281results about How to "Quick analysis" patented technology

The invention belongs to the technical field of intelligent document management and auditing in the electric power industry, and provides an electric power document autonomous review method and system fusing causal reasoning and compliance review. According to the technical scheme, obtained electric power document data is subjected to semantic analysis, and semantic representation of a document is obtained; based on the semantic representation of the document, performing event extraction on each sentence recognized in the document, and encoding each event to obtain the semantic representation of the event; constructing an initial event causal chain based on the semantic representation of the event; verifying the constructed initial event causal chain by adopting a causal reasoning algorithm, comparing each event in the verified causal chain and the incidence relation between the events with a power industry compliance rule, calculating a compliance score, and calculating the incidence relation between the events of which the compliance score is lower than a set score value or the incidence relation between the events of which the compliance score is lower than the set score value; and generating a correction suggestion, and generating a review report. And the efficiency and the accuracy of document review are obviously improved.

The invention relates to the technical field of geological disaster monitoring, and discloses a debris flow monitoring and early warning system based on Internet of Things, comprising a multi-source data acquisition module used for acquiring environmental data related to debris flow; the data transmission module is used for transmitting the environment data to a data center or a cloud end from a collection point; the data preprocessing module is used for carrying out abnormal value cleaning, time synchronization and normalization processing on the environment data; the deep learning analysis module is used for analyzing the preprocessed data so as to predict the occurrence risk of debris flow; and the dynamic early warning and publishing module is used for generating a multi-stage early warning signal according to an output result of the deep learning analysis module and publishing early warning information to a user in multiple modes. The accuracy, the real-time performance and the adaptability of the debris flow early warning system are improved through multi-source data fusion, edge calculation and a dynamic learning mechanism so as to cope with debris flow disasters in a complex geological environment.

The invention discloses an intelligent bid evaluation method and system based on a large model, and a related product, relates to the technical field of purchase bid evaluation systems, and solves the problems that an existing intelligent bid evaluation system is difficult to understand a complex logical relationship and semantic connotation and cannot provide a comprehensive and accurate scoring result. According to the technical scheme, the method comprises the steps that S1, bidding and tendering files are obtained; s2, performing disassembly processing based on the bidding and tendering file to obtain a plurality of bidding and tendering data pairs; s3, performing instruction construction on the bidding and tendering data pair based on a historical bidding and tendering database to obtain a prompt instruction of the bidding and tendering data pair; s4, processing the prompt instruction of the bidding and tendering data pair based on the large model after training and fine tuning to obtain the score of the bidding and tendering data pair, and accumulating the scores to obtain the score of the bidding file; through the method based on the large model, the scoring effect is effectively improved in the intelligent bid evaluation work, the efficiency is improved, manpower and material resources are saved, and meanwhile interference caused by human factors is avoided.

The invention relates to the technical field of leakage traceability, in particular to a water transfer project leakage traceability identification method and system, and the method comprises the following steps: setting monitoring points in a water transfer project, collecting the temperature, pressure and flow velocity data of the key monitoring points, carrying out the time sequence analysis of parameters, analyzing the water flow dynamic state and environment change in real time, and generating state monitoring data. According to the method, the environment change near the leakage is analyzed by using the state monitoring data, the abnormal change is identified through simulation comparison analysis, the leakage point is predicted and positioned more accurately, the energy state before and after the leakage is evaluated through entropy increase calculation, and the leakage position and time are further predicted accurately; by simulating energy flow under differentiated environment conditions, the accuracy of seepage path identification is improved, and more efficient seepage source positioning is realized, so that the whole seepage traceability identification process is more systematic and scientific, and the safety supervision and maintenance efficiency of water conservancy facilities is greatly enhanced.

