A production management intelligent monitoring method, system and terminal for ship componentization pre-installation

Abstract

This invention provides an intelligent monitoring method for production management of pre-outfitting of ship components, comprising the following steps: acquiring depth image information of components within the outfitting site; generating a 3D reconstruction model of the component based on the depth image information; identifying the component's identification label and obtaining the identification label information of the corresponding outfitting component; constructing the actual weighted graph adjacency matrix of the component based on the component's identification label information, the outfitting component's identification label information, and the component's 3D reconstruction model; obtaining the component's initial 3D model and initial weighted graph adjacency matrix model, and combining the component's 3D reconstruction model and actual weighted graph adjacency matrix to obtain the component's pre-outfitting completion progress and / or work time information. This invention provides an intelligent monitoring method, system, and terminal for production management of pre-outfitting of ship components, enabling real-time control of project progress under the pre-outfitting mode of ship components, and improving the efficiency of ship production management.

Description

Technical Field

[0001] This application belongs to the field of shipbuilding technology, and in particular relates to an intelligent monitoring method, system and terminal for production management of pre-outfitting of ship components. Background Technology

[0002] Ship outfitting accounts for 50% to 60% of the total shipbuilding workload and is a crucial part of the shipbuilding process. Ship outfitting involves the installation of mechanical, electrical, and electronic equipment after the main hull structure is completed and the ship is launched. It can be divided into three categories: ship outfitting, mechanical outfitting, and electrical outfitting. Pre-outfitting refers to a method of advancing the traditional outfitting work at the dock and onboard to before the sections and main sections are placed on the slipway. Moving the entire ship's outfitting work forward effectively shortens the slipway cycle, improves outfitting quality and efficiency, and simultaneously improves working conditions and ensures safe production. Currently, most shipyards adopt the section pre-outfitting model, but section pre-outfitting has problems such as poor hidden installation safety, difficulty in positioning outfitting components, and high investment in auxiliary work. Component-based pre-outfitting solves the aforementioned problems of segmented pre-outfitting. However, due to the large number of components and outfitting parts involved, manual management and recording methods are insufficient for real-time monitoring of project progress, leading to difficulties in ship production management. Furthermore, manual management and recording methods are labor-intensive and time-consuming, also impacting shipbuilding efficiency. These issues are significant obstacles to the widespread application of component-based pre-outfitting. Therefore, achieving real-time monitoring of project progress and improving ship production management efficiency under component-based pre-outfitting is a crucial problem that urgently needs to be addressed. Summary of the Invention

[0003] In view of the shortcomings of the prior art, the purpose of this application is to provide an intelligent monitoring method, system and terminal for production management of pre-outfitting of ship components, to solve the problems of difficulty in accurately controlling the progress of the project in real time, inconvenience in ship production management and low construction efficiency under the current pre-outfitting of ship components.

[0004] To achieve the above and other related objectives, this invention provides an intelligent monitoring method for production management of pre-outfitting of ship components, comprising the following steps:

[0005] Depth image information of a single component is collected in the outfitting site. Based on the depth image information, a current three-dimensional reconstruction model of the component is generated using three-dimensional reconstruction technology. The three-dimensional reconstruction model includes the three-dimensional geometric data of the component, the three-dimensional geometric data of the first outfitting component that has been pre-outfitted on the component, and the positional feature information of the first outfitting component.

[0006] Identify the identification label of the component and obtain the identification label information of the component; based on the identification label information of the component, obtain the identification label information of each second outfitting component to be installed in advance;

[0007] Based on the identification label information of the second outfitting component and the preset verification conditions, the name and location feature information of the first outfitting component are verified to obtain the first outfitting component whose name and location feature information are both verified accurately, and thus the first outfitting component is considered a valid first outfitting component.

[0008] Based on the names of the components and the names and positional features of each valid first outfitting component, the actual weighted graph adjacency matrix of the components is constructed, and the number of weighted edges in the actual weighted graph adjacency matrix is ​​extracted.

