Euclidean distance between each real-time net washing parameter within each decision tree;

[0102] Judge whether the average Euclidean distance between each real-time net washing parameter within each decision tree is less than the preset Euclidean distance; if not, re-iterate the calculation of the number of decision trees and re-allocate the real-time net washing parameters until the average Euclidean distance between each real-time net washing parameter within each decision tree is less than the preset Euclidean distance;

[0103] If the average Euclidean distance between each real-time net washing parameter within each decision tree is less than the preset Euclidean distance, then obtain the real-time net washing parameters to which each decision tree belongs, introduce the Markov chain, and calculate the state transition probability value of the real-time net washing parameters to which each decision tree belongs through the Markov chain; judge whether the state transition probability value of the real-time net washing parameters to which each decision tree belongs is greater than the preset state transition probability value;

[0104] If the state transition probability values of the real-time net washing parameters to which each decision tree belongs are not greater than the preset state transition probability values, continue to make the target net washing machine work, and control the target crane to hoist and rotate the washed fishing net based on the preset time node;

[0105] If there is a situation where the state transition probability values of the real-time net washing parameters belonging to at least one decision tree are all greater than the preset state transition probability value, then control the target net washing machine to stop working, generate a warning message, send the warning message to a preset platform, and arrange for the target crane to perform another lifting operation.

[0106] It should be noted that during the operation of the net washing machine, abnormal working conditions may occur, resulting in the failure of the net washing effect. After the net washing effect fails, if the crane is still used to lift and turn the fishing net that has not achieved the cleaning effect, it will affect the fishing effect of the fishing net at this time. Through this method, it can automatically analyze whether abnormal conditions have occurred during the operation of the net washing machine. If abnormal conditions occur, only the maintenance personnel can promptly repair and troubleshoot the faulty net washing machine to ensure the cleaning effect of the fishing net.

[0107] As Figure 3 shown, the second aspect of the present invention discloses a cooperative operation management system for a marine crane and a net washing machine. The cooperative operation management system for a marine crane and a net washing machine includes a memory 41 and a processor 42. A cooperative operation management method program for a marine crane and a net washing machine is stored in the memory 41. When the cooperative operation management method program for a marine crane and a net washing machine is executed by the processor 42, the following steps are implemented:

[0108] Obtain the image information of the fishing net to be cleaned, perform recognition processing on the image information of the fishing net to be cleaned, and obtain the fouling characteristic information of the fishing net to be cleaned;

[0109] According to the fouling characteristic information of the fishing net to be cleaned, perform feature matching on each available net washing machine in the fishing boat, and match and obtain the target net washing machine for cleaning the fishing net to be cleaned;

[0110] Obtain the position of the target net washing machine and the position of the fishing net to be cleaned, perform simulation analysis on each crane in the fishing boat according to the position of the target net washing machine and the position of the fishing net to be cleaned, and obtain the best lifting and turning path of the target crane and the target crane;

[0111] Generate the preset lifting and turning parameters of the target crane based on the best lifting and turning path, and control the target crane to move along the best lifting and turning path based on the preset lifting and turning parameters to lift and turn the fishing net to be cleaned into the target net washing machine;

[0112] Obtain the real-time lifting and turning path of the target crane, compare the real-time lifting and turning path with the best lifting and turning path, and perform corresponding adjustment processing on the real-time lifting and turning parameters of the target crane according to the comparison result.

[0113] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the couplings, direct couplings, or communication connections between the various components shown or discussed can be through some interfaces. The indirect couplings or communication connections of devices or units can be electrical, mechanical, or other forms.

[0114] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] In addition, each functional unit in the embodiments of the present invention can be all integrated in a processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0116] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments. The foregoing storage media include: removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs and other various media that can store program codes.

[0117] Alternatively, if the above-mentioned integrated units of the present invention are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the various embodiments of the present invention. The foregoing storage media include: removable storage devices, ROM, RAM, magnetic disks, or optical discs and other various media that can store program codes.

