2789 results about "Physical model" patented technology

The invention relates to the technical field of state detection and fault diagnosis, in particular to an intelligent early warning and fault diagnosis system for a thermal power plant, which comprises a multi-source data acquisition module for acquiring data in real time; the edge computing node is used for performing noise filtering and abnormal value correction on the acquired data; the digital twin modeling unit is used for constructing a dynamic simulation model of the equipment based on a physical model and historical data; the hybrid analysis engine is used for positioning early abnormal detection and fault sources; the visual early warning interface is used for dynamically displaying the health state and the fault probability of the equipment and generating a graded alarm signal; according to the invention, the multi-source data acquisition module acquires equipment multi-dimensional signals in real time, after edge computing node filtering and denoising, a digital twin modeling unit constructs a precise simulation model, a hybrid analysis engine fuses LSTM and a Bayesian algorithm, fault features are deeply mined, data weights are optimized, and the fault detection accuracy is improved. According to the system, the accuracy and timeliness of diagnosis are remarkably improved.

The invention belongs to the technical field of tunnel construction geological disaster prevention and control, and discloses a multi-source data fused refined treatment decision-making method for a complex stratum disaster source, which comprises the following steps: collecting and fusing multi-source geological data, and constructing a three-dimensional geological model; generating a disaster source risk dynamic assessment and treatment scheme; based on a fluid-solid coupling similarity theory, verifying the preliminary treatment scheme by adopting a physical model test, and determining an optimal treatment scheme; the optimal treatment scheme is executed, and the treatment process is dynamically regulated and controlled; after treatment, the treatment effect is evaluated through posterior data, and the effect data is fed back to the three-dimensional geologic model and the knowledge base, so that the dynamic updating of the model and the self-learning of the decision-making system are realized. By the adoption of the treatment decision method, the problems that a traditional method depends on experience, information is one-sided, and treatment is extensive are solved, advanced accurate forecasting and refined and personalized treatment of complex stratum disaster sources are achieved, and the safety and efficiency of tunnel construction are remarkably improved.

The present disclosure discloses a seismic inversion method based on joint constraint of a physical model and priori information. The method includes: extracting seismic wavelets based on seismic data, and determining an amplitude scaling factor of the wavelets; counting priori information of impedance parameters; establishing an initial impedance parameter model by using seismic structural interpretation information and logging data; obtaining a simplified approximate equation based on an interface weak elasticity difference hypothesis, forward modeling a seismic gather by using the simplified equation, and calculating an inversion residual; rewriting an objective function into a function related to the impedance parameters by using a generalized linear inversion idea, solving the impedance parameters by using an iterative reweighted least squares algorithm, and updating the impedance parameters; and repeating the above steps until the inversion residual reaches the requirements or reaches the maximum number of iterations, and outputting a final processing result.

The invention discloses a bus duct full life cycle health management system based on digital twinning, and relates to the technical field of health management. The multi-source sensor collects operation parameters and static information, the digital twin modeling and mapping module constructs a physical model and associates real-time data, and a thermal-electric coupling equation is used for simulating temperature; the state monitoring and fault diagnosis module compares data to judge states and diagnoses faults by means of methods such as a fault tree, the health assessment and decision making module constructs an index system to assess health and makes a maintenance decision, the data management and interaction module stores data and realizes visual interaction and system integration, and the intelligent optimization module performs intelligent optimization based on operation and maintenance data. And optimizing model parameters and a decision strategy. According to the invention, intelligent health management of the bus duct is realized, multi-source data acquisition is accurate and comprehensive, fault diagnosis is more accurate and prediction is more timely through combination of digital twinning and an algorithm, and intelligent assessment assists scientific maintenance decision; and the operation and maintenance efficiency and the power transmission stability are improved through system integration and edge calculation.

