661 results about "Calibration function" patented technology

The invention relates to the technical field of inclination angle measurement sensors, and provides a calibration method and system for a high-precision inclination angle measurement sensor, and the method comprises the steps: obtaining the original output data of the high-precision inclination angle measurement sensor at a plurality of known attitude angles, so as to construct a multi-dimensional attitude mapping table, carrying out the error gravity center vector analysis of the multi-dimensional attitude mapping table, and carrying out the calibration of the high-precision inclination angle measurement sensor. After an error mapping graph is generated, boundary deviation suppression is carried out, after a correction graph is obtained, an inclination angle residual error regulation and control mapping relation is constructed, multi-dimensional partition adjustment and optimization are carried out on the inclination angle residual error regulation and control mapping relation, a residual error calibration function set is constructed, and output data of the high-precision inclination angle measurement sensor are calibrated based on the residual error calibration function set. The calibration precision of the inclination angle measurement sensor is improved from multiple dimensions, the influence of static errors and dynamic errors is effectively eliminated, the use reliability and applicability of the sensor are enhanced, and the problems that in a high-precision scene, error modeling is not accurate enough and the anti-interference capability is insufficient in the prior art are solved.

The invention, which relates to the technical field of highway traffic safety monitoring, discloses an expressway pavement ice condensation monitoring system comprising a data acquisition module for acquiring environmental data and pavement icing state information on an expressway pavement; and the self-calibration module is connected with the data acquisition module, performs self-calibration on the data acquisition module according to the environment data acquired in real time and the road surface icing state information, and corrects sensor errors caused by external environment factors. According to the highway pavement ice condensation monitoring system, a self-calibration function is added in monitoring equipment and an intelligent algorithm is introduced, so that the monitoring system can automatically correct measurement errors caused by external environment changes in real time, and a machine learning model is combined to predict pavement conditions more accurately; the working stability of the system in severe weather can be improved, and the risk of icing of the road surface can be found earlier, so that more accurate early warning information is provided for a traffic management department, and the probability of traffic accidents is reduced.

The invention discloses a dexterous grabbing method and system for a robot, and aims to solve the technical problems that an existing robot grabbing system is high in dependence on hand-eye calibration precision (especially translation vectors), and the grabbing capacity of objects without priori knowledge is limited. According to the method, a reference-transformation-correction control framework is provided, the pose of an unknown object is accurately recognized through a multi-stage visual segmentation strategy, and a preliminary grabbing target is generated based on the reference relation of one-time teaching; most importantly, the system starts closed-loop visual servo correction, and iteratively corrects the position by detecting the real-time pose of a tail end visual mark, so that translation errors in hand-eye calibration are eliminated, and high-precision alignment is realized; in addition, the system also integrates the functions of object posture adjustment and rapid rotation calibration. Through cooperative work of open-loop target generation and closed-loop position correction, dependence on hardware accurate calibration is effectively reduced, and the grabbing success rate and robustness are improved.

The invention discloses a seeding unit integrating visual feedback and calibration functions and a control method, and relates to the technical field of agricultural machinery, the seeding unit comprises a control system, a row spacing adjusting mechanism and a seeding depth control mechanism, the seeding depth control mechanism is connected with the row spacing adjusting mechanism, and the row spacing adjusting mechanism is connected with the control system; the control system is composed of an industrial camera and an image recognition module, the image recognition module comprises a broken ridge prediction control mechanism and a ridge center line fitting and sowing offset correction mechanism, and the ridge center line fitting mechanism recognizes ridge line boundaries and fits center line tracks. The broken ridge prediction control mechanism detects a ridge line interruption area and delays ridges according to the advancing speed and response of the seeding monomers. According to the seeding monomer integrated with the visual feedback and calibration functions and the control method, the visual identification technology is integrated to monitor the earth surface condition in real time, the response is quick, the control is accurate, and the seeding monomer is suitable for high-speed seeding operation under different terrain and soil conditions.

