375 results about "Feature parameter" patented technology

The present application relates to the technical field of drilling process monitoring, and particularly relates to a method for determining pneumatic impact different damage modes based on drilling progress monitoring. The method comprises the following steps: obtaining time schedule monitoring data of a drilling process; extracting a net drilling process by using an improved window energy calculation model to obtain net drilling process data; extracting first drilling feature parameters and second drilling feature parameters; determining a preliminary damage mode recognition result by using a first judgment condition; and determining an optimized damage mode recognition result by using a second judgment condition. The present application extracts a net drilling process by using an improved window energy calculation model, combines impact pressure fluctuation intensity and displacement mutation intensity parameters, constructs a damage mode recognition model, can accurately distinguish between crushing mode and cutting mode, improves result reliability through an optimized recognition process, provides data support for drilling parameter optimization, hole collapse early warning and wall protection selection, and effectively improves hole quality and drilling efficiency.

The application discloses a kind of porous metal deformation mechanism acoustic emission online identification method, device and electronic equipment, including collection porous metal material acoustic emission signal and characteristic parameter data and pre-processing, obtain each acoustic emission signal feature vector;Determine the loss function of porous metal material deformation, build acoustic emission machine learning classifier candidate model;Train multiple different parameters machine learning classifier candidate model;Evaluation and optimization are carried out, and preferred machine learning classifier model is selected;Preferred machine learning classifier model is applied to online identification of the deformation mechanism of porous metal material acoustic emission signal.This method can be combined with the loss function determined based on the distribution characteristics of acoustic emission signal of different deformation mechanisms, build machine learning classifier model, have the characteristics of not needing label data and high identification accuracy and effectiveness.

This invention relates to the field of marine information and pattern recognition technology, and discloses a method for automatic tracking and feature parameter extraction of ocean temperature fronts. The method includes: acquiring and preprocessing continuous sea surface temperature remote sensing data; constructing an adaptive multi-scale temperature gradient tensor field; automatically identifying initial seed points using a joint criterion of local extremum response and global structural saliency; generating a preliminary front through bidirectional chain growth along the main gradient direction; optimizing the front trajectory by fusing ocean dynamics priors and spatiotemporal continuity constraints; and finally extracting feature parameters such as position, intensity, direction, curvature, and lifespan. Through the above technical solution, this invention achieves fully automatic and highly robust temperature front tracking and accurate parameter extraction, significantly improving cross-scenario generalization capabilities and operational application value.

The invention relates to an electrolytic hydrogen safe operation boundary construction and application method and system based on dynamic characteristic identification, and electronic equipment. The method comprises the following steps: acquiring actually measured dynamic response data of an electrochemical device under a dynamic excitation working condition; identifying real dynamic characteristic parameters through a system identification algorithm based on actually measured dynamic response data to replace idealized dynamic setting to construct a high-fidelity security model with a coupling sub-model; a high-fidelity security boundary is obtained based on high-fidelity security model simulation; operating parameters are collected in real time and compared with the high-fidelity safety boundary, and an instantaneous risk component is calculated; when the instantaneous risk component exceeds a safety control threshold, a power limit instruction is generated to perform closed-loop limitation on the input power. According to the method, the limitation of a traditional steady-state model is broken through, the transient out-of-limit risk can be accurately predicted and intervened, and the intrinsic safety of the electrolytic hydrogen system under the fluctuation working condition is greatly improved.

The application discloses a kind of underground pipeline detection method and system based on multiple information sources, which comprises the following steps: pipeline detection system obtains the historical information of regional pipeline, arranges pipeline detection sensor;Establish detection sub-region, obtain pipeline characteristic parameter;Design regional fault detection algorithm, obtain health center point, calculate regional fault coefficient, determine fault sub-region;Pipe robot is put into fault sub-region, design adaptive fault point detection algorithm, detect fault point, record fault point position;Output pipeline detection result, notify pipeline inspection personnel;The scheme realizes the fault detection of underground pipeline by using multiple information sources, improves the detection efficiency by using the historical information of pipeline and establishing the arrangement scheme of pipeline detection sensor, divides the entire pipeline by establishing sub-region, detects each sub-region separately, improves the detection efficiency and accuracy of pipeline fault, and reduces the safety risk caused by pipeline fault.

