Component attribute standardization method and device, medium and program product

Abstract

The invention provides a component attribute standardization method and device, a medium and a program product, the method is applied to a building information model, and the method comprises the following steps: S1, receiving the building information model and a predetermined standardization rule base related to the building information model; the building information model comprises a plurality of components, and each component comprises corresponding geometric data and corresponding engineering attributes; and S2, performing standardization processing on the building information model by using the standardization rule base to generate a standardized building information model. By means of the technical scheme, efficient prediction of the building information model component attributes can be achieved, and the efficiency and accuracy of data processing are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of metallurgical engineering, and in particular, to a method, device, medium and program product for standardizing component attributes. Background Art

[0002] Metallurgical engineering projects involve multiple professional fields, including structure, equipment, electricity, etc. Among them, each field uses specific design software in the design stage, which results in different data formats of the generated Building Information Modeling (BIM). It is difficult to efficiently integrate and utilize these data throughout the project life cycle, such as procurement, construction, operation and maintenance. Moreover, the building information model of metallurgical engineering projects usually contains tens of millions of components. Currently, it mainly relies on manual work to sort out and standardize these model data. This method is not only time-consuming and laborious with low efficiency, but also insufficient in ensuring data integrity and accuracy, and it is difficult to effectively identify and supplement missing data. Summary of the Invention

[0003] Embodiments of the present invention provide a method, device, medium and program product for standardizing component attributes to achieve efficient prediction of component attributes in a building information model, significantly improving the efficiency and accuracy of data processing.

[0004] To achieve the above object, on the one hand, a method for standardizing component attributes is provided. This method is applied to a building information model and includes:

[0005] S1, receiving a building information model and a predetermined standardization rule library related to the building information model; the building information model includes multiple components, and each component includes corresponding geometric data and corresponding engineering attributes;

[0006] S2, using the standardization rule library to perform standardization processing on the building information model to generate a standardized building information model, including:

[0007] Performing feature extraction on the geometric data and the engineering attributes through a predetermined parsing method to obtain a triangular facet representation of the geometric data and the engineering attributes in a predetermined text format;

[0008] Inputting the triangular facet representation and the engineering attributes in the predetermined text format into a pre-trained machine learning model to obtain standardized information of the component;

[0009] Comparing the standardized information with the rules in the standardization rule library. If there are conflicting rules, select a predetermined processing strategy according to the type of the conflicting rules to correct the standardized information, and then generate a standardized building information model in a predetermined format.

[0010] Preferably, in the method for standardizing component attributes, in step S1, the standardization rule library includes: design software source information, component type information, and component attribute requirements; where

[0011] the software source information includes: design software name, version number, and supported file formats;

[0012] the component type information includes: component classification code, component standard name, and component category description;

[0013] the component attribute requirements include: component attribute list, attribute specification requirements; the attribute specification requirements include: numerical range limit, unit specification requirements, and format specification requirements.

[0014] Preferably, in the method for standardizing component attributes, in step S2, using the standardization rule library to perform standardization processing on the building information model further includes:

[0015] Extracting the basic information of the building information model and storing the basic information in a preset database; where the file format of the building information model is determined in advance, and the basic information includes: the file name, type, file size, and creation date of the building information model.

[0016] Preferably, in the method for standardizing component attributes, in step S2, performing feature extraction on the geometric data and the engineering attributes through a predetermined parsing method to obtain the triangular facet representation of the geometric data and the engineering attributes in a predetermined text format includes:

[0017] Analyzing the overall shape of the component through the geometric data, identifying the characteristic structural parts and connection methods of the component, and obtaining the triangular facet representation of the geometric data;

[0018] Performing attribute feature extraction on the engineering attributes to obtain attribute features; and

[0019] Performing format conversion on the attribute features to obtain the engineering attributes in a predetermined text format;

[0020] The attribute features include: basic information, technical parameters, material information, and connection information between components, where the basic information includes: model and specification; the technical parameters include: pressure and temperature; the material information includes: valve body and seal; the connection information includes: connection type, size specifications corresponding to the connection type, and / or industrial standards corresponding to the connection type.

