1. A method of optimizing a ship building plan, comprising the steps of:

s1, acquiring an initial total shipbuilding plan, and decomposing the initial total shipbuilding plan into an engineering and efficiency plan layer, a shipbuilding production plan layer and a shipbuilding influence factor plan layer;

s2, gradually refining and decomposing the project and efficiency plan layer into a large schedule plan, a medium schedule plan and a small schedule plan, and establishing a plan network diagram according to the large schedule plan, the medium schedule plan and the small schedule plan;

s3, establishing a design line according to the large schedule plan and the shipbuilding production plan layer;

s4, classifying the influence factors in the ship building influence factor plan layer, and collecting ship manufacturing big data according to the classification result;

and S5, performing big data modeling on the ship manufacturing industry big data, and integrating the plan network diagram, the plan line and the big data modeling result to obtain an optimized ship building total plan.

2. The vessel construction plan optimization method according to claim 1, wherein the large schedule plan includes time nodes of materials, master devices, outsourcers, and outsourcer lead times between a start date and a ship delivery date;

the intermediate-daily-range plan comprises an equipment accommodation period process plan, a blanking processing process plan, a component assembly process plan, a sectional manufacturing process plan, a sectional pre-outfitting process plan, a slipway carrying process plan and time nodes corresponding to the process plans in the ship production and construction process;

the small schedule plan comprises time nodes of single job and single equipment in each process plan in the medium schedule plan.

3. The ship construction plan optimization method according to claim 2, wherein the step S3 includes the steps of:

s31, establishing an initial building plan line table by serially connecting key tasks in the shipbuilding production plan layer in a reverse order method based on the ship delivery date of the large schedule plan; the key tasks comprise contract design, technical design, production design, sectional processing and manufacturing, slipway sectional folding, wharf outfitting and ship test;

s32, segmenting the initial building plan line table by combining with the existing resources of the shipyard, and establishing a marking line; the process of marking line comprises the selection of a host and other key equipment, the selection of general corollary equipment, the selection of raw materials, and the processing of each section and pipe system.

4. The ship construction plan optimization method according to claim 3, wherein the classification result in the step S4 includes: resource demand factors, distribution and logistics management and control factors, construction quality factors, processing capacity factors, equipment scheduling factors, equipment fault maintenance management and control factors, unpredictable factors and resource constraint factors.

5. The vessel construction plan optimization method of claim 1, wherein the vessel manufacturing industry big data comprises structured data, unstructured data, and semi-structured data; the structured data is data with a uniform representation mode from an existing ship manufacturing industry database, the unstructured data comprises a three-dimensional model of a ship product and corresponding derivative data, and the semi-structured data comprises equipment maintenance records, product quality detection results, installation records, event logs, development logs and plan execution logs of various equipment.

6. The ship construction plan optimization method according to claim 5, wherein the step S5 includes the steps of:

s51, performing data integration on the structured data, the unstructured data and the semi-structured data to obtain a ship manufacturing industry big data initial model;

s52, denoising and data analysis are carried out on the ship manufacturer big data initial model, and a data network diagram, plan data and equipment running state data corresponding to the structured data, the unstructured data and the semi-structured data are set up;

s53, carrying out big data modeling on the data network diagram, the plan data and the equipment running state data to obtain a big data depth model of the ship manufacturer;

s54, processing the big data depth model of the ship manufacturing industry by using an APS system, and establishing a plan model and an equipment abnormity monitoring model;

and S55, integrating the planning network diagram, the planning line, the planning model and the equipment abnormity monitoring model to obtain an optimized ship construction total plan.

7. The vessel construction plan optimization method of claim 6, wherein the structured data and semi-structured data are collected by data warehouse techniques, and the unstructured data are collected in a stream-based manner;

in step S51, in the form of a hybrid storage model "Hadoop + NoSQL + RDBMS", the structured data, the unstructured data, and the semi-structured data are integrated by the Spark calculation engine to obtain an initial model of the ship manufacturing industry big data.

