148 results about "Industrial data processing" patented technology

The invention relates to the technical field of automatic production control and industrial data processing, in particular to a PLC-based gypsum-based flame-retardant plate production line control system and method, and the system comprises a data collection module which collects sensor data in real time; the ideal state construction module is used for constructing a pure ideal state vector; the disturbance simulation module is used for generating a theoretical damaged state vector corresponding to a specific fault mode; the difference calculation module is used for generating real and theoretical deviation vectors; the coupling verification control module is used for calculating a similarity value between the actual deviation vector and the theoretical deviation vector; if the similarity value is larger than a preset judgment threshold value, it is judged that a real physical fault exists at present, and a PLC precise compensation instruction is generated and sent to a production line execution mechanism; otherwise, judging that non-physical noise exists at present, keeping the control parameters of the production line unchanged, and starting a dynamic filtering program; according to the method, the problem that physical faults and sensor clutters are difficult to distinguish in a high-noise environment is effectively solved, and missing report is avoided.

The invention relates to the technical field of industrial data processing, and discloses a copper foil production monitoring method and system based on data storage optimization, and the method comprises the following steps: carrying out the periodic aggregation of high-frequency data when a production process is in a steady state, and carrying out the calculation of a newly recognized production process event when the production process is monitored to deviate from the steady state. Whether causal association exists or not is judged by calculating the correlation between the new event and the current activity event in time and physical dimensions, and if the association exists, a chained event ID inheriting a precursor event identifier is generated for the new event; if the event is an independent event, a brand-new root event ID is generated, context data before the event occurs is extracted in a backtracking mode, and the generated event ID is marked on a data set in a unified mode in combination with real-time data during the event occurrence period for permanent storage. According to the method, the storage configuration is obviously optimized, and the efficiency of fault causal chain tracing is improved through the structured chain ID.

The invention discloses a new energy electricity price accurate prediction method and system based on virtual power plant aggregation regulation and control, and relates to the technical field of industrial data processing. The method comprises the steps: S1, carrying out the preprocessing of meteorological environment data, output equipment data and battery power grid operation data; s2, constructing a variation dynamics analysis and mutation depth discrimination mechanism based on the meteorological environment data, and entering an output prediction and optimization process and a scheduling load response process in a layered manner; s3, executing energy storage collaborative optimization scheduling and parameter correction according to a meteorological output regression prediction analysis result; and S4, performing electricity price time sequence multi-source driving analysis, and reconstructing an electricity price fluctuation response strategy. The problems that new energy output violently fluctuates within a minute level due to sudden weather change, and electricity price prediction lags due to the fact that an existing prediction model depends on too low weather data updating frequency and cannot capture the rapid change in time are solved.

The invention belongs to the technical field of industrial data processing, and provides an intelligent material matching method and system fusing multi-modal features and fuzzy matching, and the technical scheme is that data in obtained electronic component list data is analyzed, key characters in character strings are identified, and a constructed mapping table is called to carry out mapping replacement on the key characters, so that the matching accuracy of the electronic component list data is improved. Obtaining each field parameter of the mapped electronic component; performing matching based on the constructed manufacturer alias knowledge graph and the mapped manufacturer field parameters to obtain a manufacturer matching result; screening the mapped material number parameters to obtain a material number candidate set, performing semantic similarity calculation based on the material number candidate set and a constructed special word vector model in the field of electronic components, when the similarity is greater than a set threshold, performing accurate matching, otherwise, triggering fuzzy matching, calculating a service score according to a matching result, and obtaining a service result; and performing multi-objective optimization based on a service score result to obtain an optimal matching scheme. And the matching accuracy and the purchasing decision-making efficiency are obviously improved.

The invention relates to the technical field of industrial data processing and intelligent control, and discloses an iron ore concentrate grinding medium intelligent regulation and control method and system based on real-time data processing, and the system comprises a sensing layer, an edge calculation layer, a cloud intelligent layer and an execution layer; according to the method, multi-dimensional data are obtained in real time and processed through a professional data preprocessing process, complex process characteristics are condensed into three core indexes including a particle size distribution index, a chemical component index and an energy consumption process index, and fuzzy worker experience is converted into an accurate numerical index; a reinforcement learning algorithm is introduced to enable the system to autonomously learn an optimal control strategy, so that the system has advanced intelligence of prediction, learning and global optimization; millisecond-level real-time response of index grading and medium regulation and control is achieved through the edge computing unit, timeliness of control is ensured, depth computing and model training are carried out based on cloud capacity, and automation and closed loop of the whole process from data collection to instruction execution are ensured.