The invention belongs to the technical field of eddy current sensor calibration, and discloses an eddy current sensor for a high-temperature environment and a calibration method thereof. The method comprises the following steps: synchronously acquiring working current, voltage, surface position, temperature, standard displacement signals and original output voltage of an eddy current sensor, constructing an oxide layer equivalent circuit model, and optimizing to obtain thickness distribution; building a thickness increase model, and building a correlation model to calculate time-varying impedance; calculating a sensitivity coefficient function, and designing a piecewise calibration function to obtain a calibration parameter set; and finally, dynamically compensating the original output voltage in combination with the calibration parameter set to obtain the calibrated displacement. A temperature field, a standard displacement signal and an original voltage signal are collected, a temperature-oxide layer-impedance three-dimensional dynamic model is established, and the nonlinear influence of oxide layer growth and temperature gradient is compensated in real time.

The invention discloses a rocker output and shaft self-calibration device and method of an unmanned aerial vehicle control terminal, the rocker output and shaft self-calibration device is composed of a rocker information acquisition unit, a rocker signal processing unit and a characteristic parameter storage unit, and zero calibration and extreme value calibration are executed when a rocker is started each time. After the rocker is calibrated, the information processing unit stores special parameters such as the zero position and the extreme value of the rocker into the data storage unit, and the special parameters are used for follow-up rocker processing including amplitude limiting, filtering, dead zone processing and output mapping. The device can reduce the drifting of the output result of the rocker caused by the aging of a rocker device, the voltage attenuation of a control terminal and the continuous friction loss between the mechanical structures of the rocker. The calibration device has no special requirements on rocker types, can be basically suitable for various rockers, is a rocker output and self-calibration device of an unmanned aerial vehicle control terminal with a self-calibration function and good universality, and can realize miniaturization, low cost and fitting engineering practice as much as possible by selecting a proper MCU (Microprogrammed Control Unit) chip.

The invention relates to a power cable insulation state real-time monitoring and alarm device, and belongs to the technical field of power equipment state monitoring. Comprising a multi-source sensing unit which is installed at a cable body and a joint; the edge computing terminal is fixed in the cable well or the ring main unit; and the cloud early warning platform receives the processing data and outputs an alarm instruction. According to the invention, multi-parameter deep fusion is realized, four-dimensional monitoring of grounding current, temperature, partial discharge and humidity is initiated for the first time, and limitation of a single parameter is broken through; and an insulation health index IHI is proposed, and the insulation deterioration degree is quantitatively evaluated. According to the method, tan delta and IHI are calculated on site through an edge-cloud collaborative architecture edge terminal, so that the data transmission quantity is reduced; the cloud dynamic threshold value is adjusted, and the alarm accuracy is improved. According to the invention, intelligent early warning mechanism three-level alarm linkage protection equipment is arranged; and the self-calibration function ensures long-term reliability.

The invention relates to a calibration method, device and equipment of a laser scanning galvanometer performance detection device. The method comprises the steps that a laser is controlled to emit laser, a rotating table and / or a scanning galvanometer are / is controlled to rotate until a position sensitive detector detects that a light spot of the laser is located at a preset zero point position, and the deflection angle of the rotating table is determined as an initial angle; determining an angle range based on the initial angle and a preset angle, controlling the rotating table to rotate in the angle range, and obtaining light spot positions detected by the position sensitive detectors at multiple angles in the angle range; based on the light spot positions at the multiple angles, calibration parameters in the target calibration function are solved; the solved target calibration function is used for carrying out performance detection on the scanning galvanometer. By adopting the method, the laser scanning galvanometer performance detection device can be automatically calibrated.