[0021] Preferably, in the method for standardizing component attributes, in step S2,

[0022] The types of the conflict rules include: attribute definition conflict, value range conflict, verification rule conflict, and processing logic conflict;

[0023] The predetermined processing strategies include: evaluating and processing according to the predetermined priority of the type, processing according to the predetermined general processing rules, and processing through manual confirmation.

[0024] Preferably, in the method for standardizing component attributes, in step S2, the training process of the machine learning model includes:

[0025] Collecting historical building information model data of historical projects, preprocessing the historical building information model data, and extracting features from the historical building information model data according to predetermined feature information to obtain sample data; wherein,

[0026] The preprocessing includes: unifying measurement units, standardizing value ranges, supplementing missing values, and encoding categorical data;

[0027] The feature extraction includes: extracting shape features and dimension features; wherein, the shape features include: valve body shape, driving method, connection type, and structural features; the dimension features include: nominal diameter, face-to-face dimension of components, structural height, and operating height;

[0028] Inputting the sample data into a pre-constructed machine learning model for training, and evaluating the training results until meeting the predetermined conditions.

[0029] Preferably, in the method for standardizing component attributes, after generating the standardized building information model, it further includes verifying the geometric data and attribute data of each component in the standardized building information model, wherein:

[0030] The verification of the geometric data includes: measuring the geometric data through point cloud sampling method and feature recognition method, and verifying the measurement data through tolerance zone analysis and real-time monitoring analysis;

[0031] The verification of the attribute data includes: performing integrity verification on the attribute data through predetermined attribute information.

[0032] On the other hand, an embodiment of the present invention provides an apparatus for standardizing component attributes, which includes a memory and a processor, the memory stores at least one segment of program, and the at least one segment of program is executed by the processor to implement the method for standardizing component attributes as described in any one of the above.

[0033] In another aspect, another embodiment of the present invention provides a computer-readable storage medium, wherein at least one program is stored in the storage medium, and the at least one program is executed by a processor to implement the method for standardizing component attributes as described in any one of the above.

[0034] In another aspect, another embodiment of the present invention provides a computer program product, including a computer program, wherein the computer program, when executed by a processor, implements the method for standardizing component attributes as described in any one of the above.

[0035] The above technical solutions have the following technical effects:

[0036] In the embodiment of the present invention, the received building information model is systematically standardized, features are extracted by a predetermined parsing method and converted into a unified format, and then the standardized information of components is predicted by a pre-trained machine learning model; the standardized information is compared with the standardized rule library, and for any conflicting rules found, appropriate processing strategies are selected according to their types for correction, and finally a building information model that meets the standards is generated, improving the accuracy and consistency of building information model data processing, realizing the automatic standardization processing of building information model component attributes, and greatly improving the efficiency and reliability of data management throughout the project life cycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a schematic flowchart of the method for standardizing component attributes according to an embodiment of the present invention;

[0038] Figure 2 is a schematic structural diagram of the device for standardizing component attributes according to another embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] To further illustrate the embodiments, the present invention provides drawings. These drawings are a part of the disclosure of the present invention, mainly used to illustrate the embodiments, and can be used to explain the operating principle of the embodiments in conjunction with the relevant descriptions in the specification. With reference to these contents, those of ordinary skill in the art should be able to understand other possible embodiments and the advantages of the present invention. The components in the drawings are not drawn to scale, and similar component symbols are usually used to represent similar components.

[0040] The present invention will be further described below in conjunction with the drawings and specific embodiments.

[0041] Embodiment 1:

[0042] To achieve efficient prediction of the attributes of building information model components and further improve the efficiency and accuracy of data processing, an embodiment of the present invention provides a method for standardizing component attributes. Figure 1Schematic diagram of the method for standardizing component attributes in an embodiment of the present invention. As Figure 1 shown, this method is applied to a building information model and includes:

[0043] S1. Receive a building information model and a predetermined standardization rule library related to the building information model; the building information model includes multiple components, where each component includes: corresponding geometric data and corresponding engineering attributes;

[0044] S2. Use the standardization rule library to perform standardization processing on the building information model to generate a standardized building information model, including:

[0045] Extract features from the geometric data and engineering attributes through a predetermined parsing method to obtain a triangular facet representation of the geometric data and engineering attributes in a predetermined text format;

[0046] Input the triangular facet representation and the engineering attributes in the predetermined text format into a pre-trained machine learning model to obtain the standardized information of the component;

[0047] Compare the standardized information with the rules in the standardization rule library. If there are conflicting rules, select a predetermined processing strategy according to the type of the conflicting rules to correct the standardized information, and then generate a standardized building information model in a predetermined format.