The invention relates to the technical field of industrial data processing, in particular to an intelligent safety accident early warning method and system based on risk assessment, and the method comprises the steps: obtaining a mining operation event, extracting response situations before and after the operation event, checking the response situations with a reference response template, and judging a disturbance response according to the deviation degree; a ventilation network model is constructed, and when it is detected that a monitoring point is abnormal, management traceability is carried out along a traversal upstream path in combination with an air volume distribution proportion; predicting the propagation trajectory of the abnormal gas along the wind flow path and the time of reaching a downstream node based on the ventilation network model, and obtaining spatial correlation analysis; analyzing the disturbance response and the spatial correlation, calculating a coupling risk increment, and outputting a comprehensive risk value; judging the critical degree grade of the comprehensive risk value time series data; and determining a scheduling level according to the combination of the comprehensive risk value level and the critical degree level, when the critical index indicates to evolve to a dangerous state, improving the scheduling level in advance, and generating a differentiated resource scheduling suggestion in combination with the propagation trajectory.

The invention relates to the technical field of plate processing production management and industrial data processing, in particular to a plate production order management system based on edge sealing drilling, which comprises an order data acquisition step: constructing a holographic data input layer, and acquiring a process data set and real-time performance process data; a performance benchmark construction step: establishing a dual reference system, generating an ideal performance time benchmark, and generating theoretical performance delay evaluation data in combination with a process complexity parameter; a performance difference analysis step: separating the noise and the signal, and respectively calculating an actual performance deviation and a theoretical performance deviation only containing a process complexity factor; an order state judgment step: analyzing the distribution mode similarity of the deviation, if the distribution mode similarity is higher than a threshold value, judging that compliance process delay exists and the delivery time is adjusted, and if the distribution mode similarity is lower than the threshold value, judging that abnormal performance risk exists and generating a management instruction; according to the method, confusion of processing endogenous complexity and exogenous abnormity is successfully stripped, and fine attribution oriented management is realized.

The invention discloses a streaming data compression and time sequence prediction integrated method for a geothermal monitoring platform, and relates to the technical field of industrial data processing. The method comprises the following steps of: 1, acquiring various original heterogeneous sensing protocol data from a plurality of wellheads and a plurality of layers of sensor arrays in real time on a wellhead gateway side of a geothermal monitoring platform; 2, calling a well layer wavelet domain self-adaptive compression encoder through a well site edge end processor, and performing real-time compression on the structured geothermal flow data; and 3, in a well site edge end processor, performing wavelet dynamic system coding on the multi-scale wavelet coefficient of the well layer wavelet domain compressed code stream, and outputting a temperature prediction sequence, a pressure prediction sequence and a flow velocity prediction sequence of multiple time steps in the future.

The invention belongs to the technical field of industrial data processing, and particularly relates to a production enterprise energy consumption data prediction method based on machine learning. The method comprises the following steps: deploying an Internet of Things sensor to collect power and equipment operation data, and after three-stage preprocessing of anomaly detection, deletion repair and normalization, constructing a layered feature extraction network which comprises a time sequence feature layer, an equipment association feature layer and a modal fusion layer; the two features are respectively used for capturing power consumption features and equipment collaborative consumption features and fusing the features to generate depth feature vectors; and constructing a dynamic integrated prediction model, training three types of base models including support vector machine regression and the like, screening the model entering an integrated pool by using JS divergence, and optimizing the weight through a genetic algorithm to obtain a final prediction result. The method can accurately capture the characteristics of energy consumption data, effectively improves the prediction precision, assists an enterprise in reasonably planning energy use, and reduces the cost.

The invention relates to the technical field of industrial data processing, in particular to a PDF drawing vector review method and system based on the creative technology, and the method comprises the steps: receiving a PDF drawing data stream through a creative security communication channel, and converting the PDF drawing data stream into a standardized graphic primitive containing a two-dimensional coordinate and engineering metadata through a sandbox security parser; and on the basis, a spatial semantic data structure integrating quadtree spatial indexes and semantic grouping information is constructed. According to the method, a dynamic performance benchmark test data model is also constructed; and during rendering, predicting and selecting an optimal rendering scheme capable of meeting preset target performance based on the model, efficiently generating an interactive graphic review interface by utilizing the data structure, and finally receiving and storing a user review instruction associated with the graphic object. By constructing the adaptive rendering model and fusing a data structure of space and semantic information, high-performance and safe vectorization interactive review of the PDF drawing in a credential environment is realized.