[0009] Obtain the initial 3D model of the component and the initial weighted graph adjacency matrix of the component;

[0010] Based on the reconstructed 3D model and the initial 3D model, the overlap degree of the 3D model is obtained; based on the actual weighted graph adjacency matrix of the component and the initial weighted graph adjacency matrix of the component, the completeness of the weighted graph adjacency matrix is ​​obtained; wherein, the overlap degree is the ratio of the volume of the reconstructed 3D model to the volume of the initial 3D model; the completeness is the ratio of the total number of weighted edges in the actual weighted graph adjacency matrix to the total number of weighted edges in the initial weighted graph adjacency matrix;

[0011] The completion progress of the component pre-outfitting is obtained based on the overlap degree of the 3D model and the completeness of the weighted graph adjacency matrix; the completion progress is the weighted sum of the overlap degree and the completeness.

[0012] In one embodiment of the present invention, when the method obtains the identification tag information of the component and the second outfitting component, the identification tag information of the component and the second outfitting component further includes: time information.

[0013] In one embodiment of the present invention, after obtaining the completion progress of the component pre-outfitting, the method further includes:

[0014] Based on the identification label information of the component and the identification label information of the second outfitting component, the time information of the component and the second outfitting component is obtained, and the time information of the component's component pre-outfitting is obtained based on the time information of the component and the second outfitting component.

[0015] In one embodiment of the present invention, the actual weighted graph adjacency matrix of the component is constructed in the following manner:

[0016] The names of the components and the names of the effective first outfitting parts are stored in a one-dimensional data table as vertices of the actual weighted graph adjacency matrix of the components;

[0017] The positional feature information of the effective first outfitting component is stored in a two-dimensional data table in the form of a structure, which serves as the weighted edge of the actual weighted graph adjacency matrix of the component;

[0018] Based on the vertices and weighted edges of the actual weighted graph adjacency matrix, construct the actual weighted graph adjacency matrix of the component.

[0019] In one embodiment of the present invention, the initial weighted graph adjacency matrix of the component is constructed in the following manner:

[0020] The names of the component and the second outfitting are stored in a one-dimensional data table as vertices of the initial weighted graph adjacency matrix of the component;

[0021] Based on the initial three-dimensional model of the component, the positional feature information of the second outfitting component is obtained, and the positional feature information of the second outfitting component is stored in a two-dimensional data table in the form of a structure, which serves as the weighted edge of the initial weighted graph adjacency matrix of the component.

[0022] Based on the vertices and weighted edges of the initial weighted graph adjacency matrix, the initial weighted graph adjacency matrix of the component is constructed.

[0023] In another embodiment of the present invention, after acquiring depth image information of the single component in the outfitting site, the method further includes:

[0024] Based on the acquired depth image information, image recognition technology is used to identify damage to the first outfitting component on the component, and the identification result is stored in the identification label of the corresponding outfitting component.

[0025] In one embodiment of the present invention, the method for obtaining the identification label information of the second outfitting component includes:

[0026] Identify the identification label of the component and obtain the identification label information of the component;

[0027] Based on the mapping relationship between components and outfitting parts, the identification tag information of several second outfitting parts corresponding to the component is obtained.

[0028] Correspondingly, the present invention provides an intelligent monitoring system for production management of pre-outfitting of ship components, characterized in that it includes:

[0029] The image acquisition and processing module has two functions: first, to acquire depth image information of the component and generate a three-dimensional reconstruction model of the component based on the depth image information; second, to identify damage to outfitting components based on the depth image information.

[0030] The identification label recognition module is used to identify the identification labels of components, obtain the label information of the components, and obtain the identification label information of several second outfitting parts corresponding to the components;

[0031] The actual weighted graph adjacency matrix construction module is used to construct the actual weighted graph adjacency matrix of the component based on the identification label information of the individual component, the identification label information of the corresponding outfitting component, and the three-dimensional reconstruction model of the component.

[0032] The production management module is used to calculate the completion progress and / or working hours of component pre-outfitting.

[0033] Correspondingly, the present invention provides an intelligent monitoring terminal for production management of pre-outfitting of ship components, characterized in that the terminal includes:

[0034] Memory, used to store computer programs;

[0035] A processor is configured to execute a computer program stored in the memory, so that the terminal performs the terminal-based intelligent monitoring method for production management as described in claims 1 to 7.

[0036] Correspondingly, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the intelligent monitoring method for production management as described above, applied to the terminal.