The present application belongs to the technical field of wireless communications and radar systems. Disclosed are a dual-band fusion and multiplexing frequency source, chips, a radio-frequency transceiver, a system, and a device. The system comprises: a full-function millimeter-wave CMOS 4+1 phased array chip, which is connected to an antenna end, and is used for realizing signal processing and frequency conversion between a millimeter-wave signal and a C-band intermediate-frequency signal, performing phase control and gain adjustment on the millimeter-wave signal, and providing an internal frequency source and a calibration function; a C-band front end, which is connected to the antenna end, and is used for receiving or transmitting a C-band signal; a C-band / intermediate-frequency transceiver multiplexing chip, which is used for performing frequency conversion between a C-band or intermediate-frequency signal and a baseband signal in a multiplexing manner, and performing signal processing and gain control on the C-band intermediate-frequency signal; a dual-band fusion and multiplexing frequency source, which is used for providing a local oscillator signal; and an all-digital control logic circuit, which is used for providing a control instruction. The present application improves the efficiency and performance of dual-band joint communications.

The invention discloses a calibration device with a spectrum self-calibration function and a high-resolution spectrum calibration method thereof. The device comprises a narrow-band light source, a broadband light source, an optical fiber isolator, a coupler, an interference system, a multi-way switch, an FP (Fabry-Perot) cavity, a collimator, an orthogonal dispersion system and a computer, wherein the orthogonal dispersion system consists of a cylindrical lens, a reflector, a virtual phase array, a grating, a focusing lens and an industrial camera; according to the device, different light source paths are gated, FP cavity modulation and orthogonal dispersion system light splitting are utilized, and an industrial camera is combined to receive light signals. According to the method, the mapping relation between pixels and wavelengths can be established, the two-dimensional spectrum is compressed into the one-dimensional calibration spectrum through light intensity modulation and normalization processing, the calibration process of the orthogonal dispersion system is simplified, and the measurement precision is improved; and system drift can be compensated in real time through self-checking calibration, and the reliability of a measurement result is ensured, so that accurate calibration and measurement of a high-resolution spectrum can be realized.

The invention discloses an in-situ automatic calibration system and method for a multi-channel temperature acquisition instrument. The system comprises a metering port, a change-over switch, an upper computer, a multi-channel change-over switch and a standard signal source. The metering port is connected with the multi-channel change-over switch and is used for calibrating the temperature acquisition instrument; the change-over switch is connected with the acquisition circuit board and is used for switching a measurement mode and a calibration mode, in the measurement mode, the acquisition circuit board is connected with the measurement port, and in the calibration mode, the acquisition circuit board is connected with the metering port; the multi-channel change-over switch performs channel switching under the control of the upper computer, the standard signal source is connected with the multi-channel change-over switch and is used for outputting a preset standard electric signal to the metering port, the acquisition circuit board acquires the electric signal and converts the electric signal into a digital signal, and the master control digital board processes the digital signal and transmits the digital signal to the upper computer. According to the invention, a metering calibration function is added on an original temperature acquisition instrument, so that on-site rapid calibration of the multi-channel temperature acquisition instrument can be realized.

The invention provides a force and acceleration composite sensor with a calibration function and a working method, and belongs to the field of composite sensors, the force and acceleration composite sensor with the calibration function comprises a test base, the test base is provided with a test through hole, and the test through hole is provided with a mounting hole; a pressure sensitive diaphragm II and a pressure monitoring core body are mounted in the mounting hole; an impact head limiting and fixing upper base is mounted on the test base, an impact head is mounted in a sliding through hole of the impact head limiting and fixing upper base, a first pressure sensitive diaphragm is arranged at the lower end of the impact head, and an acceleration monitoring core body is mounted at the lower end of the first pressure sensitive diaphragm; a third pressure sensitive diaphragm is installed at the bottom of the test through hole, a calibration base is arranged at the lower end of the test base, a calibration groove is formed in the calibration base, and a standard pressure sensor and a tested pressure sensor can be installed on the side wall of the calibration groove. The device has the beneficial effects that the device has multiple advantages of synchronous monitoring of force and acceleration, flexible impact resistance and integrated calibration.