The application provides a kind of data-driven thermal power unit equipment health early warning method and device, comprising: constructing historical sample data set;The feature engineering extraction is carried out to historical sample data set, determine a plurality of sensitive characteristic parameters of the equipment health state, and construct the equipment health benchmark baseline based on sensitive characteristic parameters;From real-time operation data, the real-time characteristic parameters corresponding to sensitive characteristic parameters are extracted;The multidimensional health deviation of real-time characteristic parameters relative to health benchmark baseline is calculated;Multi-dimensional health deviation is input into the health early warning model pre-trained, and the current equipment health state score and predicted degradation trend are output by health early warning model;Combined with the preset grading early warning rule, determine whether to trigger early warning and the early warning level triggered.The application can effectively solve the problem that the traditional fixed threshold method is poor in adaptability under variable working conditions, the false alarm rate is high, improve the equipment fault prediction ability and the intelligent level of operation and maintenance decision.

The application relates to a photovoltaic power station power generation amount prediction method and device and a photovoltaic demonstration system. Power generation data and environmental data collected by a photovoltaic power station are acquired, data preprocessing and feature extraction are performed on the power generation data and the environmental data, and feature parameters are obtained. Prediction is performed according to the feature parameters and a trained integrated model, prediction power is obtained, the integrated model is obtained by combining feature parameters and target variables in a structured training database and performing multi-algorithm weighted integrated training, the prediction power is analyzed to obtain prediction power generation amount per unit time and output, and the prediction power generation amount and actual power generation amount are updated to a historical database, and the integrated model is optimized through the updated historical database. The actual power generation data and the environmental data of the photovoltaic power station are collected for feature extraction, and the integrated model trained by using multi-algorithm weighted integration is used for prediction, the influence of environmental factors on power generation prediction is reduced, and the prediction accuracy is improved.

This invention discloses a data fusion-based method for predicting quality anomalies in a wood-based panel production line, belonging to the field of quality monitoring technology. Specifically, it includes: splicing and fusing mechanistic characteristic parameters, equipment state characteristic parameters, and time-series characteristic vectors to generate a panel quality profile vector; constructing a heterogeneous integrated prediction model; inputting the panel quality profile vector into the heterogeneous integrated prediction model for prediction to obtain panel anomaly probability values; setting a preset threshold; when the panel anomaly probability value exceeds the threshold, inputting the panel quality profile vector into a real-time interpreter to calculate an anomaly root cause feature list; integrating the panel anomaly probability value and the anomaly root cause feature list to generate a panel prediction report. This invention achieves a leap from "early warning" to "pre-diagnosis" through a data-driven intelligent prediction method.

This application relates to an automatic generation method, apparatus, terminal, and storage medium for distribution box drawings. The method includes responding to an operation command, extracting component feature parameters based on the operation command, and determining a preset box size; generating a preliminary drawing using the component feature parameters and preset drawing rules, and obtaining the preliminary box size in the preliminary drawing; performing a size verification based on the preliminary drawing and the preliminary box size to obtain a verified box size and a corresponding verified drawing; comparing the preliminary box size and the verified box size with the preset box size, and taking the one that is smaller than the preset box size and has the smallest difference between them as the final box size; and outputting the drawing corresponding to the final box size as the distribution box drawing. This application improves the accuracy of the drawings.

The application discloses a kind of power system low-frequency oscillation characteristic signal extraction methods, comprising: the electrical variation data of acquisition each generator outlet is preprocessed;Through complementary ensemble empirical mode decomposition, variation data is decomposed, and noise component is filtered out;SPA smoothing algorithm is used to process the electrical variation signal after denoising;Prony method is used to decompose the signal after smoothing, and the amplitude and phase of each frequency component are extracted;The application has more excellent noise suppression capability and signal fidelity, can effectively solve the problem of modal aliasing, can adaptively identify and filter out various noise components, and shows good adaptability to noise interference under different operating conditions of power system;SPA smoothing algorithm reduces the error introduced by complementary ensemble empirical mode decomposition while effectively retaining the key features of low-frequency oscillation;Combined with Prony method, the characteristic parameters of the oscillation signal can be accurately extracted in a strong noise environment, providing a reliable data basis for low-frequency oscillation source identification.

