672 results about "Data calibration" patented technology

The invention relates to the technical field of pumped storage power station multi-sensor monitoring network time-space synchronous measurement, in particular to a pumped storage power station multi-sensor safety monitoring system, which comprises a sensor data acquisition module, a time-space synchronous network module, a data calibration module, a dynamic association model construction module, a multi-dimensional data fusion module and a graded early warning module. The dynamic correlation model building module simulates dynamic response of seepage pressure and surrounding rock strain through a fluid-structure interaction equation and a discrete element digital twinborn model, updates fracture permeability boundary conditions in real time, and extracts cross-sensor space-time correlation characteristics by adopting a convolutional long-short-term memory network improved by a multi-head attention mechanism. According to the method, the real-time early warning precision of abnormal events and the reliability of structural health assessment in the complex hydraulic and mechanical coupling environment are improved.

The invention relates to the technical field of material physicochemical property monitoring of a multi-source sensing network, in particular to a multi-source sensing storage environment collaborative monitoring and early warning method, which comprises the following steps of: dividing grid units according to material storage types, binding sensor node coordinates, constructing a grid region reference model, and constructing a grid region reference model; integrating the volatilization characteristic parameters analyzed by the laboratory, historical monitoring data and an environment threshold value to generate a substance and environment relation matrix; the method comprises the following steps of: calling model parameters to invert a theoretical gas concentration value, and triggering finite element physical field simulation through residual analysis to generate a three-dimensional simulation field data set containing a temperature gradient and a diffusion path. And the dynamic correlation analysis precision and the early warning reliability of storage environment monitoring are improved.

The invention relates to the technical field of intelligent warehousing and logistics automation, in particular to a forklift dynamic path planning method based on deep reinforcement learning, and the method comprises the steps: deploying multi-view vision, geomagnetism and other multi-source sensors, achieving data calibration and fusion through employing an insect compound eye-imitating vision model, and constructing a high-dimensional state space vector; heuristic models such as migrant bird navigation and biological stress response are adopted, deep reinforcement learning is combined, decision instructions are generated from the three aspects of path planning, dynamic obstacle avoidance and energy efficiency management, actions are executed through a control system, and deviation is fed back; a reward function is used for evaluating the decision effect, rewards are formed by weighting path efficiency, obstacle avoidance success and energy consumption penalty, the weight can be updated in a self-adaptive mode, and therefore the deep reinforcement learning model is optimized. According to the method, the accuracy, safety and efficiency of forklift path planning are effectively improved, the method can adapt to complex dynamic environments, and the requirements of intelligent logistics and industrial automation for forklift intelligent operation are met.

The invention provides a water pump residual life prediction method based on a large model, and the method comprises the following steps: S1, collecting the multi-source heterogeneous data of the operation of a water pump in real time through a vibration sensor, a temperature sensor, a pressure sensor and a monitoring unit, the temperature sensor monitors temperature gradient changes of the bearing and the sealing cavity, the pressure sensor records inlet and outlet pressure fluctuation characteristics, and the monitoring unit extracts three-phase current harmonic components of the motor; s2, carrying out lightweight preprocessing on the multi-source heterogeneous original sensing data at an edge computing node, wherein the lightweight preprocessing comprises vibration signal noise reduction processing based on wavelet transform, temperature and pressure data calibration normalization of load segments according to working conditions, and transient abnormal data flow filtering through a sliding time window; and S3, inputting the preprocessed data stream into a cloud large model platform, and analyzing the long-period dependency relationship of the vibration signals through a Transform encoder in a time sequence feature extraction module.

Provided in the present invention is a ship hatch data management method based on point cloud technology. The method is implemented by means of a constructed ship hatch data management system, and the system comprises a ship scanning module, an automatic hatch identification and calculation module, a ship attitude data compensation module, and a hatch data calibration and accumulation module. In the present invention, by means of processing data of a scanner and analyzing point cloud data, a point cloud model of a ship to be subjected to operation is generated in combination with mechanism parameters of a ship loader, the position of a ship hatch is automatically identified, the spatial coordinates of the ship hatch in a rectangular coordinate system of wharf space are automatically calculated, hatch identification data for current berthing is calibrated on the basis of historical hatch data records from the same hull number after berthing in a database, and the ship loader is guided to realize unmanned and automated operation modes by means of the calculated hatch position, thereby enhancing the level of port automation.