8. The ship building plan optimization system is characterized by comprising a plan decomposition module (1), a plan network diagram building module (2), a plan line building module (3), a big data collection module (4) and a big data modeling integration module (5); the plan decomposition module (1) is connected with the plan network diagram building module (2), the plan line building module (3) and the big data collection module (4); the planning network diagram building module (2) is connected with the planning line building module (3); the big data modeling and integrating module (5) is connected with the planning network diagram establishing module (2), the planning line establishing module (3) and the big data collecting module (4); wherein:

the plan decomposition module (1) is used for acquiring an initial ship construction general plan and decomposing the initial ship construction general plan into an engineering and efficiency plan layer, a shipbuilding production plan layer and a ship construction influence factor plan layer;

the planning network diagram establishing module (2) is used for gradually refining and decomposing the engineering and efficiency planning layer into a large schedule plan, a medium schedule plan and a small schedule plan, and establishing a planning network diagram according to the large schedule plan, the medium schedule plan and the small schedule plan;

the marking line establishing module (3) is used for establishing a marking line according to the large schedule plan and the shipbuilding production plan layer;

the big data collection module (4) is used for classifying the influence factors in the ship building influence factor plan layer and collecting ship manufacturing big data according to classification results;

the big data modeling integration module (5) is used for carrying out big data modeling on the ship manufacturing industry big data, and integrating the plan network diagram, the plan line and the big data modeling result to obtain an optimized ship building total plan.

9. A storage medium having a computer program stored thereon, the computer program comprising: the computer program when executed by a processor implementing the steps of the method of optimization of a ship construction plan according to any one of claims 1 to 7.

10. A computer device, characterized by: comprising a storage medium, a processor and a computer program stored in the storage medium and executable by the processor, which computer program, when executed by the processor, carries out the steps of the method of optimizing a ship construction plan according to any one of claims 1 to 7.

Background

Through information construction and continuous investment for decades in the shipbuilding industry of China, certain achievements are obtained in various ranges such as ship design, ship building management, ship building execution and the like, but a series of problems such as low production efficiency, high building cost, long building period and the like in the shipbuilding industry are not thoroughly changed.

The publication date is 2019.05.31, and the publication number is CN 106951621B: a Simulation optimization method for adjusting a ship carrying plan is characterized in that a segmented production plan, site resources and transportation are considered, Simulation is carried out around three continuous production nodes of segmented production, total assembly and ship carrying, structural modeling is carried out through a Petri network method, Plant Simulation software carries out process modeling, and a new production plan and a ship network carrying graph are constructed in combination with a genetic algorithm. This solution has certain limitations.

Disclosure of Invention

Aiming at the limitation of the prior art, the invention provides a ship building plan optimization method, a system, a storage medium and computer equipment, and the technical scheme adopted by the invention is as follows:

a method of vessel construction plan optimization comprising the steps of:

s1, acquiring an initial total shipbuilding plan, and decomposing the initial total shipbuilding plan into an engineering and efficiency plan layer, a shipbuilding production plan layer and a shipbuilding influence factor plan layer;

s2, gradually refining and decomposing the project and efficiency plan layer into a large schedule plan, a medium schedule plan and a small schedule plan, and establishing a plan network diagram according to the large schedule plan, the medium schedule plan and the small schedule plan;

s3, establishing a design line according to the large schedule plan and the shipbuilding production plan layer;

s4, classifying the influence factors in the ship building influence factor plan layer, and collecting ship manufacturing big data according to the classification result;

and S5, performing big data modeling on the ship manufacturing industry big data, and integrating the plan network diagram, the plan line and the big data modeling result to obtain an optimized ship building total plan.

Compared with the prior art, the method takes the ship manufacturing industry big data as the drive, and generates the optimized new plan by decomposing, modeling, analyzing and predicting the initial plan. The invention fundamentally changes the existing extensive and planned high-frequency change model, shortens the ship delivery date, saves the cost, improves the productivity and efficiency, and realizes lean shipbuilding.

