43results about How to "Achieve high-precision forecasting" patented technology

The invention provides a capacity attenuation trend prediction method of a low-temperature lithium battery, and relates to the technical field of battery health management and prediction. The capacity fading trend prediction method of the low-temperature lithium battery specifically comprises the following steps of S1, initial data acquisition, S2, feature extraction, S3, hybrid prediction model construction, S4, model training and offline verification, S5, online deployment and dynamic correction, and S6, SOH evaluation and early warning output. A hybrid prediction model is constructed by fusing an electrochemical mechanism and deep learning, so that high-precision prediction and full-life-cycle intelligent health management of lithium battery capacity fading in a low-temperature environment are realized, and the problems of accelerated battery aging and prominent safety risk in an alpine region are effectively solved; early warning and intelligent management of the health state of the battery can be realized, and the service life of the battery under low-temperature application can be prolonged.

The invention relates to the technical field of biological detection, and discloses a caenorhabditis elegans reproductive toxicity intelligent evaluation system and an application method.The caenorhabditis elegans reproductive toxicity intelligent evaluation system comprises a standardized exposure and imaging module used for executing a high-flux pollutant exposure experiment under a controlled environment condition and synchronously collecting nematode behavior and gonad image data; and the multi-modal data acquisition unit is connected to the standardized exposure and imaging module and is used for extracting and preprocessing behavioral parameters and reproductive toxicity indexes from the acquired images. According to the method, 12 behavior parameters and 8 core reproductive indexes are automatically extracted by constructing a multi-modal data acquisition unit and utilizing an improved U-Net model and a specific algorithm, so that full-process automation from image acquisition to key index quantification is realized. The problems of low efficiency, large subjective deviation and poor repeatability caused by dependence on manual interpretation in the prior art are solved, and the objectivity of the evaluation result and the high-throughput screening efficiency are remarkably improved.

The invention discloses a pressure-bearing equipment welding residual stress distribution prediction method based on structural constraint, and belongs to the technical field of welding residual stress distribution prediction. The method comprises the following steps: S1, acquiring welding residual stress distribution data of a flat plate workpiece of the pressure-bearing equipment under different parameters; s2, longitudinal residual stress distribution data in the vertical welding line direction and the thickness direction are extracted, and the influence rule of all main parameters on longitudinal residual stress distribution is qualitatively analyzed; s3, establishing a residual stress distribution prediction model suitable for the flat plate workpiece of the pressure-bearing equipment in the vertical welding line direction and the thickness direction; s4, carrying out bending constraint correction on the residual stress distribution prediction model of the flat plate workpiece of the pressure-bearing equipment along the vertical welding line direction and the thickness direction; and S5, residual stress prediction is carried out on the actual pressure-bearing equipment flat plate workpiece or cylinder workpiece by using the corrected prediction model. According to the method, high-precision prediction can be carried out on the welding residual stress distribution of the thick-wall pressure-bearing equipment.

This invention discloses a method for predicting the remaining life of brake friction pads, belonging to the field of brake life prediction. The method includes the following steps: S1, obtaining an initial effective feature set based on Pearson correlation coefficient and strong wear correlation features; S2, constructing a multi-physics coupled nonlinear wear degradation model for the friction pads and outputting multi-physics degradation parameters; S3, obtaining the optimal low-dimensional feature set through dual-source fusion; S4, optimizing the hyperparameters of the hybrid basis learner group using a dynamically perturbed improved gray wolf algorithm; S5, constructing a weighted fusion remaining life prediction model and completing accuracy evaluation and error correction; S6, online adaptive updating to achieve real-time remaining life prediction and life threshold warning. Using the above-mentioned method for predicting the remaining life of brake friction pads, high-precision prediction of the entire life cycle of brake friction pads through online dynamic adaptive updating is achieved, significantly improving prediction reliability and engineering application value.