The invention discloses a sewage waste heat recovery heating control method and system based on a digital twinning heat pump. The method comprises the steps that a digital twinning platform of a sewage waste heat recovery heating system is constructed; based on the operation parameters of the entity equipment of the sewage waste heat recovery heating system, establishing a digital twinborn model of the sewage waste heat recovery heating system; deploying the established digital twinborn model of the sewage waste heat recovery heating system in the established digital twinborn platform of the sewage waste heat recovery heating system; based on the physical equipment operation parameters of the sewage waste heat recovery heating system and the virtual data of the digital twinborn model, an optimization target model of the sewage waste heat recovery heating system is constructed, and an optimal control strategy is obtained; dynamic optimization control is carried out on the heating system entity equipment according to the optimal control strategy; the prediction precision is improved through real-time data calibration, model prediction control is fused, second-level response and multivariable cooperative regulation and control are achieved, and the problems that a traditional sewage waste heat recovery heating system is low in energy efficiency, slow in response and high in maintenance cost are effectively solved.

The invention discloses a current sensor data calibration method for an industrial environment, and the method comprises the steps: collecting the original current sensor data of target equipment in the industrial environment in real time, and carrying out the dynamic preprocessing of the original current sensor data, and generating a first calibration data set; based on the first calibration data set, time domain features and frequency domain features are extracted, and a second feature vector set is constructed; iteratively calculating an optimal calibration parameter set through a self-adaptive optimization algorithm in combination with historical calibration data and the second feature vector set; and dynamically correcting the current data of the current sensor according to the optimal calibration parameter set, and outputting and updating the calibrated current value. According to the invention, through dynamic preprocessing, comprehensive time domain and frequency domain feature extraction and combination of historical calibration data, parameter adaptive optimization updating is carried out, and the problem that current sensor data calibration in an industrial environment is difficult to accurately adapt to dynamic change environment conditions in real time is effectively solved.

The invention provides an electroencephalogram eye tracker based on a brain-computer interface, a calibration method and device of the electroencephalogram eye tracker, computer equipment and a storage medium. According to the scheme, a stable stimulation source is provided for data acquisition by orderly displaying the calibration points, the eye movement data and the electroencephalogram signals are synchronously acquired, and the user state information is acquired from multiple dimensions. The attention index is quantified according to the electroencephalogram signal, the data quality is preliminarily controlled, the target calibration point is displayed again, the data is updated, and errors caused by inattention of the user are corrected. And finally, high-quality eye movement data is utilized to calibrate and compensate eye tracker system errors, individual differences and environmental influences, and the calibration robustness is greatly improved, so that the calibrated electroencephalogram eye tracker can more accurately detect the watching position of the user, and reliable data support is provided for subsequent research and application based on eye movement tracking.

The invention relates to the technical field of building environment temperature control, and discloses a temperature control equipment intelligent adjusting method and system based on machine learning, and the method comprises the steps: building a space thermal field sensing network, obtaining multi-dimensional temperature field data, and generating a temperature gradient distribution matrix; and the positions of cold and hot spots are calibrated by combining infrared temperature measurement data, an airflow path is predicted, and air supply parameters are optimized. Meanwhile, building heat capacity characteristics are analyzed, and a thermal response dynamic model is constructed. And the air supply direction is adjusted for the local supercooling area. And based on the temperature change rate and the air supply parameters, the equipment start-stop time is optimized. Through real-time temperature sampling, continuous updating of temperature gradient distribution, cyclic execution of cold and hot spot calibration, airflow prediction and air supply optimization, accurate control of space temperature is realized. According to the invention, the accuracy and energy efficiency of building space temperature adjustment can be obviously improved, and an innovative solution is provided for an intelligent temperature control system.

