111 results about "Predictive function" patented technology

The invention discloses a real-time compensation control method and system for thrust fluctuation of a linear motor, and belongs to the technical field of linear motors, and the method comprises the steps: collecting a hybrid fluctuation source in the operation process of the linear motor, splitting the hybrid fluctuation source, and generating independent geometric nonlinear fluctuation signals; further screening the mixed fluctuation source, screening out a non-geometric nonlinear fluctuation signal, and preprocessing the non-geometric nonlinear fluctuation signal; establishing an independent compensation strategy, and respectively performing targeted compensation on geometric nonlinear fluctuation and non-geometric nonlinear fluctuation; and establishing a feed-forward compensation network, inputting the compensation strategy into the feed-forward compensation network, predicting a fluctuation component, and performing pre-compensation processing in advance. In the implementation process of the technical scheme provided by the invention, the pertinence and effectiveness of a compensation strategy are ensured through precise splitting and preprocessing of the hybrid fluctuation source, and meanwhile, the compensation amount is adjusted in real time by using the prediction function of the feedforward compensation network, the thrust fluctuation is remarkably reduced, and the operation stability of the linear motor is improved.

The invention relates to a method for detecting a coal seam interface while drilling, relates to the technical field of geological exploration, overcomes the limitation of a single physical field by using multi-modal fusion of electromagnetic waves, sound waves and gamma rays, remarkably improves the detection precision, greatly reduces the identification error of a thin coal seam compared with a traditional method, and improves the identification success rate of a complex structural region (fault and dirt band). Preliminary response within 1s is realized through underground edge calculation, decision lag is compressed to 1.5 s through ground cooperative processing, and leap of data real-time performance and predictive capacity is realized; the front 0.5-1.5 m prediction function gains time for track adjustment, and the risk of penetrating out of the coal seam is reduced. The multi-sensor redundancy design still keeps the signal-to-noise ratio not less than 20dB in a strong noise environment, the detection success rate is greatly improved when mud invasion is serious, and the environmental adaptability is high. The coal seam drilling rate is increased, invalid footage is reduced, the single well comprehensive cost is reduced, and economic benefits are remarkably improved.

The invention belongs to the technical field of power system automation control, and particularly relates to a low-voltage power distribution cabinet intelligent control system applied to an intelligent power grid, which comprises a multi-dimensional sensing module, an edge calculation and decision center and an execution and communication interface module. A multi-time-scale adaptive control mechanism adopted by the system separates protection, optimization and reconstruction decisions in different periods, the problems of response lag and target conflict of a single control loop are effectively solved, and the quick response capability and the adaptive adjustment capability of the system in a dynamic load and distributed energy access scene are remarkably improved. And the operation and maintenance mode is converted into predictive maintenance from post-maintenance through a deep fusion equipment health state evaluation and prediction function, so that the risk of unplanned shutdown is greatly reduced.

The invention discloses an underwater control system based on a multi-modal neural network large model, the system comprises an underwater robot and the multi-modal neural network large model, the underwater robot is used for collecting environmental data, and is also used for decomposing a received functional control instruction into an action execution signal, and sending the action execution signal to the multi-modal neural network large model; completing a set task target based on the action execution signal; the multi-modal neural network large model is used for generating prompt information based on received environment data, underwater domain knowledge and a task target sent by the underwater robot, and extracting prediction performance function sequence information capable of realizing the task target from a robot performance function library through the prompt information, and converting the performance function sequence information into a functional control instruction. According to the system, the underwater robot has high sensing ability, and a large model has understanding and reasoning ability facing the underwater environment, so that autonomous decision and accurate control of the intelligent agent with the body are realized.

The invention discloses a real-time online superconducting accelerator low-temperature system construction method and system.The method comprises the steps that physical property calculation in a low-temperature system is simplified, and a simplified physical property function of a working medium in the low-temperature system is obtained; the key point temperature is simulated according to the combination of a one-dimensional pipeline model and a 0-dimensional tank sub-model based on an agent model technology, the one-dimensional pipeline model is used for simulating the delay of heat transfer, and the 0-dimensional tank sub-model is used for simulating heat capacity; and responding to the simplified physical property function and the key point temperature, and solving node parameters in the low-temperature system by adopting a large-scale nonlinear sparse matrix equation. According to the invention, the fast simulator which operates independently can be provided, and meanwhile, the fast simulator can be combined with a real low-temperature system to operate to provide analysis and prediction functions for the real low-temperature system.

