371 results about "Field analysis" patented technology

The invention discloses a converter station intelligent gateway image recognition system based on a YOLOv3 target detection algorithm, and the system employs a three-stage cooperative processing architecture design, and builds seamless connection of a multispectral image collection layer, an edge calculation gateway layer, and a cloud operation and maintenance management platform layer. The invention further provides an equipment defect detection method based on the system, bimodal image data are collected through the visible light camera and the thermal infrared imager, preprocessing operation is carried out, equipment positioning and defect classification are synchronously executed by utilizing the improved YOLOv3 network, a structured detection result is output, temperature field analysis is carried out on an infrared thermal image, and the equipment defect detection result is obtained. And an abnormal heating area is identified, when defects are detected, multi-level risk response early warning is generated, and a defect diagnosis report is pushed to the cloud operation and maintenance management platform layer. Real-time image analysis of converter station equipment can be realized, the method is suitable for automatic detection of typical fault defects of the equipment, and the operation and maintenance efficiency of a power grid is improved.

The invention discloses a power distribution equipment on-line monitoring system based on multi-modal data fusion, and relates to the field of power distribution equipment management, and the system comprises a sensing module which is used for collecting an electrical signal, a thermal infrared signal, a mechanical vibration signal and an acoustic signal generated in the operation process of power distribution equipment through a multi-type sensing channel, converting the collected various signals into processable equipment state original data to form an equipment operation state original data set; according to the invention, through accurate acquisition of multi-dimensional signals, combination of space mapping and time delay compensation, data quality is optimized, the reliability of original information is ensured, key features are extracted according to working conditions, subtle state changes are captured by means of temperature field analysis and a variable-resolution spectrum technology, the comprehensiveness, accuracy and response timeliness of equipment operation monitoring are effectively improved, and the real-time performance of equipment operation monitoring is improved. Misjudgment and missed judgment are reduced, and fault risks are avoided in advance.

A multi-physics computation method and system for digital twin online simulation, relating to the technical field of physics simulation. A multi-physics coupling simulation computation model of a simulated object is established, and the multi-physics coupling simulation computation model is simplified, and the order of a temperature field simulation model is reduced, thereby greatly reducing the amount of computation, and improving computational efficiency; a low-precision dataset is obtained by means of temperature field analysis, so that the data size required for a model is reduced by means of low-precision data, thus reducing modeling costs; and a basic data-driven model is constructed by means of the low-precision dataset and a sample space corresponding to the low-precision dataset, so that a temperature field distribution result can be rapidly outputted, further improving computational efficiency and reducing computational errors.

The invention discloses a thermal management control method and device for a new energy automobile battery, and relates to the field of battery thermal management control, the device comprises an entropy change module, a fault module, a decision module, a phase change module and a scheduling module, entropy change intensity and nuclear heat flow field analysis is carried out on collected current and voltage signals to obtain an aging thermal topology, and the aging thermal topology is subjected to thermal management control. The method comprises the following steps: constructing an anisotropic diffusion equation based on aging thermal topology in combination with a fault diffusion tensor, discretizing a sub-strategy set for a safety margin field, constructing a cooling Nash game, analyzing through a payment matrix and a replicated dynamic equation, screening a stable strategy, mapping, and constructing an implicit phase change criterion model for the surface temperature of a battery to obtain a phase change cumulant; the phase change cumulant latent heat is analyzed and then cooperatively arbitrated with the cooling membership degree to obtain arbitration cooling capacity, the water pump flow is obtained through limiting operation based on the arbitration cooling capacity and the temperature deviation, then cubic root mapping is conducted on the water pump flow and the arbitration cooling capacity to obtain the fan rotating speed, and accurate control over battery thermal management is achieved.