The invention relates to the technical field of data processing, in particular to an induction cooker data acquisition and processing system which comprises a power jump identification module, a response section correction module, a trend sampling analysis module, a temperature control abnormity judgment module and a working condition balance data calibration module. According to the method, the rate change value between the power sampling points in the operation period is calculated, the sections with obvious abrupt change characteristics are screened, and the power lag response is corrected in combination with the voltage change slope, so that the time offset between the control response and the electric signal change is effectively corrected; the temperature fluctuation trend and the temperature control deviation direction are analyzed on the basis of the correction sequence, a temperature control abnormal state label set is formed by matching current waveform symmetry characteristics, a basis is provided for output power adjustment according to the temperature rise rate, the adaptation capacity of data analysis to actual working conditions and the execution precision of a control strategy are improved, and the accuracy of data analysis is improved. And the stable operation capability of the electromagnetic heating equipment under the complex thermal load change is enhanced.

The invention relates to the technical field of refrigeration house energy-saving control and digital twinning, in particular to a refrigeration house fan energy-saving operation method and system, and the method achieves the whole-field temperature deduction of a sensor-free area by constructing a CFD reference model and simulating and predicting the three-dimensional transient airflow and temperature distribution in a refrigeration house. Model parameters are calibrated through measured data, and the order of the model is reduced by adopting intrinsic orthogonal decomposition and Galerkin projection, so that the calculation amount is remarkably reduced, and online optimization is supported. And in combination with a data assimilation algorithm, the prediction result of the reduced-order model is continuously corrected, and the adaptability to environment change and system aging is improved. The optimization control stage takes minimization of the total energy consumption of a fan as a target, solves an optimal fan control sequence under the hard constraint that the whole-field temperature does not exceed the cargo safety upper limit and does not exceed the cargo safety lower limit, and adopts a rolling time domain mode for execution to realize collaborative optimization of safety and energy conservation.

The invention discloses a bearing defect intelligent detection method and system based on deep learning, and relates to the field of bearing defect detection. Multi-modal data such as bearing vibration, acoustics, thermal imaging and the like are acquired by using various sensors, and a four-dimensional feature tensor is constructed through preprocessing such as noise reduction and feature extraction; features are fused through a reconfigurable multi-branch convolutional neural network, and defects are identified and a development trend is predicted in combination with a meta-learning twin network; a decision threshold is optimized by adopting a quantum heuristic algorithm, and multi-level early warning is realized; and continuous evolution of the model is completed through edge-cloud collaboration and federated learning, the functions of data calibration compensation, model dynamic optimization and the like are achieved, and efficient and accurate detection of bearing defects is achieved. The detection time is remarkably shortened, and the positioning precision is high; the novel defect response speed is high, and faults can be predicted in advance; system energy consumption is reduced, model updating is improved, stable operation of equipment is effectively guaranteed, and cost reduction and efficiency improvement of industrial intelligent operation and maintenance are facilitated.

The invention provides a semi-aviation transient electromagnetic acquisition device and method for calibrating data drift in real time, and relates to the technical field of data calibration, and the device comprises an electromagnetic data acquisition unit which receives a secondary induction signal generated by a ground transmitting end through a transient electromagnetic hollow induction coil disposed in a coil storage cabin of an unmanned aerial vehicle, and transmits the secondary induction signal to an unmanned aerial vehicle; self-adaptive gain control is carried out according to the signal intensity to obtain real-time electromagnetic data; the flight control unit monitors the swing amplitude and frequency of the coil in real time according to the inclination angle and acceleration data fed back by the sensor in the coil storage cabin, and carries out flight attitude adjustment and control; the drift calibration unit adopts a static reference mode for calibration at the beginning stage of flight; and switching to a dynamic reference mode in the flight process, and carrying out self-adaptive calibration on the real-time data stream based on a sliding window. According to the invention, drift calibration of traditional software post-processing is migrated to a hardware acquisition stage, so that synchronous completion of data acquisition and drift compensation is realized.