[0048] Embodiment 2:

[0049] The method of this embodiment of the present invention is applied to a building information model and includes:

[0050] 1. Receive a building information model and a predetermined standardization rule library related to the building information model; the building information model includes multiple components, where each component includes: corresponding geometric data and corresponding engineering attributes; in a specific implementation, the user uploads a BIM model, a standardization rule library, and corresponding data such as historical data through the provided corresponding interface;

[0051] Preferably, the standardization rule library includes: design software source information, component type information, and component attribute requirements; among them, the software source information includes: design software name such as OpenPlant, version number, and supported file format; the component type information includes: component classification code, component standard name, and component category description; the component attribute requirements include: component attribute list, attribute specification requirements; the component attribute list includes: required attributes, optional attributes, and professional attributes; the attribute specification requirements include: numerical range limit, unit specification requirements, and format specification requirements; for example, the rule for creating a check valve is as follows:

[0052] Software source: "OpenPlant Modeler V8i"

[0053] Component type: "CHECK_VALVE / Check Valve"

[0054] Attributes: Nominal diameter (15 - 1200 mm), pressure rating (PN16 / 25 / 40 / 63 / 100), connection type (flange / thread), material (WCB / WCC / LCB).

[0055] In a specific embodiment, the standardized rule library is version - controlled through a predefined rule management mechanism, which includes:

[0056] (1) Version number management, where the version number includes:

[0057] Major version number, used for major updates, including: changes in the standardized rule structure, changes in key attributes, and modifications to verification methods, etc.;

[0058] Minor version number, used for functional updates, including: adding optional attributes, expanding the usage scope, and optimizing processing logic, etc.;

[0059] Revision number, used for issue correction, including: fixing incorrect data, improving the description of standardized rules, and updating reference information;

[0060] (2) Change log: Records the content of each version number update, including: change time and personnel, specific modification content, change reason description, and impact scope assessment.

[0061] 2. Use the standardized rule library to standardize the building information model, generating a standardized building information model, including:

[0062] Extract features from geometric data and engineering attributes through a predefined parsing method to obtain a triangular facet representation of the geometric data and engineering attributes in a predefined text format;

[0063] Preferably, the predefined text format is JSON format;

[0064] In a specific embodiment, when the file source of the building information model is OpenPlant software, extract geometric data and engineering attributes through a DGN - specific parser, where the accuracy of the DGN - specific parser is 0.1 mm.

[0065] Preferably, extracting features from geometric data and engineering attributes through a predefined parsing method to obtain a triangular facet representation of the geometric data and engineering attributes in a predefined text format includes:

[0066] Analyze the overall shape of the component through geometric data, identify the characteristic structural parts and connection methods of the component, and obtain a triangular facet representation of the geometric data;

[0067] In a specific embodiment, analyzing the overall shape of a butterfly valve through geometric data includes: first identifying the main shape of components such as the valve body, then identifying secondary components such as the handwheel, and finally identifying connecting components such as flanges, and recording the relationships between components.

[0068] In a specific embodiment, feature extraction for the geometric data of a check valve includes:

[0069] (1) Main shape identification:

[0070] Identifying the valve body part, including: identifying a cylindrical main body with a measured outer diameter of 220 mm and a measured length of 440 mm for the cylindrical main body, and recording the axis direction;

[0071] Identifying the valve cover part, including: identifying a flange shape with a measured outer diameter of 260 mm and a measured thickness of 25 mm for the flange, and recording the installation position;

[0072] (2) Connection feature identification:

[0073] Identifying the inlet flange, including: identifying the flange surface, recording the bolt hole distribution, measuring the connection dimensions and determining the installation direction;

[0074] Identifying the outlet flange, including: determining that the parameters of the outlet flange are the same as those of the inlet flange, recording the relative position with respect to the inlet flange, determining symmetry and verifying parallelism.

