AI-based ship construction process unification method and system, medium and terminal

Abstract

The invention provides an AI-based ship construction process unification method, system, medium and terminal, and the process unification method comprises the steps: firstly analyzing the historical ship construction data, extracting the key features of the construction processes, and then carrying out the process sorting according to the extracted key features through employing a genetic algorithm. In the process, a ship construction process is abstracted into chromosomes, and an initial population is randomly generated; selecting an individual with high fitness as a parent chromosome; performing cross exchange of single-point genes on the selected parent chromosomes to generate a filial generation process sequence; then variation is carried out, local sequences or parameters of offspring procedures are randomly adjusted, and diversity is enhanced. The genetic algorithm can gradually converge to an optimal solution of a problem through repeated selection, crossing and variation processes and multi-generation breeding and selection, and an individual represented by the optimal solution is a better installation process, so that the purpose of performing unification on the processes is achieved, the intelligence and adaptability of process planning are improved, and the construction efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of shipbuilding, and in particular to an AI-based shipbuilding process standardization method. Background Art

[0002] In the traditional shipbuilding process, the process is complicated and highly dependent on manual experience, resulting in long construction cycles, high costs, and difficulty in accurately controlling quality. With the rapid development of artificial intelligence technology, its application in the manufacturing industry is becoming more and more extensive, providing new possibilities for optimizing shipbuilding processes. Through standardization, unnecessary waiting time and resource waste can be eliminated, construction efficiency can be improved, resource allocation can be optimized, costs can be reduced, operations can be standardized, and construction quality can be ensured. Summary of the invention

[0003] With the rapid development of artificial intelligence technology, its application in the manufacturing industry is becoming more and more extensive, providing new possibilities for the optimization of shipbuilding processes. By simulating the natural evolution process through genetic algorithms, the global optimal solution can be efficiently searched. Combined with the dynamic learning ability of AI, the intelligence and adaptability of process planning can be significantly improved.

[0004] To achieve the above-mentioned and other related purposes, the present invention provides an AI-based shipbuilding process standardization method, comprising the following steps:

[0005] S1. Analyze the historical ship construction data, including construction process data, design drawings and specification data, installation pallet data, human resources data, equipment and tool data, and external environmental factor data, to form a database of historical ship construction data feature values;

[0006] S2. Analyze the relevant data of the ship historical construction data characteristic value database, find the main processes in each construction process and the resource consumption corresponding to each process, and extract key features; the key features include: product type, construction process, process name, process time, resource consumption, process dependency, and quality requirements; among them, resource consumption includes manpower requirements, arrival constraints, and equipment constraints;

[0007] S3. Model training and optimization: Genetic algorithm is used to sort the processes according to the extracted key features, and multiple generations are generated to obtain multiple different process sequences. The process sequence with the largest fitness function is selected as the optimal process sequence.

[0008] Optionally, step S1 specifically includes:

[0009] Analyze the construction process data, including the hull construction process and the outfitting construction process. Each construction process includes multiple steps.

[0010] Parse design drawings and specifications to obtain process dependencies;

[0011] Parse and install pallet data, including arrival information and quantity information required for each process;

[0012] Analyze human resource data, including the personnel composition, skill level and work efficiency of the construction team at each process;

[0013] Analyze equipment and tool data, including the equipment required for each process, including cranes, flatbed trucks, and welding machines.

[0014] Optionally, the hull construction process includes cutting, small group assembly, medium assembly, segmentation, small total section, large total section, and ring section, and the outfitting construction process is integrated into the hull construction process according to the outfitting stages of S\C\B\P\Z\D.

[0015] Optionally, step S3 specifically includes:

[0016] S31. Abstract the shipbuilding process into chromosomes, where each gene in the chromosome represents a process node, and the gene value includes process parameters, including process time consumption, resource consumption, and process dependency; randomly generate an initial population, which includes multiple chromosomes, each chromosome has a different gene sequence, thereby forming a different process sequence;

[0017] S32, fitness function design, defining the fitness function, and calculating the fitness function of the process sequence in the initial population;

[0018] S33, using roulette or tournament to select individuals with high fitness in the initial population as parent chromosomes; performing crossover of single-point genes on the selected parent chromosomes to generate a sequence of offspring processes; then performing mutation to randomly adjust the local order or parameters of the offspring processes to enhance diversity;

[0019] S34, repeat the selection, crossover and mutation process until the predetermined number of iterations is reached, select the process sequence with the largest fitness function as the optimal process sequence, output the global optimal solution, and generate a visual Gantt chart and resource allocation table.