The invention relates to the technical field of peanut oil production control, in particular to an intelligent optimization system for a peanut oil production control process, which comprises a process parameter modeling module for collecting peanut oil production parameters, performing linear combination on the peanut oil production parameters, analyzing the correlation of the peanut oil production parameters to quality indexes, and calculating the quality indexes of the peanut oil production parameters; and obtaining a process parameter mapping matrix. According to the method, through deep correlation analysis of multiple parameters in the production process, the mapping relation between the process parameters and the oil quality indexes is established, and the precision and reliability of quality control are improved. In the process control, the specific influence of each production link on the quality index is accurately reflected through standardized and linear combinatorial analysis on the parameters such as squeezing temperature, pressure, time, stirring speed and the like. By predicting the quality index under the current production condition, the response speed to the quality change is improved, so that the quality index deviation can be quickly analyzed and evaluated in real-time data monitoring.

The invention belongs to the technical field of image segmentation, and discloses a multi-modal medical image automatic segmentation method and system based on a three-dimensional reconstruction model.The multi-modal medical image automatic segmentation method comprises the steps that multi-modal image data are acquired, and local features of the multi-modal image data are extracted; identifying a patient tissue structure in the multi-modal image data based on the local features; segmenting the tissue structure of the patient in the multi-modal image data by using a segmentation technology, and reconstructing a three-dimensional virtual model based on the tissue structure of the patient; and fusing a three-dimensional virtual model body drawing result and a three-dimensional virtual model surface drawing result to realize three-dimensional display of a segmentation result. According to the method, the influence of human errors and subjective judgment is reduced by identifying and segmenting the tissue structure, so that boundaries of various tissues are identified more accurately, automatic image segmentation can be completed in a short time, and subsequent diagnosis and analysis can be performed more quickly.

The invention provides a method for quickly training an LSTM (Long Short Term Memory) model by time series data, which relates to the technical field of data processing, and comprises the following steps: S1, a data integration stage: efficiently processing and utilizing telemetering real-time stream data through Kafka and Flink, s2, a data storage stage: storing the time sequence data processed in the integration stage into a high-performance database IoTDB specially designed for the time sequence data according to a time sequence, and S3, an algorithm application stage: constructing an LSTM model, setting parameters, optimizing the LSTM model, and performing time sequence data prediction by using an LSTM algorithm model. According to the method for rapidly training the LSTM model through the time series data, the time series telemetry data generated in the test flight process are collected and processed through Kafka, real-time data of an aircraft can be rapidly captured, processed and analyzed, data transmitted by a sensor and an algorithm model are decoupled through the Kafka, data output by the sensor can be directly sent to the Kafka, and the LSTM model can be rapidly trained through the Kafka. And it is avoided that an algorithm model needs to be concerned to process data.

The invention discloses an intelligent data analysis method based on spatio-temporal big data, and belongs to the technical field of spatio-temporal big data, the method comprises the step of obtaining original spatio-temporal data of different sources in real time, and the method comprises the steps of performing feature extraction on preprocessed spatio-temporal data, including unification of a time format, spatial coordinates and a data unit, deduplication fusion and the like, so as to obtain the spatio-temporal data of different sources. According to the method, multi-source spatio-temporal data is formed, a spatio-temporal data analysis model is constructed based on deep learning, spatio-temporal dynamic changes in data can be captured, modes in the spatial data can be effectively extracted through models such as a convolutional neural network, classification is performed through cross entropy loss, high-precision spatio-temporal data analysis is achieved, and the spatial data analysis efficiency is improved through the trained spatio-temporal data analysis model. According to the method, new spatio-temporal data are analyzed in real time, abnormal modes and trend changes in the data are rapidly identified, an anomaly detection threshold value is set, model output is compared with the set threshold value, comprehensive judgment is carried out in combination with context information, and the accuracy and efficiency of anomaly detection are improved.