[0037] As described above, the intelligent monitoring method, system, and terminal for production management of pre-outfitting of ship components described in this application have the following beneficial effects:

[0038] By employing 3D reconstruction technology and using identification tags to record information on each process of components and outfitting parts during pre-outfitting, it is possible to not only monitor the pre-outfitting completion progress, working hours, and production quantities in real time, but also to obtain the assembly and damage status of outfitting parts in a timely manner by comparing them with the model. This avoids manual comparison and monitoring, realizing digital and intelligent management of ship component pre-outfitting production, greatly reducing manpower expenditure, and making the production management of ship component pre-outfitting simpler and more efficient. Attached Figure Description

[0039] Figure 1 The diagram shown is a flowchart illustrating an intelligent monitoring method for production management of pre-outfitting of ship components, as shown in one embodiment of this application.

[0040] Figure 2 The diagram shown is a flowchart illustrating a production management intelligent monitoring method for pre-outfitting of ship components, as shown in another embodiment of this application.

[0041] Figure 3 The diagram shown is a module schematic of an intelligent monitoring system for production management of pre-outfitting of ship components, as illustrated in an embodiment of this application.

[0042] Figure 4 The diagram shown is a structural schematic of an intelligent monitoring terminal for production management of pre-outfitting of ship components, as illustrated in an embodiment of this application.

[0043] Explanation of reference numerals in the attached figures

[0044] S1~S8 Step 300 Intelligent Monitoring System for Production Management

[0045] 301 Image Acquisition and Processing Module

[0046] 302 Label Recognition Module

[0047] 303 Actual Weighted Graph Adjacency Matrix Construction Module

[0048] 304 Overlap Rate Acquisition Module

[0049] 305 Completeness Acquisition Module

[0050] 306 Production Management Module

[0051] 400 Intelligent Monitoring Terminal for Production Management

[0052] 401 Memory

[0053] 402 processor Detailed Implementation

[0054] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0055] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0056] The following embodiments of this application provide a production management method, system, and terminal for pre-outfitting of ship components. By employing three-dimensional reconstruction technology and using identification tags to record the process information of components and outfitting parts during the pre-outfitting process, it is possible to not only monitor the pre-outfitting completion progress, working hours, and production quantity in real time, but also to obtain the assembly and damage status of outfitting parts in a timely manner by comparing the outfitting parts with the model, avoiding manual comparison and monitoring, and realizing digital and intelligent management of pre-outfitting production of ship components. This greatly reduces manpower expenditure and makes the production management of pre-outfitting of ship components simpler and more efficient.

[0057] Among them, components are segments composed of various ship parts;

[0058] Outfitting components are the parts of equipment and devices to be installed on the ship, excluding the main structure of the ship, such as anchors, masts, ladders, pipelines, and circuits on the ship.

[0059] Outfitting refers to the installation of devices, facilities, and equipment other than the ship's hull structure;

[0060] Prefabricated modular assembly refers to the installation of outfitting components on segments composed of ship hull parts.

[0061] like Figure 1 As shown, in this embodiment, the intelligent monitoring method for production management of pre-outfitting of ship components according to the present invention includes the following steps:

[0062] Step S1: Collect depth image information of a single component in the outfitting site. Based on the depth image information, use 3D reconstruction technology to generate the current 3D reconstruction model of the component. The 3D reconstruction model includes the 3D geometric data of the component, the 3D geometric data of the first outfitting component that has been pre-outfitted on the component, and the position feature information of the first outfitting component.

[0063] The positional feature information of the first outfitting component includes the positional relationship between the first outfitting component and the component, and the positional relationship between the first outfitting component and other first outfitting components that have completed pre-outfitting.

[0064] The outfitting area comprises sub-areas, each of which is a sub-area obtained after the outfitting area is pre-divided into gridded areas, and each sub-area has a corresponding area number; for example, the area number is numbered with numbers along the length direction and with uppercase English letters along the width direction, and the numbering format of each sub-area is as follows: A1, A2, A3, ..., B1, B2, B3, ..., F1, F2, ...;

[0065] Specifically, binocular stereo vision recognition technology is used for 3D reconstruction to obtain the 3D geometric data of the component and the 3D geometric data of each pre-outfitted first outfitting component on the component; based on the 3D geometric data of the component and the 3D geometric data of the pre-outfitted first outfitting components on the component, a 3D reconstruction model of the component is generated; more specifically, based on the parallax principle, imaging equipment is used to acquire two images of the component from different positions, and then the positional deviation between corresponding points in the two images is calculated according to the triangulation principle; finally, the positional deviation is used for 3D reconstruction to obtain the 3D geometric information of the component and generate a 3D reconstruction model of the component.