[0020] Optionally, the fitness function is Fitness=a*(1 / T)+b*Ry*C; wherein T is the total construction period, R is the resource utilization rate, C is the number of process dependency conflicts, and a, b, y are weight coefficients.

[0021] The present invention also provides a shipbuilding process unification system for implementing the above-mentioned shipbuilding process unification method, wherein the shipbuilding process unification system comprises:

[0022] A data collection module is used to analyze the historical ship construction data to form a database of historical ship construction data feature values;

[0023] A feature extraction module is used to extract key features of the construction process from the feature value database of historical ship construction data;

[0024] The model training module uses a genetic algorithm to sort the processes according to the extracted key features and generates multiple generations to obtain multiple different process sequences, from which the process sequence with the largest fitness function is selected as the optimal process sequence.

[0025] The present invention also provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned shipbuilding process standardization method is implemented.

[0026] The present invention also provides a terminal, the terminal comprising a processor and a memory;

[0027] The memory is used to store computer programs;

[0028] The processor is connected to the memory and is used to execute the computer program stored in the memory so that the terminal executes the above-mentioned ship construction process unified method.

[0029] As described above, the present invention provides a shipbuilding process unification method, system, medium and terminal based on AI. The process unification method first analyzes the historical shipbuilding data, extracts the key features of the construction process, and then uses a genetic algorithm to sort the process according to the extracted key features. The application process of the genetic algorithm is to first abstract the shipbuilding process into chromosomes, randomly generate an initial population; select individuals with high fitness in the initial population as parent chromosomes; cross-exchange single-point genes of the selected parent chromosomes to generate a child process sequence; then mutate, randomly adjust the local order or parameters of the child process, and enhance diversity. Repeat the selection, crossover and mutation process, and finally select the process sequence with the largest fitness function as the optimal process sequence. After multiple generations of reproduction and selection, the genetic algorithm will gradually converge to the optimal solution or approximate optimal solution of the problem, and eventually one or several individuals may have very high fitness values. The individuals they represent are a better installation process, thereby achieving the purpose of unifying the process, improving the intelligence and adaptability of process planning, and improving construction efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic diagram of the process of step S3 in the first embodiment of the present invention.

[0031] Figure 2 Shown is a schematic diagram of the structure of the terminal in the first embodiment of the present invention.

[0032] Component number description

[0033] Processor 31; the memory 32. DETAILED DESCRIPTION

[0034] The following describes the embodiments of the present invention through specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention.

[0035] Embodiment 1

[0036] like Figure 1 As shown, this embodiment provides an AI-based shipbuilding process standardization method, comprising the following steps:

[0037] S1. Analyze the historical ship construction data, including construction process data, design drawings and specification data, installation pallet data, human resources data, equipment and tool data, and external environmental factor data, to form a database of historical ship construction data feature values ​​for subsequent identification of key factors affecting the construction process.

[0038] The specific process of step S1 includes:

[0039] S11 analyzes the construction process data: including the hull construction process and the outfitting construction process, which is specifically classified according to the intermediate process of hull assembly. According to the product type, the hull construction process mainly includes: cutting, small group assembly, medium assembly, segmentation, small total section, large total section, and ring section, and this is used as the basis for the classification of subsequent process data. The outfitting construction process is integrated into the hull construction process according to the outfitting stages such as S\C\B\P\Z\D; among them, each construction process includes multiple processes.

[0040] S12 Analyze design drawings and specifications: specifically including detailed design, production design drawings, and construction specifications. They specify various technical requirements and standards in the construction process, and analyze the requirements for product construction and processes as reference standards and rigid requirements for subsequent process integration. This step is to obtain process dependencies, that is, the front-end relationship. For example, a certain segmented construction process includes process 1, process 2, and process 3. Process 2 and process 3 both need to be carried out based on the completion of process 1, while process 2 and process 3 have no dependency relationship. Then process 1 must be placed before process 2 and process 3, while process 2 and process 3 have no front-end dependency relationship.

