169 results about "Manufacturing data" patented technology

The invention discloses a block chain and digital twinborn integrated production whole process credible tracing method, and belongs to the technical field of intelligent manufacturing and digital tracing. The system comprises a digital twin construction module, a block chain evidence storage module, a tracing verification module and a data acquisition module. The method comprises the following steps: creating a digital twinborn body for each product instance, and mapping material, process, equipment and quality data of the whole manufacturing process in real time; recording the twinborn key state hash value to a block chain in real time through an intelligent contract; credible tracing verification is provided based on block chain evidence storage and digital twin data; industrial Internet of Things equipment is used for collecting manufacturing data in real time to drive twin updating. According to the method, millisecond-level slice tracing in the manufacturing process is realized, the deep description capability of digital twinning and credible guarantee of the block chain are fused, the problems of insufficient data depth and low credibility of a traditional tracing system are solved, and judicial-level evidence support is provided for quality disputes.

The invention relates to a manufacturing process quality tracing and root cause analysis system based on a data graph, and belongs to the technical field of manufacturing process quality control. The system performs cleaning, duplicate removal and standardization processing on multi-source heterogeneous data in the whole manufacturing process through a data processing module to generate structured data; the data graph construction module fuses the manufacturing domain knowledge ontology, constructs a manufacturing process digital twin semantic model and a multi-dimensional manufacturing data graph, introduces a dynamic association weight updating mechanism and mines node potential implicit association; the quality tracing module positions map nodes based on query semantic vectors, and reconstructs an entity state change track by using a digital twin semantic model to generate a tracing link; and the root cause analysis module screens candidate abnormal factors, locates a root cause in combination with dynamic weight and multi-scene simulation verification, and generates a quality optimization scheme. According to the invention, full-link accurate tracing and root cause efficient positioning of the manufacturing process quality are realized, and the intelligence and refinement level of manufacturing quality management and control is improved.

The invention relates to the technical field of knowledge maps, in particular to a steel manufacturing knowledge map construction method based on multi-source heterogeneous data, which comprises the following steps: converting message data into a standardized semantic triple through a semantic mapping rule, and complementing missing attributes by using physical and chemical component balance logic to form a standardized entity; meanwhile, a semantic processor is used for extracting unstructured report text logic, cross-modal coupling is carried out on the unstructured report text logic and SEM image features, and a failure mechanism enhanced entity is generated. Then, full-process dynamic parameters are collected and regularized into equal-interval time sequence parameters; and finally, taking the normalized entity as an index feature and the mechanism enhanced entity as an association constraint, executing semantic fusion by utilizing a topological feature mapping engine, and constructing a dynamic weight graph structure by combining with a dynamic probability distribution correction operator iteration parameter weight. According to the method, efficient association and semantic organization of manufacturing whole-process multi-modal data are realized, and the retrieval precision and knowledge discovery capability of steel manufacturing data are greatly improved.

A method of overhaul is provided. During this overhaul method, a substrate is scanned using structured light to provide substrate scan data. The substrate is from a component previously installed within an engine. The substrate scan data is compared to substrate reference data to provide additive manufacturing data. Material is deposited with the substrate using an additive manufacturing device based on the substrate scan data to provide a first object. The first object is scanned using the structured light to provide first object scan data. The first object scan data is compared to first object reference data to provide machining data. The first object is machined using the machining data.

The invention discloses a metro vehicle supervision manufacturing multi-station data traceability control system, and relates to the technical field of industrial data traceability, and the system comprises a data collection module which obtains the original manufacturing data of each station of metro vehicle manufacturing; the feature extraction module is used for processing the original manufacturing data and generating behavior fingerprint vectors and station features; the identity analysis module is used for carrying out feature matching calculation and outputting a candidate component identity set and matching similarity; the logic verification module is used for carrying out logic consistency verification and determining the identity of the target component; and the traceability control module establishes a mapping relation with the original manufacturing data based on the identity of the target component, generates a unique traceability node, and writes the traceability node into a multi-station traceability data chain. According to the method, the problems of identification failure, data link breakage and affiliation errors caused by station switching or equipment sharing are solved, supervision data continuity and identity recognition accuracy are improved, and reliable support is provided for vehicle full-life-cycle data tracing.