The application discloses a kind of virtual marshalling train's tracking operation safety protection method and system, it is related to urban rail transit management technical field.The application includes: obtaining the historical data feature set of leading train and the actual acceleration of leading train in the historical operation process of virtual marshalling train.The historical data feature set is input into acceleration prediction model, and the predicted acceleration of leading train is obtained.The error of the predicted acceleration of leading train and the actual acceleration of leading train is minimized as the goal, and the acceleration prediction model is trained, and the trained acceleration prediction model is obtained.Real-time data feature set is input into the trained acceleration prediction model, and the predicted acceleration and predicted speed of leading train at next time step are obtained, and then the safety protection distance between following train and leading train at next time step is obtained.The application can significantly improve the accuracy of safety protection distance, and guarantee the safe and efficient operation of virtual marshalling train.

This invention discloses an optimization method and system for a predictive model of diabetic complications. It involves collecting routine laboratory test data from diabetic patients, performing preprocessing such as missing value removal, label merging, and SMOTE resampling to construct a balanced dataset. The average importance of indicators is evaluated using multiple machine learning models to select a subset of key features. Random forest, XGBoost, support vector machine, and multilayer perceptron are selected as base classifiers, and after hyperparameter optimization, a stacked ensemble learning model is constructed to further improve predictive performance. Finally, the model is packaged as an API service and embedded into a hospital information system to achieve high-precision, low-cost, and real-time risk prediction of diabetic complications. Experimental results show that this invention achieves an accuracy of 98.5% and an AUC of 99.76% in predicting diabetic nephropathy complications, outperforming single models.

This invention provides an online soft measurement method and apparatus for penicillin fermentation process based on deep learning, relating to the technical field of soft measurement modeling and application in industrial fermentation production processes. The method includes: establishing a penicillin fermentation process dataset by changing the initial values ​​of control parameters and state variables during the penicillin fermentation process; standardizing the penicillin fermentation process dataset, performing time window slicing, and proportionally dividing the training and testing sets required for the soft measurement deep learning network; and using the trained soft measurement deep learning network to predict the cell concentration value corresponding to each time window, thereby alleviating the technical problem that existing technologies cannot be widely adapted to soft measurement applications in biological fermentation.

The invention belongs to the technical field of deep learning, and discloses a CNN-XGBoost fusion airfoil aerodynamic coefficient prediction method based on a self-attention mechanism. The prediction method comprises the following steps: establishing an airfoil profile and an aerodynamic coefficient database of the airfoil profile; generating an airfoil geometric image; generating an airfoil grayscale image; establishing a prediction model; training and storing a prediction model; and airfoil aerodynamic coefficient prediction is carried out. According to the prediction method, an attention mechanism is introduced into a CNN and XGBoost is used for replacing an output layer in a CNN structure, so that the structure of a CNN airfoil aerodynamic coefficient prediction model is improved, the network performance is improved, airfoil image key feature learning is effectively carried out, and high-precision prediction of the airfoil aerodynamic coefficient under small sample data is realized.

The method for predicting the service life of the coiled tubing under the cooperation of plasticity and damage is characterized in that the fatigue service life and the strain amplitude under the specific curvature radius are obtained through a full-size bending fatigue test, and the fatigue service life and the strain amplitude are substituted into a Manson-Coffin model to invert an unknown coefficient; the method comprises the following steps: determining mechanical parameters of a material in combination with a uniaxial tensile test, constructing a finite element mechanical model, carrying out finite element simulation on bending working conditions of a damaged coiled tubing on a roller and a guider, extracting strain amplitudes, and further establishing strain amplitude calculation models under different working conditions by adopting a Levenberg-Marquardt algorithm; coupling the model with a Manson-Coffin equation, and respectively constructing fatigue life prediction models of the roller and the guider; and on the basis of the Miner theory, three times of bending cycles with different curvatures in one trip are regarded as complete load cycles, an accumulated damage value is calculated, a correction coefficient is determined through low-cycle fatigue finite element simulation, a calculation model of the number of remaining trip times is established, and quantitative prediction of the remaining life is achieved. The method is suitable for the technical field of petroleum and natural gas drilling engineering.

The application discloses a fermentation process soft measurement method based on convolution ONLSTM and self-attention, and belongs to the technical field of soft measurement. The method considers the redundant information in the fermentation process variables, proposes a convolutional ordered neuron long short-term memory network (ONLSTM) multilayer time series prediction model with a self-attention mechanism, first extracts local features of input variables in the fermentation process by using a CNN and reduces the dimensionality; then inputs the extracted features into a multilayer ONLSTM network for time series feature extraction, judges the importance of each input variable through a level, and filters the redundant information in the characteristic variables; finally, the feature weights are dynamically adjusted in combination with the self-attention mechanism, the internal dependency relationship between the input variables is utilized, high weight is given to the high correlation variables, the full connection layer activation function is optimized, high-precision prediction of the dominant variables in the fermentation process is realized, and the method is verified to have high-precision prediction on the penicillin concentration by taking the penicillin fermentation process as an example.