[0066] The system utilizes a binocular inverse projection transformation algorithm to obtain the positional feature information of the first outfitting component. More specifically, it uses inverse projection transformation to project the left and right images onto a reference plane; it performs difference calculation on the left and right inverse projection images to obtain a binocular inverse projection difference map; it performs binarization and morphological filtering on the difference map to highlight the target area and eliminate noise information; based on the processed difference map, it obtains the distance and direction between the component and the first outfitting component and the feature points of the outfitting site, and finally generates the positional feature information of the first outfitting component.

[0067] Step S2: Identify the identification label of the component and obtain the identification label information of the component; based on the identification label information of the component, obtain the identification label information of each second outfitting component to be installed in advance;

[0068] In one embodiment, step S2, when executed, includes:

[0069] Step S21: Identify the identification label of the component and obtain the identification label information of the component;

[0070] Step S22: Based on the mapping relationship between components and outfitting parts, obtain the identification tag information of several second outfitting parts corresponding to the component.

[0071] The identification label is a pre-constructed identifiable label attached to the corresponding component / outfitting, and the label information of the identification label includes the name and attribute information of the component / outfitting.

[0072] The component's attribute information includes: the component's size data and placement information; the component's placement information includes: the component's placement area information within the outfitting site; the placement area is a rectangular area composed of the sub-areas actually occupied by the component's projection within the outfitting site; the placement area information includes an area number; the area number is composed of the area number of the sub-area corresponding to the upper left corner and the area number of the sub-area corresponding to the lower right corner of the rectangular area;

[0073] Optionally, the attribute information of the component may further include: the time information of the component; the time information of the component includes: the transportation time of the component within the outfitting site;

[0074] The attribute information of the second outfitting component includes: the size data, placement information, and pre-set positional feature information of the second outfitting component; the placement information of the outfitting component includes: the placement area information of the outfitting component within the outfitting site and / or the placement position information of the outfitting component outside the outfitting site; the pre-set positional feature information of the second outfitting component includes: the pre-set positional relationship between the second outfitting component and the component, and the pre-set positional relationship between the second outfitting component and other second outfitting components.

[0075] Optionally, the attribute information of the second outfitting component may further include: the time information of the second outfitting component; the time information of the second outfitting component includes: the transportation time of the second outfitting component in the outfitting site, and the operation time of the second outfitting component during the pre-outfitting process;

[0076] Preferably, the identification tag is an RFID tag;

[0077] Step S3: Based on the identification label information of the second outfitting component and the preset verification conditions, verify the name and location feature information of the first outfitting component to obtain the first outfitting component whose name and location feature information are both verified accurately, and use it as a valid first outfitting component;

[0078] In one embodiment, the verification process in step S3 includes:

[0079] 1) Check whether the size data of the first outfitting component is consistent with the size data in the identification label information of the second outfitting component. If they are consistent, it is determined that the name of the first outfitting component is accurate. At the same time, the name of the second outfitting component is obtained and used as the name of the first outfitting component, that is, the name of the first outfitting component is determined.

[0080] 2) Verify whether the position feature information of the first outfitting component with the determined name is consistent with the preset position feature information in the identification label information of the second outfitting component. If they are consistent, the position feature of the first outfitting component is determined to be accurate, and the first outfitting component is regarded as a valid first outfitting component.

[0081] Step S4: Based on the name of the component and the name and position feature information of each valid first outfitting component, construct the actual weighted graph adjacency matrix of the component, and extract the number of weighted edges of the actual weighted graph adjacency matrix;

[0082] The number of weighted edges in the actual weighted graph adjacency matrix includes a first weighted edge number and a second weighted edge number; the first weighted edge number is the number of weighted edges between the first outfitting component and the component in the actual weighted graph adjacency matrix; the second weighted edge number is the number of weighted edges between the first outfitting component and other first outfitting components in the actual weighted graph adjacency matrix.