The invention belongs to the technical field of industrial data processing, and particularly relates to a PCB cutter motion control method and system based on machine vision. The method comprises the following steps: collecting multivariable sequence data of a cutter in a machining process, and carrying out normalization and first-order difference processing on the multivariable sequence data to obtain a stationary sequence; performing anomaly detection on the stationary sequence by using an improved local anomaly factor algorithm, and correcting detected abnormal points to obtain a corrected stationary sequence; predicting the corrected stationary sequence by using an ARIMA model to obtain a stationary deviation predicted value at the next moment; and reducing the stable deviation predicted value into an original deviation predicted value through a contrast operation, and calculating to obtain a cutter compensation amount in combination with a preset compensation rate and a safety margin so as to adjust the motion trail of the cutter. According to the scheme, the accuracy of anomaly detection is improved, more precise cutter motion control is realized, and the processing quality of a PCB (Printed Circuit Board) is improved.

The invention provides a digital main line processing method based on an industrial data atlas, a medium and a system, and belongs to the technical field of the industrial data atlas. Unified access of cross-system data is realized by constructing a multi-source data acquisition adapter, cleaning and standardization processing are performed on heterogeneous data, an integrated data set is constructed, and the data collection efficiency is improved. Data entities are abstracted as nodes, cross-system association relationships are abstracted as edges to construct an industrial data graph, a graph index optimization strategy and a hierarchical storage architecture are adopted to improve cross-system query performance, a graph adaptive evolution model is utilized to realize dynamic adjustment of a graph structure, and a cross-system deep association analysis function is realized through a graph traversal algorithm. And an access control and data security mechanism is established to complete system protection, so that the technical problem that the industrial data processing system is difficult to realize cross-system deep correlation analysis is solved.

The invention relates to the technical field of industrial data processing, and particularly discloses a fault prediction method for automobile motor production equipment based on machine learning, which comprises the following steps: synchronously acquiring vibration data of a main bearing and working condition data of a main shaft motor, and calculating a learning admission factor based on a deviation degree between the working condition data and a preset standard working condition; performing weighted gating on the basic drift learning rate of the dynamic baseline model by using the learning admission factor, and further updating a baseline mean value and a slow variation fluctuation rate; and calculating an instantaneous fluctuation ratio based on the instantaneous energy deviation of the vibration data and the updated baseline mean value, determining the ratio of the instantaneous fluctuation ratio to the slow fluctuation ratio as a working condition sudden change index, identifying the current working condition type and obtaining a corresponding adaptive threshold value, and when the working condition sudden change index exceeds the adaptive threshold value, judging that a fault is generated. According to the method, immunity to transient working conditions and sensitive detection to weak mutation in a steady state can be realized at the same time, and the accuracy and robustness of fault prediction are greatly improved.

The invention provides a vehicle body heterogeneous data alignment and vertical domain model fine tuning method, relates to the technical field of industrial data processing and vehicle artificial intelligence, and aims to solve the problem that the incubation period quality risk induced by complex physical causes is difficult to early warn in the prior art. The method comprises the following steps: acquiring a logic difference between an actual process sequence and a reference sequence as first data; responding to a specific event, synchronously acquiring a multi-modal physical signal, and calculating physical characteristics of the multi-modal physical signal as second data; fusing the first data and the second data through a preset causal association probability model to generate an indication signal representing the risk, such as a causal inertia index CII; and finally, according to whether the indication signal satisfies a dynamic risk condition, a differentiated linkage fine tuning instruction is generated. According to the method, dynamic and self-adaptive early warning of potential quality risks is realized through deep fusion of process logic and physical processes, and the refined management and control level of the manufacturing process is improved.

The invention relates to the technical field of industrial data processing and resource scheduling, and discloses a garment intelligent manufacturing process dynamic optimization management system based on a large model, comprising an unstructured load waveform semantic analysis module used for receiving a load demand data stream and analyzing to generate a discrete load pulse sequence, calculating a semantic cognitive entropy representing the certainty of the load request; the resource capacity space-time constraint dynamic reconstruction module is used for generating a capacity slack variable based on the semantic cognitive entropy and embedding the capacity slack variable into the resource network load distribution model as a hard physical safety margin parameter; according to the invention, a direct mapping channel from a probability semantic space to a physical resource space-time environment is established, so that the problem of resource allocation mismatch caused by unstructured load fluctuation is effectively solved; and the stability and the self-adaptive balancing capability of the production resource network in dealing with the high-uncertainty load are improved.

