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

Abstract

The invention provides an AI-based shipbuilding man-hour unification method and system, a medium and a terminal, and the method comprises the steps: data collection and preprocessing, feature extraction, clustering algorithm application, model generation and the like. Three-dimensional model data and attribute information of ship parts of design end production design modeling are analyzed, an unsupervised learning algorithm is used for automatic classification, the parts with similar characteristics are classified into one class, and the average working hours of the parts of the same class are statistically analyzed in combination with currently recorded part working hour information. Part working hours of similar categories are unified into one datum, part categories in actual construction working hour management are reduced, working hour data are standardized, and field production is guided.

Description

Technical Field

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

[0002] The number of parts and components of ship products is huge and the types are complex. On the one hand, the construction hours of different parts vary due to factors such as their complexity, size and characteristics. On the other hand, the current construction hours are estimated and reported by the production department. The estimation efficiency is low and may cause inconsistent construction hours for the same parts within different departments. The construction hours are an important basis for the production department's dispatch of work, the operation department's planning management, and the payment of workers' wages. It is also the key to cost control. The current working hour management model can no longer meet the requirements of refined shipbuilding management. Therefore, it is necessary to give full play to the role of the model on the design side on the basis of stable production, standardize the ship construction hours through AI technology, and improve the standardized ship working hour system. Summary of the invention

[0003] In view of the above-mentioned shortcomings of the prior art, the present invention provides a shipbuilding work time standardization method based on AI, comprising the following steps:

[0004] S1. Data collection and preprocessing: Collect the production design 3D models of ship parts and their attribute information;

[0005] S2. Feature extraction: Extract key part features that affect working time from the attribute information of ship parts. Key part features include material name, specification information, weight, operation stage, installation posture, ship type, installation environment, and working time information;

[0006] S3. Form a feature vector for each ship part according to the key part features, and the feature vector is expressed as [a, b, c, d, e, f, ...], where a, b, c, d, e, f, ... correspond to the values ​​of each key part feature;

[0007] S4. Analysis using K-means clustering algorithm, by combining the feature vectors with the K-means clustering algorithm, similar ship parts are classified into the same category, and it is determined that the parts in each category have similar key part features, so that the relative differences of a, b, c, d, e, f, ... of the parts belonging to the same category are within a preset range;

[0008] S5. Man-hour statistics: statistics and analysis are performed on the man-hours of each category of parts to obtain the average construction man-hours of the category; the construction man-hours of similar parts belonging to the same category are unified into one data to form a standardized man-hour estimation model;

[0009] S6. Continuous monitoring and feedback. During the shipbuilding process, continuously collect and analyze man-hour data, monitor the performance of the man-hour estimation model, and adjust the model parameters in a timely manner to improve accuracy.

[0010] Optionally, in step S1, the attribute information includes the material name, specification information, weight, installation pallet information, area information, operation stage, installation posture, ship type, installation environment, project number information, and existing working hours information of the ship parts.

[0011] Optionally, in step S2, the specification information includes: the overall dimensions of the parts, length, width, height, inner diameter, and outer diameter; the operation stage corresponds to the C / B / P / Z / D outfitting stage in the ship production and construction process; the installation posture corresponds to the normal state, inverted state, and lying state in the construction process; the installation environment corresponds to a conventional cabin and a narrow cabin; the ship type corresponds to a liquefied gas tanker and a container ship.

[0012] Optionally, the model parameters of the man-hour estimation model include the rate of change of man-hour with changes in a single key part feature and the weight ratio of the impact of each key part feature on the man-hour.

[0013] The present invention also provides a shipbuilding work time unification system, which is used to implement the shipbuilding work time unification method, and the shipbuilding work time unification system includes:

[0014] A data collection module, used to collect three-dimensional models of ship parts and their attribute information;

[0015] The feature extraction module is used to extract key part features that affect the working time from the attribute information of the ship parts, and form a feature vector for each ship part according to the key part features. The feature vector is expressed as [a, b, c, d, e, f, ...], where a, b, c, d, e, f, ... correspond to the values ​​of each key part feature;

[0016] A cluster analysis module is used to classify similar ship parts into the same category in combination with feature vectors, and determine that the parts in each category have similar key part features, so that the relative difference of each value (i.e., a, b, c, d, e, f, ...) in the feature vector of each part belonging to the same category is within a preset range;

[0017] The model generation module is used to unify the construction time of similar parts belonging to the same category into one data to form a standardized time estimation model.