[0083] In one embodiment, the actual weighted graph adjacency matrix of the component is constructed in the following ways:

[0084] Step S41: Store the name of the component and the name of the effective first outfitting component in a one-dimensional data table as vertices of the actual weighted graph adjacency matrix of the component;

[0085] Step S42: Store the position feature information of the effective first outfitting component in a two-dimensional data table in the form of a structure, as the weighted edge of the actual weighted graph adjacency matrix of the component;

[0086] Step S43: Based on the vertices and weighted edges of the actual weighted graph adjacency matrix, construct the actual weighted graph adjacency matrix of the component;

[0087] Step S5: Obtain the initial 3D model of the component and the initial weighted graph adjacency matrix of the component;

[0088] The initial 3D model of the component is a pre-constructed 3D model of the component, used to show the 3D form of the component after pre-outfitting, including the size data of the component, the size data of the second outfitting component on the component, the positional relationship between the component and the second outfitting component on the component, and the positional relationship between each second outfitting component on the component;

[0089] The initial weighted graph adjacency matrix of the component is a weighted graph adjacency matrix pre-constructed based on the initial three-dimensional model of the component, which includes the weighted edges between the second outfitting component and the component, and the weighted edges between each of the second outfitting components;

[0090] In one embodiment, the initial weighted graph adjacency matrix of the component is constructed in the following manner:

[0091] Step S51: Store the names of the component and the second outfitting component in a one-dimensional data table as vertices of the initial weighted graph adjacency matrix of the component;

[0092] Step S52: Based on the initial three-dimensional model of the component, obtain the position feature information of the second outfitting component, and store the position feature information of the second outfitting component in the form of a structure in a two-dimensional data table as the weighted edge of the initial weighted graph adjacency matrix of the component;

[0093] Step S53: Based on the vertices and weighted edges of the initial weighted graph adjacency matrix, construct the initial weighted graph adjacency matrix of the component;

[0094] In one embodiment, the weighted graph adjacency matrix of the component is updated in real time based on the updated identification tag information of the component and the identification tag information of the second outfitting component.

[0095] Step S6: Based on the 3D reconstructed model and the initial 3D model, obtain the overlap degree of the 3D model; based on the actual weighted graph adjacency matrix of the component and the initial weighted graph adjacency matrix of the component, obtain the completeness of the weighted graph adjacency matrix; wherein, the overlap degree is the ratio of the volume of the 3D reconstructed model to the volume of the initial 3D model; the completeness is the ratio of the total number of weighted edges in the actual weighted graph adjacency matrix to the total number of weighted edges in the initial weighted graph adjacency matrix;

[0096] In one specific embodiment, the overlap degree of the three-dimensional model is calculated as follows:

[0097] Where C1 represents the overlap degree of the three-dimensional model; V c V represents the total volume of the component and the first outfitting piece in the three-dimensional reconstruction model; s The total volume of the initial three-dimensional model.

[0098] The overlap of the three-dimensional model takes into account the impact of outfitting components of different volumes on the component pre-outfitting process. Since in the actual production process, larger outfitting components take more time to pre-outfit than smaller ones, the completion progress calculation method of this application can more accurately show the changes in the component pre-outfitting completion progress of the components after the pre-outfitting of different outfitting components is completed. This allows managers to adjust the production plan based on the actual pre-outfitting progress and makes it easier for managers to control the engineering of ship production.

[0099] In one specific embodiment, the completeness of the weighted graph adjacency matrix is ​​calculated as follows:

[0100] Where C2 is the completeness of the adjacency matrix of the weighted graph; α1 is the weight of the number of first weighted edges in the actual weighted graph adjacency matrix; N sa α1 represents the number of first-weighted edges in the actual weighted graph's adjacency matrix; α2 represents the weight of the first-weighted edges in the actual weighted graph's adjacency matrix; N represents the number of first-weighted edges in the actual weighted graph's adjacency matrix. so N represents the number of second-weighted edges in the adjacency matrix of the actual weighted graph; t This represents the total number of weighted edges adjacent to the initial weighted graph.

[0101] The completeness of the weighted graph adjacency matrix considers not only whether each outfitting component is installed at its corresponding position on the component, but also whether the outfitting components meet their mutual positional requirements. It reflects not only the degree of outfitting component installation on the component, but also the accuracy of outfitting component installation on the component.

[0102] Preferably, considering that the outfitting component is installed on the component and has a higher degree of correlation with the component, α1 can be set to 0.85 and α2 to 0.15.