The invention discloses a spectral analysis-based PCB chemical preparation ratio intelligent adjustment method and system, and relates to the technical field of industrial data processing. The method comprises the following steps: monitoring a cleaning solution flowing through a PCB cleaning tank in real time to obtain continuous spectrum time sequence data; analyzing in real time to obtain a copper ion concentration value sequence and a corrosion inhibitor concentration value sequence, and calculating a copper ion concentration change rate and a corrosion inhibitor concentration change rate in real time; analyzing the real-time change trend of the copper ion concentration value and the corrosion inhibitor concentration value, and analyzing the real-time numerical relationship between the copper ion concentration change rate and the corrosion inhibitor concentration change rate; judging whether a harmful side reaction which mainly consumes the corrosion inhibitor occurs or not; and when the harmful side reaction is judged to occur, inputting the copper ion concentration change rate and the corrosion inhibitor concentration change rate into a pre-trained proportioning optimization model, and outputting to obtain an acid agent adjustment amount and a corrosion inhibitor adjustment amount. According to the invention, the precise, real-time and intelligent adjustment of the proportion of the PCB chemical agent is realized.

The present application belongs to the technical field of industrial data processing application, and particularly relates to a data management method based on industrial big data, comprising the following steps: S1, obtaining multi-source heterogeneous industrial data; S2, cleaning and converting the data obtained in S1; S3, auditing and improving the quality of the data according to the published data standard; S4, externally opening the audited and improved data in the form of API sharing and providing data application services. Using the method, the effectiveness, format consistency and applicability of the data can be ensured, and the audited and improved data can be fully utilized, thereby solving the problems of low data quality and difficult data utilization in the industrial field. In addition, the method can reduce the human waste caused by manual data quality checking.

The present application belongs to the technical field of industrial data processing, and particularly relates to a kind of equipment fault intelligent diagnosis method and system for forging production line, and the method comprises: collecting the current signal of sawing machine main shaft motor to extract effective cutting segment data sequence;Intercept the initial stable segment data of effective cutting segment, obtain refined data set by eliminating abnormal data points, and calculate the refined material benchmark and standard deviation of refined data set;Based on the refined material benchmark and standard deviation, a material cutting instability index for evaluating the inherent fluctuation characteristics of material cutting is constructed;Based on the refined material benchmark, standard deviation and material cutting instability index, an adaptive threshold is generated to realize the diagnosis of equipment failure.The present application can automatically adapt to the load benchmark and fluctuation characteristics of different materials, solves the false alarm and missed alarm problem of fixed threshold under multi-material working condition, and improves the accuracy and reliability of diagnosis.

This application relates to the field of industrial data processing and intelligent control technology, and discloses a method for dynamic modeling and prediction of industrial big data combined with digital twins. The method includes: acquiring operating status data, process execution data, control command records and prediction results, and constructing a sequence of control action events; segmenting the operating status data according to the sequence of control action events to form natural operating data segments and intervention operating data segments, extracting distribution characteristics, fluctuation characteristics and response characteristics, and generating a segmented behavioral feature set; calculating the control reflexive influence quantity and generating a reflexive drift marker, dividing the natural evolution dataset and the control feedback dataset, and predicting them separately; generating control risk constraint quantity, screening, delaying or limiting the control commands to be executed, and iteratively correcting the dataset according to the execution results; this method can distinguish between control feedback changes and natural evolution changes, reduce drift misjudgments, and suppress multi-round oscillations and parameter fluctuations.

The invention provides an electric spark discharge machining machine control method and system based on industrial data processing, and relates to the technical field of industrial data processing.The method comprises the steps that in the movement process of an electric spark machining machine, working conditions are captured, and high-frequency real-time sensing data flow is output; receiving a high-frequency real-time sensing data stream through a redundant dual-channel RS485 bus, and synchronously calling a processing position time sequence slice; isomorphic processing scene matching is carried out to obtain a historical control parameter sequence; outputting a multi-modal real-time working condition feature tensor; carrying out discharge parameter increment prediction, and outputting an updated pulse parameter adjustment vector; sending the parameters to a PLC (Programmable Logic Controller) to drive a discharge module of the processing machine to execute smooth parameter adjustment transition; and iteratively executing closed-loop prediction parameter adjustment. The technical problems that in the prior art, an electric spark machining machine often depends on manual adjustment and experience to select discharge parameters, so that the precision and consistency of the machining process are difficult to guarantee, the debugging period is long, and the production efficiency is low are solved.