The invention provides a jelly foreign matter deep learning detection method based on multi-mode intelligent sensing data driving, and the method comprises the steps: obtaining an original image of jelly, and generating a cross-view light field matrix through a polarized light compensation algorithm and synchronous triggering time sequence control; a cross-view light field matrix is obtained, the attenuation path of each light ray is reversely tracked in the jelly volume direction, and the foreign matter shielding probability is calculated in combination with a sugar degree-absorbance curve in a material library; foreign matter existence probability thermodynamic diagrams are generated in the three physical levels respectively, and a three-dimensional centroid probability field is obtained; and dynamically compressing a three-dimensional centroid probability field analysis time window according to the passing speed of the current production line jelly, comparing misjudgment cases of the same kind of jelly in a historical library, and adjusting a judgment threshold value of a corresponding space level to obtain a real-time judgment instruction set with production line parameter adaptability. Through deep cooperation of multi-mode light field perception and cross-level probability modeling, the technical breakthrough of full-dimensional foreign matter detection of jelly products is realized.

A micron-sized speckle preparation method for quasi-in-situ OIM-DIC mesoscopic strain field analysis comprises the following steps: (1) polishing the surface of a sample to be detected to obtain a bright and scratch-free mirror surface; (2) preparing Si powder turbid liquid; (3) dipping speckles of a sample to be detected in the Si powder turbid liquid to obtain micron-sized speckles; and (4) observing and shooting speckle morphology, and if Si particles are uniformly distributed and dispersed, applying the Si particles to quasi-in-situ OIM-DIC mesoscopic strain field analysis. The method is simple, convenient and rapid, low in operation and construction cost, high in practicability, good in particle dispersity, high in precision, more suitable for calculation of a quasi-in-situ OIM-DIC mesoscopic strain field, controllable in preparation process, low in cost and free of damage to the surface of a sample, the definition and stability of speckle characteristics are remarkably improved, DIC mesoscopic micron-scale operation under a quasi-in-situ OIM mechanical test can be effectively achieved, and the method is suitable for large-scale industrial production. And the grain and mesoscopic strain field information is successfully coupled.

The invention provides an automatic equipment anomaly monitoring method and system based on image processing, and relates to the technical field of automatic equipment anomaly monitoring, and the method comprises the steps: converting an equipment operation video into a multi-dimensional physical field feature: in a motion field dimension, based on optical flow field analysis, extracting a full-period displacement statistical histogram and a space thermodynamic diagram, the motion instability characteristic of the mechanical transmission system is accurately quantified; in a vibration field dimension, an energy spectrum and a vibration thermodynamic diagram are generated innovatively through time-frequency transformation of a displacement signal of a frequency spectrum monitoring point, and frequency domain feature visualization of a hidden vibration fault is achieved; in the dimension of a structure field, edge gradient analysis and texture feature extraction technologies are fused, a time sequence structure thermodynamic diagram sequence is constructed to capture a progressive damage evolution rule, a three-field abnormal index dynamic weighting fusion mechanism overcomes the limitation of traditional single-point monitoring, connected domain analysis of a fused thermodynamic diagram is combined with an LBP texture and morphological feature decision tree, and the defect of the prior art is overcome. Automatic equipment abnormity monitoring based on image processing is realized.

The invention relates to the technical field of graphene electric heating floor heating, and discloses a graphene electric heating floor heating intelligent temperature control system and method.The system comprises an area temperature recognition module, an instruction analysis module, an energy consumption division module and the like; the thermal field monitoring module collects basic temperature data, a real-time power curve and thermal imaging data, the energy consumption division module judges the temperature and energy consumption grade, the temperature control strategy module generates a dynamic adjustment strategy according to the grade, and the temperature difference judgment module and the path correction module achieve power correction and path optimization. And the thermal field analysis module is combined with the user terminal to early warn abnormity and visualize thermal imaging data. According to the scheme, regional refined temperature control, dynamic energy consumption management and intelligent path planning are achieved, the heating comfort level and the energy utilization rate are improved, and the method is suitable for intelligent temperature control scenes of graphene electric floor heating.

The invention relates to the technical field of computer modeling, in particular to an earthquake resistance and disaster reduction simulation system for a liquefiable foundation. The system comprises a cyclic stress ratio field analysis unit, an excess pore pressure ratio evolution analysis unit and a stress coupling correction unit, the cyclic stress ratio field analysis unit is used for generating a cyclic stress ratio field by using a depth reduction relation; the excess pore pressure ratio evolution analysis unit is used for deducing an excess pore pressure ratio and establishing an evolution relation of the excess pore pressure ratio along with time and depth; and the stress coupling correction unit is used for updating the effective vertical stress value based on the excess pore pressure ratio, synchronously correcting the shear modulus according to the coupling relationship between the shear wave velocity and the excess pore pressure ratio, and feeding back the corrected shear modulus to the excess pore pressure ratio evolution analysis unit. According to the method, the scientificity and engineering applicability of earthquake resistance and disaster reduction of the liquefiable foundation are effectively improved.