[0103] Step S7: Based on the overlap degree of the three-dimensional model and the completeness of the weighted graph adjacency matrix, obtain the completion progress of the component pre-outfitting of the component; the completion progress is the weighted sum of the overlap degree and the completeness.

[0104] In one specific embodiment, the completion progress of the component pre-outfitting of the single component is calculated as follows: C = ω1 × C1 + ω2 × C2;

[0105] Where C represents the completion progress of component pre-outfitting; ω1 represents the weight of the overlap of the 3D model in the completion progress of component pre-outfitting; C1 represents the overlap of the 3D model; ω2 represents the weight of the completeness of the weighted graph adjacency matrix in the completion progress of component pre-outfitting; and C2 represents the completeness of the weighted graph adjacency matrix.

[0106] Preferably, considering that in the actual production process, there is a higher requirement for each outfitting component to be installed in the pre-planned corresponding position, ω1 can be set to 0.2 and ω2 to 0.8.

[0107] In another embodiment of the present invention, after acquiring depth image information of the single component in the outfitting area, the method further includes:

[0108] Based on the acquired depth image information, image recognition technology is used to identify damage to the first outfitting component on the component; and the identification result is stored in the corresponding outfitting component's identification tag to realize the tracking and monitoring of the outfitting component's status; the damage identification is based on existing damage identification methods and is not limited here.

[0109] Please see Figure 2 The diagram shows a flowchart of another embodiment of the intelligent monitoring method for production management of pre-outfitting of ship components according to the present invention; as shown below. Figure 2 As shown, in this embodiment, when the method executes step S2, the identification label information of the component further includes: time information; the identification label information of the second outfitting component further includes: time information; after executing step S7, the intelligent monitoring method for production management of pre-outfitting of ship components further includes:

[0110] Step S8: Based on the identification label information of the component and the identification label information of the second outfitting component, obtain the time information of the component and the second outfitting component, and obtain the component pre-outfitting time information of the component based on the time information of the component and the second outfitting component.

[0111] In one specific embodiment, the calculation method for the time information of the component pre-outfitting is: T = T' + t1 + t'1 + ... + t n +t′ n ;

[0112] Where T represents the pre-outfitting time of the component at the current completion progress; T' represents the transportation time of the component within the outfitting site; t1, ..., t n These represent the time spent on pre-outfitting of outfitting components 1, ..., n, respectively, obtained from the time information in the identification tags of the outfitting components; t'1, ..., t' n These represent the transportation time of outfitting component 1, ..., outfitting component n within the outfitting site; n is the number of outfitting components that have completed pre-outfitting on the current component.

[0113] The intelligent monitoring method for production management of pre-outfitting of ship components provided in the above embodiments, by adopting three-dimensional reconstruction technology and using identification tags to record the process information of components and outfitting parts during the pre-outfitting process, can not only monitor the pre-outfitting completion progress, working hours, and production quantity of components in real time, but also obtain the assembly status and damage status of outfitting parts in a timely manner by comparing outfitting parts with the model, avoiding manual comparison and monitoring, realizing digital and intelligent management of pre-outfitting production of ship components, greatly reducing manpower expenditure, and making the production management of pre-outfitting of ship components simpler and more efficient.

[0114] like Figure 3 As shown, in this embodiment, the present invention provides an intelligent monitoring system for production management of pre-outfitting of ship components, comprising:

[0115] The image acquisition and processing module 301 has two functions: first, to acquire depth image information of the component and generate a three-dimensional reconstruction model of the component based on the depth image information; and second, to identify damage to outfitting components based on the depth image information.

[0116] The identification label recognition module 302 is used to identify the identification label of the component, obtain the label information of the component, and obtain the identification label information of a plurality of second outfitting parts corresponding to the component;

[0117] The actual weighted graph adjacency matrix construction module 303 is used to construct the actual weighted graph adjacency matrix of the component based on the identification label information of the individual component, the identification label information of the corresponding outfitting component, and the three-dimensional reconstruction model of the component.