The invention provides a medium and long term electricity price prediction method based on causal TCN-HSMM duration perception, and relates to the technical field of electricity market analysis, and the method comprises the steps: obtaining first multi-source data needed by electricity price prediction, and carrying out the preprocessing of the first multi-source data, the first multi-source data at least comprises electricity prices, power system loads, renewable resource output, meteorological elements and holiday and festival identifiers at all time points in a first historical time period; inputting the first multi-source data into a neural network model, performing baseline prediction on the electricity price in the high-fluctuation scene, and generating a first prediction result; the fluctuation state of the first prediction result is recognized through a statistical model, the first prediction result is layered according to the fluctuation state, and a structured second prediction result is generated and comprises low-bit interval data, middle-bit interval data and high-bit interval data; and high-precision prediction of medium-and-long-term electricity price in a high-fluctuation scene is realized.

The present application relates to the technical field of data prediction, and discloses a coal calorific value high-precision prediction method based on machine learning; the method comprises the following steps: obtaining coal quality detection data and performing windowing processing to form a coal calorific value sequence and a multi-source coal quality component sequence; a disturbance embedding vector group is constructed according to adjacent measurement value changes; statistical features and dominant amplitudes of coal quality component variables are extracted, a signal-to-noise factor is constructed, and a selection weight is obtained through mapping to generate a variable-level coal quality feature vector group; the disturbance embedding vector group and the variable-level coal quality feature vector group are combined in time sequence to form a coal quality correlation modeling set, and a sparse correlation structure field is constructed based on a training set; a comprehensive state representation is obtained through correlation propagation and steady-state consistency constraints; a test set is input into the mechanism to obtain a coal calorific value prediction result sequence; the method can strengthen disturbance expression, improve feature fusion quality, and maintain prediction structure stability, and a coal calorific value high-precision prediction result is obtained.

The invention discloses a cattle weight calculation method and system based on computer vision, and belongs to the technical field of computer vision and machine learning, and the system comprises a target detection module, a point cloud collection module, a point cloud processing module, an index calculation module and a weight prediction module. The target detection module comprises a cattle recognition module and a cattle posture recognition module. According to the method, point cloud, deep learning and machine learning are combined, cattle recognition and cattle posture recognition are carried out through deep learning, when an object is recognized and the posture meets the condition, data are collected through a depth camera, calculation is carried out through point cloud data collected by the depth camera, the calculation result is cascaded to a machine learning regression algorithm, and the posture of the object is recognized. And high-precision prediction of the slaughtering weight of the three-dimensional object is realized.

The application discloses a green pressure relief method for mine pressure appearance caused by multi-coal seam mining residual coal pillars and belongs to the technical field of multi-coal seam mining. The intelligent decision system of multi-source data fusion is used to solve the problem of response lag of the traditional method. The coupling process of supercritical CO2 gas expansion pressure relief and biodegradable hydraulic fracturing technology is adopted to realize low pollution and coal pillar structure protection in the pressure relief process. Through the whole-process closed loop of "monitoring-prediction-decision-verification", the problem of multi-coal seam stress superposition control is broken through, and the method is especially suitable for the complex geological environment of mine pressure appearance caused by multi-coal seam superimposed mining.

The application relates to a construction method, system and device of a novel normal variable restitution coefficient model, and the method comprises the following steps: establishing a physical model of a ball and a base contact collision, obtaining a functional relationship between a restitution coefficient and an equivalent strain in a plastic stage according to an energy equivalence principle under the condition that a volume of an effective deformation domain at a maximum compression moment is equal to a volume of an elastic effective deformation domain; establishing a numerical simulation model of a ball-base normal contact collision, performing numerical simulation of the contact collision under multiple working conditions based on the simulation model to obtain simulation results; introducing a dimensionless parameter and fitting a mapping relationship between the dimensionless parameter and the equivalent strain in the plastic stage by combining the simulation results; and obtaining the normal variable restitution coefficient model based on the functional relationship between the restitution coefficient and the equivalent strain in the plastic stage and the mapping relationship between the dimensionless parameter and the equivalent strain in the plastic stage. According to the application, high-precision prediction of contact collision dynamics response results can be realized without relying on complex contact collision theories.