A physical AI-based magnetic field environment modeling method and a physical AI-based magnetic field environment modeling system are disclosed, the physical AI-based magnetic field environment modeling system comprises a data layer, a preprocessing layer, a core modeling layer and a verification and application layer, and the core modeling layer comprises a physical knowledge base and stores physical laws, material constitutive relationships and boundary conditions related to a target magnetic field environment; the model construction module is responsible for designing and constructing a main body structure of a physical AI model according to problem characteristics and a physical knowledge base; the physical AI engine represents a constructed or trained physical AI model instance, receives input and quickly outputs a predicted magnetic field value; and the model training module is responsible for training the neural network model generated by the model building module by using the preprocessed data and physical constraints in the physical knowledge base. The core innovation point of the invention lies in that a physical artificial intelligence normal form is systematically introduced and applied to the modeling process of a complex magnetic field environment, and an efficient, accurate, robust and physically consistent magnetic field modeling system is created through deep fusion of physical laws and data driven learning.

The invention discloses a bridge management and maintenance decision-making system and method based on multi-agent collaborative optimization, and the system comprises a monitoring agent which is deployed in a cloud server and is used for obtaining abnormal data in a bridge structure and environment data; the diagnosis agent is used for evaluating the health state of the bridge by utilizing a built-in knowledge base, a built-in machine learning model and a built-in physical model based on the abnormal data; the decision-making agent is used for generating a plurality of candidate maintenance schemes based on an evaluation result, and screening out an optimal scheme by integrating the comprehensive utility of each scheme and the resource matching degree score of the resource scheduling agent on each scheme; the resource scheduling agent generates a construction plan according to the optimal scheme; the coordination / communication agent is used for ensuring efficient cooperation among the agents through a communication protocol and a negotiation mechanism among the agents; the diagnosis report, the optimal scheme and the construction plan are integrated and presented to a bridge manager through a human-computer interaction interface; and collaborative optimization of bridge management and maintenance decisions is realized through continuous feedback and self-learning.

The invention discloses a radar lifting control method and system based on meteorological monitoring, and relates to the technical field of radar lifting control, and the method comprises the steps: completing the switching of a power supply and communication after a radar is powered on, initializing a controller, collecting the data of a meteorological station, and generating a future fusion wind speed in real time through a Kalman filtering physical model and a residual neural network; future fused wind speed is converted into wind pressure for evaluation, the risk degree is judged according to the evaluation result, early warning is given out, and the controller is preheated to enter a lifting preparation state. The input stability is improved through meteorological data sliding window smoothing and feature extraction, wind speed dynamic prediction and uncertainty quantification are achieved through XGBoost prediction and residual variance estimation, the time sequence consistency and robustness are enhanced through remote API interpolation correction and adaptive extended Kalman filtering, residual correction is conducted through a neural network, the prediction precision is improved, and the prediction accuracy is improved. And a reliable decision basis is provided for radar lifting control.

The invention discloses a flood disaster monitoring and early warning system and a flood disaster monitoring and early warning method. A cloud, rain, water and I integrated sensing network is constructed through a full-chain monitoring capability; a hybrid prediction model coupled with HEC-HMS and SWMM physical models and an LSTM-Transformer deep learning architecture is established, parameter deviation is dynamically corrected through NSGA-II and a symbolic regression multi-objective optimization algorithm, the flood prediction period is prolonged to 10 days (the precision of the southern watershed is larger than or equal to 90%, and the precision of the northern watershed is larger than or equal to 70%), the flood peak time error is compressed to be within 30 minutes, and compared with a scheme based on a static flood risk model, the method has the advantage that the flood prediction efficiency is greatly improved. The false alarm rate is reduced from 20% to 5% through the dynamic threshold calibration technology; hierarchical response and survivability communication are adopted, Beidou satellite and NB-IoT dual-channel redundant transmission is deployed, and a Mesh ad hoc network and frequency modulation subcarrier technology are combined, so that the direct rate of early warning information in extreme weather is ensured to be greater than or equal to 99%; and three-dimensional GIS platform dynamic rendering is supported, and collaborative visualization of a submerging thermodynamic diagram, a material scheduling path and ecological flow monitoring is realized.