[0118] The above is only a specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A collaborative operation management method for a marine crane and a net washing machine, characterized in that Including the following steps: Obtain the image information of the fishing net to be cleaned, perform recognition processing on the image information of the fishing net to be cleaned, and obtain the fouling characteristic information of the fishing net to be cleaned; Perform feature pairing on each available net washer in the fishing boat according to the fouling characteristic information of the fishing net to be cleaned, and pair to obtain the target net washer for cleaning the fishing net to be cleaned; Obtain the position of the target net washer and the position of the fishing net to be cleaned, perform simulation analysis on each crane in the fishing boat according to the position of the target net washer and the position of the fishing net to be cleaned, and obtain the best lifting and turning path of the target crane and the target crane; Generate the preset lifting and turning parameters of the target crane based on the best lifting and turning path, and control the target crane to move along the best lifting and turning path based on the preset lifting and turning parameters to lift and turn the fishing net to be cleaned into the target net washer; Obtain the real-time lifting and turning path of the target crane, compare the real-time lifting and turning path with the best lifting and turning path, and perform corresponding regulation and control processing on the real-time lifting and turning parameters of the target crane according to the comparison result.

2. The collaborative operation management method of a marine crane and a net washing machine according to claim 1, wherein, Obtain the image information of the fishing net to be cleaned, perform recognition processing on the image information of the fishing net to be cleaned, and obtain the fouling characteristic information of the fishing net to be cleaned. Specifically: Based on the big data network, retrieve the characteristic image information corresponding to the fishing nets with various fouling characteristic information during the historical operation of the fishing boat, construct a knowledge graph, import the characteristic image information corresponding to the fishing nets with various fouling characteristic information into the knowledge graph, and regularly update the knowledge graph; wherein, the fouling characteristic information includes the degree of attachment and the type of fouling; Obtain the image information of the fishing net to be cleaned, introduce the perceptual hashing algorithm, and calculate the hash values between the image information of the fishing net to be cleaned and each characteristic image information in the knowledge graph based on the perceptual hashing algorithm to obtain multiple hash values; Construct a sorting table, input the multiple hash values into the sorting table for size sorting, after the sorting is completed, extract the maximum hash value, and obtain the characteristic image information corresponding to the maximum hash value; Pair and identify the fouling characteristic information of the fishing net to be cleaned according to the characteristic image information corresponding to the maximum hash value in the knowledge graph.

3. A collaborative operation management method for a marine crane and a net washing machine according to claim 1, characterized in that, Perform feature pairing on each available net washer in the fishing boat according to the fouling characteristic information of the fishing net to be cleaned, and pair to obtain the target net washer for cleaning the fishing net to be cleaned. Specifically: Obtain the real-time working status of each net washer in the fishing boat, and calibrate the net washer with the real-time working status of the idle working status as the available net washer; Obtain the functional characteristic information of each available net washer, introduce the multi-head attention mechanism algorithm, and analyze the attention weights between the fouling characteristic information of the fishing net to be cleaned and the functional characteristic information of each available net washer based on the multi-head attention mechanism algorithm to obtain several attention weights; And compare each attention weight with the preset weight one by one; If there is only one case where the attention weight is greater than the preset weight, then calibrate the available net washer corresponding to the attention weight greater than the preset weight as the target net washer; If there are multiple cases where the attention weights are greater than the preset weight, obtain the energy consumption information of the available net washing machines corresponding to each attention weight greater than the preset weight, sort the energy consumption information of each available net washing machine, extract the available net washing machine with the minimum energy consumption information, and designate the available net washing machine with the minimum energy consumption information as the target net washing machine; If all attention weights are not greater than the preset weight, sort the several attention weights, extract the maximum attention weight, and designate the available net washing machine corresponding to the maximum attention weight as the target net washing machine; Transport the target net washing machine to the cloud platform.

4. A collaborative operation management method for a marine crane and a net washing machine according to claim 1, characterized in that, Obtain the position of the target net washing machine and the position of the fishing net to be cleaned. Conduct a simulation analysis on each crane in the fishing boat based on the position of the target net washing machine and the position of the fishing net to be cleaned to obtain the optimal lifting and turning path of the target crane and the target crane. Specifically: Obtain the real-time working status of each crane in the fishing boat, and designate the crane with the real-time working status as the idle working status as a type-I crane; and obtain the working range information of each type-I crane; Obtain the position of the target net washing machine and the position of the fishing net to be cleaned; judge one by one whether the working range of each type-I crane can cover the position of the target net washing machine and the position of the fishing net to be cleaned at the same time; If it can, further designate the corresponding type-I crane as an available crane, and obtain the position of each available crane; if not, designate the corresponding type-I crane as an invalid crane; Determine the target area based on the position of the target net washing machine, the position of the fishing net to be cleaned, and the position of the available crane, obtain the real-time scene image of the target area, and construct a real-time scene three-dimensional model diagram of the target area according to the real-time scene image; In the real-time scene three-dimensional model diagram, designate the position of the available crane as the path starting point, the position of the fishing net to be cleaned as the path transfer point, and the position of the target net washing machine as the path ending point; Introduce the particle swarm optimization algorithm, and plan several lifting and turning paths based on the particle swarm optimization algorithm in the real-time scene three-dimensional model diagram according to each path starting point, path transfer point, and path ending point; And obtain the path length value of each lifting and turning path; Select the lifting and turning path with the shortest path length value, and obtain the available crane corresponding to the lifting and turning path with the shortest path length value, and designate the available crane corresponding to the lifting and turning path with the shortest path length value as the target crane; and designate the lifting and turning path with the shortest path length value as the optimal lifting and turning path; Transport the target crane and the optimal lifting and turning path to the cloud platform.