The invention discloses an ultrasonic water meter detection device and method, and relates to the technical field of ultrasonic flow metering, the device comprises an ultrasonic detection unit, a block chain evidence storage unit, a zero-knowledge proof module, a master control MCU and a low-power-consumption communication unit, the ultrasonic detection unit collects downstream and countercurrent ultrasonic propagation time difference delta t through symmetrically installed transducers, a time difference measurement module (precision + / -1ns) is combined with water temperature data to calibrate a delta t value, the block chain evidence storage unit constructs a Merkel tree for a delta t sequence according to a time window, and root hash is written into a private chain by improving a PBFT consensus mechanism (threshold 4 / 5 node confirmation). The method covers the whole process of data collection, evidence storage, verification and auditing, solves the problems that traditional water meter data is easy to tamper, privacy is leaked and installation is limited through a hash chain and zero-knowledge proof technology, and is suitable for an intelligent water affair scene.

The invention relates to the technical field of unmanned aerial vehicle supervision, and discloses a multi-band multi-channel unmanned aerial vehicle RID signal analysis system. According to the system, RID signals of 2.4 GHz, 5.2 GHz and 5.8 GHz frequency bands are collected in parallel through a multi-frequency-band antenna group and a multi-channel radio frequency receiving module, and real-time analysis and algorithm scheduling of the RID signals are achieved through an FPGA + ARM heterogeneous processing unit. Four modules of multi-sensor space-time alignment and cross validation, lightweight national secret encryption and data integrity verification, self-adaptive scheduling based on reinforcement learning and unmanned aerial vehicle behavior digital twinning and intrusion early warning are integrated in algorithm, and a closed-loop processing flow from RID signal receiving, data calibration and secure transmission to intelligent research and judgment is formed. The method effectively solves the problems of incomplete RID signal coverage, low data reliability, weak safety protection, insufficient early warning capability and the like in the prior art, has the advantages of high analysis precision, good safety, high resource utilization rate, accurate early warning and the like, and is suitable for low-altitude supervision scenes such as urban security and protection, border management and control and the like.

The invention discloses an automatic control gradient LED lamp energy-saving illumination method, which comprises the following steps: S1, asynchronous sampling is carried out through an illumination sensor A and an illumination sensor B, ambient light change data is collected, a sampling timestamp is recorded, a time difference weight is obtained based on the timestamp, data fusion is carried out through the time difference weight, and ambient light intensity data is obtained; s2, performing data calibration on the ambient light intensity data through a state space model, and performing optimization through a weighted moving average method to obtain an ambient light intensity change rate; and S3, acquiring a light change condition based on an environment illumination intensity change rate, adjusting a brightness duty ratio through a probability model based on Bayesian reasoning to output an initial control variable, performing optimization based on the initial control variable in combination with a particle filtering algorithm to obtain a final control scheme, and performing optimization through the probability model and the algorithm to obtain a final control scheme. A relatively accurate brightness adjustment scheme can still be given, and the intelligent level of lamp control is improved.

The invention provides a temperature sensor data calibration method and system, and relates to the technical field of sensor calibration, and the method comprises the steps: collecting a time sequence voltage sequence of a to-be-calibrated temperature sensor under the excitation of a temperature step; calculating a gradient change rate of the time sequence voltage sequence to obtain a dynamic response characteristic of the to-be-calibrated temperature sensor; based on the gradient change rate, the dynamic response asymmetry degree of the temperature sensor to be calibrated under temperature step excitation is calculated; establishing a thermal inertia evolution equation of the temperature sensor to be calibrated according to the dynamic response asymmetry degree; the theoretical lag amplitude of the temperature sensor to be calibrated is corrected with the trend of the thermal inertia evolution equation to be stable as the target, and the actual lag amplitude is obtained; obtaining the original measurement temperature of the target temperature by the temperature sensor to be calibrated; and correcting the original measurement temperature in combination with the actual lag amplitude and the dynamic response asymmetry degree to complete data calibration of the temperature sensor to be calibrated. And the measurement precision of the temperature sensor in a complex temperature change scene is improved.