Preferably, the large schedule comprises time nodes of materials, main equipment, outsourced parts and delivery date of the outsourced parts between the operation date and the ship delivery date;

the intermediate-daily-range plan comprises an equipment accommodation period process plan, a blanking processing process plan, a component assembly process plan, a sectional manufacturing process plan, a sectional pre-outfitting process plan, a slipway carrying process plan and time nodes corresponding to the process plans in the ship production and construction process;

the small schedule plan comprises time nodes of single job and single equipment in each process plan in the medium schedule plan.

Further, the step S3 includes the following steps:

s31, establishing an initial building plan line table by serially connecting key tasks in the shipbuilding production plan layer in a reverse order method based on the ship delivery date of the large schedule plan; the key tasks comprise contract design, technical design, production design, sectional processing and manufacturing, slipway sectional folding, wharf outfitting and ship test;

s32, segmenting the initial building plan line table by combining with the existing resources of the shipyard, and establishing a marking line; the process of marking line comprises the selection of a host and other key equipment, the selection of general corollary equipment, the selection of raw materials, and the processing of each section and pipe system.

Further, the classification result in the step S4 includes: resource demand factors, distribution and logistics management and control factors, construction quality factors, processing capacity factors, equipment scheduling factors, equipment fault maintenance management and control factors, unpredictable factors and resource constraint factors.

Preferably, the shipbuilding big data comprises structured data, unstructured data and semi-structured data; the structured data is data with a uniform representation mode from an existing ship manufacturing industry database, the unstructured data comprises a three-dimensional model of a ship product and corresponding derivative data, and the semi-structured data comprises equipment maintenance records, product quality detection results, installation records, event logs, development logs and plan execution logs of various equipment.

Further, the step S5 includes the following steps:

s51, performing data integration on the structured data, the unstructured data and the semi-structured data to obtain a ship manufacturing industry big data initial model;

s52, denoising and data analysis are carried out on the ship manufacturer big data initial model, and a data network diagram, plan data and equipment running state data corresponding to the structured data, the unstructured data and the semi-structured data are set up;

s53, carrying out big data modeling on the data network diagram, the plan data and the equipment running state data to obtain a big data depth model of the ship manufacturer;

s54, processing the big data depth model of the ship manufacturing industry by using an APS system, and establishing a plan model and an equipment abnormity monitoring model;

and S55, integrating the planning network diagram, the planning line, the planning model and the equipment abnormity monitoring model to obtain an optimized ship construction total plan.

Further, the structured data and the semi-structured data are collected through a data warehouse technology, and the unstructured data are collected in a flow-based mode;

in step S51, in the form of a hybrid storage model "Hadoop + NoSQL + RDBMS", the structured data, the unstructured data, and the semi-structured data are integrated by the Spark calculation engine to obtain an initial model of the ship manufacturing industry big data.

The present invention also provides the following:

a ship building plan optimization system comprises a plan decomposition module, a plan network diagram building module, a plan line building module, a big data collection module and a big data modeling integration module; the plan decomposition module is connected with the plan network diagram building module, the plan line building module and the big data collection module; the planning network diagram building module is connected with the planning line building module; the big data modeling and integrating module is connected with the planning network diagram establishing module, the planning line establishing module and the big data collecting module; wherein:

the plan decomposition module is used for acquiring an initial ship construction general plan and decomposing the initial ship construction general plan into an engineering and efficiency plan layer, a shipbuilding production plan layer and a ship construction influence factor plan layer;

the planning network diagram establishing module is used for gradually refining and decomposing the engineering and efficiency planning layer into a large schedule plan, a medium schedule plan and a small schedule plan, and establishing a planning network diagram according to the large schedule plan, the medium schedule plan and the small schedule plan;

the marking line establishing module is used for establishing a marking line according to the large schedule plan and the shipbuilding production plan layer;

the big data collection module is used for classifying the influence factors in the ship building influence factor plan layer and collecting ship manufacturing big data according to classification results;

and the big data modeling integration module is used for carrying out big data modeling on the big data of the ship manufacturing industry and integrating the planning network diagram, the planning line and the big data modeling result to obtain an optimized ship building total plan.

A storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the aforementioned method of vessel construction plan optimization.

A computer arrangement comprising a storage medium, a processor and a computer program stored in the storage medium and executable by the processor, the computer program, when executed by the processor, implementing the steps of the aforementioned vessel construction plan optimization method.

Drawings

Fig. 1 is a schematic flow chart of a ship building plan optimization method provided in embodiment 1 of the present invention;

FIG. 2 is an exemplary diagram of a score line provided in embodiment 1 of the present invention;

FIG. 3 is an exemplary diagram of an optimized ship building overall plan according to embodiment 1 of the present invention;

fig. 4 is a schematic flowchart of step S3 provided in embodiment 1 of the present invention;

fig. 5 is a schematic flowchart of step S5 provided in embodiment 1 of the present invention;

fig. 6 is an exemplary diagram of a data network diagram provided in embodiment 1 of the present invention;

FIG. 7 is a schematic diagram of a vessel construction plan optimization system provided in embodiment 2 of the present invention;

description of reference numerals: 1. a plan decomposition module; 2. a planned network diagram building module; 3. a score line establishing module; 4. a big data collection module; 5. and a big data modeling integration module.

Detailed Description

The drawings are for illustrative purposes only and are not to be construed as limiting the patent;

it should be understood that the embodiments described are only some embodiments of the present application, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without any creative effort belong to the protection scope of the embodiments in the present application.

The terminology used in the embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the embodiments of the present application. As used in the examples of this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the application, as detailed in the appended claims. In the description of the present application, it is to be understood that the terms "first," "second," "third," and the like are used solely to distinguish one from another and are not necessarily used to describe a particular order or sequence, nor are they to be construed as indicating or implying relative importance. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.

Further, in the description of the present application, "a plurality" means two or more unless otherwise specified. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. The invention is further illustrated below with reference to the figures and examples.

In order to solve the limitation of the prior art, the present embodiment provides a technical solution, and the technical solution of the present invention is further described below with reference to the accompanying drawings and embodiments.

Example 1

Referring to fig. 1, a ship building plan optimization method includes the following steps:

s1, acquiring an initial total shipbuilding plan, and decomposing the initial total shipbuilding plan into an engineering and efficiency plan layer, a shipbuilding production plan layer and a shipbuilding influence factor plan layer;

s2, gradually refining and decomposing the project and efficiency plan layer into a large schedule plan, a medium schedule plan and a small schedule plan, and establishing a plan network diagram according to the large schedule plan, the medium schedule plan and the small schedule plan;

s3, establishing a design line according to the large schedule plan and the shipbuilding production plan layer;

s4, classifying the influence factors in the ship building influence factor plan layer, and collecting ship manufacturing big data according to the classification result;

and S5, performing big data modeling on the ship manufacturing industry big data, and integrating the plan network diagram, the plan line and the big data modeling result to obtain an optimized ship building total plan.

Compared with the prior art, the method takes the ship manufacturing industry big data as the drive, and generates the optimized new plan by decomposing, modeling, analyzing and predicting the initial plan. The invention fundamentally changes the existing extensive and planned high-frequency change model, shortens the ship delivery date, saves the cost, improves the productivity and efficiency, and realizes lean shipbuilding.

Specifically, in step S1, the initial total plan of ship construction may be decomposed by an engineering decomposition method, a quantitative management method, and a time-limit planning method; the engineering decomposition method is a method for disassembling engineering projects from big to small; the quantitative management method is a method for distributing various information resources of a project; one of the time-of-day planning methods is the basic method of determining the progress of a project and its timing relationship.

In step S2, a decentralized planning management method may be adopted to gradually refine the project and efficiency planning layer into a large schedule plan, a medium schedule plan and a small schedule plan; the decentralized plan management method is a basic method for straightening up plans, projects and management relations, guaranteeing planning feasibility and reducing management difficulty.