5. A collaborative operation management method for a marine crane and a net washing machine according to claim 4, characterized in that, Obtain the real-time lifting and turning path of the target crane, compare the real-time lifting and turning path with the optimal lifting and turning path, and perform corresponding regulation and control processing on the real-time lifting and turning parameters of the target crane according to the comparison result. Specifically: Collect the real-time position information of the target crane at multiple preset time nodes, and construct the real-time lifting and turning path of the target crane according to the real-time position information of the target crane collected at multiple preset time nodes; Obtain the optimal lifting and turning path of the target crane, integrate the optimal lifting and turning path into the real-time scene three-dimensional model diagram to obtain the three-dimensional model diagram of the lifting path; Input the real-time lifting and slewing path into the three-dimensional model diagram of the lifting path, and calculate the coincidence degree between the real-time lifting and slewing path and the optimal lifting and slewing path in the three-dimensional model diagram of the lifting path based on the Euclidean distance algorithm; and compare the coincidence degree with the preset coincidence degree; If the coincidence degree is greater than the preset coincidence degree, no adjustment processing is performed on the real-time lifting and slewing parameters of the target crane; If the coincidence degree is not greater than the preset coincidence degree, adjustment processing is performed on the real-time lifting and slewing parameters of the target crane.

6. The collaborative operation management method of a marine crane and a net washing machine according to claim 5, characterized in that, If the coincidence degree is not greater than the preset coincidence degree, adjustment processing is performed on the preset lifting and slewing parameters of the target crane. Specifically: Obtain the real-time lifting and slewing parameters of the target crane, compare the real-time lifting and slewing parameters of the target crane with the preset lifting and slewing parameters, and obtain the deviation values of the lifting and slewing parameters between the real-time lifting and slewing parameters and the preset lifting and slewing parameters; Compare the deviation values of the lifting and slewing parameters between the real-time lifting and slewing parameters and the preset lifting and slewing parameters with the preset deviation values; Calibrate the real-time lifting and slewing parameters with deviation values of the lifting and slewing parameters greater than the preset deviation values as normal lifting and slewing parameters, Calibrate the real-time lifting and slewing parameters with deviation values of the lifting and slewing parameters greater than the preset deviation values as abnormal lifting and slewing parameters, and perform adjustment processing on the abnormal lifting and slewing parameters based on the corresponding deviation values of the lifting and slewing parameters.

7. A collaborative operation management system for a marine crane and a net washing machine, characterized in that, The marine crane and net washing machine collaborative operation management system includes a memory and a processor. A marine crane and net washing machine collaborative operation management method program is stored in the memory. When the marine crane and net washing machine collaborative operation management method program is executed by the processor, the following steps are implemented: Obtain the image information of the fishing net to be cleaned, perform recognition processing on the image information of the fishing net to be cleaned, and obtain the fouling characteristic information of the fishing net to be cleaned; Perform feature matching on each available net washing machine in the fishing boat according to the fouling characteristic information of the fishing net to be cleaned, and match the target net washing machine for cleaning the fishing net to be cleaned; Obtain the position of the target net washing machine and the position of the fishing net to be cleaned, perform simulation analysis on each crane in the fishing boat according to the position of the target net washing machine and the position of the fishing net to be cleaned, and obtain the optimal lifting and slewing path of the target crane and the target crane; Generate the preset lifting and slewing parameters of the target crane based on the optimal lifting and slewing path, and control the target crane to move along the optimal lifting and slewing path based on the preset lifting and slewing parameters to lift the fishing net to be cleaned into the target net washing machine; Obtain the real-time lifting and slewing path of the target crane, compare the real-time lifting and slewing path with the optimal lifting and slewing path, and perform corresponding adjustment processing on the real-time lifting and slewing parameters of the target crane according to the comparison result.

Images