The invention discloses a sectional type wind power blade manufacturing method and system based on intelligent assembly control. The method comprises the steps of obtaining segmented component design data, and generating assembly path planning information based on a dynamic assembly optimization model; real-time monitoring is carried out through a multi-sensor fusion technology, and an intelligent assembly control instruction is generated; the assembly precision is verified in combination with a self-adaptive deformation compensation mechanism, and a blade assembly record is generated; and storing the record to a manufacturing data system and completing manufacturing. The deformation compensation mechanism optimizes pose deviation and interface stress based on finite element analysis and real-time data, and integrates gravity and temperature influence. The system comprises a data acquisition module, an instruction generation module, a precision verification module and a storage execution module. Millimeter-level precise butt joint and bonding quality control of the large-size blades are achieved, and the assembly efficiency and reliability are improved.

The invention discloses a processing defect detection method and system based on a semiconductor integrated circuit, and belongs to the technical field of semiconductor manufacturing data processing and defect detection, and the method comprises the steps: obtaining a high-resolution surface topography scanning matrix, an interlayer stress distribution matrix and a transient electrical response matrix of a specified process layer of a target wafer, and constructing an original feature tensor after correction; generating a multi-dimensional coupling feature matrix, and constructing a spatial adjacency topology network and a cross-layer coupling energy propagation graph model; performing energy iteration deduction on the basis of introducing a current density direction vector and a thermal diffusion coefficient parameter to obtain a potential energy gathering path; a microdefect risk coupling coefficient distribution diagram is generated through time sequence folding mapping and nonlinear coupling calculation, hidden defect characterization parameters are extracted through multi-scale feature compression and abnormal clustering analysis, and defect space positioning and process compensation parameter adjustment suggestion output are achieved; according to the invention, the subcritical microscale latent defect can be identified, and the detection sensitivity and reliability are improved.

The invention discloses an automobile part manufacturing process data processing method and system based on artificial intelligence, and relates to the technical field of data processing. The automobile part manufacturing process data processing method and system based on artificial intelligence comprises the steps of S1, collecting process record data and process characteristic data of automobile part manufacturing, preprocessing the process record data and the process characteristic data, and constructing a part manufacturing database; s2, fluctuation sensitivity judgment is carried out through the process characteristic data, and signal quality grading, enhancement parameter adjustment and noise suppression processing operation are executed according to the judgment result; s3, integrating the amplitude quantity and the information correlation quantity to construct a cross-channel causal coupling characterization quantity, and triggering the generation of a causal link; and S4, realizing aging state identification by fusing amplitude offset, an attenuation baseline and causal coupling features and combining offset grading analysis and link traceability processing. The problems of synchronous dislocation of multi-channel signals, insufficient perturbation detection precision, difficulty in causal chain reconstruction and difficulty in aging drift identification and tracking are solved.

The invention discloses a mechanical part cost decision support system and method driven by an industrial knowledge graph, and relates to the technical field of mechanical manufacturing cost decision, and the system comprises a multi-modal data collection module which collects multi-type data of the whole process of mechanical manufacturing and processes the multi-type data to form a unified set; the multi-modal knowledge graph construction module constructs a graph and establishes an updating mechanism; the intelligent reasoning decision module inputs new part parameters to screen an optimal scheme; the dynamic optimization adjustment module collects data in real time to update a result reversely; the decision result output module generates a visual report and supports multi-format export; according to the method, manufacturing data dispersion pain points are broken, multi-source data fusion precipitation and knowledge systematization are realized, and accurate support is provided for cost decision making; meanwhile, an optimal scheme is screened through multi-algorithm cooperation and multi-target evaluation, field data are collected in real time to dynamically optimize decisions, the crossing from static estimation to dynamic optimization is achieved, the core target is effectively balanced, and the economical efficiency and the stability are improved.

The invention provides a multidisciplinary collaborative design and engineering digitization platform for a motor system, which integrates natural language processing and large language model technologies, is connected with electrical, electromagnetic, thermal and control multidisciplinary simulation tools, realizes full-process collaborative optimization from demand input to manufacturing output, and improves the design efficiency. The platform converts a natural language into standardized parameters through an instruction analysis module, drives electrical modeling, electromagnetic simulation, thermal analysis and control algorithm design, automatically generates a two-dimensional / three-dimensional model and a corresponding processing technology file based on an optimization result, and further constructs a unified digital main line through an engineering data middle platform. Integrated management and closed-loop optimization of design, simulation and manufacturing data are achieved, meanwhile, a user can monitor a simulation result and manufacturing feasibility in real time through a graphical interface, the platform supports interdisciplinary collaborative iteration and parameter linkage closed-loop optimization, the design efficiency and manufacturing feasibility are remarkably improved, and the design cost is reduced. The method is suitable for digital and intelligent development of a motor system in the industrial and scientific research field.