This application discloses a method, system, electronic device, and storage medium for generating digital human assets, belonging to the field of artificial intelligence technology, to improve the generation efficiency of digital human assets. The method includes: determining image feature parameters, action feature parameters, and voice feature parameters based on a natural language description input by a user; generating a digital human image image based on the image feature parameters; generating digital human actions based on the action feature parameters; generating voice audio based on the voice feature parameters; and generating a digital human model based on the digital human image image, the digital human actions, and the voice audio. The digital human asset includes the digital human image image, the digital human actions, the voice audio, and the digital human model.

The application relates to a method for training a text similarity model, comprising: obtaining one or more original offer text pairs; performing the following operations on each of the one or more original offer text pairs: generating a first similarity score of the original offer text pair based on a first text similarity model; extracting an offer feature parameter corresponding to the original offer text pair; correcting the first similarity score based on the offer feature parameter to generate a second similarity score by using a preset correction formula; performing floating sampling on the offer feature parameter to generate a plurality of enhanced offer feature parameters, and restoring each of the plurality of enhanced offer feature parameters to an enhanced offer text pair; and performing model training by using an enhanced training set to generate a second text similarity model, wherein the enhanced training set comprises the one or more original offer text pairs and the enhanced offer text pair generated based on each original offer text pair.

The application is suitable for the technical field of data processing, and provides a method and device for image processing, electronic equipment and storage medium, the method comprising: in response to a first operation initiated by a user, acquiring multiple images; for any image in the multiple images, determining an image order of the image in the multiple images according to a feature parameter of the image in at least one visual feature dimension; and generating an album based on the image order of the multiple images, wherein each image in the album is sorted based on the image order. In the embodiment of the application, the order of the images in the album is determined according to the difference degree between the visual feature dimensions, the similarity of the image content between adjacent images is improved, the continuity of switching between different images in the album by the user is improved, the fragmentation of the picture is reduced, and the use experience of the user is improved.

The application relates to the technical field of quantifiable test indexes of new energy vehicles, and particularly discloses a method for constructing a typical road spectrum working condition based on a genetic algorithm and new energy platform data, data acquisition, invalid data section elimination rules including static data section elimination and abnormal continuous duration elimination; data abnormal value identification rules: speed abnormal values are defined and a correction method is set; data smoothing and denoising rules: a median filter is used to preliminarily denoise a speed sequence; characteristic parameter calculation: including kinematic characteristic parameters and new energy light truck characteristic parameters; construction of an initial section library; multi-objective genetic algorithm optimization; road spectrum synthesis and post-processing: optimal sections filtered by the algorithm are spliced, and smoothing processing is carried out to ensure the continuity of a speed curve; multi-objective genetic algorithm selection: selecting an NSGA-III algorithm as a multi-genetic objective algorithm condition; the application realizes rapid construction and iteration of the road spectrum, and is high in efficiency.

Embodiments of the present application disclose a method for determining the number of effective particles, the method comprising: obtaining the total number of particles of a detection sample and pulse signals of each particle; performing waveform feature analysis based on the pulse signals to obtain waveform feature parameters of each particle, the waveform feature parameters at least including: a waveform feature type of the particle and a waveform feature value corresponding to the waveform feature type; generating a feature parameter distribution map of the particles in the detection sample according to the waveform feature type of each particle and the waveform feature value corresponding to the waveform feature type; determining an effective area of the feature parameter distribution map and the number of effective particles in the effective area. The waveform feature parameters of all the particles in the detection sample are counted to obtain the feature parameter distribution map, and the number of effective particles in the effective area of the feature parameter distribution map is further obtained, so that the number of particles that are misdetected as effective particles and not in the effective area is excluded, and a more accurate number of effective particles is obtained.

This invention discloses a peak retrieval and feature extraction method suitable for environments with strong electromagnetic interference, belonging to the field of signal processing and high-speed data acquisition technology. Due to the presence of a large amount of broadband random noise and high-frequency interference in signals under strong electromagnetic environments, the peak features of signals are difficult to extract accurately. This invention proposes a peak detection and feature extraction method based on continuous comparison. This method constructs a sliding comparison model to quickly locate candidate peaks by comparing the amplitudes of adjacent sampling points, and combines a threshold decision mechanism to remove false peaks caused by noise. Based on this, feature parameters such as peak amplitude, peak position, and pulse width are extracted. Simultaneously, a dual-RAM ping-pong cache structure is introduced to achieve alternating storage and parallel output of feature data, avoiding data processing blockage and improving system real-time performance and stability. This invention has a simple structure, is easy to implement in FPGA, and can achieve high-precision peak detection and continuous data output under high-speed sampling conditions. It has good anti-interference performance and engineering application value.