The invention provides a wind power plant unit state monitoring and fault early warning system and method based on deep learning, and belongs to the field of wind power generation and artificial intelligence. According to the system, a cloud edge collaborative architecture is adopted, an edge computing terminal operates a data-driven space-time prediction model and a physical digital twinborn model in parallel, and abnormity is preliminarily screened by calculating a double-track residual error and comparing the double-track residual error with a dynamic early warning threshold value. And when an exception occurs, the cloud platform receives multi-modal data including a sensor, a model state and an operation and maintenance text, performs deep root cause analysis by using a diagnosis model fused with a wind power fault knowledge graph, and generates an interpretable diagnosis report. According to the method, deep fusion of data and a physical model is realized, and the accuracy of fault monitoring, the interpretability of diagnosis and the intelligent level of operation and maintenance decision are remarkably improved through a data-physical double-track driving mode.

The invention relates to a small sample fault prediction method based on physical information guidance and multi-source adaptive fusion. The method comprises the following steps: collecting real operation data of preprocessing target equipment; according to the physical model or domain knowledge of the target equipment, generating simulation sensor data conforming to a physical rule under various fault modes of different degrees; constructing diversified training samples in combination with real data and simulation data; for different types of sensor data, designing corresponding feature extraction branches, mining potential fault features in the data, and dynamically adjusting the weight of each data source fault feature for fusion based on an output result of a physical model and data-driven feature correlation analysis; inputting the obtained fusion features into a fault prediction model based on a small sample learning framework for training; comprehensively considering the fault prediction result, the real operation data and the analysis result of the physical model, and carrying out quantitative evaluation on the overall health state of the target equipment; and causal diagnosis and visual interpretation are carried out.

The invention discloses a carbon fiber composite material surface modification spraying system and a control method thereof. The system comprises a multi-axis robot, a plasma spray gun, a contact angle measuring probe, a 3D line laser scanner, a hyperspectral imager, an environment sensor and a controller. According to the method, the plasma power and the robot speed are adjusted in real time through contact angle measurement and plasma treatment feedback control, so that the CFRP surface can accurately reach a target value, and the coating adhesive force is improved; 3D line laser scanning and hyperspectral imaging are combined, and the posture, the distance, the wet film thickness and the component uniformity of the spray gun are monitored in real time; based on a prediction model fusing a physical model and a neural network, a self-adaptive fuzzy PID control algorithm is adopted, and the coating flow and the track posture of a spray gun are accurately regulated and controlled in real time. The problems of weak coating binding force, uneven thickness, orange peel, sagging and serious coating waste in traditional spraying are effectively solved, and self-adaptive, high-quality and green spraying of workpieces with complex curved surfaces is achieved.

The invention belongs to the technical field of laser processing, and particularly relates to a laser processing control method based on a neural network, and the method specifically comprises the following steps: a target definition and input stage; a physical model and database stage: establishing a basic model library; establishing a mapping database; in the AI core engine stage, a training model learns a complex nonlinear relation among laser parameters, material response and a final processing result; searching an optimal laser parameter combination by using an optimization algorithm based on the prediction model and a target set by a user; a laser parameter automatic adjustment and execution stage; a real-time monitoring and feedback stage; and an iterative learning and system improvement stage. The invention further discloses a control system, electronic equipment and a computer storage medium. According to the method, submicron precision control is achieved, thermal damage can approach to zero, the development period is shortened, online real-time regulation and control are achieved, energy consumption is reduced, the material utilization rate is increased, and the method has an interpretable decision-making mechanism and cross-material generalization ability.

The invention provides a heat storage heat pump system control method based on a physical information neural network, and belongs to the technical field of heat storage pump system intelligent control. Aiming at the problems that in the prior art, an algorithm is difficult to adapt to dynamic energy consumption requirements, engineering application of a model is difficult due to building space heterogeneity, high-order RC model prediction credibility is weak, engineering feasibility is poor and the like, a solution combining a physical information sequence to sequence neural network technology and a finite-state machine control strategy is provided. On the model level, a 2R2C resistance-capacitance RC model of building temperature change is established, and then a PI-Seq2seq prediction model is proposed based on the physical model. On the control flow optimization level, on the basis of an industrial and commercial time-of-use electricity price policy, an FSM control model is designed, a system state set is defined, parameters and a transfer function are input, and a control rule is constructed in combination with the working period of a building heat pump and the characteristics of a heat storage tank. And finally, energy consumption cost optimization and indoor temperature stabilization under the peak-valley electricity price are realized.