The project and efficiency plan layer controls the date of the main key node, and the cost can be saved and controlled by optimizing the project and efficiency plan layer; the shipbuilding production plan layer mainly takes a ship production flow as a task line, key tasks are correlated, and the manufacturing quality can be controlled by optimizing the shipbuilding production plan layer; the ship construction influence factor plan layer controls the actual implementation progress of production, and by optimizing the ship construction influence factor plan layer, uncertain factors in execution can be reduced, so that the plan work is smoother, and the productivity and the efficiency are improved.

In general, an example of such a score line is seen in FIG. 2; referring to fig. 3, the contents of the optimized ship building total plan, namely the plan network diagram, are indicated by arrows in fig. 3, the middle part is also an example of the score line, and the lower part represents the result of big data modeling.

As a preferred embodiment, the large schedule includes time nodes of materials, master devices, outsourced parts, and outsourced part delivery dates between the start date and the ship delivery date;

the intermediate-daily-range plan comprises an equipment accommodation period process plan, a blanking processing process plan, a component assembly process plan, a sectional manufacturing process plan, a sectional pre-outfitting process plan, a slipway carrying process plan and time nodes corresponding to the process plans in the ship production and construction process;

the small schedule plan comprises time nodes of single job and single equipment in each process plan in the medium schedule plan.

Specifically, the large schedule plan mainly comprises key equipment ordering, detailed design, production design, steel plate ordering and each node between ship docking and ship handing, and comprises time determination of key backward-going projects such as shaft-rudder system stay wire illumination, whole ship deck through, host machine and upper building hoisting, generator motor vehicle, boiler ignition, inclination test empty ship weighing, host motor vehicle, host machine mooring test and submission, pilot run and the like, and provides a main basis for each functional department to plan and carry out engineering control.

The intermediate schedule plan is a schedule plan of each production link from work starting to ship delivery. The method is comprehensively compiled according to factors such as construction guidelines, process engineering methods, standard construction periods of all operation stages, processing sequence tables, production site facilities, climate influences, holidays and the like. In the preparation process, it should be noted that when the production capacity cannot meet the production plan requirement in a part of stages or is rich, the production capacity needs to be properly allocated, and the quantity is properly moved forward or backward on the premise of ensuring that the rhythm is stable and meets the production.

The small schedule plan mainly comprises a weekly or daily operation plan, a production technology preparation plan, a safety week plan, a quality plan and the like of each production team. Wherein the week/day operation plan is a team attendance list and a dispatching list which do not roll in two weeks, the production technology preparation plan is a drawing, material and tray plan which is compiled according to week classification, and the tooling preparation inspection plan is a quality standard and a control point of an operation project; the safety plan is the main point of safety control of the operation project.

The planned network diagram is drawn by taking the ship platform carrying process plan, and a new task can be inserted into the middle of the planned network diagram according to actual conditions, so that the drawing is expanded leftwards and rightwards.

Further, referring to fig. 4, the step S3 includes the following steps:

s31, establishing an initial building plan line table by serially connecting key tasks in the shipbuilding production plan layer in a reverse order method based on the ship delivery date of the large schedule plan; the key tasks comprise contract design, technical design, production design, sectional processing and manufacturing, slipway sectional folding, wharf outfitting and ship test;

s32, segmenting the initial building plan line table by combining with the existing resources of the shipyard, and establishing a marking line; the process of marking line comprises the selection of a host and other key equipment, the selection of general corollary equipment, the selection of raw materials, and the processing of each section and pipe system.

Specifically, in the step S32, the segmentation is performed by using the design specification segmentation/total segmentation map of the ship building to determine the relationship between the key tasks.

Further, the classification result in the step S4 includes: resource demand factors, distribution and logistics management and control factors, construction quality factors, processing capacity factors, equipment scheduling factors, equipment fault maintenance management and control factors, unpredictable factors and resource constraint factors.

Specifically, the resource demand factor reflects uncertainty of demand of human resources, equipment resources, and the like; the distribution and logistics management and control factors reflect logistics and management of links such as steel processing, assembly construction, sectional construction, large sectional construction, storage yard and the like; the construction quality factor monitors the rework cycle and the rework plan of products in each process; the process capability factor concerns the product life cycle; the equipment scheduling factor concerns scheduling conditions of dock equipment, yard equipment and the like; the unpredictable factors are used for adjusting plans caused by conditions such as weather; the resource constraint factors reflect that effective carrying plans and production schedules are planned under limited resources.