The invention discloses a working condition self-adaptive excavator pressure sensor soft measurement method, which comprises the following steps of: firstly, constructing a working condition self-adaptive variable screening framework, and integrating causal analysis, working condition sensing variable selection and a soft attention gate mechanism to realize accurate screening and weighting of key characteristic variables; further, designing an adaptive Kalman filtering algorithm, and dynamically adjusting parameters according to working conditions to suppress noise interference; on the basis, a CGM hybrid network fusing a convolutional neural network, a gating circulation unit and a multi-head attention mechanism is built, so that the time sequence feature extraction capability is enhanced; and furthermore, through an improved IPOA algorithm, CGM network hyper-parameters are optimized, and an IPOA-CGM high-precision pressure prediction model is constructed to predict a pressure value. The method can effectively meet the control requirements under various working conditions, provides reliable soft measurement signals when the sensor fails, improves the robustness and safety of the system, and has good engineering application value.

The invention discloses a single-cell drug response prediction method based on two-channel comparative learning, and relates to the field of artificial intelligence assisted drug research and development. The invention aims to solve the problem that the existing single-cell drug reaction prediction precision is low. The method comprises the following steps: acquiring an original single cell transcriptome counting matrix corresponding to a to-be-detected single cell, extracting a to-be-detected gene set with an expression counting value greater than 0 from the original single cell transcriptome counting matrix, acquiring a gene identity embedding vector and an expression intensity embedding vector, and acquiring a cellular-level semantic feature vector by utilizing the expression intensity embedding vector; obtaining a structural feature representation vector of a single cell layer by using the gene identity embedding vector; and acquiring a drug response result and a corresponding probability by using the cellular-level semantic feature vector and the structural feature representation vector of the single cell level. The method is used for obtaining the single cell response reaction under the given drug condition.

This invention discloses a multi-process optimization method for CNC grinding machines that balances accuracy and energy consumption, relating to the field of CNC grinding machine process optimization. The method establishes a first relational model characterizing the relationship between process parameters and axial error. This first relational model reflects the relationship between process parameters and the axial error of the CNC grinding machine during actual machining under those process parameters, enabling high-precision prediction of axial error in the actual machining process. A second relational model is also established to reflect the relationship between process parameters and grinding machine energy consumption. Furthermore, multi-objective optimization is performed with axial error and grinding machine energy consumption as objectives, achieving the goal of suppressing spindle axial error while improving resource utilization efficiency and reducing production costs.

A spatiotemporal multimodal quality prediction system for bananas and its training method are disclosed, relating to the field of intelligent detection and preservation information technology for agricultural products. This system alleviates the problems of existing banana quality prediction technologies, such as difficulty in comprehensively reflecting the intrinsic mechanisms of banana quality evolution and the tendency for error accumulation during long-term prediction. The spatiotemporal multimodal quality prediction system for bananas includes an image data acquisition module for obtaining visual spatial features based on the time series of images of the banana to be detected; a physiological data acquisition module for obtaining physiological features based on physiological data; a multimodal data fusion module for fusing the visual spatial features and physiological features through multimodal data fusion to obtain global temporal features; and a multimodal quality prediction module for using the global temporal features to obtain a predicted banana image and corresponding predicted physiological data through multi-task collaborative decoding. This invention is applicable to fields such as multimodal data fusion and non-destructive testing of agricultural product quality.