The invention discloses an intelligent life prediction and optimization system and method for a steam turbine rotor welded joint. The system comprises a multi-source data acquisition module, a digital twin modeling module, a health state evaluation and life prediction module, a risk early warning module and an operation collaborative optimization module. The multi-source data acquisition module acquires the multi-dimensional physical quantity of the rotor welding joint in real time. The digital twin modeling module establishes a high-fidelity virtual model and realizes real-time synchronization and correction of a physical entity and a digital model. And the health state evaluation and life prediction module is used for calculating a damage accumulation rate and a health index based on fusion of a physical model and an LSTM neural network so as to realize residual life estimation. And the risk early warning module performs graded early warning according to the dynamic trend of the health state. And the operation collaborative optimization module adaptively adjusts operation parameters and optimizes the unit efficiency based on a reinforcement learning algorithm. All the modules are interconnected through an industrial network to form a closed loop, and real-time monitoring, intelligent evaluation and active service life management of the rotor welding joint are achieved.

The invention belongs to the technical field of tunnel engineering, and provides a multi-physics field real-time assimilation simulation and regulation method and system in a tunnel grouting process in order to solve the problem that real-time dynamic simulation and automatic regulation are lacked in existing tunnel construction, and the real-time assimilation simulation and regulation method and system in the tunnel grouting process are provided by utilizing ensemble Kalman filtering and combining real-time monitoring data in the tunnel grouting process. Dynamically correcting parameters of the multi-physical model; time correlation in the slurry condensation process is considered, a time-varying condensation model depicting physical property changes of slurry evolving along with time is integrated, the time-varying condensation model serves as an external function in the time step length to be embedded into the multi-physical field model in correction, and the slurry flowing state is adjusted in a self-adaptive mode through numerical simulation; and generating control parameters of tunnel grouting according to a dynamic simulation result, and realizing closed-loop regulation and control of tunnel grouting. Synchronous linkage of numerical simulation and on-site working conditions is realized.

The invention provides a method for predicting the residual life of a power transformer based on digital-analog fusion, and belongs to the technical field of transformer detection.The method comprises the steps that multi-dimensional sensor data of the power transformer is collected, wavelet transform preprocessing is conducted, a normalized data matrix is established, a physical equation is established, and a deterministic physical model is formed; a data-driven model is established based on an improved adaptive multi-scale network to realize multi-scale feature adaptive extraction, a topological phase change algorithm is introduced to identify key transition points in an aging process, and a deterministic physical model and the data-driven model are fused to establish a digital-analog fusion prediction framework. A generative adversarial network is adopted to perform data enhancement to solve the problem of scarcity of fault samples, a Bayesian neural network and a Monte Carlo random inactivation technology are utilized to construct an uncertainty quantization framework to output a residual life prediction value and a confidence interval thereof, and the technical problem that the prediction precision of the residual life of the transformer is not high is solved.

The invention discloses a truss structure wind-induced dynamic response prediction method and system based on physical enhancement. The method comprises the following steps: carrying out feature extraction and alignment fusion on input data containing condition parameters and wind speed time sequence data by utilizing a long short-term memory network and a physical enhancement attention mechanism; extracting multi-scale features from the fusion features through expansion convolution, and performing weighted aggregation on the multi-scale features; the physical priori knowledge of structural vibration is fused into position coding and a self-attention mechanism so as to carry out response prediction; and integrating physical model information of the truss structure and a dynamic control equation into a loss function, and calculating physical information residual loss so as to improve the physical interpretability of a prediction result. According to the method, data heterogeneity can be eliminated, complementary information can be fused, the multi-scale characteristic of wind-induced response is coped with, the accuracy and efficiency of wind-induced dynamic response prediction of the truss structure are effectively improved, and the physical interpretability and generalization ability are enhanced.