[0018] Optionally, the key part features include material name, specification information, weight, operation stage, installation posture, ship type, installation environment, and working time information.

[0019] 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 ship construction work time standardization method is implemented.

[0020] The present invention also provides a terminal, the terminal comprising a processor and a memory;

[0021] 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 ship construction work time standardization method.

[0022] As described above, the present invention provides an AI-based ship construction work time unification method, system, medium and terminal. The ship construction work time unification method includes data collection and preprocessing, feature extraction, application of clustering algorithm, model generation and other steps. The present invention analyzes the three-dimensional model data and attribute information of the ship parts produced by the design end, and automatically classifies them using an unsupervised learning algorithm, so that parts with similar features are classified into one category, and then combined with the currently recorded part work time information, the average work time of each part of the same category is statistically analyzed, and the work time of parts of similar categories is unified into one data, thereby reducing the part categories in the actual construction work time management, standardizing the work time data, and guiding on-site production. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 Shown is a flow chart of the ship construction work time unification method in the first embodiment of the present invention.

[0024] Figure 2 Shown is a schematic diagram of the structure of the terminal in the first embodiment of the present invention. DETAILED DESCRIPTION

[0025] 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.

[0026] Embodiment 1

[0027] like Figure 1 As shown, this embodiment provides a ship construction work time standardization method based on AI, comprising the following steps:

[0028] S1. Data collection and preprocessing: Collect the production design 3D model of ship parts and their attribute information, which specifically includes the material name, specification information, weight, installation pallet information, area information, operation stage, intermediate product construction posture information (installation posture), ship type, installation environment, project number information, existing man-hour information, etc. Preferably, the collected 3D model data is denoised and standardized to ensure the quality and consistency of the data.

[0029] S2. Feature extraction: Extract key part features that affect working time from the attribute information of ship parts. As an example, key part features include material name, specification information, weight, operation stage, installation posture, ship type, installation environment, working time information, etc. The specification information mainly includes: the overall dimensions of the part, length, width, height, inner diameter, outer diameter, etc.; the operation stage corresponds to the outfitting stage such as C / B / P / Z / D in the ship production and construction process; the installation posture corresponds to the normal, reverse, lying and other construction postures in the construction process; the installation environment corresponds to conventional cabins, narrow cabins, etc.; the ship type corresponds to liquefied gas ships, container ships, etc.

[0030] S3. Based on the above key parts features, a feature vector is formed for each ship part as an input sample for subsequent classification. The feature vector is expressed as [a, b, c, d, e, f, ...], where a, b, c, d, e, f, ... correspond to the values ​​of each key part feature.

[0031] S4. The K-means clustering algorithm is used for analysis. The K-means clustering algorithm is a classic unsupervised learning algorithm that is mainly used to divide a data set into K classes. The center of each class is calculated based on the mean of all values ​​in the class. The algorithm continuously optimizes the clustering results in an iterative manner until a certain termination condition is met.

[0032] The core of the K-means algorithm is to calculate the distance between each sample and K cluster centers and assign the sample to the class corresponding to the nearest cluster center. Then, the center position of each class is recalculated, and this process is repeated until the termination condition is met, such as the class center no longer changes or the preset number of iterations is reached. The steps of the K-means algorithm generally include: (1) Determine the value of K: Select a suitable value of K through methods such as the elbow rule or silhouette coefficient. (2) Initialize the centroid: Randomly select K data points as the initial centroid. (3) Iterative optimization: Assign data points, assign the data points of each part to the nearest centroid to form K clusters, that is, divide different ship parts into K categories; update the centroid, recalculate the centroid of each cluster as the new centroid; repeat the assignment and update until the centroid no longer changes or the preset number of iterations is reached.