[0075] In a specific embodiment, feature extraction for the geometric data of a butterfly valve includes:

[0076] (1) Main shape identification:

[0077] Identifying the valve body part, including: identifying a disc-shaped main body with a center thickness of 40 mm, an outer diameter of 380 mm, and a channel diameter of DN200;

[0078] Identifying the operating structure, including: identifying a handwheel with a handwheel diameter of 320 mm, a total height of 460 mm, an installation position of vertically upward, and an operating space requirement of a radius of 500 mm;

[0079] (2) Connection feature identification:

[0080] Inlet and outlet flanges, including: each flange has an outer diameter of 340 mm, a thickness of 22 mm, 8 - φ22 bolt holes, and a center distance of 295 mm.

[0081] Performing attribute feature extraction on engineering attributes to obtain attribute features; and,

[0082] Perform format conversion on the attribute features to obtain engineering attributes in a predetermined text format;

[0083] The attribute features include: basic information, technical parameters, material information, and connection information between components. Among them, the basic information includes: model and specification; the technical parameters include: pressure and temperature; the material information includes: valve body and seal; the connection information includes: connection type, size specifications corresponding to the connection type, and / or industrial standards corresponding to the connection type. Preferably, the connection type includes: flange; the industrial standard of the connection type includes: flange standard. For example, the format conversion of the butterfly valve attribute features is as follows:

[0084] Original data: Name: “Butterfly Valve 8”, Type: “Wafer Type”, Press: “150PSI”, Temp: “120F”;

[0085] Conversion result: Name: “D71X - 16 wafer - type butterfly valve”, Specification: “DN200”, Pressure rating: “PN16”, Operating temperature: “-10~120℃”.

[0086] In a specific embodiment, the feature extraction and format conversion for the attribute data of the check valve include:

[0087] (1) Original data collection:

[0088] Collect data from the design software, including:

[0089] Name: “Check Valve 8”;

[0090] Rating: “150#”;

[0091] Material: “Carbon Steel”;

[0092] Connection: “RF Flange”;

[0093] Collect data from the manufacturer, including:

[0094] Model: “H44H - 16”;

[0095] Nominal pressure: “1.6MPa”;

[0096] Material: “WCB”;

[0097] Connection form: “RF flange”;

[0098] (2) Feature extraction is performed on the collected original data to obtain basic information, technical parameters, and material information. Format conversion is carried out on the basic information, technical parameters, and material information, including:

[0099] After format conversion, the basic information is as follows:

[0100] Name: "H44H-16 Check Valve";

[0101] Specification: "DN200";

[0102] Pressure rating: "PN16";

[0103] Connection type: "RF flange";

[0104] After format conversion, the technical parameters are as follows:

[0105] Working pressure: "1.6MPa";

[0106] Working temperature: "-29~425°C";

[0107] Applicable medium: "Water, steam, oil products";

[0108] Flow direction: "One-way";

[0109] After format conversion, the material information is as follows:

[0110] Body material: "WCB";

[0111] Bonnet material: "WCB";

[0112] Disc material: "WCB";

[0113] Sealing material: "Stainless steel".

[0114] In a specific embodiment, feature extraction and format conversion for the attribute data of the butterfly valve include:

[0115] (1) Original data collection:

[0116] Collect data from the design software, including:

[0117] Name: "Butterfly Valve 8";

[0118] Type: "Wafer Type";

[0119] Press: "150PSI";

[0120] Temp: "120F";

[0121] Collect data from the manufacturer, including:

[0122] Model: "D71X-16";

[0123] Nominal diameter: "200";

[0124] Working pressure: "1.6 MPa";

[0125] Applicable temperature: "50 °C";

[0126] (2) Extract features from the collected original data to obtain basic information, technical parameters, and material information, and perform format conversion on the basic information, technical parameters, and material information, including:

[0127] After format conversion, the basic information is as follows:

[0128] Name: "Wafer type butterfly valve D71X-16";

[0129] Specification: "DN200";

[0130] Structure type: "Wafer type";

[0131] Driving method: "Manual";

[0132] After format conversion, the technical parameters are as follows:

[0133] Pressure rating: "PN16";

[0134] Working temperature: "-10 to 120 °C";

[0135] Working pressure: "1.6 MPa";

[0136] Applicable medium: "Water, oil products";

[0137] After format conversion, the material information is as follows:

[0138] Valve body: "WCB";

[0139] Valve plate: "2Cr13";

[0140] Valve seat: "EPDM";

[0141] Shaft: "2Cr13".