The invention discloses a fire temperature field analysis and prediction method based on artificial intelligence, and the method comprises the steps: 1, deploying a distributed heterogeneous sensor network, and outputting a heterogeneous original data set; 2, constructing a space-time diagram convolutional recursive network based on the heterogeneous original data set in the step 1; 3, constructing a heat conduction constraint generative adversarial network by using the spatial-temporal characteristic matrix and the dynamic graph structure in the step 2; 4, constructing a multi-modal fusion prediction model; 5, carrying out self-feedback closed-loop dynamic calibration; the method has the beneficial effects that a fire temperature field prediction system with physical interpretability and environmental adaptability is constructed through a heterogeneous data collaborative closed loop, a physical constraint conduction closed loop and a model self-evolution closed loop, and accurate and reliable technical support is provided for early fire early warning and emergency decision making.

The invention relates to the technical field of alignment precision of LDI exposure machines, and particularly discloses an LDI exposure machine light path deformation monitoring method based on multi-mode deformation field analysis, which comprises the following steps: acquiring multi-mode monitoring data of a substrate, the multi-modal monitoring data of the substrate comprises substrate datum point array data, a composite calibration pattern, a near-infrared image, grating temperature field distribution data and vibration spectrum data; obtaining deformation characteristic data of a plurality of substrate areas according to the near-infrared image, the substrate reference point array data and the composite calibration pattern; based on each piece of deformation characteristic data, the grating temperature field distribution data and the vibration spectrum data, obtaining fused deformation characteristic data; and generating a light path continuous deformation field corresponding to each substrate area according to the fused deformation feature data. According to the invention, by acquiring the multi-modal monitoring data of the substrate, such as the reference point array data of the substrate, the composite calibration pattern, the near-infrared image and the like, the state of the substrate is comprehensively reflected from multiple dimensions, and the defects of traditional single data monitoring are overcome.

The invention relates to the technical field of highway engineering safety monitoring, in particular to a highway subgrade three-dimensional deformation monitoring system based on unmanned aerial vehicle oblique photography, and the system comprises an unmanned aerial vehicle oblique photography module which adopts a five-lens synchronous shooting strategy to realize the omni-directional coverage of a subgrade; the three-dimensional point cloud generation engine generates a high-precision three-dimensional point cloud model through feature extraction, registration and triangulation strategies; the deformation field analysis platform models a roadbed surface into a parameterized Riemannian manifold based on a differential geometry theory, captures deformation dynamic characteristics through multi-scale curvature flow analysis, and identifies potential risks by using topological evolution characteristics of deformation singular points; and the risk evaluator evaluates the risk level based on the singular point density, the change rate and the topological stability and generates early warning information. According to the invention, millimeter-level accurate monitoring of roadbed deformation is realized, various deformation modes from micro-cracks to large-scale settlement can be captured, the potential landslide risk is early warned 30-45 days in advance, and the false alarm rate is significantly reduced.

The invention provides an injection mold temperature control method, system and equipment based on industrial Internet of Things and a medium. The method comprises the following steps: controlling a plurality of miniature temperature sensors in a temperature monitoring network to carry out temperature acquisition on a target injection mold to obtain multi-point temperature data; based on the multi-point temperature data, temperature field analysis is conducted on the target injection mold, and a temperature distribution model in the target injection mold is generated; identifying a temperature deviation area according to the temperature distribution model, and generating a temperature regulation and control instruction of each temperature control unit according to the temperature deviation area; and controlling the corresponding temperature control unit in the mold temperature control network to perform uniform temperature control on the target injection mold based on the temperature regulation and control instruction of each temperature control unit. And uniform distribution of the temperature in the mold is realized through multi-point monitoring and intelligent regulation and control of the Internet of Things, and the quality and the yield of injection molding products are improved.