The invention discloses an existing building outer wall internal and external heat insulation energy consumption optimization method based on a building model, and belongs to the technical field of building design. In order to solve the problems of insufficient data comprehensiveness and incomplete thermal insulation scheme evaluation, the thermal insulation performance of a building can be evaluated more accurately by checking an outer wall structure on site, recording material types, damage degrees and the current situation of a thermal insulation layer and combining scientific methods such as thermal resistance testing and heat transfer coefficient measurement; digitization and visualization of building information are achieved through the BIM technology, historical energy consumption data are collected from multiple data sources and systematic arrangement and classification are carried out, the readability of the data is improved, rapid import and analysis can be conveniently carried out in energy consumption simulation software, and therefore the energy consumption condition of a building is reflected more accurately; according to the method, comprehensive coverage of multiple possibilities is achieved, the influence of different heat preservation schemes on energy consumption can be evaluated more comprehensively, differentiated design is conducted on the thickness of the heat preservation layer based on the energy consumption simulation result, and the heat preservation performance of a building is effectively improved.

The invention discloses a case anomaly detection method and system based on deep learning, and relates to the technical field of medical images. Comprising a data collection and preprocessing module, a multi-modal feature extraction module, a feature fusion module, a context information integration module, an anomaly detection model module, a model training and optimization module, a model iteration training and verification module and a real-time monitoring and feedback module. The method further comprises the following steps: step 1, collecting medical image data from different modalities, and carrying out denoising and standardization processing on the medical image data; 2, extracting features of different modal images by using a deep convolutional neural network, and fusing the features to form a comprehensive feature vector; 3, combining the clinical information of the patient with the fusion features to generate a comprehensive feature vector; 4, analyzing the fused feature vector through the trained deep learning model, and outputting an anomaly detection result; 5, the system monitors a new case in real time, automatically prompts abnormity and continuously updates the model according to feedback of a doctor.

The invention discloses a self-supervision enhanced semi-supervised wafer failure prediction method and system, and belongs to the field of wafer failure detection. Obtaining wafer acceptability test / probe test data to construct a training set; carrying out self-supervision pre-training on the wafer feature encoder; a pre-training wafer feature encoder is used to generate original wafer coding features of each sample, strong / weak noise is added, data enhancement constraint is introduced when the strong noise is added, and loss is calculated; using a wafer failure classifier to predict whether the wafer fails according to the wafer coding features before and after the strong / weak noise is added, and calculating consistency loss; in addition, the supervision loss of a small amount of labeled data needs to be calculated; and semi-supervised training is performed on the pre-trained wafer feature encoder and the wafer failure classifier by combining the loss, and the semi-supervised trained model is used for actual wafer failure detection. According to the method, a large amount of wafer label-free data and a small amount of wafer label data are fully utilized, and the prediction accuracy of wafer failure is improved.

The invention discloses a lightweight crack penetration degree detection method based on ground penetrating radar and Swin Transform optimization, and the method comprises the following steps: 1, collecting ground penetrating radar data, and carrying out the preprocessing and feature extraction; step 2, constructing a multi-feature fusion data set; step 3, designing a two-stage through crack detection model based on Swin Transform optimization; 4, a first-stage through crack detection model optimized on the basis of Swin Transformer-YOLOv8 is designed, and a second-stage through crack detection model is designed on the basis of Swin Transformer-YOLOv8 optimization; and step 5, training and predicting the data of the training set and the test set according to the model architecture in the step 3 and the step 4. According to the invention, the accuracy of crack penetration degree detection is improved, and a scientific basis is provided for road maintenance; the detection speed is greatly improved, and the requirement of large-area rapid detection is met; the calculation complexity is reduced, the equipment performance pressure is reduced, and the detection efficiency is improved; the generalization ability of the model is enhanced, and the method can adapt to different road conditions; and the development of an intelligent road detection technology is promoted.