[0033] In the process of shipbuilding, a large number of different parts need to be processed. The three-dimensional models of these parts and their attribute information, including material name, specification information, weight, operation stage, installation posture, ship type, installation environment, etc., determine their construction time. In this embodiment, the application of the K-means clustering algorithm specifically includes:

[0034] By using the K-means clustering algorithm, similar ship parts are classified into the same category in combination with the feature vector, and it is determined that the parts in each category have similar key part features, that is, the relative differences of the values ​​(i.e., a, b, c, d, e, f, ...) in the feature vectors of the parts belonging to the same category are within a certain range. Regarding the specific code implementation of the clustering algorithm, there are many records in the prior art, which will not be repeated here.

[0035] Specifically, through the K-means clustering algorithm, similar parts can be automatically classified into the same category. For example, suppose there are the following types of part data:

[0036] -Part A: Material name (steel door), specification (400x350), weight (15T), operation stage (B), installation posture (normal), ship type (liquefied gas ship), installation environment (conventional cabin)

[0037] -Part B: Material name (escalator), specification (450x400), weight (20T), operation stage (P), installation posture (reverse state), ship type (liquefied gas ship), installation environment (conventional cabin)

[0038] -Part C: Material name (steel door), specification (400x350x), weight (18T), operation stage (B), installation posture (normal), ship type (liquefied gas ship), installation environment (conventional cabin)

[0039] By extracting and standardizing the data of these parts, the feature vector corresponding to each part can be formed:

[0040] -Part A: [400, 350, 15, 1, 1, 1, 1]

[0041] -Part B: [450, 400, 20, 2, 2, 1, 1]

[0042] -Part C: [450, 350, 18, 1, 1, 1, 1]

[0043] Using the K-means clustering algorithm, part A and part C can be classified into the same category, while part B can be classified into another category. Here, the relative differences of the values ​​in the feature vectors of part A and part C are within a certain range, so they can be classified into the same category.

[0044] S5, working hours standardization

[0045] The man-hour statistics and analysis are performed on the parts of each category to obtain the average construction man-hour of the category. The construction man-hours of similar parts belonging to the same category are unified into one data to form a standardized man-hour estimation model. For example, the man-hour estimation model needs to consider the rate of change of man-hours with the change of the characteristics of a single key part and the weight ratio of the impact of each key part feature on the man-hour. As a simplified linear calculation method, the man-hour t = ax1y1+bx2y2+cx3y3+dx4y4+…, the model parameters x1, x2, x3, x4 are the change rates, and y1, y2, y3, y4 are the weight ratios. For example, the larger the specifications and weight, the longer it takes; the weight ratio of the installation environment is higher than the weight ratio of the ship type. Under this man-hour estimation model, input the parts and their key part features to obtain the corresponding man-hour estimation value.

[0046] S6. Continuous monitoring and feedback:

[0047] During the shipbuilding process, we continuously collect and analyze man-hour data and monitor the performance of the man-hour estimation model. Once we find a large deviation between the model prediction and the actual man-hour, we promptly adjust the model parameters to improve accuracy. Based on feedback from the actual construction process, we continuously optimize the man-hour standardization method to improve management efficiency.

[0048] This embodiment also provides a shipbuilding work time unification system, which is used to implement the above-mentioned shipbuilding work time unification method, and the shipbuilding work time unification system includes:

[0049] A data collection module, used to collect three-dimensional models of ship parts and their attribute information;

[0050] The feature extraction module is used to extract key part features that affect the working time from the attribute information of ship parts, and form a feature vector for each ship part based on the key part features as an input sample for subsequent classification. Among them, the key part features include material name, specification information, weight, operation stage, installation posture, ship type, installation environment, working time information, etc. The feature vector is expressed as [a, b, c, d, e, f, ...], where a, b, c, d, e, f, ... correspond to the values ​​of each key part feature.

[0051] The clustering analysis module is used to classify similar ship parts into the same category in combination with the feature vectors, and determine whether the parts in each category have similar key part features, that is, the relative differences of the various values ​​(i.e., a, b, c, d, e, f, ...) in the feature vectors of the parts belonging to the same category are within a certain preset range.

[0052] The model generation module is used to unify the construction time of similar parts belonging to the same category into one data to form a standardized time estimation model.

[0053] 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.

[0054] 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 construction time standardization 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.

[0055] 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.

[0056] like Figure 2 As shown, this embodiment further provides a terminal. The terminal of the present invention includes a processor 31 and a memory 32.