The invention provides a multi-dimensional data fusion analysis method and system, and the method comprises the steps: collecting multi-source manufacturing information of a manufacturing execution system, carrying out the time sequence alignment of the multi-source manufacturing information through employing a production technology constraint, carrying out the attribute reduction of a multi-dimensional manufacturing data set obtained through alignment, and obtaining a core attribute set, and calculating the importance value of each manufacturing sub-task based on the core attribute set, and generating a task priority sequence. Based on the task priority sequence, candidate resources corresponding to the priority subtasks are extracted from the multi-dimensional manufacturing data set, and the multi-dimensional matching degree of the candidate resources is calculated. And performing weighted fusion on the multi-dimensional matching degree through historical execution data to obtain a resource matching matrix, and performing resource conflict resolution according to the resource matching matrix and the task constraint relationship to generate a resource allocation scheme. According to the method, accurate resource allocation is realized through time sequence alignment and multi-dimensional matching degree calculation, so that the resource utilization rate and the production scheduling efficiency are improved.

Methods, computer systems, and computer-readable memory media for determining a warp function. An as-designed watertight spline model of an object is received. A point cloud and the as-designed watertight spline model are used to construct a model of the object. The point cloud is obtained from a physical or virtual (simulated) inspection and / or manufacturing process. A warp function is determined based on a difference between the as-designed watertight spline model and the constructed model. The warp function is a continuous function quantifying differences between the as-designed model and the constructed model. As-preprocessed instructions for a simulation or analysis process of the object are determined based on metadata of the as-designed watertight spline model and the warp function. The simulation or analysis process is performed on the object according to the as-preprocessed instructions to produce as-simulated data, and the as-simulated data is stored in a non-transitory computer-readable memory medium.

A system and method for collecting real time manufacturing data from a factory having multiple machines therein using internet-of-things (IoT) connectivity, comprising: at least one gateway comprising at least one server, the at least one gateway receiving data from the multiple machines; at least one machine communications module (MCM) that applies to the received data at least factory, enterprise, and analytics applications, and which outputs command and control information from the applications to the at least one gateway to directly control operations of the multiple machines; wherein the gateway provides security isolation on the machine side of the gateway, and encryption, authentication, and authorization security on the MCM side of the gateway; and wherein the applications process and normalize data from at least a plurality of types and generations of the multiple machines.

To support a user in monitoring of manufacturing data.SOLUTION: A manufacturing data analysis device is provided with an acquisition unit, an analysis unit, and an output data generation unit. The acquisition unit acquires, from manufacturing data related to a plurality of products, in a first acquisition condition, first manufacturing data including a manufacturing condition data group including one or more pieces of manufacturing condition data related to values indicating manufacturing conditions for the products and a quality data group including one or more pieces of quality data related to values indicating quality of each of the products. The analysis unit analyzes the first manufacturing data to calculate a degree of influence of the first manufacturing condition data included in the manufacturing condition data group on the respective pieces of quality data included in the quality data group. The output data generation unit generates output data including details related to at least one of the first manufacturing condition data, one or more pieces of quality data provided, by the first manufacturing condition data, with the degree of influence satisfying a first determination condition, and the degree of influence satisfying the first determination condition.SELECTED DRAWING: Figure 1

The present disclosure presents systems and methods for creating and recording digital cyber-physical passports during a manufacturing process. One such system or method is adapted to supply manufacturing data for a particular physical part instance being manufactured by the manufacturing machine; track a progress of the manufactured part instance and store manufacturing data supplied by the one or more monitoring devices and / or the manufacturing machine in a data store; generate digital cyber-physical passports for each completed phase of manufacturing for the particular part instance, wherein the cyber-physical passport contains proof data associated with the physical part instance, wherein the proof data indicates a compliance status of the particular part instance with one or more tolerance requirements, structural requirements, functional requirements, manufacturing requirements, or compatibility requirements; and record individual cyber-physical passports on a cyber-physical passport-linked ledger on a distributed ledger technology platform during the manufacturing process of the part instance.