The invention relates to the technical field of industrial data processing, in particular to a computer-aided transformer substation three-dimensional model data dynamic mapping method. Transformer substation monitoring data and model data after three-dimensional model mapping are obtained, and multi-dimensional monitoring can be achieved; however, if the three-dimensional model mapping is not timely and accurately refreshed, the virtual and actual physical states are deviated; therefore, in dynamic mapping, based on electric quantity fluctuation, control response data time sequence interval and multi-data source deviation joint analysis, a dynamic mapping distortion index is constructed, and the matching degree of a quantitative model and an actual state is quantified; in view of continuous existence of delay in operation of the transformer substation, determining a model error change index and representing an error change accumulation degree by analyzing an electrical quantity time sequence, a model data difference change rule and an alarm log change trend; and finally, dynamically adjusting the model mapping refresh frequency according to the two indexes, so that the refresh frequency adapts to a data state, and the balance of efficiency and precision is realized.

The invention relates to the field of industrial data processing, and particularly discloses an industrial data anomaly detection method and system.The industrial data anomaly detection method comprises the steps that firstly, an alarm event is responded to capture a real-time context snapshot representing a physical world state, and after preliminary vector retrieval is completed, a set of multi-dimensional fidelity scoring mechanism based on risk self-adaptive gating is introduced; the mechanism firstly evaluates the potential influence of knowledge, dynamically generates a situation sensitivity index and a collection threshold value on the basis of the potential influence of the knowledge, and then achieves strong override on low-situation consistency knowledge, especially high-risk knowledge through an indexed gating factor. Finally, only the verified knowledge set passing the strict verification is constructed into a high-fidelity cue word and input into a large language model, it is ensured that a generated diagnosis report is established on the basis of high-quality knowledge which is matched with the current working condition, reliable in source and subjected to risk adaptation evaluation, and safe, credible and traceable diagnosis is achieved.

The invention relates to the technical field of industrial data processing, in particular to a potato starch food material production standardized data management method, which comprises the following steps of: extracting a cleaning workshop, extracting an aggregation query field parameter, a data table identification parameter and a time range parameter in a workshop production scheduling board, and generating a query syntax tree hash abstract; in the invention, a network address of a bottom node controller of a drying workshop is transferred into a vertex label, a network layer medium access control address is combined to generate workshop virtual node distribution coordinates, a topological distance numerical value is used for screening and querying a forwarding path, and cross-workshop data transmission is converted into ordered delivery according to a distribution interval from disordered broadcasting. Compared with the prior art, the method has the advantages that the network jump path is clearer, the link conflict probability is reduced, higher directionality is achieved during batch major key cross-workshop extraction, and the method is suitable for scenes of frequent scheduling, cross-regional transfer and dense state switching in potato starch food material production.

The invention relates to a drainage basin flood collaborative prevention and control and emergency scheduling system based on rainfall forecast big data, and relates to the technical field of big data acquisition and preprocessing and industrial data processing. The technical means comprises the following steps: constructing a multi-source heterogeneous data fusion mechanism through an industrial data acquisition and preprocessing method; intelligent data cleaning and feature extraction are realized by adopting an artificial intelligence technology; and space-air-ground integrated monitoring data access is realized based on a sensor network protocol. The method has the technical effects that the problems of non-uniform industrial data standards and time-space alignment of multi-source data are solved, and the data preprocessing efficiency and quality are remarkably improved; through cooperation of big data intelligent processing and a sensor network, full-process optimization of industrial data from acquisition, processing to application is realized, and high-reliability data support is provided for intelligent decision making.

The application discloses an operation data intelligent measurement and analysis system and method for an industrial scene, relates to the technical field of industrial data processing and intelligent analysis, and comprises the following steps: in order to realize the operation data intelligent measurement and analysis of an industrial operation process, continuously collected data in the industrial operation process is recorded according to an original time scale, and the number of data changes is counted in each unit time to construct a time series. The application dynamically rearranges the time scale of a trend calculation interval by introducing the fluctuation frequency per unit time and combining the high-frequency fluctuation coverage time range, reconstructs the statistical rhythm around the starting time of the shift of the trend judgment, weakens the influence of short-time high-frequency disturbance on the trend fitting, improves the accuracy of the trend judgment on the basis of maintaining the integrity of the data, reduces the risk of false triggering of dispatching control, and guarantees the stability of the industrial operation rhythm.