[0142] Input the triangular facet representation and engineering properties in a predetermined text format into a pre-trained machine learning model to obtain the standardized information of the component;

[0143] In a specific embodiment, the training process of the machine learning model includes: collecting historical building information model data of historical projects, preprocessing the historical building information model data, and extracting features from the historical building information model data according to predetermined feature information to obtain sample data; inputting the sample data into a pre-constructed machine learning model for training, and evaluating the training results until the predetermined conditions are met;

[0144] Among them, the preprocessing includes: unifying the measurement unit, standardizing the numerical range, supplementing missing values, and encoding categorical data; the feature extraction includes: extracting shape features and dimensional features; among them, the shape features include: valve body shape, drive mode, connection type, and structural features; the dimensional features include: nominal diameter, face-to-face dimension of components, structural height, and operating height.

[0145] Preferably, the machine learning model uses a recurrent neural network as the basic prediction model, uses word embedding technology to process the text features of the input text, and supports automated iterative training.

[0146] In a specific embodiment, the training process of the machine learning model with ball valve training data includes:

[0147] (1) Extracting features from the ball valve training data, including:

[0148] Extracting the shape features of the ball valve training data, for example:

[0149] Valve body shape: spherical;

[0150] Drive mode: handwheel;

[0151] Connection type: flange;

[0152] Structural feature: fixed ball;

[0153] Extracting the dimensional features of the ball valve training data, for example:

[0154] Nominal diameter: DN200;

[0155] Face-to-face dimension: 230 mm;

[0156] Structural height: 315 mm;

[0157] Operating height: 520 mm;

[0158] (2) Standardizing the data after feature extraction, including:

[0159] Standardizing the numerical features, for example:

[0160] Converting the dimension to mm;

[0161] The pressure is converted to MPa;

[0162] The weight is converted to kg;

[0163] The angle is converted to degrees;

[0164] Standardize the categorical value features, for example:

[0165] Unify the coding of material codes;

[0166] Standardize the connection form code;

[0167] Number the types of drive methods;

[0168] The code of the structured seal structure.

[0169] In a specific embodiment, a machine learning model is used to predict the component type to which the triangular facet representation and the engineering attributes in a predetermined text format belong, including:

[0170] (1) Perform feature analysis on the triangular facet representation to obtain the final matching result:

[0171] Identify the features in the triangular facet representation and perform matching to obtain the matching result. Determine the option with the highest matching degree in the matching result as the final matching result. Initially determine that the component is a butterfly valve. The matching results include: 95% matching degree with the butterfly valve features, 45% matching degree with the ball valve, and 30% matching degree with the gate valve; The identified features include: disc-shaped body, central axis penetration, handwheel drive, and wafer-type connection;

[0172] (2) Perform feature verification on the engineering attributes according to the final matching result to obtain the component type:

[0173] Verify the engineering attributes through the key parameters of the final matching result, including: the pressure rating meets the butterfly valve range, the material combination is a typical butterfly valve configuration, and the connection form is a standard wafer-type. Finally, confirm that the component type is a butterfly valve.

[0174] Compare the standardized information with the rules in the standardization rule library. If there are conflicting rules, select a predetermined processing strategy according to the type of the conflicting rules to correct the standardized information, and then generate a standardized building information model in a predetermined format.

[0175] Preferably, the predetermined format is IFC format or OBJ format.

[0176] Preferably, the types of conflicting rules include: attribute definition conflict, value range conflict, verification rule conflict, and processing logic conflict; The predetermined processing strategies include: evaluating and processing according to the predetermined priority of the type, processing according to the predetermined general processing rules, and processing through manual confirmation. For example, the rule conflict handling of the check valve includes:

[0177] (1) The rules for determining conflicts are: the first rule from the predetermined design standard and the second rule from the manufacturer's standard; among them, the first rule is: pressure rating: PN16 / 25 / 40, material requirement: WCB / WCC, connection form: flange connection; the second rule is: pressure rating: PN16 / 25 / 40 / 63, material requirement: WCB / LCB, connection form: flange / thread connection.

[0178] (2) Analyze the conflicting rules, including:

[0179] Pressure rating conflict: The second rule has an extra PN63;

[0180] Material requirement conflict: WCC and LCB are mutually exclusive;

[0181] Connection form conflict: Whether thread connection is allowed.