The invention discloses a method for complementing data in a cigarette manufacturing process based on a GAN (Germanic Analysis)-Transformer (Germanic Analysis-Transformer). The method comprises the following steps: acquiring multi-modal time sequence data in a cigarette manufacturing process, performing preliminary interpolation to obtain a multi-modal original tensor, and generating a missing mask at the same time; performing feature extraction on the multi-modal original tensor, and embedding process prior to obtain sparse perception unified representation; inputting the sparse perception unified representation and the missing mask into the generative adversarial network to obtain a preliminary completion sample; and inputting the preliminary completion sample and the multi-modal original tensor into a mixed Transform model in parallel for fine calibration, and obtaining a corrected completion sequence. Through cooperation of multi-modal deep fusion, physical knowledge embedding, uncertainty quantification and online reinforcement learning, the problem of data missing is solved, and data support is provided for a credible, reliable and evolvable cigarette manufacturing data intelligent maintenance system.

The invention provides a reactor core coolant flow failure probability calculation method and system and a readable medium, and relates to the technical field of reactors. The failure probability calculation method comprises the following steps: acquiring manufacturing standard deviation data of at least part of real fuel plates in a reactor core; obtaining average value data corresponding to at least part of real fuel plates; according to the manufacturing standard deviation data and the average value data, randomly generating simulated manufacturing data of the plurality of simulated fuel plates according to normal distribution; according to all the simulation manufacturing data corresponding to each simulation fuel assembly, simulation flow values of the simulation fuel assemblies are obtained through calculation, and according to all the simulation flow values, a distribution type and at least one target standard deviation are determined; and obtaining a flow acceptance limit value and a minimum flow value of the real fuel assembly, and calculating a failure probability value corresponding to the at least one target standard deviation according to the distribution type, the minimum flow value, the flow acceptance limit value and the at least one target standard deviation.

The present application relates to the technical field of die stamping manufacturing, and discloses a die stamping manufacturing cost intelligent prediction method. The method first acquires a multi-dimensional manufacturing data set composed of material characteristic parameters, process machining parameters and equipment operation parameters. Then, based on the material characteristic parameters, key process features are extracted, a process influence topology graph is generated according to the process machining parameters, and the equipment operation parameters are processed to obtain an equipment state evolution trend. Then, these data are input into a multi-factor evaluation model to generate a cost prediction requirement vector, and finally, a self-adaptive prediction strategy graph is constructed through a dynamic programming algorithm to output a manufacturing cost prediction scheme. The present application comprehensively considers multi-dimensional data, can effectively process data dynamic changes, improves the accuracy and reliability of die stamping manufacturing cost prediction, and helps enterprises to reasonably control costs, optimize production decisions and improve market competitiveness.

The invention relates to the technical field of manufacturing data processing, and discloses a production business data processing system for a discrete manufacturing workshop, which comprises an asynchronous data acquisition module for acquiring an asynchronous event pulse sequence of a discrete execution node; the mapping transformation module establishes an addressing mapping relation between an event source and a memory logic bit plane and generates an original differential bitmap; the bitmap filtering module is used for hedging paired logic flipping signals by utilizing an exclusive-OR logic self-reversal principle and filtering jitter interference at the edges of the signals so as to generate a net value difference bit plane; the state synchronization processing module performs in-situ upset updating on the state global bitmap through address offset addressing according to the bit identifier, and through a bitmap differential synchronization mechanism, asynchronous state updating without transaction lock constraint is achieved, calculation blocking generated by high-frequency pulse impact is relieved, and the real-time performance and stability of system data throughput are enhanced.

This invention relates to the field of finite element analysis technology, and provides a method for designing and constructing cast-in-place piles using a single-sided open-closed temporary casing based on finite element analysis. The method includes importing constitutive parameters of soft rheological silt into computer-aided engineering nonlinear finite element software to establish a spatial mesh model of the single-sided open-closed temporary casing with upper and lower reinforcing cylinder ends and a central standard cylinder; applying high-order friction penalty function contact constraints to the sliding pin, tension rod flange, and positive and negative labyrinth joints; sequentially loading three dynamic simulation conditions: pressing, holding, and large deformation during pull-out; outputting a solid manufacturing data table based on the simulation results of the three dynamic simulation conditions; constructing a closed-loop mud circulation system to maintain head balance; and achieving low-damage pull-out and demolding. This invention combines simulation-driven design, structural optimization, and refined construction control, significantly improving the reliability, efficiency, and pile quality of cast-in-place pile construction in soft rheological strata.