The invention discloses a ventilation wall air conditioner regulation and control method and system fusing a graph neural network and genetic optimization. The method comprises the steps that multi-source data are collected; performing data preprocessing on the multi-source data to obtain preprocessed data; constructing a graph structure model containing a node set and an edge set, and generating an initial graph neural network prediction model in combination with the graph attention network; collecting training data, and training the initial graph neural network prediction model through the training data to obtain a graph neural network prediction model; inputting the preprocessed data into a graph neural network prediction model, and outputting a field distribution prediction result of the cold channel; based on a preset time interval, performing dynamic rolling optimization on the field distribution prediction result of the cold channel through a genetic algorithm, and determining an optimal control strategy; and adjusting and controlling the ventilation wall air conditioner according to the optimal control strategy. According to the invention, comprehensive analysis is carried out through the graph neural network and the genetic algorithm, so that efficient energy-saving, dynamic response and safe operation of the cooling system are realized.

The application relates to the technical field of artificial intelligence and intelligent decision-making, and provides a business process optimization and intelligent decision-making method and device.The method comprises the following steps: determining multi-modal fusion features according to multi-modal business data and a business scenario; inputting the multi-modal fusion features and timestamp data into a target time sequence fusion transformer model to obtain a business demand prediction result output by the target time sequence fusion transformer model; determining a target decision threshold according to the business demand prediction result and a preset threshold adjustment strategy; and determining a target business process decision scheme according to the multi-modal fusion features, the business demand prediction result and the target decision threshold.The business process optimization and intelligent decision-making method and device provided by the application can realize business process optimization and high-efficiency, high-precision intelligent decision-making.

The invention relates to the technical field of artificial intelligence, in particular to a cross-hardware performance prediction method for a black box task in a computing power platform and related equipment. The method comprises the steps that in response to a received target task, short-time pilot run is started on source computing equipment matched with task configuration, and a kernel event sequence generated in the short-time pilot run process of the target task and corresponding first performance data are collected; analyzing the kernel event sequence, and extracting a stable iteration mode representing target task core calculation logic; based on a pre-stored hardware feature library, obtaining hardware performance parameters of the source computing device and the target computing device; for each kernel event in the stable iteration mode, determining a performance scaling rule suitable for the kernel event according to the event attribute of the kernel event and the first performance data, and calculating second performance data of the kernel event running on the target computing device according to the hardware performance parameters; and generating an overall performance prediction result of the target task on the target computing device according to the second performance data.

The invention discloses a wind power plant current oscillation control method, and belongs to the technical field of power system automation. Comprising the following steps: constructing a data set and an oscillation prediction network, and training and testing the oscillation prediction network according to the data set; obtaining a target operation parameter sequence and a target space topological graph of the target wind power plant, and processing the target operation parameter sequence and the target space topological graph according to the oscillation prediction network to obtain a prediction result; and the control system of the target wind power plant performs parameter adjustment on equipment of the target wind power plant according to the prediction result. According to the method, the target operation parameters and sequence of the target wind power plant and the target space topological graph are obtained, oscillation prediction of the target wind power plant is achieved, then the equipment parameters of the target wind power plant are adjusted in time according to the prediction result, and timely and accurate prediction and suppression of current oscillation of the target wind power plant are achieved.

The application discloses a soybean protein gelation multi-step prediction method based on ultrasound. The ultrasound waveform of the gelation process is organized into a time sequence, and a sequence-to-sequence neural network model based on an attention mechanism is combined. The original waveform of all sampling points is adaptively weighted through a gated attention mechanism, the encoder hidden state is aggregated through an additive attention mechanism with a linear proximate bias, and information is dynamically retrieved from the encoding history for each future prediction step through a scaled dot-product cross-attention mechanism. The model outputs the gelation degree prediction value of the next 5 time steps through self-recurrence, and the gelation endpoint is determined in advance accordingly. Under leave-one-out cross-validation, the overall average accuracy of the method to the unseen gelation conditions reaches 95.72%, and the average absolute percentage error in short-term prediction in the later stage of gelation is as low as 1.02%, which provides intelligent technical support for real-time tracking and early prediction of the gelation endpoint in the industrial production of bean products.

This invention provides a method and apparatus for optimizing a filtered antenna. The method includes: obtaining the value range of the antenna structural parameters to be optimized in the target filtered antenna; iteratively optimizing the full-band electromagnetic response sequence of the target filtered antenna using a multi-objective optimization algorithm based on a pre-constructed multi-objective evaluation function and the value range, to obtain the optimal full-band electromagnetic response sequence of the target filtered antenna; and optimizing the target filtered antenna based on the target values ​​of the antenna structural parameters corresponding to the optimal full-band electromagnetic response sequence. The multi-objective evaluation function is determined based on a trained target multi-resolution Transformer surrogate model, which is trained based on sample value data corresponding to the antenna structural parameters and simulated values ​​of the full-band electromagnetic response sequence. This invention can achieve collaborative optimization of multiple performance indicators, with high optimization accuracy, short optimization time, and low optimization cost.