The present application relates to the field of industrial data processing, and particularly relates to a human eye perceived multi-dimensional time sequence similarity evaluation method, system, device and medium, the method comprising: processing a real value sequence and a predicted value sequence to generate a mapping sequence pair; extracting waveform geometric features of the mapping sequence pair to obtain a global shape similarity; performing exponential mapping on a cumulative cost of a nonlinear regular path using fluctuation scales of the mapping sequence pair to obtain a time regularity similarity; extracting local extreme points in the mapping sequence pair as feature anchor points, and obtaining a feature matching score based on offset distances of the mutually matched feature anchor points; extracting statistical moment features and statistical distribution evolution components of the mapping sequence pair to obtain a global distribution similarity; and finally performing multi-dimensional feature fusion to obtain a comprehensive evaluation score. Thus, the present application reconstructs a multi-dimensional evaluation system when a professional observes time sequence data from four dimensions of macro profile, phase alignment, key events and distribution density.

This invention discloses a full-process monitoring and management system for chlor-alkali chemical production based on the Industrial Internet of Things (IIoT), specifically relating to the field of industrial data processing technology. It includes a data sensing and acquisition module, a raw salt intelligent proportioning and cost optimization module, a brine quality early warning and reagent dosing module, an electrolyzer intelligent optimization module, and a full-process collaborative management feedback module. The data sensing and acquisition module uses sensor technology to collect chlor-alkali production operating data in real time and performs preprocessing to obtain a standard dataset for full-process monitoring and management. Through the brine quality early warning and reagent dosing module and the electrolyzer intelligent optimization module, this invention achieves full-process collaborative management, enabling early transmission of upstream water quality fluctuations and reverse tracing of downstream voltage anomalies. This ensures the safe operation of the electrolyzer, reduces power consumption per ton of alkali, extends the service life of core equipment, reduces maintenance costs, and achieves the comprehensive goals of improving quality, reducing consumption, increasing production, and extending the lifespan of chlor-alkali production.

The invention relates to the technical field of industrial data processing, and discloses an industrial data processing method for preparing a modified PC material, which comprises the following steps: acquiring an image of the surface of a product, identifying whether black spots exist on the surface of the product, judging the cause of the black spots on the surface of the product, and taking corresponding remedial measures. According to the industrial data processing method for preparing the modified PC material, black spot generation reasons are comprehensively and systematically analyzed, black spot distribution characteristics and potential reasons can be accurately positioned through image processing and statistical analysis, the accuracy of problem diagnosis is improved, a specific solution and improvement measures are provided, and the industrial data processing method is suitable for popularization and application. The method can be directly applied to quality control in the production process, helps enterprises and operators to quickly respond and solve quality problems, and helps to find potential problems in advance, take preventive measures, reduce defective products and improve production efficiency and product quality through comprehensive evaluation of raw materials, equipment and processes.

The invention discloses an MES data verification method and system, and relates to the technical field of industrial data processing, and the method comprises the steps: data collection and preprocessing: collecting multi-source MES original data of production equipment, a sensor, an ERP system and manual input through a multi-interface adaptation unit, performing format standardization, redundant data elimination and missing value preliminary marking processing on the original data to obtain preprocessed data; multi-dimensional comprehensive verification is realized: through verification operation of four dimensions of integrity, accuracy, consistency and safety, the whole process quality hidden danger of MES data from collection to storage is covered, and the problem of incomplete verification coverage in the prior art is solved; a real-time data acquisition and parallel verification mechanism is adopted, so that data exception can be found in time; and in combination with technologies of a machine learning prediction model, hash value comparison and the like, the accuracy of data verification and the abnormal positioning capability are improved.

This invention relates to the field of industrial data processing technology, specifically to a real-time location and tracking system for carbon sources in industrial parks that integrates physical constraints. The system includes acquiring 3D point clouds of buildings using lidar and boundary wind speed vectors using a micro-weather station array; constructing an unstructured no-slip boundary based on the building 3D point cloud and establishing a carbon emission convection-diffusion equation; acquiring discrete spatiotemporal sampling coordinates within the unstructured no-slip boundary and inputting them into a physical information neural network to generate a predicted gas concentration field; calculating observation errors and physical residuals to generate a joint loss function; setting the coordinate parameters and source strength parameters of the carbon emission sources to be inverted as trainable variables, updating them through backpropagation using an automatic differentiation algorithm, and outputting the updated coordinate parameters and source strength parameters. This invention provides physical parameter support for the refined supervision of emission facilities by constructing an integrated monitoring system that deeply couples micro-environment perception, physical mechanism constraints, and deep learning inversion.