1752 results about "Collection system" patented technology

The invention relates to the technical field of power system simulation, in particular to a new energy power system simulation method, which comprises the following steps: S1, constructing a multi-dimensional information acquisition system, S2, constructing a new energy station model, S3, constructing a power grid control system model, S4, constructing a typical transient scene model, and S5, carrying out optimization solution and model correction. A full-chain model covering a new energy station, a power grid control system and a typical transient scene is constructed, and parameter optimization and a multi-objective decision technology are combined, so that the dynamic characteristics of the new energy power system are accurately simulated.

The invention discloses an optical fiber vibration signal time identification and classification method, system and device based on a Mam-YOLOv10 neural network and a medium, and belongs to the technical field of optical fiber communication, and the method comprises the steps: obtaining OTDR signals of a plurality of targets based on an optical fiber vibration signal collection system, and carrying out the denoising of the OTDR signals; performing short-time Fourier transform on the de-noised OTDR signal to obtain a two-dimensional time-frequency diagram of the vibration signal; based on the two-dimensional time-frequency diagram, multi-scale features of the optical fiber vibration signals are extracted; and inputting the multi-scale features into a Mam-YOLOv10 neural network containing a Mama attention block to complete identification and classification of the optical fiber vibration signals. According to the method, the influence of interference fading on the pattern recognition accuracy is effectively reduced, meanwhile, the hardware complexity is reduced, the attention weight is automatically adjusted according to different fault scenes and data characteristics, and the accuracy of optical fiber fault recognition and classification is improved.

The invention relates to the technical field of rail transit intelligence, and discloses a rail transit intelligent scheduling management method and system, and the method comprises the steps: collecting the entering and exiting data of passengers, the number of people in a waiting area, the train load factor and the platform congestion degree through an automatic fare collection system, a video monitor and a sensor of each station of rail transit; the collected passenger flow data are preprocessed, a box plot about passenger flow distribution is constructed, and sudden passenger flow fluctuation areas are identified in different time windows; a K-means clustering algorithm is adopted to classify passenger flow modes in peak periods, and the distribution type of passenger flow fluctuation is analyzed; a time sequence prediction model is constructed by adopting a Transform model in combination with weather, holidays and festivals and emergencies, the future short-term and medium-and-long-term passenger flow trend is predicted, and the train departure interval is optimized; and based on the predicted passenger flow distribution, a scheduling optimization objective function is constructed, and a reinforcement learning algorithm is combined. The method has the advantage of improving the passenger flow prediction precision in the peak period.

The invention provides a mountain power station current collection system state online monitoring method and device, and relates to the field of data processing. According to the method, distributed optical fiber data, environmental meteorological data and electrical measurement data are acquired to construct a multi-mode time sequence matrix, an operation state diagram is formed through graph structure representation and graph signal processing, a working condition mode cluster is obtained by combining dynamic clustering, a constraint diagram optimization framework is input, thermal, electrical and mechanical constraints are introduced, and an operation state track is generated. And constructing and fusing a non-stationary degradation path library and environment exposure history to form a dynamic degradation evolution model, and finally outputting in-service reliability and predicting residual life by a risk inference engine to realize online monitoring of the state of the current collection system of the mountain power station. By implementing the technical scheme provided by the invention, the accuracy of online monitoring of the state of the current collection system of the mountain power station is improved.

The invention relates to the technical field of digital twinning, in particular to a smart park digital twinning construction method and system based on big data, and the method comprises the steps: constructing a multi-source heterogeneous data fusion collection system, deploying an Internet of Things sensor in a smart park to collect data, and carrying out the data preprocessing; constructing a distributed big data storage architecture to store the collected data, and extracting data depth features in combination with machine learning and deep learning algorithms; constructing a park high-precision digital twin three-dimensional model, and accurately associating the extracted data depth features with a model entity; a real-time data monitoring mechanism is set, a message queue and edge calculation are adopted for data transmission and processing, a multi-terminal human-computer interaction interface regular evaluation model is developed, and an optimization algorithm is used for iteratively upgrading the digital twinborn body. Through full-process data driving and model iteration, digital mapping of the smart park is realized, and the management efficiency and decision scientificity of the smart park are improved.