The invention relates to an active optimization design method of an axial flow fan blade, which comprises the following steps of: defining a blade profile construction line by adopting seven parameters such as a leading edge radius, and parameterizing and representing two-dimensional blade profile geometric characteristics based on NURBS curve control points; a two-dimensional blade profile and three-dimensional fan coordinate system is constructed, and control point coordinate mapping is achieved through matrix transformation; the method comprises the following steps: acquiring an initial sample based on Latin hypercube sampling, and establishing a Gaussian process proxy model by combining two-dimensional CFD calculation data; a K-RVEA algorithm is applied, maximization of a worst attack angle lift-drag ratio and minimization of a resistance coefficient are taken as double targets, Pareto optimization is carried out in combination with geometry and performance constraints, and iteration is terminated through a hyper-volume convergence criterion; and the optimized two-dimensional blade profile parameters are converted into NURBS description, and stacking is carried out in the spanwise direction to generate a three-dimensional blade entity. The grid sensitive effect in three-dimensional optimization is overcome, the flow field analysis precision is improved, invalid calculation is reduced, the blade profile curvature continuity and the process feasibility are guaranteed, and the design period of the axial flow fan is shortened.

The invention discloses a deep sea ultra-shallow gas layer drilling shaft multiphase flow obstacle risk prediction method, and relates to the technical field of petroleum and natural gas engineering, and the method comprises the following steps: building a shaft-sedimentary layer heat-force-solid-chemical multi-physics field coupling model and a 3D model, setting initial boundary conditions, and dividing grids; model parameters are input, a finite element method is used for solving a multi-physics field coupling numerical value, and the gas invasion amount and the hydrate blocking rate are calculated; analyzing a gas invasion-migration-pressure evolution mode; researching the secondary generation and deposition characteristics of the hydrate; establishing a risk assessment system based on the parameters to divide risk levels; a historical data verification model is selected, and when the deviation rate exceeds 15%, parameters are optimized and solution is carried out again. According to the method, the defects of traditional single-field analysis are overcome, the multi-phase flow obstacle risk prediction accuracy is improved, intervention guidance is provided, model verification guarantees stability, safe and efficient mining of the deep sea ultra-shallow gas layer is assisted, and related development technology progress is promoted.

The invention relates to the field of aero-engine core engine performance monitoring and flow field analysis, and discloses a core engine compression turbine component inlet and outlet flow field reconstruction method based on a fusion neural network, and the method comprises the following steps: S1, obtaining a sparse measurement value, carrying out the interpolation based on the sparse measurement value, and generating an initial interpolation field; s2, generating a first feature vector, an attention weight map and a spatial feature map; s3, weighting to obtain a spatial feature map, and fusing the spatial feature map with the first feature vector to obtain a fused feature vector; and S4, training the full connection branch and the convolution branch through a mixed loss function containing a data fidelity loss item and a physical constraint loss item. A physical constraint loss item is introduced into model training and is combined with a data fidelity loss item, so that a reconstructed flow field is ensured to follow a fluid continuity equation on the basis of conforming to measurement data, and the global physical consistency of a reconstruction result is improved.

The invention belongs to the technical field of computational fluid mechanics and artificial intelligence crossing, and discloses an anisotropic turbulence modeling method and system based on scale adaptive physical convolution. Comprising a physical anchor point expansion layer used for improving a physical constraint coverage range, a physical information neural network basic full-connection layer, a convolution layer comprising a feature scale convolution kernel generation mechanism and a loss calculation process. According to the method, a physical anchor point expansion layer is introduced, additional physical calculation points are generated by setting a physical point expansion coefficient on the basis of training data points of a traditional physical information neural network, and the additional physical calculation points are combined with an original data point set to form a physical constraint calculation point set which is wider in coverage range and more reasonable in distribution; a convolution kernel size self-adaptive generation mechanism based on a turbulence characteristic scale is utilized, the turbulence characteristic scale is obtained through vorticity field analysis and energy spectrum calculation, the size of a convolution kernel is determined according to the turbulence characteristic scale, convolution operation can be matched with multi-scale physical characteristics of turbulence in a self-adaptive mode, and pertinence is higher.