[0057] 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.

[0058] 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 work time standardization method.

[0059] 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.

[0060] 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.

[0061] In summary, the present invention provides an AI-based ship construction work time unification method, system, medium and terminal, the ship construction work time unification method includes data collection and preprocessing, feature extraction, application of clustering algorithm, model generation and other steps. The present invention analyzes the three-dimensional model data and attribute information of the ship parts produced by the design end, and automatically classifies them using an unsupervised learning algorithm, so that parts with similar features are classified into one category, and then combined with the currently recorded part work time information, the average work time of each part of the same category is statistically analyzed, and the work time of parts of similar categories is unified into one data, thereby reducing the part categories in the actual construction work time management, standardizing the work time data, and guiding on-site production.

[0062] 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 construction time standardization method based on AI, characterized in that: The steps include: S1. Data collection and preprocessing: Collect the production design 3D models of ship parts and their attribute information; S2. Feature extraction: Extract key part features that affect working time from the attribute information of ship parts. Key part features include material name, specification information, weight, operation stage, installation posture, ship type, installation environment, and working time information; S3. Generate a feature vector for each ship part based on the key part features. The feature vector is expressed as [a, b, c, d, e, f, …], where a, b, c, d, e, f, … correspond to the values ​​of each key part feature; S4. Analysis using K-means clustering algorithm, by combining the feature vectors with the K-means clustering algorithm, similar ship parts are classified into the same category, and it is determined that the parts in each category have similar key part features, so that the relative differences of a, b, c, d, e, f, ... of the parts belonging to the same category are within a preset range; S5. Man-hour statistics: Man-hour statistics and analysis are performed on each category of parts to obtain the average construction man-hour of that category; The construction time of similar parts belonging to the same category is unified into one data to form a standardized time estimation model; S6. Continuous monitoring and feedback. During the shipbuilding process, continuously collect and analyze man-hour data, monitor the performance of the man-hour estimation model, and adjust the model parameters in a timely manner to improve accuracy.

2. The AI-based shipbuilding man-hour standardization method according to claim 1 is characterized by: In step S1, the attribute information includes the material name, specification information, weight, installation pallet information, area information, operation stage, installation posture, ship type, installation environment, project number information, and existing working hours information of the ship parts.

3. The AI-based shipbuilding man-hour standardization method according to claim 1 is characterized by: In step S2, the specification information includes: the overall dimensions of the parts, length, width, height, inner diameter, and outer diameter; the operation stage corresponds to the C / B / P / Z / D outfitting stage in the ship production and construction process; the installation posture corresponds to the normal state, inverted state, and lying state in the construction process; the installation environment corresponds to the conventional cabin and the narrow cabin; the ship type corresponds to the liquefied gas carrier and the container ship.

4. The AI-based shipbuilding man-hour standardization method according to claim 1 is characterized by: The model parameters of the labor time estimation model include the rate of change of labor time with the change of a single key part feature and the weight ratio of the impact of each key part feature on the labor time.

5. A shipbuilding work time system, characterized by: The shipbuilding work time unification system is used to implement the shipbuilding work time unification method according to any one of claims 1 to 4, and the shipbuilding work time unification system includes: A data collection module, used to collect three-dimensional models of ship parts and their attribute information; The feature extraction module is used to extract key part features that affect the working time from the attribute information of the ship parts, and form a feature vector for each ship part according to the key part features. The feature vector is expressed as [a, b, c, d, e, f, ...], where a, b, c, d, e, f, ... correspond to the values ​​of each key part feature; A cluster analysis module is used to classify similar ship parts into the same category in combination with feature vectors, and determine that the parts in each category have similar key part features, so that the relative difference of each value (i.e., a, b, c, d, e, f, ...) in the feature vector of each part belonging to the same category is within a preset range; The model generation module is used to unify the construction time of similar parts belonging to the same category into one data to form a standardized time estimation model.

6. The AI-based shipbuilding man-hour standardization method according to claim 5 is characterized in that: The key parts features include material name, specification information, weight, operation stage, installation posture, ship type, installation environment, and working time information.

7. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the ship construction work time unification method described in any one of claims 1-4.

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 ship construction time standardization method described in any one of claims 1-4.

Images