The invention provides an intelligent voltage monitoring system with an adaptive calibration function, and relates to the technical field of data processing. An environment monitoring module; the intelligent drift modeling module is used for training associated data based on a neural network model, learning a nonlinear drift rule under a multi-factor coupling condition and constructing a drift prediction model; the prediction calibration module is used for generating a calibration vector for uncollected original voltage data, and performing dynamic superposition calibration in a real-time sampling process to generate prediction calibration voltage data; the closed-loop self-learning module is used for extracting a deviation trend based on the periodic deviation of the predicted calibration voltage and the reference voltage, and carrying out online updating on the drift prediction model according to the deviation trend; the application output module is used for providing the predicted calibration voltage data to a control unit of the power equipment; according to the invention, the autonomy and accuracy of intelligent voltage monitoring are improved.

The utility model relates to an organic carbon element carbon monitoring system and an automatic standard solution dropwise adding device thereof, and belongs to the technical field of carbon detection. The organic carbon element carbon monitoring system comprises a heating furnace and a control system, an optical channel is located in the heating furnace, a sampling filter membrane is arranged in the optical channel, and a detector is arranged at an outlet of the optical channel; the device for automatically dropwise adding the standard solution comprises a first branch pipe, a quantitative pipeline and a carrier liquid supply pipeline, wherein the first branch pipe is used for extending into a heating furnace; the quantitative pipeline is used for providing quantitative standard solution; the carrier liquid supply pipeline is used for providing carrier liquid; the input end of the first branch pipe is communicated with the output end of the standard solution quantitative pipeline; the output end of the carrier liquid supply pipeline is communicated with the input end of the standard solution quantification pipeline, and the carrier liquid supply pipeline is used for driving a quantitative standard solution to a reaction area of the organic carbon element carbon monitoring system. According to the device, the measurement of carbonate carbon in the ambient air particulate matters is realized. The automatic titration calibration device avoids the influence of manual operation, has an automatic titration calibration function and is good in repeatability.

The invention discloses a dual-lens laser particle analyzer with an automatic calibration function. The dual-lens laser particle analyzer comprises a lead-in assembly, a shaking assembly and a mist brushing assembly, the introduction assembly is used for mixing and introducing to-be-measured particles and a water source, the shaking assembly is used for continuously shaking the particles of a to-be-measured mixed solution so as to ensure that the particles are uniformly dispersed, and the mist brushing assembly is used for brushing away mist which is generated on a lens due to too high humidity and interferes with the laser measurement degree. Through the combination of the first fixing plate, the first fixing shaft, the fixing ring and the torsional spring, the first sample pool can flexibly shake within a certain range, the motor drives the reciprocating lead screw to drive the toothed plate to move, the first sample pool can shake and swing, and through the continuous and diverse movement mode, the detection accuracy is improved. The uniform distribution of the particles in the solution is ensured, the interference of particle precipitation or aggregation on the measurement result is avoided, and the accuracy of measuring the particle size by the laser particle analyzer is obviously improved.

The invention discloses a soil humidity inversion method and device, a medium and equipment, and relates to the technical field of microwave remote sensing inversion. According to the method, the total backscattering coefficient, the normalized vegetation index, the leaf area index and the average leaf inclination angle of the electromagnetic waves of the target area pixel by pixel are obtained in combination with microwave remote sensing data and atmospheric apparent reflectance data of the target area; according to the normalized vegetation index, the leaf area index and the average leaf inclination angle, spatial clustering is carried out on vegetation, spatial heterogeneity of crop types is captured, and then based on the constraint that the surface roughness parameters and the vegetation parameters of the same vegetation type are the same and the soil humidity in the same surface space window is the same, the spatial heterogeneity of crop types is obtained. Through two-stage iteration inversion of the intra-class scale and the ground surface space window scale, the time dynamic state is adapted, the parameter calibration function of the in-situ soil humidity data is replaced, and the model parameters and the soil humidity can be determined without the in-situ soil humidity data. According to the invention, the accuracy and reliability of the soil humidity inversion method are improved.