The invention discloses an indoor water tank sediment pushing characteristic acquisition system and method, the system mainly comprises a water tank main body, a buffer unit, a drainage adjusting unit, a sediment throwing device, an imaging unit, an adjustable support and a data processing unit, and according to the method, non-contact data acquisition is carried out through a high-definition camera and a three-dimensional terrain measuring instrument; automatic identification, parameter extraction and migration speed calculation of landforms such as sand waves are achieved, the sediment bed surface is not touched in the whole process, damage to the bed surface form caused by traditional contact type measurement is eliminated, and the authenticity and reliability of data are ensured. Meanwhile, the buffer design of the combination of the flow slowing plate and the multi-stage water baffle is adopted, the kinetic energy of water flow is effectively dissipated through the graded water outlet structure, the impact force of injected water flow is greatly reduced, the bed surface is prevented from being scoured in the initial water injection stage, and the stability of the initial test condition is powerfully protected.

The invention provides an offshore wind plant current collection network topology optimization method based on an improved grey wolf optimization algorithm, and the method comprises the steps: S1, obtaining basic data of an offshore wind plant, initializing the grey wolf algorithm, and generating an initial solution set; s2, adopting polar coordinates and a minimum spanning tree to optimize and expand the initial solution set; s3, optimizing a connection mode in each group; s4, executing the optimal connection of each group of fan combination; s5, performing optimal solution set exploration on the grey wolf algorithm by adopting an operator; s6, repeatedly executing until a preset maximum number of iterations is reached, and generating a topology model of the current collection system of the offshore wind plant; the method can improve the initial solution quality and the convergence efficiency, gives consideration to the global search capability and the local optimization precision, and achieves the quick and effective processing of geometric constraints.

The invention relates to the technical field of heavy oil product treatment, in particular to a method and device for co-production of a carbon material through molten salt pyrolysis of a liquid oil product, and the method comprises the following steps: the liquid heavy oil product is put into an electric heating molten salt reactor through a continuous feeding system, and the molten salt reactor is filled with a molten alkaline molten salt medium; carrying out catalytic pyrolysis reaction on the oil product in a liquid phase environment of the molten salt medium, wherein the oil product stays in the molten salt for 5-10 seconds; the liquid oil product is uniformly cracked in the liquid phase of the molten salt to generate low-carbon hydrocarbon gas, hydrogen and dispersed fine carbon particles, and the carbon particles suspend on the surface under the buoyancy action of the molten salt and are not deposited and gathered; suspended carbon particles are collected from the surface of the fused salt in real time through a mechanical push rod continuous collection system; according to the method, continuous and stable pyrolysis of the heavy oil product and efficient and continuous separation of the product can be realized in the liquid-phase molten salt environment, the production efficiency is improved, and the stability of the product quality is ensured.

The invention relates to the field of log burying point downloading, and discloses a front-end log classified downloading method and device and a storage medium. The method comprises the steps that a log collection system collects a DOM event triggered by a user behavior, and behavior JSON data is generated; the data processing coordinator performs data filtering processing on the behavior JSON data according to a preset filtering rule to generate filtered JSON data; based on a preset classification algorithm, performing label classification processing on the filtered JSON data to obtain classified JSON constraint data; the storage system performs hierarchical encryption of metadata and content on the classified JSON constraint data to obtain encrypted data; and the transmission system receives a log downloading request, queries corresponding log data from the persistent queue based on the log downloading request, and obtains requested log data. In the embodiment of the invention, log collection, data processing and storage are integrated at the front end, so that the conditions of network delay and data loss are reduced, and the classification efficiency of the log data is improved by utilizing the classification labels for marking.

The invention provides a dynamic cloud side-end security collaborative unloading method, system and device and a medium, and belongs to the technical field of edge computing. The method comprises the steps that original data are collected through terminal equipment, differential privacy processing is carried out, and preprocessing task data with multi-dimensional feature marks are generated; analyzing the feature marks through an edge cloud gateway, and performing task grading and hierarchical mapping by using a rule engine to generate a scheduling instruction; executing corresponding security processing according to the task level and generating task result data; monitoring a node resource state in real time, dynamically adjusting a node role based on a preset condition, and updating a resource topology; collecting system operation data and dynamically adjusting a scheduling strategy through an optimization algorithm; and finally, a task result is delivered to an application end, an operation log is written into the block chain, and system configuration is continuously optimized based on historical data. According to the invention, accurate matching of tasks and resources, full-link security protection and dynamic optimization of system resources are realized, and the efficiency and security of cloud side-end collaboration are improved.