The invention relates to wafer detection, in particular to a data calibration and wafer scanning data alignment method based on polar coordinate sampling, and the data calibration method based on polar coordinate sampling comprises the steps: carrying out the alignment of the collection data of a photoelectric detector and the periodic data of a grating type displacement sensor; determining a time point for starting detection and a time point for ending detection, and cutting the collected data; counting the scanning period of the grating type displacement sensor according to the data width of the current sampling timestamp; scanning the cross-period signals in the clipped acquisition data, and determining the relative offset of each cross-period signal; according to the scanning period of the grating type displacement sensor and the relative offset of each cross-period signal, position offset calibration is carried out on the collected data in each period; according to the technical scheme provided by the invention, the defect that the position deviation of the acquired data caused by the speed fluctuation of the motion shaft is difficult to effectively calibrate and align in the prior art can be effectively overcome.

The invention discloses a slope monitoring data calibration and three-dimensional point cloud matching method, belongs to the field of monitoring data calibration, and aims to improve orientation errors caused by the fact that global satellite positioning and navigation system measurement endpoint errors and equipment length problems are not fully considered in existing slope radar measurement. The method solves the problem of position deviation of a monitoring result caused by the fact that the position of a deformation area is monitored, breaks through the limitation of insufficient precision when a traditional radar image is converted into geographic space coordinates, improves the accuracy and reliability of data, remarkably improves the position precision of slope radar monitoring data, and enables the position monitoring of the deformation area to be more accurate. The high-precision requirement of slope stability monitoring is met, reliable data support is provided for fine monitoring of slope stability, potential safety hazards can be found in time, and corresponding measures can be taken.

The invention discloses a marine environment risk identification method based on big data, and the method comprises the steps: constructing a terrain prediction model based on initial static terrain and dynamic sediment migration data, and correcting the terrain data in real time; predicting topographic change in combination with corrected data and information such as weather and ocean current, and constructing an ocean environment numerical model; calibrating the model by using measured data, and judging whether to simulate or not according to real-time monitoring parameters; analyzing a simulation result, dividing a risk area, and determining a grid risk level; according to the scheme, through real-time terrain correction, accurate change prediction and dynamic model calibration, the marine environment prediction accuracy and real-time response capability are greatly improved, and scientific and efficient technical support is provided for coastal risk prevention and control, resource management and decision making.

The invention relates to a dynamic multi-dimensional quality evaluation system and method for a thermal power plant intelligent inventory supervision model. Real-time data flow of the DCS is collected and compared with the model prediction value, and a prediction error is generated; based on the load rate, the fuel characteristic and other characteristics, the current operation state is matched to a preset working condition library, and historical data is called for index calculation; the method comprises the following steps of: according to stability, reusability and economic indexes such as a variable coefficient of a prediction error, a model calling frequency, economic benefit influence and the like, normalizing the indexes by adopting a range method, and calculating the weight of each index by utilizing an entropy weight method; constructing a weighted standardization matrix, defining a dynamic ideal solution, calculating a close degree index, and outputting a comprehensive evaluation result; according to the scoring result, an optimization instruction is automatically pushed, and model parameter adjustment or data calibration is carried out, a set of dynamic and multi-dimensional thermal power plant supervision model evaluation system is constructed, the model quality can be objectively and comprehensively evaluated, and a closed-loop optimization mechanism is provided.