As a preferred embodiment, the shipbuilding big data comprises structured data, unstructured data, and semi-structured data; the structured data is data with a uniform representation mode from an existing ship manufacturing industry database, the unstructured data comprises a three-dimensional model of a ship product and corresponding derivative data, and the semi-structured data comprises equipment maintenance records, product quality detection results, installation records, event logs, development logs and plan execution logs of various equipment.

Further, referring to fig. 5, the step S5 includes the following steps:

s51, performing data integration on the structured data, the unstructured data and the semi-structured data to obtain a ship manufacturing industry big data initial model;

s52, denoising and data analysis are carried out on the ship manufacturer big data initial model, and a data network diagram, plan data and equipment running state data corresponding to the structured data, the unstructured data and the semi-structured data are set up;

s53, carrying out big data modeling on the data network diagram, the plan data and the equipment running state data to obtain a big data depth model of the ship manufacturer;

s54, processing the big data depth model of the ship manufacturing industry by using an APS system, and establishing a plan model and an equipment abnormity monitoring model;

and S55, integrating the planning network diagram, the planning line, the planning model and the equipment abnormity monitoring model to obtain an optimized ship construction total plan.

Specifically, in the step S52, the initial model of the big ship data is denoised by using a "maximum/minimum median filter" to filter out data such as equipment data fluctuation, equipment startup and shutdown problems, and the specific process may refer to the following formula:

wherein the content of the first and second substances,representing the data after de-noising, and,representing acquired data, a_i(k) Representing white gaussian noise; p (k | k) represents a median filter, P (k | k) represents a convolution result of the median filter P (k | k),some transformation, such as Fourier transformation, for the convolution result P (k | k); in general, only knowledge is requiredOther quantities can be found using known functions.

In the step S53, a health management and control method may be selected to operate by using the main device, and an anomaly detection (anomaly detection) algorithm is used to model: firstly, establishing and preparing detection sample data by taking a time sequence of equipment as a horizontal axis, forming an operation sample library by the data subjected to SCADA denoising, and establishing an expression domain of an abnormal value and a normal value; and then carrying out big data modeling through relevant knowledge modeling, machine learning and structural insight analysis, plan prediction and optimization model, knowledge granularity and other processing to obtain a final big data model of the ship manufacturing industry.

Fig. 6 is an example of the data network diagram (local part) of a segment hoisting network in the ship building process, which reflects that different operations use the same equipment due to the construction process requirements, and therefore, some of the operations in the diagram can only be performed in sequence and cannot be performed in parallel due to the limitation of the construction machine.

An example of the planning data is seen in the following table:

TABLE 1 planning data example

The planned completion time of each process is reflected in the plan data example; the total field number in the table consists of three parts of 4-to 7-bit characters: the first part is an assembly structure code and is represented by a 2-bit character; the second part is a position or a serial number, which is represented by 2 digits at most; the third part is a partition number, represented by a maximum of 3 digits. For example, CB01PCS, HB is a groove-shaped bulkhead and a rib plate segment, 04 is a position number, P represents the left, C represents the middle, and S represents the right.

An example of the device operating state data is shown in the following table:

TABLE 2 operating State data of the devices

This is equipment operating status data relating to the flatbed equipment; the stopping transportation means that the transportation of the flat car is interrupted due to the stopping of the front vehicle in the running process, and the idling means that the flat car is parked at a parking point of the flat car to wait for the transportation task. For the example, the data analysis can show that the utilization rate of the flat cars is extremely low, and the flat cars are in a waiting state for most of time, so that only 1 flat car needs to be configured for optimization.

The APS (advanced Planning and scheduling) system refers to an advanced Planning and scheduling system.