The embodiment of the invention discloses an intelligent collection system and method based on automatic measurement of fish growth data, and the system comprises a data collection module which is used for collecting fish image data, fish sound data and breeding environment data; the data transmission module is used for stably transmitting the data acquired by the sensing layer module to a data processing center through a wireless transmission technology; the data processing module is used for processing and analyzing the transmitted data and realizing fish target positioning segmentation, feature point detection, growth parameter calculation, weight estimation and growth cycle prediction; and the data management module is used for performing associative storage and visual display on the processing result and automatically generating an analysis report. According to the invention, the automation of fish growth data acquisition and analysis is realized, and the precision is greatly improved.

The invention relates to the technical field of pulse acquisition, in particular to a high-speed ADC (Analog to Digital Converter) and FPGA (Field Programmable Gate Array) coordinated extremely-narrow pulse signal acquisition system, which comprises a phase identification monitoring module, a phase lock reference updating module, a sampling permission control module, a prohibition feedback identification module and a synchronous trigger adjustment module. According to the method, a beat tolerance judgment mechanism is introduced, hyper-bound phase deviation trend statistics and frequency vector extraction are combined, beat correction is carried out by utilizing a directional hopping cumulant and a period adjustment amount, a sampling permission judgment and keeping window alignment mechanism is introduced in a multi-frame period, and a two-way judgment means of a sampling starting trigger value is adopted, so that the beat tolerance of the multi-frame period is judged. And meanwhile, centralized extraction and frequency directivity statistics are carried out on the hopping direction in the sampling prohibition time sequence, the synchronous mismatch trend is distinguished, and the initial beat position is adjusted, so that the time domain characteristics of the narrow pulse waveform are kept continuous, the edge response is prevented from deviation, the trigger structure is stable and reliable, and the overall sampling judgment is more accurate and efficient.

The invention relates to the technical field of spectrum detection, and particularly discloses a preparation method of a microstructure enhanced optical fiber and a Raman spectrometer light collection system thereof, the system comprises: a light source assembly for generating laser and performing collimation treatment on the laser to make the collimated laser irradiate a to-be-detected sample; the detection area assembly is used for placing a to-be-detected sample and positioning the to-be-detected sample; the collection assembly is used for collecting Raman scattering light generated by the sample to be detected under laser irradiation based on the microstructure enhanced optical fiber, and the optical fiber end face of the microstructure enhanced optical fiber is provided with a micro-nano structure; the geometric parameters of the micro-nano structure are determined by global optimization by using the genetic algorithm to maximize the coupling efficiency of the unpolarized diffused light in a preset wavelength range as an optimization target; and the control analysis assembly is used for carrying out signal acquisition from the collected Raman scattering light and identifying component information corresponding to the to-be-detected sample through a preset component identification model based on a signal acquisition result.

The present disclosure relates to the technical field of cleaning device and discloses a garbage collection system, including a landing assistance mechanism, a base station and a controller. The base station includes a holding section for a pool automatic cleaning device, a garbage collection device and a water flow guiding mechanism. In a case where the pool automatic cleaning device is located at the holding section, a filtering device of the pool automatic cleaning device is interconnected to the garbage collection device, and the controller is configured to control the water flow guiding mechanism to perform water spraying, so as to move garbage in the filtering device from the filtering device to the garbage collection device.

The invention provides a power collection system topology optimization method and device based on a variable weight minimum spanning tree, and relates to the technical field of offshore wind power topology optimization. The method comprises the following steps: grouping a plurality of fans based on the angle difference among the plurality of fans according to the position information of the offshore booster station to obtain a plurality of fan sets; a Delaunay triangulation method is adopted to construct a reference grid connecting line of each fan set; and based on the reference grid connection line of each fan set, generating the optimal topology of the to-be-processed offshore current collection system based on a variable weight minimum spanning tree algorithm. According to the method, the grouping clustering method, the Delaunay triangulation method and the variable weight minimum spanning tree algorithm are combined, and the topology design of the offshore wind plant current collection system is efficiently, economically and rapidly achieved. According to the invention, topological connection and cable specification type selection can be optimized synchronously, and a global optimal solution is sought between the cable path length and the type cost difference caused by the change of the current-carrying capacity, so that the fine control of the overall cost of the current collection system is realized.