The invention discloses a medicine bottle defect detection method and system based on machine vision and deep learning, belongs to the technical field of defect detection, and solves the problems that a twin defect classification network is sensitive to a highlight area caused by light reflection in appearance image information and the defect detection accuracy of the twin defect classification network is interfered in the existing method. The method comprises the following steps: constructing a defect detection model based on deep learning in combination with a YOLOV5 model, carrying out conjoint analysis detection on a time sequence image set by the defect detection model in combination with a medicine bottle simulation model, carrying out defect identification on the time sequence image set by the defect detection model, positioning a medicine bottle defect area, and carrying out defect detection on the medicine bottle. Classifying and marking defect types of the defect areas of the medicine bottles in a short circuit and random vector machine combined mode; according to the invention, the mean filter is introduced into the defect detection model, so that background filtering can be carried out on the image acquired under machine vision under the condition of light reflection of the medicine bottle, effective information of a small-size target image is effectively reserved, and the defect classification and recognition accuracy is ensured.

The invention provides a link tracking method and system for a service cluster based on log burying points, and belongs to the technical field of distributed monitoring. According to the method, a link tracking ID is generated through a snowflake algorithm at a starting point of service calling, and service IDs are distributed to micro-service nodes participating in service calling; setting log burying points at the entrance, the exit and the key logic processing points of each service according to preset burying point logic; asynchronously recording link tracking information contained in the service node through the log burying point, and uploading the information to a storage system for storage; according to the link tracking ID and the service ID in the link tracking information, the link tracking information is connected in series, a complete calling link called by the service is restored, and meanwhile a service calling topological graph is generated. According to the method, real link information can be quickly and accurately tracked, and quick retrieval and analysis of a large amount of real-time link data can be supported.

The invention discloses a method and system for analyzing high-voltage electromagnetic resonance noise of an electric vehicle, and relates to the technical field of automobile electromagnetic vibration noise, and the method comprises the steps: obtaining noise information data during the operation of the vehicle, the key parts of the vehicle comprising a high-voltage motor and a battery pack; the collected noise data are preprocessed and analyzed, and the noise data are decomposed into different frequency components. The invention further discloses a system for analyzing the high-voltage electromagnetic resonance noise of the electric vehicle. According to the system of the method for analyzing the high-voltage electromagnetic resonance noise of the electric vehicle, the high-voltage electromagnetic resonance noise of the electric vehicle can be rapidly analyzed through the automatic data acquisition and signal processing flow, the analysis efficiency is improved, and the analysis accuracy is improved by adopting an advanced signal processing algorithm and analysis technology. According to the method, the resonant frequency can be accurately identified, the resonant mechanism can be accurately analyzed, the analysis precision is improved, and the electrical system and structural characteristics of the electric vehicle are considered.

The invention discloses a method for analyzing a complex system by using a surface enhanced Raman spectrum three-dimensional code and application of the method. The method specifically comprises the following steps: obtaining SERS sensing channels with different affinity characteristics by using an unmarked or functionally-marked SERS substrate; collecting an SERS spectrum data set by utilizing the constructed SERS sensing channel, and integrating the SERS spectrum data set into a'three-dimensional code 'image through data conversion and integration of three dimensions of Raman vibration band distribution, the SERS sensing channel and SERS intensity, so as to realize imaging of the molecular landscape; the feature information in the SERS three-dimensional code is screened and extracted through a convolutional neural network algorithm, and a mapping relation between the SERS three-dimensional code and a complex system label is established, so that a complex system classification / regression model is established, rapid qualitative or quantitative analysis of a complex system is realized, and the accuracy of the SERS three-dimensional code is improved. More applications can be expanded in the fields of molecular recognition, biological sample classification and identification, disease diagnosis, cell monitoring and the like.

The invention provides a multi-mode ship intelligent identification system for coping with a complex marine environment, and the system comprises a data collection and enhancement module which is used for collecting ship pictures and corresponding auxiliary information, and carrying out the enhancement of the ship pictures; the image definition improving module is used for improving the definition of the enhanced image; the image segmentation module is used for carrying out ship identification and background separation on the enhanced picture; and the multi-modal classification module is used for classifying and identifying the ship pictures and determining ship models. Through multi-modal data fusion, an advanced image processing technology, an innovative classification model design and detailed knowledge base construction, the accuracy, adaptability and efficiency of marine ship identification are greatly improved.