The invention relates to the technical field of biomedical engineering and computer vision, in particular to a non-contact physiological signal extraction method and system based on frequency self-adaption and illumination noise perception.The method comprises the following steps of multi-mode video stream collection and spatio-temporal data preprocessing, illumination-noise perception mask generation and feature filtering, multi-mode video stream collection and spatio-temporal data preprocessing, illumination-noise perception mask generation and feature filtering, and non-contact physiological signal extraction. Frequency adaptive gating and frequency domain feature enhancement, depth time attention feature re-calibration, physiological signal regression and closed loop optimization; the method has the beneficial effects that a lightweight end-to-end deep learning network architecture is constructed by systematically fusing three core modules of illumination-noise perception mask, frequency adaptive gating and depth time attention, and the defects that a traditional physical model depends on artificial prior and is poor in anti-interference performance and high in reliability are overcome. And the one-sidedness caused by high calculation complexity and difficulty in distinguishing the signal and noise of the existing deep learning model is avoided, and the weak physiological signal can be recovered from the face video more accurately and robustly.

The invention discloses an intelligent concrete automatic curing system and method based on real-time monitoring, and the system comprises a multi-parameter sensing module which collects the environment parameters and internal structure parameters of a concrete structure through a plurality of sensors and label identification codes, and an edge calculation module which is used for carrying out the preprocessing, feature extraction and emergency decision-making of collected data. The cloud intelligent module is used for storing data, establishing a prediction model and generating a dynamic maintenance strategy; the maintenance execution module is used for adjusting and executing spraying, temperature control or crack repair operation according to the maintenance strategy; by integrating structural strain, crack detection and environment air pressure monitoring, the limitation of traditional single temperature and humidity monitoring is broken through, multi-dimensional sensing and accurate diagnosis of concrete are achieved, meanwhile, the system combines a physical model and a data driving model, the self-adaptive optimization capability is achieved, and the system is suitable for large-scale popularization and application. And the edge gateway is adopted to process emergencies, and the cloud platform is responsible for global optimization, so that the system gives consideration to the real-time performance and the calculation depth, and the maintenance efficiency and the concrete quality are effectively improved.

The invention discloses an urban inland inundation simulation prediction method and system based on interpretable machine learning, and the method comprises the steps: obtaining multi-driving-factor data, and obtaining urban inland inundation data through the combination of physical model simulation; constructing a spatial analysis unit of the city, taking multi-driving factor data as an input feature and waterlogging data as an output target variable, training the candidate machine learning models, comparing the prediction precision of each candidate machine learning model which is completely trained, and determining an optimal prediction model; and based on the optimal prediction model, key driving factors and a nonlinear influence mechanism thereof are identified in combination with an interpretability method, the influence of interaction among different factors on the waterlogging risk is analyzed, and finally, a prevention and control and treatment scheme is formulated and output. According to the method, the specific influence of each driving factor on urban waterlogging and the interaction relationship among the factors are disclosed, and a scientific basis is provided for urban climate risk treatment and prevention and control.

The invention discloses an optical surface defect data detection method based on deep learning, and relates to the technical field of optical defect detection, and the method comprises the following steps: constructing an optical scattering physical model, inputting a collected optical surface image into the optical scattering physical model for multi-modal data synthesis, and generating multi-modal image data; constructing a deep learning feature extraction network, inputting multi-modal image data, and performing multi-scale feature fusion and enhancement through a bidirectional attention feedback mechanism to generate a deep feature map; performing spatial domain analysis on the depth feature map by using a deep learning region generation method, positioning coordinates of potential defect regions, and generating a candidate defect region coordinate set; through multi-modal data synthesis driven by an optical scattering physical model, the limitation of a single imaging mode is broken through, the scattering characteristics of defects under multi-physics field coupling are dynamically analyzed, the recognizable degree of weak defects in a complex scattering environment is enhanced, and the problem of defect missing detection is solved.