The invention discloses a traffic safety risk early warning method and system based on intersection traffic flow information, and relates to the technical field of traffic safety monitoring, and the method comprises the steps: dividing an intersection region into space-time grids, generating a pixel-level optical flow field through a minimization energy function, converting the pixel-level optical flow field into a physical optical flow field, and carrying out the early warning of the traffic safety risk based on the physical optical flow field. Mapping the physical optical flow field to a space-time grid, and fusing the average optical flow vector and the velocity vector through a least square method to generate a fused velocity vector; predicting the future trajectory of each vehicle based on a kinematic equation, generating a grid risk by integrating the traffic flow density, the normalized grid confusion degree and the optimized strategy probability vector, and calculating the overall risk of the intersection through weighted average; and carrying out risk early warning on the overall risk of the intersection. According to the method, optical flow field analysis is combined with velocity vector fusion, the representation precision of the motion state of the vehicle is improved, kinematics prediction is combined with trajectory intersection analysis, and the capability of finding potential collision risks in advance is improved.

The invention relates to the technical field of a multi-field coupling simulation shield pump pressure-bearing component service life prediction method, particularly discloses a multi-field coupling simulation shield pump pressure-bearing component service life prediction method, and aims to solve the problem of service life prediction distortion caused by difficult accurate modeling of a nonlinear coupling effect in traditional single field domain analysis. The method comprises the following steps: constructing a three-dimensional self-adaptive grid model covering a pressure-bearing shell, a flange and a bearing seat; defining multi-physical field boundary conditions containing temperature gradient, pressure pulsation, electromagnetic excitation and time-varying creep parameters; and executing thermal electromagnetic full-coupling transient simulation to obtain a stress-strain evolution field. According to the method, through strong coupling modeling, time-varying constitutive embedding and data closed-loop correction, crack dynamic tracking and life rolling prediction under extreme working conditions are realized, and failure early warning perspectiveness and engineering decision reliability are remarkably improved.

The invention discloses a pollutant monitoring system and method guided by turbulence degree of a flow field of a clean room, and aims to solve the problem that the existing monitoring technology lacks self-adaption and active tracking capability. The invention provides an innovative solution aiming at the defects that a fixed point position sensor has a blind area and a robot cannot deal with the change of a dynamic flow field during fixed inspection. The system comprises a mobile robot and a set of calculation and control system with a hierarchical data processing architecture. The remote computer is responsible for complex flow field analysis and decision making, the local industrial personal computer processes original data and executes bottom layer control, the load of the robot is effectively reduced, and efficient, stable and intelligent data transmission is achieved. The core of the method is an intelligent collaborative algorithm guided by the turbulence degree of the flow field. When the system detects that the flow field is disordered, the robot can start headwind search for rapid positioning, then seamlessly switches to disorder degree gradient tracking for accurate tracking, and finally the pollution source is locked. According to the cooperative mechanism of rough positioning and accurate tracking, the hysteresis problem of a traditional method is effectively solved, monitoring is changed from a passive mode to an active mode, and the real-time performance and the accuracy of clean room pollutant monitoring are greatly improved.

The invention discloses a composite insulator large cluster parachute heating defect judgment interference suppression method. The system comprises an infrared image acquisition and preprocessing module, a composite insulator target detection and positioning module, a composite insulator temperature field analysis module, a large umbrella group reflection area identification module, a composite insulator central axis reconstruction module and a heating defect intelligent diagnosis and interference suppression module. Complex infrared image analysis is converted into refined analysis of a temperature field and geometric features, and meanwhile, a strategy of combining deep learning and morphology is introduced to improve the precision of target detection and segmentation and ensure the robustness of central axis reconstruction and interference suppression. The method has the beneficial effects that the false alarm rate can be obviously reduced, the detection accuracy of the real heating defect is improved, the result is highly consistent with the interpretation result of an artificial expert, the processing efficiency is high, and the method is suitable for a large-scale unmanned aerial vehicle inspection scene.