The invention provides a carbon emission accounting method, system, equipment and medium in a port and aviation container transportation process, and belongs to the technical field of logistics carbon management and intelligent algorithm crossing. The method comprises the following steps: collecting transportation and energy consumption data of roads, waterways, railways and logistics storage links in a classified manner, and preprocessing the transportation and energy consumption data to form a standardized data set; a carbon emission factor parameter library is created in combination with industrial standards, different transportation modes and cargo types, and dynamic updating is performed through a machine learning algorithm. And special accounting sub-models are constructed for different transportation modes, and carbon emission accounting is carried out by using corresponding formulas and parameters. And inputting the standardized data into the nuclear operator model, calculating the carbon emission and screening an optimal path. And model parameters are calibrated by using historical data to ensure accuracy. And finally, collecting data in real time, inputting the data into the accounting sub-model, generating a decision support report comprising implementation steps, resource demands and expected effects, and assisting in realizing low-carbon and efficient management of the transportation process.

The invention relates to the technical field of agricultural intellectualization, and discloses a fruit tree growth monitoring system based on multi-sensor fusion, which comprises a multi-mode sensor array, an integrated soil humidity sensor, a three-dimensional ultrasonic ranging sensor, a hyperspectral imaging sensor and a microenvironment meteorological station, and realizes multi-parameter synchronous acquisition; a nonlinear data calibration model adopts a layered architecture, and cross interference between sensors is eliminated; a dynamic weight distribution algorithm is built in the edge computing node, multi-source heterogeneous data are fused in real time, a fruit tree growth situation map is generated, and a low-power-consumption processor is adopted to support lightweight AI model deployment; the self-adaptive power supply module adopts a photovoltaic-temperature difference composite power generation structure to realize cable-free deployment; the wireless ad hoc network communication unit constructs an inter-tree relay network based on a LoRa protocol, supports low-power-consumption remote data return, and integrates a relay node health degree evaluation mechanism. The real-time performance of fruit tree growth monitoring, the data reliability and the situation analysis accuracy are improved.

The invention discloses a data calibration compensation method for an off-axis magnetic encoder, and the method comprises the following steps: S1, calibration initialization: carrying out the initialization of used peripherals, calibration parameters and an encoder chip, and making preparations for calibration; s2, forcibly dragging the motor to align: forcibly dragging a motor rotor to rotate to a position 0 of a nearest electrical angle by adopting a non-inductive control mode, and recording a calibration initial position; s3, calculating calibration data by rotating the motor: recording a data compensation result of the encoder by taking the original data of the encoder as an index; the calibration method does not need other equipment to drive the motor to coaxially rotate for calibration, the stator magnetic field is directly utilized to calibrate the motor, system errors caused by external equipment are avoided, the accurate relative position relation between the electron magnetic field and the rotor magnetic field can be obtained, the driving efficiency is higher, the driving dead zone is smaller, and the calibration precision is higher. And various coaxiality and roundness error data of the off-axis magnetic encoder can be improved.

The invention provides a metering data automatic calibration method and system, and the method comprises the steps: obtaining an actual measurement output value of a target intelligent sensor for a measured physical quantity in a normal operation process of metering equipment, accessing a standard reference signal outputted by an external standard device subjected to the traceability of the quantity value, reading a pre-stored standard reference value and a standard threshold value, and carrying out the calibration of the measured physical quantity. According to the actually measured output value, the standard reference value and the standard reference signal, obtaining a standardized output value through a fitting mode; when the standardized output value exceeds a standard threshold value, switching to a calibration mode, providing forward and reverse standard input quantities by an external standard device, acquiring a response signal, and calculating a nonlinear compensation coefficient and a hysteresis correction coefficient; and updating the output correction parameter according to the compensation coefficient. By adopting the scheme of the invention, the cost constraint of different error attention in measurement data calibration can be realized, and the calibration robustness is improved.

The invention provides a data calibration method and system for a high-precision direct current collector, and relates to the technical field of direct current collectors, and the method comprises the steps: integrating a traceable reference source and a temperature sensor, and building a collector calibration architecture; error calibration is carried out on the target direct current collector to obtain a collection error data set, and periodic calibration is carried out on the operational amplifier bias voltage; environment temperature values are collected in real time, and calibration time is recorded at the same time; and constructing a collector drift prediction network, and introducing the collector drift prediction network to perform data calibration on the DC optimized collector based on the temperature-time joint compensation channel to obtain a reconstruction signal calibration result. The technical problem that in the prior art, due to environment interference or long-term operation, drifting of the direct current collector can be accumulated step by step, and consequently the collection precision of the direct current collector is poor is solved, error calibration is conducted by introducing the traceable reference source and the drifting prediction network, and the precision and reliability of direct current signal collection are improved.