[0041] S13 analyzes the installation pallet data: specifically includes the arrival information and material quantity information required for each process, so as to be used for subsequent analysis of the impact of arrival and material quantity on process integration;

[0042] S14 analyzes human resource data: specifically including the personnel composition, skill level and work efficiency of the construction team of each process, which can be converted into the actual construction time data of the personnel, and used for subsequent analysis of the sequence of processes in the process model and optimization of the coordination between processes;

[0043] S15 Equipment and tool data: including performance parameters and availability of equipment such as cranes, flatbed trucks, and welders. Used for subsequent analysis of the impact of equipment scheduling and maintenance on process integration.

[0044] S16 External environmental factors: such as weather and policy changes, consider the impact on process integration and the response measures.

[0045] S2. Process feature extraction: Analyze the relevant data of the ship historical construction data feature value database, find the main processes in each construction process and the resource consumption corresponding to each process based on relevant technical requirements and specification rules, and extract the key features. Perform data cleaning during the process, and use the data of these processes as input for extracting core feature data. Based on the processed data, use feature engineering technology to extract the key features of the construction process. The key features include: product type, construction process, process name, process time, resource consumption (including manpower requirements, arrival constraints, equipment constraints), process constraints (process dependencies), quality requirements, etc. These features will serve as the basis for subsequent model training.

[0046] Among them, product type, construction process, process name, and process time are obtained based on construction process data; manpower requirements are obtained based on human resource data; arrival constraints are obtained based on installation pallet data; equipment constraints are obtained based on equipment and tool data; process dependencies and quality requirements are obtained based on design drawings and specification data.

[0047] S3, model training and optimization: Genetic algorithms are used to sort the processes based on the extracted key features, and multiple generations are generated to obtain multiple different process sequences, from which the process sequence with the largest fitness function is selected as the optimal process sequence. The goal is to formulate reasonable construction processes, combining factors such as manpower, resources, environment, arrival status, technical requirements, etc., to reduce waiting operations, shorten the construction cycle, and improve construction efficiency. Figure 1 As shown, this step specifically includes:

[0048] S31 abstracts the shipbuilding process into chromosomes, where each gene represents a process node, and the gene value contains process parameters (process time, resource consumption, process dependency, etc.). The initial population is randomly generated, and the initial population includes multiple chromosomes, each with a different gene order.

[0049] S32 Fitness function design: Define the fitness function to evaluate the quality of the process sequence. Calculate the fitness function of the process sequences with different arrangements, and finally select the process sequence with the largest fitness function as the optimal process sequence.

[0050] As an example, the calculation factors of the fitness function include: total construction period (T), the value of T in the optimal process sequence should be as small as possible to minimize the total construction time; resource utilization (R), the value of R should be as large as possible to maximize the balanced use of equipment and manpower; conflict penalty (C), C represents the number of process dependency conflicts, and the value of C should be as small as possible to reduce the dependencies between processes and ensure that the process sequence can be completed smoothly. Formula example: Fitness = a*(1 / T)+b*Ry*C (a, b, y are weight coefficients).

[0051] S33 uses roulette or tournament to select individuals with high fitness in the initial population as parent chromosomes; crossover of single-point genes is performed on the selected parent chromosomes to generate a sequence of offspring processes; mutation is then performed to randomly adjust the local order or parameters of the offspring processes to enhance diversity.

[0052] S34 repeats the selection, crossover and mutation process until a predetermined number of iterations is reached or a stop condition is met. The process sequence with the largest fitness function is selected as the optimal process sequence, the global optimal solution is output, and a visual Gantt chart and resource allocation table are generated. Regarding the specific code implementation of the genetic algorithm, there are many records in the prior art, which will not be repeated here.

[0053] Specifically, after multiple generations of reproduction and selection, the genetic algorithm will gradually converge to the optimal solution or approximate optimal solution to the problem, and eventually one or several individuals may have very high fitness values. The individuals they represent are a better installation process, thereby achieving the purpose of standardizing the process and improving construction efficiency. In the process, it is necessary to continuously adjust the model parameters according to the actual construction situation and continuously optimize the standardization method and process.

[0054] For example, in the process of generational reproduction, the dynamic optimization process can be further considered.

[0055] Dynamic optimization: Receive sensor data (such as equipment status, design changes) in real time and dynamically adjust the weight coefficient of the fitness function; if a process delay is detected, re-iterate the optimization and output a correction plan.

[0056] For ease of understanding, step S3 is described below by way of example.