The invention relates to a solid-liquid two-phase flow field analysis method and device, a simulation system and a computer storage medium, and belongs to the technical field of flow field analys.The solid-liquid two-phase flow field analysis method comprises the steps that a solid-liquid two-phase flow field model is constructed, dividing the solid-liquid two-phase flow field model into a multi-layer grid model according to the distance between a fluid and a rigid body in the solid-liquid two-phase flow field model; performing discrete analysis on the particles according to the particle volume of each particle in the solid-liquid two-phase flow field model and the grid volume of the multi-layer grid model, determining the particle volume fraction in each grid, and calculating the drag force of the fluid to the particles based on the particle volume fraction and a preset drag force model; and determining the motion state of each particle in the flow field based on the drag force and the contact force during particle collision, and determining the distribution state of each particle in the flow field based on the motion state. According to the invention, fine analysis of the solid-liquid two-phase flow field can be realized.

The invention discloses an underground water flow field simulation method, an underground water flow field simulation device, underground water flow field simulation equipment and a computer readable storage medium, and the method comprises the steps: carrying out the collection of multi-source geological data based on drilling basic information, a digital elevation model and a hydrogeological map, and obtaining the multi-source geological data; constructing a three-dimensional geological model based on the multi-source geological data to obtain a three-dimensional geological entity model; performing aquifer recognition based on the profile information of the three-dimensional geological entity model to obtain aquifer spatial distribution; performing groundwater flow field analysis based on the aquifer spatial distribution to obtain groundwater flow field data; and performing model construction based on the groundwater flow field data to obtain a groundwater flow field model. The integrated simulation method for fine description of stratums, automatic identification of aquifers, flow field feature analysis and comprehensive evaluation of thermal reservoirs is realized, so that the precision and efficiency of geothermal resource exploration evaluation are improved.

The invention discloses a signal integrity simulation analysis method for a digital radio frequency hybrid microsystem, and belongs to the field of advanced packaging of integrated circuits. According to the method, a complete analysis process accompanied with product research and development is established, systematic work of qualitative simulation evaluation, rule design and quantitative analysis verification is sequentially carried out in various stages of project approval demonstration, scheme design, design verification and the like of product design, and process conditions, material characteristics and rationality and feasibility of system layout are rapidly evaluated; qualitative support is provided for agile design of the scheme; designing rules and optimization ranges of structures such as a radio frequency link, a digital link and a coupling shield are formulated according to process and material rules, and accurate initial input is provided for comprehensive design of a product; according to the layout wiring form, digital, radio frequency and coupling areas are formed through division, time domain analysis, frequency domain analysis and near field analysis are carried out in a targeted mode, quantitative reference is provided for judging design reasonability, and an effective basis is provided for optimizing design content.

The invention relates to the technical field of zero-point positioning mother board pressure compensation, and discloses a pneumatic type zero-point positioning mother board pressure adaptive compensation system which performs multi-source fusion processing on initial pressure field data and covers a compensation sequence of static reference features, a feedback sequence of dynamic deformation features and a calibration sequence of axial offset features. And the pressure compensation module carries out dynamic fluctuation suppression on the real-time deformation data flow, realizes pressure field balance identification through a multi-field coupling layer and generates a compensation instruction. The pressure standardization module performs space grid division, anomaly filtering and data calibration, and a pressure field analysis layer, a zero point self-adaption layer and a compensation trigger layer of the field intensity reconstruction module sequentially complete feature fusion, dynamic correlation modeling and multi-dimensional field intensity fusion. According to the system, through algorithms such as deformation segmentation, virtual interpolation and dynamic clustering, the pressure field balancing capability and positioning precision of the mother board under complex working conditions are improved, and the system is suitable for high-precision positioning requirements in the field of industrial automation.