The present application provides a multi-modal deep learning network-based overlay mark asymmetry compensation method and apparatus. Manufacturing data of different modalities is acquired and then inputted into a multi-modal deep learning network for processing, so as to obtain a prediction error of overlay mark asymmetry, wherein the multi-modal deep learning network performs feature extraction on the manufacturing data of different modalities, performs feature fusion on vector features corresponding to different modalities, and associates and combines physical parameters of actual production in a manufacturing process with parameters observed by a device, so as to obtain the prediction error of overlay mark asymmetry, thereby compensating for an actual overlay mark in actual production. By introducing a multi-modal learning network, a variety of data features are fully mined and utilized, the generalization ability of a model is enhanced, and the intelligence of the device is realized by means of the machine learning technology, thereby providing an effective traceability and localization solution for process problems in wafer production.

This invention discloses a PCB characteristic impedance simulation optimization method and system based on 3D modeling, relating to the field of high-speed intelligent circuit technology. The method involves acquiring measured material parameters and process deviations of the PCB to generate twin parameter vectors; constructing a local 3D subdomain model; concatenating the local 3D subdomain model with the manufacturing twin dataset to obtain multi-dimensional physical feature vectors, which are then processed to obtain a sequence of key influencing factors; processing the key influencing factor sequence using an impedance prediction proxy model to obtain the time-domain reflection impedance curve and the corresponding coordinates of 3D spatial impedance abrupt change points; adjusting the coordinates of the 3D spatial impedance abrupt change points based on an impedance reshaping strategy to obtain optimal 3D compensation parameters; reconstructing the 3D simulation model using the optimal 3D compensation parameters to obtain updated PCB manufacturing data; and outputting impedance control parameters through a target verification rule engine to accurately locate the coordinates of impedance abrupt change points in 3D space, thereby improving design efficiency and quality.

The invention discloses an ultrahigh-voltage cable insulation detection method and an ultrahigh-voltage cable maintenance method, and relates to the technical field of crosslinked polyethylene cable manufacturing, and the method comprises the steps: carrying out the in-situ and non-contact terahertz time-domain spectrum three-dimensional full-field scanning of a produced cable, obtaining the time-domain waveform of each space point of a cable insulation layer in the cable, and carrying out the in-situ and non-contact terahertz time-domain spectrum three-dimensional full-field scanning; according to the method, the insulation microstructure is comprehensively perceived through non-destructive terahertz scanning, the manufacturing data and the molecular dynamics mechanism are combined, the crossing from microdefect positioning to long-term performance prediction is realized by using the mixed AI model, and the method has the advantages that the method is simple and convenient, and the cost is low. Therefore, after the production of the cable is completed, in-situ and quantitative evaluation and life prediction can be carried out on the insulation reliability of the cable, a closed loop for guiding process optimization is formed, and the fundamental transformation from passive inspection to active predictive quality control is finally realized.

The invention relates to the technical field of mechanical design automation, in particular to a parameterized three-dimensional modeling and engineering drawing automatic generation method for mechanical parts, which comprises the following steps that: a user inputs design parameters of the mechanical parts through a visual interface, the design parameters comprise basic dimension parameters, characteristic geometric parameters and engineering constraint parameters, and the basic dimension parameters, the characteristic geometric parameters and the engineering constraint parameters are input into the visual interface; all the parameters and the mutual dependency relationship are stored in a configuration data structure; and constructing a parameter dynamic constraint network. According to the method, parameter self-consistent and compliance verification is guaranteed through a parameter dynamic constraint network, complex feature modeling is achieved through a coordinate system rotation matrix, automatic labeling is completed in combination with geometric topology analysis, intelligent view planning and a parameterized template, and the method depends on a three-layer architecture platform. One-button type closed-loop automation from parameter input to model generation, interference diagnosis and drawing output is achieved, and the design and manufacturing data transmission bottleneck is broken through.