[0182] (3) Process the conflicting rules, including: pressure rating processing, material requirement processing and connection form processing. Among them, pressure rating processing includes: query the project requirements document to confirm that the maximum pressure of the project is PN40, and compare to determine the pressure range of the first rule; material requirement processing includes: check the project environmental conditions, and if there are corrosive media, select the material requirements of the first rule; connection form processing includes: analyze the installation and maintenance requirements and consider the convenience of maintenance, and determine to use flange connection.

[0183] (4) Determine the finally adopted rules, and record the processing basis and process. The finally adopted rules are:

[0184] Pressure rating: PN16 / 25 / 40;

[0185] Material requirement: WCB / WCC;

[0186] Connection form: flange connection.

[0187] In a specific embodiment, using a standardized rule library to standardize a building information model further includes:

[0188] Extract the basic information of the building information model and store the basic information in a preset database; among them, the file format of the building information model is predetermined, and the file format of the building information model is in the predetermined format list. The basic information includes: the file name, type, file size and creation date of the building information model.

[0189] In a specific embodiment, after generating the standardized building information model, it further includes verifying the geometric data, attribute data and weight of each component in the standardized building information model, where:

[0190] The verification of geometric data includes: measuring the geometric data through point cloud sampling method and feature recognition method, and verifying the measurement data through tolerance zone analysis and real-time monitoring analysis;

[0191] The verification of attribute data includes: performing integrity verification on the attribute data through predetermined attribute information;

[0192] Moreover, the verification of weight includes: verifying through the calculation of the material and volume of the component;

[0193] In a specific embodiment, the verification of the geometric data of the ball valve is as follows: sampling the surface of the ball valve through the point cloud sampling method, and then performing feature recognition on the sampling data to obtain the recognition result; wherein, the sampling settings of the point cloud sampling are: approximately 500,000 total sampling points, a basic grid of 0.1 mm, a feature edge line of 0.05 mm, and a curved surface area of 0.08 mm; the recognition result includes: 2 flange planes, a spherical valve body, a valve stem hole, and a sealing surface;

[0194] Performing dimensional measurement according to the recognition result, including automatically measuring the dimensions of the ball valve by fitting the flange plane, extracting the outer contour circle, and calculating the feature dimensions;

[0195] Verifying the measurement data through tolerance zone analysis and real-time monitoring analysis, including:

[0196] Verifying the measurement data through tolerance zone analysis includes: analyzing through a pre-established tolerance model, and the tolerance model is analyzed by setting a reference plane, creating a tolerance zone, defining measurement points, and calculating deviation values; for example, verifying the flange through tolerance zone analysis includes:

[0197] (1) Verifying the flatness of the flange, including:

[0198] Reference plane: flange sealing surface;

[0199] Tolerance zone: 0.1 mm;

[0200] Measurement points: 1000 points;

[0201] Maximum deviation: 0.08 mm;

[0202] (2) Verifying the coaxiality of the flange, including:

[0203] Reference axis: valve body center line;

[0204] Tolerance value: 0.2 mm;

[0205] Measurement circles: 4;

[0206] Maximum deviation: 0.15 mm;

[0207] The dynamic verification of measurement data through real-time monitoring and analysis includes: continuously collecting measurement data and calculating the deviation in real time, determining whether the deviation exceeds a predetermined threshold, and generating a warning message if the predetermined threshold is exceeded.

[0208] In a specific embodiment, the verification of the ball valve attributes includes:

[0209] (1) Basic attribute check:

[0210] Verify the integrity of the basic attributes. For example:

[0211] The basic attributes of the ball valve obtained include:

[0212] Model: Q41F-16C;

[0213] Specification: DN200;

[0214] Pressure rating: PN16;

[0215] Connection standard: HG20592;

[0216] Basic material: WCB;

[0217] Compare the above basic attributes of the ball valve with the predetermined attribute information, and determine that the missing items are: the execution standard number and the anti-corrosion grade, and prompt and suggest that the user supplement and improve the missing items;

[0218] (2) Professional attribute check:

[0219] Verify the integrity of the professional attributes. For example:

[0220] Operating temperature: -29~425°C;

[0221] Applicable medium: water, oil products;

[0222] Test pressure: 2.4MPa;

[0223] Operating mode: manual 90°;

[0224] Compare the above professional attributes of the ball valve with the predetermined attribute information, and determine that the missing items are: the packing model and the maintenance period, and prompt and suggest that the manufacturer provide the missing item information.