The invention discloses a double-domain artifact correction method based on multi-energy-level data and physical prior fusion, and the method achieves the efficient and precise removal of dispersive metal artifacts through the construction of a complete technical scheme of the combination of multi-energy-level data collection, double-domain cooperative correction and physical model constraint. The system has the beneficial effects that the system covers multiple fields of medical treatment, industry, security and protection, aerospace and the like, and has extremely high universality and adaptability. On the basis of a multi-energy-level slow switching scanning protocol, full-angle scanning of at least two energy levels is completed by dynamically adjusting radiation source parameters, and obtained complete multi-energy-level projection data is converted into a high-dimensional tensor through a channel dimension splicing image fusion method. The constructed multi-channel virtual image completely retains attenuation characteristics and structure information of a target object under each energy, provides a more comprehensive input source with discrimination for a deep learning network, builds a data basis for accurate correction in different fields fundamentally, and adapts to various imaging scenes containing metal targets.

The invention discloses a physical-data dual-drive retaining wall catastrophe robustness evaluation method, and relates to the technical field of structure catastrophe evaluation and computer science crossing. Aiming at the problems that an existing retaining wall catastrophe robustness evaluation method cannot correct physical model errors in real time and is insufficient in accuracy, the invention provides a retaining wall catastrophe process robustness evaluation method driven by fusion of a physical model and a neural network. The method comprises the following steps: 1, carrying out time discretization and parameter vectorization on retaining wall catastrophe monitoring parameters; 2, constructing a performance attenuation function based on the physical model; 3, updating an implicit damage state in combination with a neural network Cell module; 4, correcting an error through a feedforward network to obtain a total performance attenuation function; and 5, finally calculating a robustness index and outputting a corresponding robustness grade, thereby realizing quantitative evaluation of the retaining wall catastrophe robustness. Reliable quantitative support can be provided for retaining wall design optimization, operation monitoring and post-disaster recovery evaluation.

The invention provides an accident consequence simulation calculation method based on mathematical physical model coupling solution, and the method comprises the steps: constructing an accident chain knowledge graph and a physical trigger graph, and building a causal relationship and physical constraints among equipment, states, events and consequences; gathering and mapping historical records, expert rules and online observation data into map entities and relationships, forming a baseline accident scene and calculating a baseline index; generating candidate paths by utilizing graph reasoning and coupled multi-physics field simulation, and realizing a closed loop of graph reasoning and physical solution through consistency check; performing scoring and disturbance simulation analysis on the candidate paths, and screening robust target paths; and carrying out high-fidelity simulation on the target path, identifying key nodes in combination with sensitivity analysis and a minimum cut-off set, and generating disposal suggestions and action priorities. According to the method, high-credibility prediction of accident evolution and emergency response closed-loop linkage are realized, and the method has high precision, high robustness and engineering implementability.

The invention discloses a method for detecting abnormal metering performance of an intelligent electric energy meter, which belongs to the technical field of electric energy metering equipment and comprises the following steps of: 1, establishing a reference response curved surface of parasitic parameters of a voltage sampling resistor and a current transformer in the electric energy meter relative to temperature and humidity; step 2, during the operation period of the electric energy meter, acquiring the real-time measurement value of the parasitic parameter in situ; and step 3, matching the real-time measurement value with the reference response curved surface. According to the method, an active matching model library can be constructed by fusing an underlying physical model of a component and a mapping rule set for a complex environment with sudden change of plateau outdoor temperature and humidity, the internal mechanism that parasitic parameters change along with temperature and humidity is explained from the physical essence level, and the limitation of a pure data statistical method is made up; the dynamic error judgment threshold value can adapt to environmental stress changes in real time, and the accuracy of metering performance anomaly detection and the complex environment adaptability are effectively improved.

The invention relates to the technical field of robot control, and discloses an industrial robot adaptive control method and system based on multi-modal sensor fusion, and the method comprises the steps: collecting multi-modal original data, and carrying out the time-space alignment; capturing space-time semantic association of visual textures, tactile pressure distribution and force sense fluctuation in the multi-modal data through a multi-head attention mechanism guided by a physical model, and performing space-time registration; a CNN-LSTM hybrid model is adopted to extract visual texture features and time sequence tactile features in the physical information enhanced multi-modal feature matrix; and carrying out dynamic weight distribution on the fusion feature vectors with physical consistency by utilizing a weight distribution model driven by element reinforcement learning to generate dynamic weighted fusion features. According to the method, the spatial positioning precision of the industrial robot in a precise assembly scene is greatly improved, the contact force control stability is greatly improved, and the control robustness in a complex operation scene is remarkably enhanced.