The invention relates to an optical distance measuring device with an automatic calibration function and a measuring method thereof, and relates to the technical field of measuring devices.The optical distance measuring device comprises a base, a calibration piece is arranged on the base, a liftable supporting plate is arranged above the base, and a laser range finder and a measuring plate which are opposite to each other are arranged on the supporting plate; the device further comprises a probe assembly, a moving assembly, a follow-up air injection assembly and a follow-up marking assembly, the follow-up marking assembly is connected to the probe assembly, and the probe assembly makes contact with and extrudes the measuring face, so that the follow-up marking assembly automatically marks the uneven position of the surface. When the uneven position is detected, the marking coating is sprayed out of the annular spraying pipe by extruding the second air bag, the uneven position is marked in real time, marking is convenient and rapid, the time and energy of manual marking are saved, the uneven position which is automatically marked is convenient for workers to directly observe, and the efficiency of follow-up repairing or processing work is improved.

The invention discloses a comprehensive monitoring platform for an auxiliary system of an intelligent substation, and the platform comprises a sensing layer which is provided with diversified sensors and is used for collecting the operation state, environmental parameters, security and protection information and fire-fighting information of equipment in the substation in real time, and the sensors have the self-diagnosis and self-calibration functions; the edge computing layer is composed of a plurality of edge computing gateways; the cloud platform is used for carrying out deep fusion, storage, analysis and intelligent decision making on the data uploaded by the edge computing node; and the application layer is used for providing an interactive interface and a functional module for a user, and the user can log in the technology through various terminal devices. Through a multi-level architecture and an intelligent analysis technology, comprehensive perception, intelligent analysis and automatic control of equipment states are realized, faults are predicted in advance, downtime is reduced, and reliability and stability of a power system are improved. The response time is shortened by an intelligent linkage strategy and an edge computing local decision-making mechanism, sudden safety events and equipment faults can be quickly handled, and accident loss is reduced.

The invention discloses a pinch roll gap cascade control system with an automatic calibration function. The pinch roll gap cascade control system comprises a hydraulic module, a detection module and an upper computer, the hydraulic modules are arranged on the two sides of the pinch roll device. The detection module is arranged on the hydraulic module; the upper computer is connected with the hydraulic module and the detection module. The invention further discloses a pinch roll gap cascade control method with the automatic calibration function. The invention provides a control system which is good in pinch roll gap adjusting effect and considers automatic calibration in the high-precision steel plate production process.

The invention relates to the technical field of dead pixel detection and compensation of a digital light processing projection system, in particular to a DLP dead pixel calibration and compensation method and system based on a Transform attention mechanism. According to the DLP dead pixel calibration and compensation method based on the Transform attention mechanism, a multi-scale feature pyramid is constructed, global features are extracted by using a layered multi-mode Transform encoder, and a dead pixel confidence coefficient heat map is generated in combination with a dynamic sparse mask multi-head attention mechanism; dynamically selecting compensation strategies for different types of dead pixels by adopting a dead pixel type-scene demand dual-drive time-space domain compensation pipeline; ambient light and partition temperature sensor data are integrated, and the influence of optical crosstalk and thermal drift is eliminated through a brightness adaptive calibration function; and finally, carrying out closed-loop verification and iterative optimization by adopting a loss function fused with HVS perception loss. According to the method, the defective pixel detection precision is improved from 82.3% to 99.2%, the PSNR after compensation is improved from 32.6 dB to 42.5 dB, the processing delay is reduced to 7ms / frame, and the visual quality and reliability of a DLP system are improved.

The invention discloses a radar and photoelectric equipment detection error solving method. The method comprises the steps of S1, radar and photoelectric equipment base levelness error detection, S2, equipment orientation and pitching zero position reference error detection, S3, radar reference error detection, S3, radar and equipment angle detection, S4, error matrix fitting, S5, error value correction and S6, error correction. According to the radar and photoelectric equipment detection error solving method, a measurement tool, a calibration device, an unmanned aerial vehicle and carrying equipment are finely prepared and calibrated, the accuracy of a measurement result is ensured, in the step S3 and the step S4, collected error data are processed, an angle error matrix is constructed, and the accuracy of the measurement result is ensured. The generalization ability of the fitting model is evaluated by adopting technical means such as cross validation, all angle ranges needing to be measured are comprehensively covered by planning flight paths in different directions, heights and distances, error data are obtained, model parameters are optimized, an angle error calibration function is obtained, and the effectiveness and accuracy of the angle error calibration function are evaluated through verification.