The invention discloses a full-automatic condensation water collection system and method in desert, and the system comprises an environment pretreatment layer: a bionic honeycomb filter screen is combined with an electrostatic adsorption technology to filter sand and dust, a spiral pre-cooling channel is used for pre-cooling, and back flushing cleaning is automatically started every 2 hours to maintain the performance of the filter screen; in the energy supply layer, the optimal combination of photovoltaic-wind energy-heat energy three-mode power generation is dynamically calculated through an AI algorithm; photovoltaic power supply is preferentially used in the daytime, and residual energy is stored in the nitrate phase change energy storage material; wind power generation is started when the wind speed is high at night, and phase-change energy storage is used for complementing when the wind speed is insufficient; condensing the core layer: when the environment humidity is relatively high, the modified MOF material preferentially adsorbs water vapor, and switching to a condensation mode every 4 hours; the thermoelectric refrigeration sheet is started to trigger phase change condensation; the intelligent control layer is used for collecting data through a sensor, predicting future environmental parameters through an LSTM neural network and adjusting condensation power in advance; and fault early warning is carried out by combining vibration analysis and temperature gradient detection.

The invention discloses a planning method and system for a high-reliability current collection system of an offshore floating type wind power plant, and the method comprises the steps: applying a looped network topology in the current collection system of the offshore floating type wind power plant to improve the operation reliability, and enabling the looped network topology to be an electrical connection mode that a plurality of fans are connected into a closed loop through cables; wherein the energy can flow bidirectionally, and performing two-stage dynamic planning for the current collection system: firstly executing dynamic site selection and topology planning of an offshore substation, then executing optimization and topology planning of substations by fans, and outputting the optimal substation position, fan distribution set and wind power plant planning total cost. The method aims at rapidly achieving dynamic multi-target planning of the offshore floating type wind power plant so as to ensure the operation reliability of the offshore floating type wind power plant and the economical efficiency of the whole life cycle cost, precise optimization of substation site selection is achieved, and the optimal configuration of the membership relation of fans and substations is ensured.

The invention provides a power transmission and distribution equipment fault detection method and system based on deep learning, and relates to the technical field of deep learning, and the method comprises the steps: synchronously collecting operation electrical parameters, physical state parameters and appearance image data of power transmission and distribution equipment through a multi-source data collection system, and obtaining a standardized data set after preprocessing; a multi-modal deep learning fault detection model comprising a data fusion module, a feature extraction module and a fault classification module is constructed, the data fusion module adopts an attention mechanism to realize cross-modal data fusion, and the feature extraction module combines CNN and LSTM to extract space and time sequence features; then training the model by using a data set containing normal samples and various fault samples to ensure that the classification accuracy of the model reaches the standard; and finally, inputting data acquired in real time into the trained model to realize fault type identification, probability output and alarm, generating a detection report containing a fault position, and periodically updating the model to ensure generalization ability.

The invention provides a collapsed rockfall accurate identification and monitoring method and device based on AI and machine vision, and relates to the technical field of geological disaster monitoring, and the method comprises the steps: collecting the multi-modal visual data and environmental parameters of a collapse hidden danger region through a cooperative collection system; performing recognition, contour extraction and spatial parameter calculation on the multi-modal visual data through the recognition and positioning model to obtain a contour sequence, a volume sequence, a spatial coordinate sequence and a spatial attitude sequence of the collapsed rockfall; on the basis of the space coordinate sequence, the space attitude sequence and the multi-modal visual data, predicting the movement track and the speed sequence of the collapsed rockfall through a mixed time sequence AI model; inputting the environment parameters, the contour sequence, the volume sequence, the motion trail and the speed sequence into a kinetic energy calculation model, and calculating to obtain the impact energy of the collapsed rockfall; according to the contour sequence, the volume sequence, the motion trail, the speed sequence and the impact energy of the collapsed rockfall, the collapsed rockfall risk level is obtained through calculation.

Disclosed herein is a urine collection bag, system, and methods directed to automated measurement of a quantity of urine. The urine collection system can include the urine collection bag, a catheter, and flexible drainage tubing. The urine collection bag can include a collection area, force sensors, and circuitry configured to determine the volume of urine in the collection area based on pressure or weight measured by the force sensors, and the specific gravity of the urine. The catheter may include a small female external catheter (FEC) with an opening on a top side, a wicking catheter with a wicking area on a top side, a finger-mountable catheter, or a male external catheter (MEC). The tubing may be secured to a patient's leg with a stabilization device or a fabric strap. The catheter can remain on a patient while the patient stands or walks.