The application provides a generator oversize retainer ring bulging process parameter optimization method and system, relates to the plastic processing technical field, and the method comprises the steps of constructing a multi-source sensor array, synchronously collecting trace gas concentration field information and sealing gap change information, forming a leakage original data set and a wear original data set respectively, obtaining a leakage characteristic parameter and a wear amount parameter, constructing a high-dimensional feature vector based on the leakage characteristic parameter and the wear amount parameter, calculating bulging uniformity, wear unevenness, wear leakage coupling abnormality index and instability risk index according to the high-dimensional feature vector, determining a bulging process state category according to a multi-threshold-based judgment logic tree, and generating a corresponding process parameter adjustment strategy according to the bulging process state category. The technical problems of isolated multi-source sensing information, incomplete state representation, lagging abnormality identification and lack of closed-loop control mechanism are solved.

This invention discloses a method for comfortable anesthesia and controlled-release analgesia for daytime thoracic surgery, belonging to the field of computer technology combining computer vision and medical device control. The method involves: acquiring a first image acquisition command to control the image acquisition unit to acquire a facial region image stream of the subject at a first acquisition frequency; performing a wrinkle feature extraction operation on the current facial frame to obtain a first wrinkle feature parameter set containing contour length values ​​and grayscale gradient values; comparing this parameter set with a preset benchmark wrinkle parameter set to generate a wrinkle change offset; determining infusion control parameters from a preset control strategy mapping table based on this offset, and generating an infusion control command to instruct the infusion unit to perform the corresponding infusion action. This invention achieves refined control of the anesthesia process by real-time quantitative analysis of facial wrinkle morphological changes and automatically generating and adjusting infusion control commands.

The application relates to the technical field of tunnel engineering disaster prediction, and discloses a soft rock tunnel large deformation prediction method based on a particle swarm optimization neural network, which comprises the following steps: selecting geological construction characteristic parameters such as water content of surrounding rock and construction methods as input factors, and establishing a qualitative index and quantitative value mapping; based on orthogonal test design and numerical simulation, engineering sample data sets are constructed and normalized; subsequently, the initial connection weight and bias of an error back propagation neural network are globally iteratively optimized by using a particle swarm optimization algorithm, so that optimal initial values are obtained by taking network errors as fitness values; finally, data training is carried out to generate a mature model, and a predicted deformation value is output and combined with a double check mechanism to carry out engineering early warning. The application solves the problems that traditional neural networks are slow in convergence and prone to falling into local optimization due to random parameter initialization, and effectively improves the prediction accuracy of soft rock tunnel large deformation and the reliability of engineering early warning.

The present application relates to a kind of intelligent detection method and detection system of surface coating micron-sized pore, scheme as follows: obtain coating surface image to be detected and execute standardization preprocessing;Preprocessing image is input into trained hole profile segmentation model, and hole profile coordinates are obtained;Based on hole profile coordinates, construct hole connected region by morphological operation, and according to geometric feature, Gap region that does not need to be punched is screened;Preprocessing image is input into trained missed hole detection model, and real missed hole region is obtained;According to hole profile coordinates, calculate geometric feature parameter, determine collapse hole and calculate hole distribution density, finally output detection quality result.The present application realizes the high-precision, automation detection of micron-sized pore by the combination of deep learning model and morphological operation, geometric parameter calculation, solves the inherent defects of artificial detection, meets the high consistency, large batch fast control demand of modern manufacturing industry to surface coating quality.

This invention relates to a method for predicting ship maneuvering motions under high sea states, comprising the following steps: establishing a three-dimensional numerical model of ship-wave coupling under high sea states based on computational fluid dynamics; installing sensors on the ship to collect real-time motion data of the ship under high sea states, and preprocessing the collected data; extracting feature parameters related to the ship's six degrees of freedom motion based on the preprocessed data; using the feature parameters as input, constructing a ship maneuvering motion prediction model using a neural network model, the output of which is the prediction result of the ship's six degrees of freedom motion over a future period; training and validating the prediction model using historical data; inputting the real-time collected data into the trained prediction model to perform real-time prediction of the ship's six degrees of freedom motion; generating ship maneuvering suggestions based on the prediction results; and providing real-time feedback and correction to the model based on the comparison between actual operating data and the prediction results. This invention has the effects of improving prediction accuracy, ensuring ship safety, and improving prediction precision.