The invention provides a calibration method, device and equipment for a digital electric energy meter with a self-calibration function, and the method comprises the steps: obtaining a to-be-detected pulse electric energy signal and a standard electric energy pulse signal which are inputted to the digital electric energy meter in real time, and carrying out the preprocessing of the signals, and generating an error sequence; performing multi-scale coarse graining processing on the error sequence to generate a coarse graining sequence based on different scale factors; calculating a sample entropy value of each coarse graining sequence, generating entropy spectrum characteristics, and identifying frequency components based on an error source in the entropy spectrum characteristics; and realizing calibration of the digital electric energy meter based on the frequency components and the corresponding calibration weights. Through a multi-scale entropy analysis technology, multi-scale quantization of error signal complexity is realized, and the limitation that a traditional single time window comparison method cannot distinguish frequency characteristics is overcome.

The utility model relates to the technical field of pad printing processing, in particular to a multi-station pad printing device with a calibration function. Comprising a base, a transfer printing module, a second linear moving module, a rotating platform and a visual assembly, the transfer printing module is arranged on the base and comprises a first linear moving module, and the first linear moving module is connected with a plurality of transfer printing heads; the second linear moving module is arranged on the base and located below the transfer printing module, the rotating platform is arranged on the second linear moving module, and a jig is arranged on one side of the rotating platform; the visual assembly comprises a camera, a memory and a display screen, the camera is arranged on the second linear moving module or the base, the jig can move to the position corresponding to the camera, the memory is used for storing images, and the display screen is used for displaying image information. The problem that in the prior art, a transfer printing device lacks reference during machining, and consequently the machining precision is affected is solved.

The invention relates to an automatic temperature compensation system of a pressure transmitter, which comprises a plurality of modules such as the pressure transmitter, a temperature sensor, a signal conditioning circuit, a microprocessor and the like, the temperature sensor is arranged in a measured pipeline to obtain a temperature signal, and the signal conditioning circuit is used for conditioning the signal; the microprocessor receives the conditioned signals and compensates the temperature according to parameters of the pressure transmitter, three-dimensional temperature field modeling and analysis functions are achieved, the self-adaptive learning module adjusts a compensation strategy through a biological heuristic algorithm according to the environment and the measured data history, and the display module displays related temperature data. The storage module stores various data, adopts a symmetric encryption algorithm to encrypt and has a data redundancy function, the environmental parameter sensor collects environmental data and high-precision and high-frequency collection and has a self-calibration function, the communication module transmits the data, and an internal quantum encryption communication sub-module ensures transmission safety. According to the invention, the temperature can be accurately compensated, the pressure measurement precision is improved, and the data safety and the system adaptability can be guaranteed.

The invention is suitable for the technical field of optical fiber precision machining and integrated manufacturing, and provides an optical fiber array arranging and bundling device and an arranging method.The optical fiber array arranging and bundling device comprises a main body assembly, a circular disc body and a U-shaped groove body, the main body assembly comprises two bases and a vertical plate installed at the tops of the two bases, and a gap is formed between the two bases; the device solves the problems that a manual arrangement method is low in efficiency and consumes a large amount of time and manpower, optical fibers are prone to dislocation due to factors such as manipulation differences of operators and visual fatigue, and application requirements of mass production and multi-core precise layout are difficult to meet. According to the device, the angle-adjustable supporting seat is arranged to be matched with the positioning protrusions placed on the flexible board, pre-arrangement positioning of optical fibers is achieved, the automatic clamping and transferring actions of the transferring assembly and the angle calibration function of the positioning mechanism on the circular disc body are combined, the dislocation problem caused by human factors in manual arrangement is avoided, and the accuracy of arrangement of the optical fibers is improved. And meanwhile, human input and time consumption are reduced.