[0118] The overlap degree acquisition module 304 is used to acquire the overlap degree of the three-dimensional model of the component based on the three-dimensional reconstruction model and the initial three-dimensional model; the overlap degree is the ratio of the volume of the three-dimensional reconstruction model to the volume of the initial three-dimensional model;

[0119] The completeness acquisition module 305 is used to acquire the completeness of the adjacency matrix of the component based on the actual weighted graph adjacency matrix and the initial weighted graph adjacency matrix of the component; the completeness is the ratio of the total number of weighted edges in the actual weighted graph adjacency matrix to the total number of weighted edges in the initial weighted graph adjacency matrix;

[0120] The production management module 306 is used to obtain the completion progress of the component pre-outfitting of the component based on the overlap and completeness; and / or to obtain the working time information of the component pre-outfitting based on the time information of the component and the second outfitting component.

[0121] like Figure 4 As shown, in this embodiment, the present invention provides an intelligent monitoring terminal for production management of pre-outfitting of ship components. The terminal 400 includes a memory 401 and a processor 402. The memory 401 is used to store computer programs; the processor 402 is used to execute the computer programs stored in the memory 401, so that the terminal 400 executes the refined distribution method for pre-outfitting of ship components according to any of the above embodiments of the present application. Since the specific implementation process of the refined distribution method for pre-outfitting of ship components has been described in detail in the above embodiments, it will not be repeated here.

[0122] The memory 401 includes various media that can store program code, such as ROM (Read Only Memory image), RAM (Random Access Memory), magnetic disk, USB flash drive, memory card or optical disk.

[0123] The processor 402 is connected to the memory 401 and is used to execute the computer program stored in the memory 401 so that the terminal 400 can execute the above-mentioned intelligent monitoring method for production management.

[0124] Preferably, the processor 402 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 gate or transistor logic devices, or discrete hardware components.

[0125] This application also provides a computer-readable storage medium. Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof. The storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state drive (SSD)).

[0126] This application embodiment may also provide a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application embodiment are generated. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0127] When the computer program product is executed by a computer, the computer performs the method described in the foregoing method embodiments. The computer program product can be a software installation package; when the foregoing method is required, the computer program product can be downloaded and executed on the computer.

[0128] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0129] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method of intelligent monitoring of production management of ship componentized pre-outfitting, characterized in that, The method comprises the following steps: Collecting depth image information of a single component in a fitting site, generating a current three-dimensional reconstruction model of the component by using a three-dimensional reconstruction technology based on the depth image information, wherein the three-dimensional reconstruction model comprises three-dimensional geometric data of the component, three-dimensional geometric data of a first fitting part that has been completed pre-fitting on the component, and position characteristic information of the first fitting part; Identifying an identification tag of the component, and obtaining identification tag information of the component; based on the identification tag information of the component, obtaining identification tag information of each second fitting part that is pre-set to be installed on the component; Based on the identification tag information of the second fitting part and a pre-set checking condition, checking the name and position characteristic information of the first fitting part to obtain the first fitting part whose name and position characteristic information are both accurately checked, as an effective first fitting part; Based on the name of the component and the name and position characteristic information of each effective first fitting part, constructing an actual power graph adjacency matrix of the component, and extracting the number of power edges of the actual power graph adjacency matrix; Obtaining an initial three-dimensional model of the component and an initial power graph adjacency matrix of the component; wherein the initial three-dimensional model of the component is a three-dimensional model of the component that is pre-constructed to show the three-dimensional shape of the component after pre-fitting; the initial power graph adjacency matrix of the component is a power graph adjacency matrix that is pre-constructed based on the initial three-dimensional model of the component, and comprises power edges between the second fitting part and the component, and power edges between each second fitting part; Based on the three-dimensional reconstruction model and the initial three-dimensional model, obtaining a coincidence degree of the three-dimensional model; based on the actual power graph adjacency matrix of the component and the initial power graph adjacency matrix of the component, obtaining a completeness degree of the power graph adjacency matrix; wherein the coincidence degree is a ratio of a volume of the three-dimensional reconstruction model to a volume of the initial three-dimensional model; the completeness degree is a ratio of a total number of power edges of the actual power graph adjacency matrix to a total number of power edges of the initial power graph adjacency matrix; According to the coincidence degree of the three-dimensional model and the completeness degree of the power graph adjacency matrix, obtaining a completion progress of componentized pre-fitting of the component; the completion progress is a weighted sum of the coincidence degree and the completeness degree.