This invention discloses a joint estimation method and system for state and characteristic parameters based on maneuver intensity perception. It primarily addresses the problems of filter divergence and low parameter estimation accuracy caused by sudden changes in target maneuvering when estimating parameters for hypersonic targets in existing technologies. The implementation scheme is as follows: receiving observation data and calculating innovation; introducing a forgetting factor to adaptively update the process noise covariance, and using the innovation norm to construct a gain factor to adjust the observation weights, completing the posterior state update; calculating the sliding window length based on the adaptive process noise covariance, and constructing the arrival cost using the output of the posterior state update; transforming physical constraints into a penalty function, and combining the arrival cost to establish a rolling time-domain estimation objective function and solve for the optimal estimate. This invention can perceive maneuver intensity in real time, dynamically adjust the estimation window and observation weights, significantly improving the accuracy and robustness of the joint estimation, and can be applied to guidance information extraction and trajectory prediction for near-space hypersonic gliders.

The application relates to a one-way scanning method, device, storage medium and simulation method, which are used for layout feature parameter extraction. The method comprises the following steps: scanning all polygons in a layout, recording vertex coordinates of the polygons, and reserving vertical edges and oblique edges of the polygons; traversing the oblique edges of the polygons, obtaining intersection coordinates of the oblique edges and the vertical edges and intersection coordinates of the oblique edges and the oblique edges; determining scanning nodes after removing and sorting all the obtained coordinates, and forming scanning areas between two adjacent scanning nodes; respectively scanning the scanning areas along a first axis direction, reserving effective result edges of all the scanning areas according to a result of Boolean processing of the polygons, and constructing an effective result edge linked list according to a pairing condition of the effective result edges of adjacent scanning areas; and based on the effective result edge linked list, arranging to obtain result polygons as the result of the Boolean processing of the polygons in the layout. Through management of the effective result edges and the linked list, the layout graph scanning processing efficiency is improved.

This invention discloses a gravity field orientation adaptability analysis method based on image texture features. This method can select adaptability regions rich in gravity information, providing directional guidance for gravity field trajectory planning and effectively improving the accuracy of multi-directional gravity field matching. This invention comprehensively considers both gravity field statistical feature parameters and image texture feature parameters, fusing these two features to determine the adaptability region, making the selected adaptability region more continuous and the texture features more obvious. During dataset training, a parallel convolutional neural network is used, simultaneously training statistical feature parameters reflecting gravity field statistical features and gray-level gradient co-occurrence matrix parameters reflecting image texture features. These features are mapped to the output layer for classification, and the gravity field adaptability region is determined based on the classification results, thus achieving the evaluation of the orientation adaptability of the gravity field adaptability region.

The application discloses a fine-grained sedimentary rock facies identification method based on deep learning, relates to the technical field of deep learning and sedimentary rock facies identification, and comprises the following steps: collecting facies curve data and microstructure image data and screening characteristic parameters, generating a standardized multi-modal feature set through a special analysis engine; calling a specific model to perform hierarchical feature extraction on the microstructure image to obtain a deep microstructure feature vector; inputting the two types of features into a special network to output a preliminary identification result through cross-modal attention weight distribution; and adopting a specific algorithm to perform inversion correction and dynamic adjustment on the preliminary result, combining feedback information to construct a facies classification system to complete accurate division. Through multi-source feature deep fusion, cross-modal correlation enhancement and multi-link collaborative optimization, the application realizes efficient and accurate identification of fine-grained sedimentary rock facies, adapts to complex lithological characteristics, and provides support for technical application in related fields.

This invention discloses a method and system for judging the anti-interference threshold of power system measurement point data. The method includes: collecting raw data from power system measurement points and preprocessing it; inputting the preprocessed measurement point data into a Kalman filter model; setting a normal data threshold range and a fluctuation threshold according to the type and operational requirements of the power measurement points, and calculating the fluctuation characteristic parameters of the data; establishing anti-interference judgment rules, comparing the fluctuation characteristic parameters with preset thresholds, and distinguishing between normal data fluctuations, external interference, and real anomalies through multi-feature collaborative judgment; if interference or data anomaly is determined, triggering corresponding early warning and verification mechanisms; if the verification is correct, outputting early warning information; if the verification is abnormal, adjusting the filter parameters or threshold range. This invention can improve the accuracy and stability of power system measurement point data monitoring.