The invention belongs to the technical field of reservoir water temperature prediction and regulation and control, and particularly discloses an upstream discharged water temperature prediction and flexible water retaining curtain wall regulation and control method and system. According to the method, a physical mechanism of an LSTM neuron structure is reconstructed, a water body stratification stability mechanism and a vertical thermal diffusion mechanism are deeply fused in a deep learning network, an improved LSTM model can well predict a water temperature stratification phenomenon of upstream incoming water, and high-precision prediction of vertical water temperature distribution of a reservoir under a complex meteorological condition is realized. A water temperature mixing model calculation formula is created for the first time, and the problem that the discharged water temperature requirement is difficult to calculate is solved. The vertical water temperature predicted by the improved LSTM is combined with the discharged water temperature inverted by the downstream ecological target, and the optimal water taking elevation is compared and determined, so that accurate lifting regulation and control of the flexible water retaining curtain wall are guided, the ecological water temperature requirement of a downstream river channel is strictly guaranteed, meanwhile, water resource waste is effectively avoided, and the power generation benefit and the flux utilization rate of a reservoir are maximized.

The invention relates to the technical field of micro-grid management optimization prediction, and discloses a micro-grid energy management optimization prediction method, which comprises the following steps: constructing a data acquisition network, synchronously acquiring basic meteorological data, enhanced meteorological data and micro-grid equipment operation data, and fusing through an edge computing gateway to generate a multi-source feature vector; and building a physical enhanced prediction model, taking Transform as a core, embedding an ash deposition influence index and a temperature coefficient correction factor, carrying out interval prediction on the photovoltaic output and load demand of the micro-grid, and outputting a confidence interval result. Basic meteorology is introduced into the prediction model, multi-source fusion of meteorology and micro-grid equipment operation data is enhanced, and high-precision prediction of photovoltaic output and load demand is realized in combination with Transform time sequence feature extraction capability.

The invention discloses a rapid self-adaptive prediction method for a few-sample working condition of a hydrogen-electricity double-source vehicle and a related device, and relates to the technical field of new energy electric vehicle prediction.The method comprises the steps that a current-stage working condition prediction model is determined according to obtained current-stage operation data and a previous-stage working condition prediction model of a target hydrogen-electricity double-source vehicle, and the current-stage working condition prediction model is determined according to the previous-stage working condition prediction model of the target hydrogen-electricity double-source vehicle; load power demand data of a next stage is predicted based on the current-stage operation data and the current-stage working condition prediction model, and when the current-stage operation data is the initial-stage operation data, the previous-stage working condition prediction model is a pre-trained global meta-model, and when the current-stage operation data is the initial-stage operation data, the previous-stage working condition prediction model is a pre-trained global meta-model; the global meta-model is a model obtained by training a constructed space-time diagram attention network based on a meta-learning algorithm and historical operation data of a plurality of hydrogen-electricity double-source vehicles acquired offline; according to the method, the problem of few samples can be solved, and high-precision prediction of future load power requirements is realized.

The invention discloses an intelligent decision-making method and system for electricity market information based on hierarchical model fusion. The method comprises the following steps: collecting multi-time scale operation data, executing multi-model grading prediction, and generating an electric power system operation key parameter prediction result containing a confidence interval; constructing a multi-target evaluation sample set based on the prediction result and the operation data, quantifying a conflict relationship among income, fluctuation, risk and clean energy consumption, and calculating a decision target weight by adopting an analytic hierarchy process; combining the weights to construct a comprehensive fitness function, and generating candidate decision-making schemes through an adaptive genetic algorithm; performing feasibility check on the candidate schemes in a multi-time scale scene to form a virtual running path, and fusing cross-scene information; and determining a final scheme according to a benefit balance requirement, and feeding back the operation deviation to update a prediction model and a weight system, thereby realizing a dynamically adaptive power market intelligent decision.