[0057] The construction of a certain ship unit includes the following processes (simplified):

[0058] Process A: Sheet installation (10 days, 2 assemblers, occupies gantry crane)

[0059] Process B: Installation of iron outfitting 1 (4 days, completed by process A, 2 assemblers)

[0060] Process C: Installation of electrical equipment 1 (2 days, completed by A, 2 assemblers)

[0061] Process D: Installation of pipe and outfitting 1 (8 days, completed by A, occupies 2 copper workers and occupies gantry crane)

[0062] Process E: Installation of pipe and outfitting 2 (8 days, completed by B, occupies 2 copper workers and occupies gantry crane) ......

[0064] Resource constraints: 1 crane, 6 assemblers, 4 copper workers

[0065] Genetic algorithm implementation steps:

[0066] S31: Encoding and initialization

[0067] 1. Chromosome coding example: [ABCDE] must satisfy the process dependency.

[0068] 2. Randomly generate an initial population (such as 10 feasible sequences)

[0069] Individual 1: [ABCDE] (total duration = 10 days)

[0070] Instance 2: [ACDBE]

[0071] S32: Fitness calculation

[0072] Suppose a sequence is [ABCDE], total construction period = 10+4+2+8+8 = 32 days, resource utilization = 85%, and number of conflicts = 0.

[0073] Fitness score: Fitness = 0.4*(1 / 32)+0.5*0.85-0.1*0 = 0.0125+0.425 = 0.4375

[0074] S33: Genetic Operations

[0075] Selection: Keep the top 50% of individuals in terms of fitness.

[0076] Crossover: The parents [ABCDE] and [ACDBE] cross to generate the offspring [ACDBE] and [ABCDE].

[0077] Mutation: The descendant [ACDBE] mutates to [ACBDE] (fixed due to dependency conflict).

[0078] S34: Dynamic optimization and output results

[0079] If a gantry crane failure is found in process D during the iteration, the fitness function weight is dynamically adjusted (such as increasing the resource utilization weight B)

[0080] Output result: optimal solution [ABCD], total construction period 10 days, resource utilization rate 90%.

[0081] This embodiment also provides a shipbuilding process standardization system, which is used to implement the above-mentioned shipbuilding process standardization method, and the shipbuilding process standardization system includes:

[0082] A data collection module is used to analyze the historical ship construction data to form a database of historical ship construction data feature values;

[0083] A feature extraction module is used to extract key features of the construction process from the feature value database of historical ship construction data;

[0084] The model training module uses a genetic algorithm to sort the processes according to the extracted key features and generates multiple generations to obtain multiple different process sequences, from which the process sequence with the largest fitness function is selected as the optimal process sequence.

[0085] It should be noted that it should be understood that the division of the various modules of the above system is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or physically separated. Moreover, these modules can be implemented in the form of software calling through processing elements; or in the form of hardware; or some modules can be implemented in the form of software calling through processing elements, and some modules can be implemented in the form of hardware.

[0086] This embodiment also provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned shipbuilding process unified method is implemented. The storage medium may include, but is not limited to, a floppy disk, an optical disk, a CD-ROM (full name in English: CD-Read-Only Memory), a magneto-optical disk, a ROM (full name in English: Read-Only Memory), a RAM (full name in English: Random Access Memory), an EPROM (erasable programmable read-only memory), an EEPROM (electrically erasable programmable read-only memory), a magnetic card or an optical card, a flash memory, or other types of media / machine-readable media suitable for storing machine-executable instructions.

[0087] Furthermore, the storage medium may be a product that is not connected to a computer device, or a component that is connected to a computer device for use.

[0088] like Figure 2 As shown, this embodiment further provides a terminal, which includes a processor 31 and a memory 32.

[0089] The memory 32 is used to store computer programs; preferably, the memory 32 includes: ROM, RAM, disk, USB flash drive, memory card or optical disk, etc., various media that can store program codes.

[0090] The processor 31 is connected to the memory 32 and is used to execute the computer program stored in the memory 32 so that the terminal executes the above-mentioned ship construction process unified method.

[0091] Preferably, the processor 31 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0092] Furthermore, the number of the memory 32 may be one or more, and the number of the processor 31 may also be one or more. Figure 2 Take one as an example.