After the planning model and the equipment abnormity monitoring model are obtained, the following optimization contents can be completed:

aiming at equipment abnormity, the mode of equipment abnormity is determined through collected running state data and maintenance logs of key equipment in the ship manufacturing process, such as cranes, welding machines, steel plate cutting equipment, carrying trolleys and the like, the future fault probability is predicted by using big data while monitoring, and the maintenance time of the equipment with faults is added into the optimized ship building general plan.

Aiming at the segment precision quality, processing the manufacturing deviation of the key carrying points of the segment, determining potential equipment, management and process problems by actively analyzing the trend change of the segment manufacturing quality and the sensitivity of the segment process on the precision quality, and early warning; the yield of the segmented manufacturing is improved through the analysis and the processing, and the rework time is reduced, so that the segmented construction plan is accurate;

and comparing and analyzing historical data of factors influencing ship construction. By tracking each plan in the construction process, analyzing the plan completion condition of each node in the small schedule plan, influencing the elements for plan completion, planning a topological network, finding out production and equipment state data, processing information and resource information, and accurately analyzing the mutual influence relationship of each element of the plan; making a new plan or changing a ship building total plan by determining the influence relationship;

optimizing a key manufacturing process, wherein parameters in the ship manufacturing process are various and mutually influence, analyzing the key manufacturing process influence elements through big data, establishing a process optimization prediction model, finding out the optimal construction method and resources, and immediately giving an alarm once the process parameters are found to deviate outside the interval, so that an operator and an engineer can immediately adjust or make other decisions, thereby ensuring that the execution plan of construction procedures and work steps is prepared, and the whole shipway carrying plan and the like are smoothly completed;

calculating and predicting whether the dock utilization rate is matched with the stock yard utilization efficiency and the manufacturing equipment efficiency; if not, factors causing plan delay such as dispatching, idle running and occupied time of storage yards, docks and slipway equipment are adjusted to optimize the use efficiency of the docks and the storage yards.

Furthermore, the structured data and the semi-structured data are acquired through a data warehouse technology, and the unstructured data are acquired in a flow-based mode;

in step S51, in the form of a hybrid storage model "Hadoop + NoSQL + RDBMS", the structured data, the unstructured data, and the semi-structured data are integrated by the Spark calculation engine to obtain an initial model of the ship manufacturing industry big data.

Specifically, the data warehouse technology, namely, the ETL (Extract-Transform-Load) technology; the hybrid storage model refers to a mode of rapidly and organically storing data to a disk on the basis of not reducing the system efficiency.

Example 2

A ship building plan optimization system, please refer to fig. 7, which includes a plan decomposition module 1, a plan network diagram building module 2, a plan line building module 3, a big data collection module 4 and a big data modeling integration module 5; the plan decomposition module 1 is connected with the plan network diagram building module 2, the plan line building module 3 and the big data collection module 4; the planning network diagram building module 2 is connected with the planning line building module 3; the big data modeling and integrating module 5 is connected with the planning network diagram establishing module 2, the planning line establishing module 3 and the big data collecting module 4; wherein:

the plan decomposition module 1 is used for acquiring an initial ship building total plan and decomposing the initial ship building total plan into an engineering and efficiency plan layer, a shipbuilding production plan layer and a ship building influence factor plan layer;

the planning network diagram establishing module 2 is used for gradually refining and decomposing the engineering and efficiency planning layer into a large schedule plan, a medium schedule plan and a small schedule plan, and establishing a planning network diagram according to the large schedule plan, the medium schedule plan and the small schedule plan;

the design and marking line establishing module 3 is used for establishing a design and marking line according to the large schedule plan and the shipbuilding production plan layer;

the big data collection module 4 is used for classifying the influence factors in the ship building influence factor plan layer and collecting ship manufacturing big data according to classification results;

the big data modeling integration module 5 is used for carrying out big data modeling on the ship manufacturing industry big data, and integrating the planning network diagram, the planning line and the big data modeling result to obtain an optimized ship building total plan.

Example 3

A storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the ship construction plan optimization method of embodiment 1.

Example 4

A computer device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable by the processor, the computer program, when executed by the processor, implementing the steps of the vessel construction plan optimization method of embodiment 1.

It should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.