The invention discloses a parachute flight performance prediction method based on follow-up coupling flow field analysis, and the method is suitable for a parafoil and a traditional round parachute. Parachute flight flow field aerodynamic characteristics and flight dynamic characteristics are coupled by using a body-attached dynamic grid and a self-adaptive flow field boundary technology, real-time changes of a parachute streaming flow field along with body motion are accurately reflected, and the attitude, the speed and the flight trajectory of the parachute are automatically solved and obtained. According to the method, on one hand, real-time aerodynamic characteristics and motion characteristics of the parafoil are coupled, the coupling influence of flight attitude speed change on aerodynamic force and aerodynamic torque of the parafoil is reflected, and the calculation precision is guaranteed; and meanwhile, the change of the streaming flow field of the parachute system is decoupled into the change of the relative incoming flow and the change of the posture, so that the redundancy of flow field grids and the complex grid reconstruction are avoided, and the simulation calculation efficiency is improved.

The invention relates to the technical field of artificial intelligence, in particular to a non-deterministic boundary thermal convection flow field intelligent analysis method based on deep learning, which comprises the following steps: acquiring sparsely distributed training data in a thermal convection system, constructing a physical information neural network and designing a composite loss function comprising a prediction error, a physical constraint error and a boundary condition error; and dynamically adjusting a weight coefficient by using a quasi-Newton optimization algorithm to carry out network training, and finally realizing prediction of full-field physical quantity distribution and inversion of missing boundary conditions. According to the method, a fluid mechanics control equation is used as a physical constraint to be embedded into a deep learning framework, the dependence of an existing calculation method on accurate boundary conditions is overcome, and the problems of flow field analysis and parameter inversion caused by unknown boundary conditions or difficulty in direct measurement are effectively solved; the method has important application value in engineering scenes such as aero-engine thermal management.

The invention relates to the technical field of power supply modules, and discloses an IPM (Intelligent Power Module) power supply module embedded with a temperature sensor. The module comprises a temperature data sensing module, a temperature field analysis module, a regulation and control decision module and a power execution module. The temperature data sensing module obtains original temperature data through the micro thermocouple array, and outputs a substrate thermal field distribution diagram through the thermal field reconstruction unit; the temperature field analysis module calculates a thermal field deformation signal by using a nonlinear heat conduction model and generates a thermal expansion stress distribution diagram; the regulation and control decision module dynamically corrects a temperature safety threshold according to the thermal expansion stress distribution diagram and generates a driving signal regulation parameter; and the power execution module adjusts the IGBT conduction time sequence according to the adjusting parameters and controls the flow speed of the micro-channel cooling system. According to the module, comprehensive sensing and dynamic regulation and control of a thermal field are achieved through multi-module cooperation, and the operation requirement under the complex working condition is met.

The invention relates to the technical field of crossing of water conservancy and nuclear power engineering, in particular to a nuclear power water taking open channel flow field analysis method based on a physical model test, and solves the problems that flow field analysis in the prior art mainly depends on theoretical calculation or numerical simulation, flow field characteristics under the combined action of tidal current, waves, water taking operation and other factors are difficult to truly restore, and the flow field analysis accuracy is low. And the analysis result is greatly deviated from the actual analysis result. The method comprises the following steps: constructing a physical model for accurately simulating key facilities such as a water intake, a drain grating net and a pump room, setting multiple typical working conditions, carrying out a flow field simulation test, and recording data such as a flow velocity, a flow direction and a water level. Through a physical model test means, actual water flow characteristics under a complex marine environment and various working conditions can be reflected more truly, the accuracy and reliability of flow field analysis are remarkably improved, and a scientific basis and technical support are provided for design, operation and risk assessment of a water intake system of a nuclear power plant.

The invention discloses a green building energy consumption adaptive regulation and control system based on dynamic environment parameters, and relates to the technical field of building energy consumption regulation and control, and the system comprises a multi-source environment sensing module which comprises a plurality of environment parameter collection devices which are arranged at different spatial positions of a building atrium area and are used for collecting various kinds of environment parameter information, generating a structured data packet; and the control analysis module is used for receiving the structured environment data packet, performing field analysis, generating a control intention set based on a preset atrium environment control rule, identifying an environment parameter conflict relationship caused by vertical spatial characteristics of the atrium, and outputting the control intention set with a conflict identifier. According to the invention, multi-point synchronous acquisition of parameters such as temperature, humidity, air quality and illumination intensity in a building atrium area is realized through environment parameter acquisition devices arranged at different spatial levels, and a comprehensive credibility weight is generated in combination with personnel quantity information to construct a structured data packet.