The invention discloses a lithium battery tab laser welding spot detection method and system, and the method comprises the steps: building a collection system of a multispectral camera, an infrared thermal imaging camera and a photoacoustic imaging module, synchronously collecting the surface optics, internal heat distribution and microstructure characteristics of a welding spot, and reconstructing the internal defect three-dimensional distribution of a preset depth; constructing a feature association matrix, verifying association between features and defects in combination with three-dimensional distribution, and outputting fusion features containing three-dimensional distribution parameters through an attention weighted fusion network; dynamically adjusting visual parameters based on the working condition parameters; detecting defects in combination with fusion features and a causal database, and outputting a process adjustment instruction in advance by a pre-judgment module; and through 3D U-Net, micro defects are segmented and graded. The method covers the full-dimension defects, improves the false defect elimination rate, reduces the defect rate, gives consideration to the detection precision and the production efficiency, and meets the high-reliability detection requirements of the lithium battery tabs.

The invention relates to the technical field of embedded systems and signal acquisition, in particular to a high-speed AD acquisition system and method based on MCU and FPGA time division multiplexing. A change-over switch is integrated in an FPGA processor, the change-over switch is used for communicating an ADC SPI interface with an SPI interface of an MCU controller in a parameter configuration stage and communicating the ADC SPI interface with main control logic in the FPGA processor in a high-speed acquisition stage, and the FPGA processor is further provided with a high-speed parallel bus interface which is used for being connected with a parallel bus interface of the MCU controller in a data reading stage. And batch transmission of the cached data is realized. Physical path isolation is achieved through the change-over switch in the FPGA processor, it is ensured that the MCU controller is completely separated from the AD control bus in the high-speed collection stage, time sequence interference and bus conflict caused by the AD control bus are fundamentally avoided, and the stability and data integrity of the collection process are guaranteed.

The invention discloses a method for evaluating voltage unbalance of a following / construction network type hybrid wind power collection system. The method is suitable for a hybrid wind power plant grid-connected scene comprising a construction network type converter (GFM) and a following network type converter (GFL). The method comprises the following steps: firstly, constructing fundamental frequency negative sequence impedance models in different access modes, and establishing a negative sequence equivalent circuit model by combining system electrical topology; secondly, the voltage unbalance degree of each confluence node is calculated through sequence component analysis; secondly, analyzing the influence rule of factors such as the number proportion of the network-forming type units, the access voltage level and the space layout on the voltage imbalance; and finally, verifying the evaluation method through a power system simulation platform to ensure the accuracy and applicability of the result. The method can be used for electric energy quality evaluation and optimal configuration analysis under the regional-level and multi-wind-power-plant grid-connected condition.

The utility model discloses a simple continuous flow microreactor device with replaceable packing. The simple continuous flow microreactor device comprises a liquid pipeline system, a gas pipeline system, a microreactor and a cooling and product collecting system, the micro-reactor is a filler type micro-reaction tube, the filler type micro-reaction tube comprises a tube body, the tube body is filled with a replaceable porous filler, and the porous filler has both a microporous structure and a mesoporous structure; filtering sieve plates for intercepting porous fillers with different sizes are respectively arranged at the upper end and the lower end of the pipe body, and are respectively connected with the material inlet and outlet joint through fixing pieces for stabilizing the fillers; a blade ring and a sealing ring are sequentially arranged between the fixing piece and the pipe body from top to bottom. The microreactor disclosed by the utility model is applied to preparation of amide compounds, and compared with a conventional microreactor, the microreactor disclosed by the utility model can obtain higher product yield.

The invention provides a normalized lane charging system and charging method for a highway toll station, and relates to the technical field of intelligent traffic. According to the method, a system lane front-end function module is arranged at the front end of a lane of a toll station and used for directly interacting with vehicles in the lane, collecting vehicle information and executing a control instruction; the edge node processing module is arranged at an edge node of a toll station level, and is used for processing transaction data and picture information from the lane front-end function module based on a virtualization technology, and carrying out collaborative management on multiple pieces of lane service data under the condition that the edge node processing module is matched with the cloud service management module; and the cloud service management module is deployed at a cloud end and is used for carrying out unified management on the charging services of the plurality of toll stations. The system can decouple business processing and equipment control by adopting a cloud-side-end system architecture, and improves the lane passing efficiency.