The invention discloses a preparation method and processing equipment of herbal composite granules, and relates to the technical field of composite granules. Comprising the following components in parts by weight: 15-20 parts of soybean phospholipid, 10-15 parts of glutamine, 10-15 parts of L-arginine, 5-10 parts of a ginseng extract, 5-10 parts of phytosterol, 5-10 parts of xylooligosaccharide, 5-10 parts of inositol, 5-10 parts of a hawthorn extract, 5-10 parts of a blueberry extract, 5-10 parts of an acerola cherry extract, 0-5 parts of yeast beta glucan, 0-5 parts of a sea-buckthorn extract, 0-5 parts of a tartary buckwheat extract, 0-5 parts of haematococcus pluvialis and the like. The composition is innovative and breakthrough in successful application in the aspects of heart and cerebral vessels and anti-aging, and can regulate intestines, protect liver, reduce blood pressure and regulate blood fat; thrombus is melted, the vascular endothelial function is improved, and arteriosclerosis is prevented; meanwhile, the effects of resisting oxidation, resisting inflammation, resisting aging and enhancing immunity can also be achieved.

The invention provides a roof equipment maintenance accessibility calibration method comprising the following steps: calibrating node attributes of barrier grids in a grid node graph NBMap, the node attributes comprising node types and node weights; on the basis of the triangular patch set meshTriangles, node attributes of a spanning component grid are calibrated; based on the calibrated node attribute of the spanning component grid, calibrating the node attribute of the grid of the pipeline which cannot be spanned; based on the grid node graph NBMap and the initial grid, obtaining a grid node graph newBMap; based on the node weight of each grid in the grid node graph newBMap, the accessibility of each grid in the grid node graph newBMap is determined; and drawing the reachability grid plane graph in a three-dimensional space. According to the method, the reachability of roof maintenance is rapidly and automatically analyzed through an intelligent algorithm, the passing area and the obstacle area are marked, the reachable position and the unreachable position of the whole roof are given, reference is provided for subsequent scheme adjustment, maintenance route design is preliminarily completed, and cost is reduced.

The invention relates to a GH5605 cobalt-based high-temperature alloy and a manufacturing method thereof, and belongs to the technical field of metal smelting. The GH5605 alloy comprises the following chemical components: 0.05%-0.15% of C, less than or equal to 1.0% of Si, 1.0%-2.0% of Mn, less than or equal to 0.03% of S, less than or equal to 0.03% of P, 19.0%-21.0% of Cr, 9.0%-11.0% of Ni, 14.0%-16.0% of W, less than or equal to 3.0% of Fe and the balance of Co and other inevitable impurities. According to the manufacturing method, the GH5605 electrode bar is smelted through a vacuum induction furnace, refining and argon protection processes are adopted, and it is ensured that the Mn element content of the electrode bar is qualified. And in the vacuum consumable remelting process, argon with the pressure of 2000-3000 Pa is filled, so that the vacuum degree is reduced, Mn element volatilization is effectively inhibited, and section component uniformity is achieved. Detection shows that the Mn content at the edge, the 1 / 2 radius and the central part of the steel ingot meets the technical standard. The process is simple and efficient, the quality of molten steel is not affected, the performance consistency and production stability of the GH5605 steel ingot are remarkably improved, and the process is suitable for the high-end application field.

The invention innovatively provides a laser cladding processing device control system which comprises the following steps: a target extraction step: collecting to-be-processed workpiece image data acquired by a visual sensor to obtain a total data set, and performing similarity analysis on the total data set in a rough classification strategy to obtain a target detection data set; an image analysis step: training the target detection data set to obtain a plurality of to-be-processed workpiece target detection models, obtaining a dimension reduction plane through point projection according to the to-be-processed workpiece target detection models, and constructing the dimension reduction plane into a plurality of grid matrixes; a defect extraction step: according to the grid matrix, a change grid is obtained through change ratio analysis in a fine analysis strategy, and the change grid reflects a change point of the workpiece to be machined; and a defect judgment step: obtaining the change grid and judging whether the workpiece to be machined has defects or not through a state analysis strategy.