The invention relates to the technical field of energy system control, and discloses a distributed cooperative fault-tolerant control method for a multi-energy-station cooling and heating system, and the method comprises the steps: enabling each energy station to measure and calculate a residual error based on a physical model and a sensor, forming a normalized health index, and carrying out the neighborhood broadcasting; carrying out robust anomaly judgment by utilizing a neighborhood median and a median absolute deviation, and isolating an abnormal site; cost coefficients are automatically generated for available sites according to equipment maneuverability, and control redistribution of minimum disturbance is solved and implemented through distributed consistency optimization; an exponential weighting updating mechanism of a residual error sequence is adopted to carry out online self-adaption on a noise baseline and a judgment threshold value so as to realize closed-loop self-calibration; when sensor abnormity, equipment errors or individual station faults occur in the multiple energy stations which work cooperatively, distributed rapid identification is achieved, faults are isolated, energy supply is redistributed with minimum disturbance, system control requirements are met, and equipment safety constraints are kept.

According to the spectrum-to-mass concentration imaging method and device based on physical mechanism deep learning provided by the invention, the actually measured spectrum and the reference spectrum of the pollution gas smoke plume are collected, the spectrum data set is constructed after differential processing, the meteorological data and the online mass concentration label are synchronously collected, and meanwhile, the spectrum-to-mass concentration imaging method and device based on physical mechanism deep learning are provided. A high-resolution gas absorption section is obtained and is convolved into a matrix; and constructing a deep learning model fusing a feature extraction module, an expanded least square module and a full connection module, taking the spectral data set, the meteorological data and the absorption cross section matrix as input, performing training in combination with labels to obtain an optimization model, and predicting the mass concentration of the target gas. According to the method, the problems of error accumulation, low calculation efficiency and poor interpretability caused by dependence on a complex physical model in a traditional method are solved, and high-precision, high-efficiency and interpretable real-time imaging of the mass concentration of the smoke plume of the pollution gas is realized.

The invention discloses a multivariate monitoring data fusion method and system for a slope tunnel model test, particularly relates to the technical field of geotechnical engineering physical model test, and aims to solve the problem that dynamic stress waves in an existing model test integrating static and dynamic measurement cause static monitoring signal distortion and further influence the model state evaluation accuracy. Coupling interference in static signals is identified by synchronously collecting dynamic excitation and static response signals; obtaining signal samples before and after a model state sudden change event to perform frequency domain comparative analysis, identifying characteristic frequency components related to sudden change, and evaluating a coupling interference dominant frequency band; separating an effective static response component from the original static signal based on the frequency band; and finally, fusing the effective component with a soil dynamic parameter derived from dynamic excitation to generate comprehensive stability evaluation data. Dynamic interference is effectively suppressed, the authenticity of static signals is improved, and the reliability of model stability state evaluation is improved.

The invention relates to the technical field of mine safety monitoring and geophysical exploration, in particular to a mine water disaster intelligent alarm system responding to multi-dimensional physical field parameter abnormity, which comprises a full-space data acquisition module for acquiring monitoring area observation data and calling a background geological physical model; the ideal reference reconstruction module is used for constructing an ideal physical field reference in a non-abnormal state; the double difference extraction module is used for calculating an observation residual error of observation data relative to a reference and a theoretical residual error of simulation response relative to the reference; the inversion coupling verification module is used for driving the theoretical residual error to approach to the observation residual error and extracting parameter sensitivity characteristics; the intelligent alarm judgment module is used for analyzing sensitivity characteristics and convergence states; generating an alarm instruction if the feature is determined to be the entity fluid abnormal feature; if it is determined that the target abnormal interference feature is not the target abnormal interference feature, signal suppression processing is executed; according to the invention, the false alarm rate of mine water disaster detection is greatly reduced.