[0225] In a specific embodiment, the verification of the ball valve weight includes:

[0226] (1) Volume calculation:

[0227] Calculate the valve body part, including:

[0228] External shape volume: 3.85L;

[0229] Inner cavity volume: 1.2L;

[0230] Net volume: 2.65 L;

[0231] Machining allowance: 5%;

[0232] Perform calculations on the valve cover part, including:

[0233] Blank volume: 1.8 L;

[0234] Machining allowance: 8%;

[0235] Net volume: 1.66 L;

[0236] Bolt holes: 0.12 L;

[0237] (2) Weight calculation:

[0238] Perform calculations on the material density, including:

[0239] WCB: 7.85 kg / L;

[0240] Stainless steel: 7.93 kg / L;

[0241] Sealing ring: 1.6 kg / L;

[0242] Perform calculations on the weights of each component, including:

[0243] Valve body: 2.65 × 7.85 = 20.8 kg;

[0244] Valve cover: 1.66 × 7.85 = 13.0 kg;

[0245] Valve ball: 1.98 × 7.93 = 15.7 kg;

[0246] Other parts: 5.5 kg;

[0247] Total weight: 55.0 kg.

[0248] The specific numerical values in the embodiments of the present invention are only exemplary and are used to more clearly describe the use of the method of the embodiments of the present invention, and do not constitute a limitation on the present invention; according to specific design scenarios and specific components, other appropriate numerical values can be taken.

[0249] Preferably, when generating a standardized building information model, an attribute report and a verification report of the standardized building information model are synchronously generated. The attribute report contains the attribute data and corresponding attribute values of all components, and the verification report records the verification process and verification results of all components.

[0250] Further, it also includes the steps of receiving user feedback and optimizing the processing results to improve the accuracy and processing efficiency of the model. In one implementation, the system regularly analyzes user feedback, identifies common problems, optimizes and updates the corresponding models and rules, and retrains the machine learning model based on the feedback data to improve prediction accuracy. For example, when receiving the problem that the prediction of certain attributes by the user is inaccurate, record the feedback and analyze the relevant data, and find that the model performs poorly on a specific type of valve; subsequently, adjust the model parameters to improve the prediction accuracy of this type of valve.

[0251] Embodiment Three:

[0252] The present invention also provides a device for standardizing component attributes, such as Figure 2 shown. The device includes a processor 201, a memory 202, a bus 203, and a computer program stored in the memory 202 and executable on the processor 201. The processor 201 includes one or more processing cores. The memory 202 is connected to the processor 201 through the bus 203. The memory 202 is used to store program instructions. When the processor 201 executes the computer program, it implements the steps in the above method embodiment of Embodiment One of the present invention.

[0253] Further, as an executable solution, the device for standardizing component attributes may be a computer unit, and this computer unit may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer unit may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above composition structure of the computer unit is only an example of the computer unit, and does not constitute a limitation on the computer unit. It may include more or fewer components than the above, or combine some components, or different components. For example, the computer unit may further include input and output devices, network access devices, a bus, etc., and the embodiments of the present invention do not make limitations in this regard.

[0254] Further, as an executable solution, the so-called processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the computer unit, connecting various parts of the entire computer unit through various interfaces and lines.

[0255] The memory can be used to store the computer program and / or modules. The processor realizes various functions of the computer unit by running or executing the computer program and / or modules stored in the memory, and by calling the data stored in the memory. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store the operating system and application programs required for at least one function; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices.

[0256] Embodiment 4:

[0257] The present invention also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the method in the above embodiments of the present invention are implemented.

[0258] If the modules / units integrated in the computer unit are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0259] Embodiment Five:

[0260] The present invention also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the method as described above are implemented.

[0261] Although the present invention has been specifically shown and described in conjunction with the preferred embodiments, those skilled in the art should understand that various changes can be made to the present invention in form and details without departing from the spirit and scope of the present invention defined by the appended claims, and all of them are within the protection scope of the present invention.