The invention provides an attack path restoration method and equipment, which can be applied to the technical field of computers. The method comprises the following steps: monitoring the running state of an application program in each server by using an RASP agent installed on each server, and collecting key data of the application program in the running process; when an attack event is detected, alarm information is generated according to the key data, and a target server having an association relationship with the attack event in the servers is determined according to the alarm information; generating a server attack path according to the interaction relationship among the plurality of target servers; and generating an attack path corresponding to the attack event according to the server attack path and each component in the target server. According to the method, the attack path of the attack event can be quickly and accurately restored.

The utility model discloses a sample transfer device for an automatic headspace sampler, which comprises a base, a vertical plate vertically mounted in the middle area of the base, a sampling mechanism fixedly arranged on the vertical plate, and a sample feeding mechanism embedded in a groove of the base and positioned below the vertical plate, the control system is used for controlling the sampling mechanism and the sample feeding mechanism to move; a sample supply frame is movably arranged on a sample feeding mechanism, and headspace bottles are arranged on the sample supply frame in order; a movable sampling needle is arranged on the sampling mechanism; the position matching of the sampling mechanism and the sample feeding mechanism is adjusted through the control system, so that the sampling needle is inserted into the headspace bottle to realize headspace sample injection analysis. The sample transferring device of the headspace sample injector is compact in overall structural arrangement, space of an instrument is saved, meanwhile, sample transferring and accurate positioning of headspace sample injection are facilitated, temperature control and pressure adjustment of a headspace bottle are achieved, and consistency of the temperature of an airtight sample injection needle is guaranteed in the sampling and sample injection process in actual detection work.

The invention relates to the field of semiconductor circuit packaging detection, and discloses a via hole welding spot tin penetration depth detection device and method based on infrared thermal imaging, and the device comprises an excitation source unit, a control system, an infrared imager, and a tested piece. A plurality of via hole welding spots are distributed on the surface of the tested piece, the infrared imager and the excitation source unit are located on the two sides of the tested piece respectively, and the excitation source unit is used for heating the surface of the tested piece; a camera of the infrared imager is aligned with a plurality of via hole welding spots on the surface of the tested piece; the control end of the control system is respectively connected with the control ends of the infrared imager and the excitation source unit, the excitation source unit can quickly heat the surface of the test piece to be tested, the infrared imager can capture and record the temperature change in real time, and the captured image is fed back to the control system; and the tin penetration depth of the via hole welding spot is obtained through processing of the control system, so that the detection efficiency of the tin penetration depth of the via hole welding spot is effectively improved.

The invention discloses a phase-locked loop suitable for amplitude-frequency modulation signal measurement and a working method thereof, and the phase-locked loop comprises a delay phase correction module which is used for carrying out the delay phase correction of a three-phase voltage signal to obtain a correction value; the FFT measurement module is used for performing FFT measurement on the correction value to obtain oscillation frequency; and the fundamental wave frequency measurement module is used for averaging the oscillation frequency and the angular frequency tracked by the phase-locked loop to obtain a fundamental wave frequency measurement value. According to the invention, an improved measurement loop is added on an existing conventional phase-locked loop to measure an amplitude-frequency modulation signal, so that the phase-locked loop can track an alternating current signal phase modulated by actual amplitude and frequency without error. The amplitude and frequency of the amplitude-frequency modulation signal can be rapidly extracted under the rotating coordinate system, the accuracy of the amplitude-frequency modulation signal measurement method based on the phase-locked loop is guaranteed, and rapid analysis and suppression of oscillation are achieved in engineering.