Embodiments of the present application disclose a card manufacturing data verification method and device and electronic equipment, which are used for effectively verifying card manufacturing data containing unknown data elements. The method comprises the following steps: obtaining a card manufacturing file to be verified, wherein the card manufacturing file to be verified contains multiple card manufacturing data, and one of the card manufacturing data contains at least one unknown data element; obtaining characteristic coefficients of data elements in the card manufacturing file to be verified; determining an element type corresponding to the characteristic coefficients of the data elements in the card manufacturing file to be verified based on a preset data characteristic information table, wherein the data characteristic information table contains a previously established corresponding relationship between the types of data elements and the characteristic coefficients of data elements; and verifying the data elements in the card manufacturing file to be verified based on a data verification algorithm corresponding to the element type of the data elements in the card manufacturing file to be verified.

The invention relates to a method for segment-by-segment parameter assignment to a component, comprising the steps of: a) reading a three-dimensional component dataset describing a geometry of a component, which describes the component by means of three-dimensional data of a surface of the component, into a computer; b) virtually segmenting the component dataset into multiple component portions, and assigning the segmented component portions to one type of at least two different component portion types by means of a computing model formed by machine learning; wherein by means of the computing model, c) a first parameter is assigned to a first component portion of the multiple component portions. The invention is characterized in that the assigning of the first parameter in step c) is a computer-assisted determination of a first wall thickness in the region of the first component portion from data of the component data set describing the first component portion.

The invention discloses a construction method, device and equipment of an assembly type steel structure building and a storage medium, and relates to the technical field of assembly type buildings. The method comprises the steps that in response to a construction instruction of a target building, construction information parameters of the target building are determined, and a reference steel structure design model matched with the target building is determined from a pre-stored structure design model library according to the construction information parameters; determining a target steel structure design model matched with the target building based on the reference steel structure design model; generating a building information model matched with the target building according to the target steel structure design model, generating component manufacturing data based on the building information model and the building information parameters, and converting the component manufacturing data into processing control data; and processing the structural material based on the processing control data to obtain prefabricated parts, and assembling the prefabricated parts on the construction site to obtain a target building. According to the scheme, the design efficiency, the material utilization rate and the construction precision can be improved.

This application provides a method for manufacturing a multi-zone integrated silicone orthodontic appliance, comprising: acquiring three-dimensional data of a user's jaw and constructing a three-dimensional digital model of the appliance based on the three-dimensional data of the user's jaw; obtaining anatomical location data of teeth and orthodontic biomechanical design data, and dividing the target appliance into functional zones with at least two different hardnesses based on the three-dimensional digital model of the appliance, and assigning a zone hardness value to each functional zone; performing mechanical simulation on the three-dimensional digital model of the appliance, analyzing the stress distribution information of each functional zone acting on the teeth and periodontal tissues under the zone hardness value configuration of the virtual appliance constructed by the three-dimensional digital model of the appliance, so as to optimize the three-dimensional digital model of the appliance based on the stress distribution information feedback; converting the manufacturing data output by the optimized stage three-dimensional digital model of the appliance into manufacturing instructions, and driving a printing device to manufacture the corresponding appliance mold or print the corresponding appliance according to the manufacturing instructions.

Computer-readable media, methods, and systems are disclosed for facilitating source to target translation and synchronization of production details for manufacturing of one or more production articles. A plurality of versioned technical design inputs in structured and unstructured formats is received. A plurality of translation inputs corresponding to one or more parameters associated with the plurality of versioned technical design inputs is received. A mapping of the plurality of versioned technical design inputs to a plurality of manufacturing data elements associated with one or more data models of a manufacturing system is automatically generated, based on the plurality of translation inputs. Finally, a plurality of manufacturing routings for implementing production of the one or more production articles is generated.

The invention provides an intelligent manufacturing data exception identification method and system based on artificial intelligence, and relates to the field of data processing. According to the method, multi-source signals of production, control and detection equipment are collected through an energy manifold sensing architecture, and a global signal flow is constructed; performing event triggering type observation through a space-time perception model to generate a local state sequence; identifying a cross-process coupling relationship through the coupling analysis model to form an interference spectrum set; the virtual manufacturing cognitive body is used for executing mimicry copying and generating an abnormal perception event flow; an abnormal path is backtracked by an energy propagation model to identify an energy leakage set; and finally, generating an energy narrative set containing causes, propagation and attenuation fragments through a semantic narrative model, and realizing intelligent identification and interpretation of manufacturing data anomalies. By implementing the technical scheme provided by the invention, the root cause and the propagation path of the abnormity can be effectively traced, and the intelligent manufacturing data abnormity identification effect is improved.