Claims

1. A method for standardizing component attributes, applied to a building information model, characterized in that Including: S1, receiving a building information model and a predetermined standardized rule library related to the building information model; The building information model includes a plurality of components, wherein each component includes corresponding geometric data and corresponding engineering attributes; S2, performing a standardization process on the building information model using the standardized rule library to generate a standardized building information model, including: Performing feature extraction on the geometric data and the engineering attributes through a predetermined parsing method to obtain a triangular facet representation of the geometric data and engineering attributes in a predetermined text format; Inputting the triangular facet representation and the engineering attributes in the predetermined text format into a pre-trained machine learning model to obtain standardized information of the component; Comparing the standardized information with the rules in the standardized rule library, if there are conflicting rules, then selecting a predetermined processing strategy according to the type of the conflicting rules to correct the standardized information, and then generating a standardized building information model in a predetermined format.

2. The method for standardizing component attributes according to claim 1, characterized in that, In step S1, the standardized rule library includes: design software source information, component type information, and component attribute requirements; wherein, The software source information includes: design software name, version number, and supported file formats; The component type information includes: component classification code, component standard name, and component category description; The component attribute requirements include: component attribute list, attribute specification requirements; the attribute specification requirements include: numerical range limit, unit specification requirements, and format specification requirements.

3. The method for standardizing component attributes according to claim 1, characterized in that Performing the standardization process on the building information model using the standardized rule library in step S2 further includes: Extracting basic information of the building information model and storing the basic information in a preset database; wherein the file format of the building information model is predetermined in advance, and the basic information includes: file name, type, file size, and creation date of the building information model.

4. The method for standardizing component attributes according to claim 1, characterized in that, Performing feature extraction on the geometric data and the engineering attributes through a predetermined parsing method in step S2 to obtain a triangular facet representation of the geometric data and the engineering attributes in a predetermined text format includes: Analyzing the overall shape of the component through the geometric data, identifying the characteristic structural parts and connection methods of the component, and obtaining a triangular facet representation of the geometric data; Performing attribute feature extraction on the engineering attributes to obtain attribute features; and, Performing format conversion on the attribute features to obtain engineering attributes in a predetermined text format; The attribute features include: basic information, technical parameters, material information, and connection information between components, wherein the basic information includes: model and specification; the technical parameters include: pressure and temperature; the material information includes: valve body and seal; the connection information includes: connection type, size specifications corresponding to the connection type, and / or industrial standards corresponding to the connection type.

5. The method for standardizing component attributes according to claim 1, characterized in that, In step S2, The types of the conflicting rules include: attribute definition conflict, value range conflict, verification rule conflict, and processing logic conflict; The predetermined processing strategies include: evaluating and processing according to a predetermined priority of the type, processing according to a predetermined general processing rule, and processing through manual confirmation.

6. The method for standardizing component attributes according to claim 1, characterized in that, In step S2, the training process of the machine learning model includes: Collecting historical building information model data of historical projects, preprocessing the historical building information model data, and extracting features from the historical building information model data according to predetermined feature information to obtain sample data; wherein, The preprocessing includes: unifying measurement units, standardizing numerical ranges, supplementing missing values, and encoding categorical data; The feature extraction includes: extraction of shape features and dimension features; wherein, the shape features include: valve body shape, drive mode, connection type, and structural features; the dimension features include: nominal diameter, face-to-face dimension of components, structural height, and operating height; Inputting the sample data into a pre-constructed machine learning model for training, and evaluating the training results until they meet predetermined conditions.

7. The method for standardizing component attributes according to claim 1, characterized in that, After generating the standardized building information model, it further includes verifying the geometric data and attribute data of each component in the standardized building information model, wherein: The verification of the geometric data includes: measuring the geometric data through point cloud sampling methods and feature recognition methods, and verifying the measurement data through tolerance zone analysis and real-time monitoring analysis; The verification of the attribute data includes: performing integrity verification on the attribute data through predetermined attribute information.

8. An apparatus for standardizing component attributes, characterized in that It includes a memory and a processor, and the memory stores at least one segment of program, and the at least one segment of program is executed by the processor to implement the method for standardizing component attributes as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, At least one segment of program is stored in the storage medium, and the at least one segment of program is executed by the processor to implement the method for standardizing component attributes as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for standardizing component attributes as described in any one of claims 1 to 7.

Images