2. The method of claim 1, wherein, When obtaining the identification tag information of the component and the second fitting part, the identification tag information of the component and the second fitting part further comprises time information; after obtaining the completion progress of componentized pre-fitting of the component, the method further comprises: Based on the identification tag information of the component and the identification tag information of the second fitting part, obtaining time information of the component and the second fitting part, and obtaining work hour information of the componentized pre-fitting of the component based on the time information of the component and the second fitting part.

3. The method of claim 1, wherein, The construction method of the actual power graph adjacency matrix of the component comprises: Storing the name of the component and the name of the effective first fitting part into a one-dimensional data table as vertices of the actual power graph adjacency matrix of the component; The position feature information of the effective first outfitting part is stored in a two-dimensional data table in a form of a structure body as a weighted edge of an actual weighted graph adjacency matrix of the part; An actual weighted graph adjacency matrix of the part is constructed based on the vertices and weighted edges of the actual weighted graph adjacency matrix.

4. The method of claim 1, wherein, The initial weighted graph adjacency matrix of the part is constructed in a manner comprising: The name of the part and the second outfitting part is stored in a one-dimensional data table as a vertex of the initial weighted graph adjacency matrix of the part; Position feature information of the second outfitting part is acquired based on the initial three-dimensional model of the part, and the position feature information of the second outfitting part is stored in a two-dimensional data table in a form of a structure body as a weighted edge of the initial weighted graph adjacency matrix of the part; An initial weighted graph adjacency matrix of the part is constructed based on the vertices and weighted edges of the initial weighted graph adjacency matrix.

5. The method of claim 1, wherein, After the depth image information of the single part is collected in the outfitting site, the method further comprises: Based on the collected depth image information, an image recognition technology is used to identify damage of the first outfitting part on the part, and the identification result is stored in the identification tag of the corresponding outfitting part.

6. The method of claim 1, wherein, The identification tag information of the second outfitting part is acquired in a manner comprising: An identification tag of the part is identified to acquire identification tag information of the part; Based on the mapping relationship between the part and the outfitting part, identification tag information of a plurality of second outfitting parts corresponding to the part is acquired.

7. A production management intelligent monitoring system for ship componentized pre-outfitting, characterized in that, The system comprises: An image collection and processing module is used to collect depth image information of a part, and generate a three-dimensional reconstruction model of the part based on the depth image information; and is used to identify damage of an outfitting part based on the depth image information; An identification tag identification module is used to identify an identification tag of a part, acquire identification tag information of the part, and acquire identification tag information of a plurality of second outfitting parts corresponding to the part; An actual weighted graph adjacency matrix construction module is used to construct an actual weighted graph adjacency matrix of the part based on the identification tag information of the single part, the identification tag information of the corresponding outfitting part, and the three-dimensional reconstruction model of the part; An overlap degree acquisition module is used to acquire a three-dimensional model overlap degree of the part based on the three-dimensional reconstruction model and the initial three-dimensional model of the part; the overlap degree is a ratio of a volume of the three-dimensional reconstruction model to a volume of the initial three-dimensional model; the initial three-dimensional model of the part is a three-dimensional model of the part constructed in advance, used to show a three-dimensional shape of the part after pre-outfitting; and the initial weighted graph adjacency matrix of the part is a weighted graph adjacency matrix constructed in advance based on the initial three-dimensional model of the part, containing weighted edges between the second outfitting part and the part, and weighted edges between the second outfitting parts; A completeness degree acquisition module is used to acquire an adjacency matrix completeness degree of the part based on the actual weighted graph adjacency matrix and the initial weighted graph adjacency matrix of the part; the completeness degree is a ratio of a total number of weighted edges of the actual weighted graph adjacency matrix to a total number of weighted edges of the initial weighted graph adjacency matrix. A production management module is configured to obtain a completion progress of the componentized pre-installation of the component based on the coincidence degree and the completeness degree.

8. The system of claim 7, wherein, The identification tag recognition module of the system is further configured to obtain time information of the component and the second installation part, and the production management module of the system is further configured to obtain work hour information of the componentized pre-installation of the component based on the time information of the component and the second installation part.

9. A production management intelligent monitoring terminal for ship componentization pre-outfitting, characterized in that, The terminal comprises: a memory for storing a computer program; a processor for executing the computer program stored in the memory, so that the terminal executes the terminal-based production management intelligent monitoring method in claims 1 to 6.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the production management intelligent monitoring terminal of the ship componentized pre-installation, and the method in claims 1 to 6 is implemented.

Images