The invention provides a complex reactor core collaborative design system suitable for a research reactor, relates to the technical field of reactor core design systems, aims to improve the reliability of reactor core design, and comprises a model library module, a model database module, a model database module and a model database module, the model library comprises a reactor model library and an irradiation device model library; the interactive interface module is used for realizing interactive operation; the reactor core scheme design module is used for carrying out autonomous initialization design on a reactor core, and solving the problem of fuel assembly and target position loss caused by pore channel opening operation and the area demand of a newly added beryllium aluminum assembly caused by pore channel closing operation; and the reactor core scheme evaluation module is used for evaluating the reactor core. The method has the advantages of being intelligent in design, easy to operate and reliable in design quality.

The invention provides a refrigeration host health state assessment method based on assessment working condition parameter estimation and a refrigeration host. The method comprises the following steps of: 1, performing correlation degree grading on fault characteristic parameters and working environment parameters; 2, setting a working environment parameter combination under the examination working condition; and 3, establishing a membership function between the health degrees corresponding to the fault feature parameters. And 4, establishing and dynamically updating an association evaluation model. And predicting each fault characteristic parameter under the assessment working condition, and calculating a corresponding health degree. According to the method, in each detection period, a data set is updated by using newly added data, and a correlation evaluation model is re-established; therefore, under the non-assessment working condition, the updated association evaluation model is utilized to predict the fault characteristic parameters under the assessment working condition, complex data at different times and under different working conditions are unitized and unified, fault characteristic parameter changes caused by working condition differences are eliminated, and the multi-dimensional health degree can be accurately obtained under different working conditions.

The invention discloses a python language-based Excel data verification and import method, system and device and a medium, and the method comprises the following steps: S1, obtaining an Excel file, and obtaining a corresponding import parameter; s2, reading the data of the Excel file; and storing the data in a memory. S3, verifying the data of the Excel file; and verifying each row of data one by one by utilizing a rule engine technology, and recording a verification result in a log. And if the data verification is not passed, displaying corresponding error prompt information. And S4, processing a verification result, if verification is qualified, storing Excel file data into a specified database or data table, and in the storage process, enabling fields in the data table to correspond to columns in the Excel file by a system according to a field mapping relationship set by a user, so as to ensure the correctness and integrity of the data. If the verification result is not qualified, the data of the Excel file is wrongly recorded. The method has the advantage that the efficiency and the accuracy of Excel file data processing are improved.

The invention discloses an ANS-based aquaculture dynamic water quality monitoring method and system. The method comprises the following steps: data acquisition: firstly, carrying out standardization processing on acquired water quality data; model construction: an ANS water quality prediction model is constructed, an ANN network architecture is adopted, an LSTM layer is added in an ANN network to be connected between an input layer and a hidden layer, and the added LSTM hidden layer is used for extracting water quality time sequence correlation features; model training; and water quality prediction: inputting water quality data collected in real time into the trained ANS water quality prediction model, and performing water quality prediction to obtain predicted values of various water quality indexes in a future set time period. And related water quality parameters are predicted through the ANS water quality prediction model, so that the accuracy of water quality prediction is improved. In addition, the dynamic monitoring equipment polls that the fish can realize autonomous cruise in the culture lake, images and water quality information are transmitted to the intelligent terminal in real time, and accurate water quality parameters of the culture lake are provided in real time.

The embodiment of the invention discloses an image data acquisition method, a storage medium and an image acquisition device, and belongs to the field of image processing. Through a double-lens orthogonal synchronization mode, that is, when the first image sensor (sensor0) outputs half-frame data, the synchronization pulse signal is triggered to control the second image sensor (sensor1) to start to output frame data of the second image sensor (sensor1), so that accurate and synchronous acquisition of image data of the two sensors is realized. According to the synchronization mode, the problem of data coverage possibly occurring under the condition that each sensor only has a single buffer area is avoided, and data output of the two sensors is carried out alternately, so that the integrity and accuracy of data are ensured.