The embodiment of the invention discloses an intelligent data collection method and device, computer equipment and a storage medium. The data intelligent collection method is applied to the data intelligent collection system, the data intelligent collection system comprises an RPA assembly and a data processing large model, and the method comprises the steps that the RPA assembly obtains a webpage source code of a target webpage and sends the webpage source code to the data processing large model; the data processing large model determines a collection script of the RPA component according to the webpage source code, and sends the collection script to the RPA component; the RPA component performs multi-modal information collection on the target webpage based on the collection script to obtain multi-modal data corresponding to the target webpage; the large data processing model carries out data fusion and verification processing on the multi-modal data, and target webpage data corresponding to the target webpage are acquired. By implementing the method provided by the embodiment of the invention, the RPA component can dynamically adapt to the webpage structure change to automatically collect the webpage data.

The invention provides an intelligent scheduling system fusing public and social data in a data element industrial park, which relates to the field of electric digital data processing and comprises a multi-source data acquisition module, a data fusion modeling module, an intelligent scheduling decision module and an execution management optimization module. The multi-source data acquisition module is used for establishing an industrial park-oriented multi-source heterogeneous data unified acquisition system, the data fusion modeling module is used for converting multi-source heterogeneous data into a unified knowledge graph, and the intelligent scheduling decision module is used for generating an executable optimal scheduling scheme. The execution management optimization module is used for realizing landing execution, real-time monitoring and effect evaluation of a scheduling scheme; according to the system, a dynamic credibility evaluation mechanism is particularly adopted to process data conflicts, collaborative strength scoring and adaptive relaxation are introduced to optimize resource allocation, the resource utilization efficiency of an industrial park can be effectively improved, decision scientificity is improved, and technical support is provided for construction of a smart park driven by data elements.

The invention relates to an electric power collection system and method based on a Beidou satellite communication link. The electric power collection system comprises a collection terminal, a Beidou satellite and a Beidou front-end processor which are connected in sequence. The acquisition terminal comprises a pairing module which tries to establish communication connection with the terminal site at various baud rates and various communication protocols, and establishes communication connection with the Beidou satellite through a Beidou short message sending module; the data acquisition module is used for acquiring electric energy data of a terminal station; the internal storage unit is used for recording and storing the Baud rate and the communication protocol used this time in the internal storage unit, and storing the electric energy data in the internal storage unit; the time service module is used for carrying out precise time service operation on the terminal stations or the data acquisition module with the disordered clocks; the Beidou short message sending module is used for analyzing the stored electric energy data into Beidou No.3 short messages and orderly sending the Beidou No.3 short messages to a Beidou satellite according to a specified sending interval; and the Beidou satellite receives the short message and then sends the short message to the Beidou front-end processor.

The invention relates to the technical field of greenhouse cultivation, in particular to an intelligent vacuum glass thermoelectric greenhouse which comprises a vacuum glass plate, a collecting system, a circulating system and a control system. The vacuum glass plates are arranged at the top and the periphery of the mounting framework; the collecting system is connected with a vacuum glass plate at the top of the mounting framework; the circulating system is connected with the collecting system; the control system is electrically connected with the circulating system; through the vacuum glass plate integrated with the perovskite solar cell layer, the Low-E film and the microfluid channel, solar energy can be accumulated in winter, and heat can be efficiently supplied to the interior of the greenhouse in a one-way mode; rainwater can be collected and circulated in the micro-fluid channel for active cooling, meanwhile, strong light direct radiation in summer is converted into soft scattering, and the seedling cultivation environment is guaranteed. The problems that energy consumption of cold and hot regulation and control of a vacuum glass greenhouse in summer and winter is high, and the generating capacity of a traditional solar photovoltaic panel cannot effectively maintain a temperature regulation and control system are solved.

The invention provides a wind turbine generator running temperature monitoring method and system, and the method comprises the steps: installing temperature sensors at a generator, a gear box, a main shaft bearing and a cabin environment of a wind turbine generator, and collecting temperature signals in real time; filtering the acquired signal, sending the filtered signal to a reference temperature unit, and comparing the filtered signal with a standard temperature signal to obtain a deviation; calculating a compensation coefficient according to the deviation and performing temperature drift compensation on the signal; and the corrected signal is digitalized by the analog-to-digital conversion module and then input into the controller. A reference temperature unit and a compensation calculation module are arranged in an acquisition system to form an independent calibration loop. The system reads a standard temperature signal in real time and calculates the deviation while collecting the temperature signal, and then performs linear or segmented correction compensation according to the deviation, so that the measurement error of the thermocouple or the thermistor caused by environment temperature change, aging or lead resistance drift can be effectively counteracted, and the output temperature value is always kept consistent with the actual temperature.