The invention provides a multi-parameter fusion filtering equipment health monitoring method and system. The method comprises the following steps: acquiring a filter membrane pressure harmonic component and a particulate matter concentration change rate, and aligning according to a time window to generate a characteristic matrix; calibrating a pressure component in a matrix through real-time data of a honeycomb array layout pressure sensor, and judging an effective blockage characteristic when the node detects that the pressure is abnormal; a health score and a blockage risk thermodynamic diagram are generated through probability inference in combination with the particulate matter concentration time sequence trend; and calculating a distribution deviation between the thermodynamic diagram and a real-time abnormal region, and dynamically adjusting a pressure harmonic weight coefficient and a topology verification threshold value, so that the thermodynamic diagram approaches actual distribution, and closed-loop monitoring is formed. According to the invention, dynamic sensing and closed-loop optimization of the blockage risk of the filter membrane are realized, and the multi-parameter fusion monitoring precision and the micro-blockage early warning timeliness are improved.

The invention provides a ground-air combined road slope collapse measurement system and method, and relates to the field of road slope inspection. According to the system, all-weather non-contact acquisition of millimeter-level displacement data of side slope key points is realized through a scientific-level CMOS camera of the ground detection module and a digital image correlation algorithm, and a high and steep side slope is covered; the aerial detection module carries a synthetic aperture radar and a multispectral sensor through an unmanned aerial vehicle to obtain a slope overall three-dimensional deformation field and soil humidity data. Carrying out high-precision space-time registration on the data layer by adopting a dual-function mark point and a least square method; calibrating aerial deformation data on the feature layer through ground displacement data to realize association of macroscopic and microscopic features; and constructing an improved U-Net network and a hybrid prediction model in the model layer to realize accurate tracking of the crack and prediction of the collapse probability. Visual display is carried out through a digital twin platform, and graded early warning linked with a traffic management system is triggered. According to the invention, the limitation of a single detection mode is overcome, and accurate perception, intelligent prediction and dynamic response of road slope safety are realized.

The invention relates to the field of air tightness testers, and discloses an automatic data calibration method and system for an air tightness tester, and the method comprises the steps: obtaining a temperature sensor value T, a pressure sensor value P and a humidity sensor value H from the air tightness tester; performing three-dimensional coordinate positioning in the three-dimensional coordinate space to obtain a coordinate position C1; mapping the coordinate position C1 to a distribution model for coordinate mapping by using a coordinate transformation matrix M; obtaining a compensation parameter set S1 based on the error characteristic value E and the compensation parameter combination S; adjusting the compensation weight of each environment parameter according to the compensation parameter set S1; fusing the adjusted compensation weight with the error characteristic value E and the compensation parameter combination S to obtain a comprehensive compensation coefficient Kc; and performing correction processing on the original measurement data by using the comprehensive compensation coefficient Kc. The method has the advantages that automatic extraction and dynamic adjustment of calibration parameters are achieved when the test environment changes.

The invention relates to the field of animal husbandry industry environment regulation and control system optimization, in particular to a lightweight digital twinborn breeding environment monitoring method and system, and the method comprises the following steps: S1, carrying out the construction of a computational fluid dynamics (CFD) model for a breeding farm environment; s2, environment data are collected; s3, comparing model prediction with real-time data, and monitoring a breeding environment according to a comparison result; and S4, data presentation. According to the invention, through cooperative work of the flow field modeling unit, the environment data acquisition unit, the model prediction and data calibration unit and the visualization unit, light-weight, full-range and high-precision breeding environment monitoring and regulation are realized.