[0093] In summary, the present invention provides a shipbuilding process unification method, system, medium and terminal based on AI. The process unification method first analyzes the historical shipbuilding data, extracts the key features of the construction process, and then uses a genetic algorithm to sort the process according to the extracted key features. The application process of the genetic algorithm is to first abstract the shipbuilding process into chromosomes, randomly generate an initial population; select individuals with high fitness in the initial population as parent chromosomes; cross-exchange single-point genes on the selected parent chromosomes to generate a child process sequence; then mutate, randomly adjust the local order or parameters of the child process, and enhance diversity. Repeat the selection, crossover and mutation process, and finally select the process sequence with the largest fitness function as the optimal process sequence. After multiple generations of reproduction and selection, the genetic algorithm will gradually converge to the optimal solution or approximate optimal solution of the problem, and eventually one or several individuals may have very high fitness values. The individuals they represent are a better installation process, thereby achieving the purpose of unifying the process, improving the intelligence and adaptability of process planning, and improving construction efficiency.

[0094] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A shipbuilding process standardization method based on AI, characterized in that: The steps include: S1. Analyze the historical ship construction data, including construction process data, design drawings and specification data, installation pallet data, human resources data, equipment and tool data, and external environmental factor data, to form a database of historical ship construction data feature values; S2. Analyze the relevant data in the ship historical construction data characteristic value database, find the main processes in each construction process and the resource consumption corresponding to each process, and extract the key features; Key features include: product type, construction process, process name, process duration, resource consumption, process dependency, and quality requirements; resource consumption includes manpower requirements, arrival constraints, and equipment constraints; S3. Model training and optimization: Genetic algorithm is used to sort the processes according to the extracted key features, and multiple generations are generated to obtain multiple different process sequences. The process sequence with the largest fitness function is selected as the optimal process sequence.

2. The AI-based shipbuilding process standardization method according to claim 1 is characterized in that: Step S1 specifically includes: Analyze the construction process data, including the hull construction process and the outfitting construction process. Each construction process includes multiple steps. Parse design drawings and specifications to obtain process dependencies; Parse and install pallet data, including arrival information and quantity information required for each process; Analyze human resource data, including the personnel composition, skill level and work efficiency of the construction team at each process; Analyze equipment and tool data, including the equipment required for each process, including cranes, flatbed trucks, and welding machines.

3. The AI-based shipbuilding process standardization method according to claim 2 is characterized by: The hull construction process includes cutting, small group assembly, medium assembly, segmentation, small total block, large total block, and ring section. The outfitting construction process is integrated into the hull construction process according to the S\C\B\P\Z\D outfitting stages.

4. The AI-based shipbuilding process standardization method according to claim 1 is characterized in that: Step S3 specifically includes: S31. Abstract the shipbuilding process into chromosomes, where each gene in the chromosome represents a process node, and the gene value includes process parameters, including process time consumption, resource consumption, and process dependency; randomly generate an initial population, which includes multiple chromosomes, each chromosome has a different gene sequence, thereby forming a different process sequence; S32, fitness function design, defining the fitness function, and calculating the fitness function of the process sequence in the initial population; S33, using roulette or tournament to select individuals with high fitness in the initial population as parent chromosomes; performing crossover of single-point genes on the selected parent chromosomes to generate a sequence of offspring processes; then performing mutation to randomly adjust the local order or parameters of the offspring processes to enhance diversity; S34, repeat the selection, crossover and mutation process until the predetermined number of iterations is reached, select the process sequence with the largest fitness function as the optimal process sequence, output the global optimal solution, and generate a visual Gantt chart and resource allocation table.

5. The AI-based shipbuilding process standardization method according to claim 1 is characterized by: The fitness function is Fitness = a*(1 / T)+b*Ry*C; where T is the total construction period, R is the resource utilization rate, C is the number of process dependency conflicts, and a, b, and y are weight coefficients.

6. A shipbuilding process unified system, characterized in that: The shipbuilding process standardization system is used to implement the shipbuilding process standardization method described in any one of claims 1 to 5 above, and the shipbuilding process standardization system includes: A data collection module is used to analyze the historical ship construction data to form a database of historical ship construction data feature values; A feature extraction module is used to extract key features of the construction process from the feature value database of historical ship construction data; The model training module uses a genetic algorithm to sort the processes according to the extracted key features and generates multiple generations to obtain multiple different process sequences, from which the process sequence with the largest fitness function is selected as the optimal process sequence.

7. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the shipbuilding process standardization method described in any one of claims 1 to 5.

8. A terminal, characterized in that: The terminal includes a processor and a memory; The memory is used to store computer programs; The processor is connected to the memory and is used to execute the computer program stored in the memory so that the terminal executes the shipbuilding process standardization method described in any one of claims 1-5 above.

Images