The invention provides a three-dimensional rotary table with an internal heat source and a high-precision temperature calibration function, which comprises a working table top, a pitching device, a rotating device, a lifting device and a base, and is characterized in that the pitching device comprises a driving shaft fixedly connected with the bottom of the working table top and a pitching driving assembly for driving the driving shaft to swing; the rotating device comprises a rotating plate fixedly connected with the pitching driving assembly and a rotation driving assembly driving the rotating plate to rotate, and the lifting device comprises a lifting table fixedly connected with the rotation driving assembly and a lifting driving assembly fixedly arranged on the base. The three-dimensional rotary table further comprises a hot air gun and a high-precision surface source black body, wherein the hot air gun is fixedly arranged below the working table top, and an air outlet of the hot air gun is aligned with the working table top. Heating and temperature calibration of a measured object are achieved through the integrated internal heat source and the high-precision surface source black body, the space utilization rate and the load capacity are improved through the modular layered design, meanwhile, the disassembly and assembly maintenance space is sufficient, and the maintenance cost is reduced.

The invention provides a bidirectional energy buffer system based on a farad capacitor bank, and relates to the technical field of robot working power control, and the system can intelligently switch between energy storage and release through integrating the farad capacitor bank and an advanced bidirectional DC-DC conversion technology, and effectively cope with the rapid change of load power. An intelligent control framework with a micro-control unit as a core is introduced, signal conditioning and bus communication functions are combined, and accurate regulation and control of power flow are achieved. In the operation process, the power response speed can be remarkably increased, energy generated during braking of the motor can be reused through a unique energy recovery mechanism, and therefore the overall energy efficiency is improved. In addition, the system also has an automatic parameter calibration function, so that the performance is further optimized.

A system for monitoring and responding to medical emergencies in high-humidity environments includes a processor, a memory storing computer-executable instructions, and a sensor array comprising motion detection, fall detection, and vital signs monitoring. The sensor array includes a steam-adaptive calibration configured to adjust detection thresholds based on vapor density and humidity levels. A privacy-preserving architecture processes non-identifiable inputs such as motion signatures, radar signals, or acoustic triggers without storing visual or audio recordings. When inactivity, collapse, or absence of respiration is detected for a predefined threshold period, the privacy-preserving architecture initiates a first notification to staff interface and response tools. If the first notification is not acknowledged within a predetermined escalation period, a secondary notification is transmitted. The system operates in real time to provide emergency alerts while preserving occupant privacy.

The invention relates to a robust federated learning method and device based on a federated probability Shapley value, and the method comprises the steps: constructing a utility function for a prediction probability and a preset calibration function of a verification set based on a global model; the prediction probability is the same prediction probability of the prediction label of the data in the verification set and the actual label; receiving target data uploaded by the client in each round; based on the target data, determining a local federal probability Shapley value of the current round of the client through a utility function; determining a weight corresponding to the client based on the local federation probability Sharpley value of the current round; and updating the global model based on the weight corresponding to each client, updating the local training model of each client based on the updated global model parameter, and carrying out the next round of federated learning until an iteration condition is reached. Through the method and the device, the problem that federated learning lacks robustness is solved, contribution of each client in model training is effectively evaluated, and the robustness of federated learning is improved.

The invention relates to the technical field of radio frequency, and discloses a differential phase self-calibration single-power-supply variable gain distributed balun circuit which comprises a differential phase calibration module, an ultra-wideband matching gain adjustment module and a distributed balun amplifier core module connected with the differential phase calibration module and the ultra-wideband matching gain adjustment module. On the basis of a traditional differential-to-single-ended distributed balun circuit, the defect that a traditional distributed balun needs multiple sets of power voltages is overcome by only needing one set of power voltages, and meanwhile, the distributed balun circuit provided by the invention also has a digital gain calibration function, so that the balun has a higher degree of freedom in use. In addition, a differential signal self-calibration circuit is further used, and it is guaranteed that the phase error of balun differential input is minimized.