The invention discloses a centrifugal pump vibration digital twinning method and system based on deep learning. The method comprises the steps that real-time working condition data and real-time vibration data of a centrifugal pump are obtained; constructing a fluid domain model and a solid domain model of the centrifugal pump, and performing fluid-solid coupling simulation based on the fluid domain model and the solid domain model to obtain vibration data under the extreme working condition; fusing the vibration data under the extreme working condition and the real-time vibration data to obtain fused vibration data; and on the basis of the real-time working condition data and the fused vibration data, an LSTM-CNN deep learning network model is constructed, and the LSTM-CNN deep learning network model is used for achieving mapping from the real-time working condition data to vibration response and obtaining the vibration acceleration of the centrifugal pump. According to the invention, through the LSTM-CNN hybrid deep learning model, a high-precision vibration prediction function is realized.

The invention discloses a centrifuge full life cycle intelligent analysis and operation and maintenance method. The method comprises the following steps: constructing a health scoring model which is based on an SAE-SOM neural network and comprises wavelet denoising and future parameter prediction functions; constructing an equipment life prediction model; a data set obtained from detection equipment is subjected to problem sample screening and normalization operation, and then a feedforward neural network is trained. And the hyper-parameter of the feedforward neural network is determined through a genetic algorithm. And a fault tracing model is constructed. The system is composed of a feature extraction network, a middle layer, a relation measurement network and a fault classification network. And establishing an equipment operation environment cross validation module. According to the invention, through mutual cooperation of the equipment health assessment module, the whole machine life estimation module, the fault alarm module, the early warning and traceability module, the operation environment cross validation module and the warning module, fusion analysis is carried out on key operation parameters of the centrifugal machine and external environment data; the method can be widely applied to water plants and other complex industrial scenes with high requirements for the operation reliability of key equipment.

The invention discloses a power transmission line icing dynamic visualization method, system and device based on a three-dimensional GIM model, and a medium, and the method comprises the steps: building a GIM model based on unmanned plane laser point cloud data, carrying out the precise digitalization of the geometric structure of a power transmission line through a multi-level filtering and feature extraction algorithm, and enabling the model precision to reach the centimeter level; a complete icing state evaluation system is formed through integration of multi-source icing data fusion and intelligent feature extraction, and an icing prediction function is realized; according to the three-dimensional dynamic physical simulation technology based on the catenary theory, traditional two-dimensional calculation is creatively expanded to a three-dimensional space, uneven distribution of icing and wind load time-varying characteristics are considered, and real physical expression of the icing state of the wire is achieved; and dynamic presentation and deep data mining of the icing process are realized through time axis dynamic demonstration and a multi-dimensional interactive visualization technology. Through organic combination of the above schemes, the modeling precision, the data processing capability, the physical simulation and the interactive experience are improved compared with a traditional method.

The invention belongs to the technical field of vehicle maintenance, and particularly relates to a vehicle intelligent maintenance system and a vehicle, the vehicle intelligent maintenance system comprises a multi-source data acquisition module, a fault reasoning module, a maintenance knowledge graph engine module, a central control screen augmented reality maintenance guidance module and a maintenance process information interaction and support module; the multi-source data acquisition module is used for acquiring operation data of the vehicle in a preset time period before and after a fault; the fault reasoning module is used for analyzing the fault data, calculating the part failure probability and generating a fault influence degree thermodynamic diagram; the maintenance knowledge graph engine module is used for storing and managing a maintenance knowledge graph and supporting natural language interactive query; the central control screen augmented reality maintenance guidance module is used for providing maintenance guidance in a three-dimensional animation and augmented reality form; and the maintenance process information interaction and support module is used for realizing information interaction between maintenance personnel and the system and providing operation guidance for the maintenance personnel. According to the invention, functions of vehicle intelligent maintenance and fault prediction can be realized.

The invention discloses a lithium ion battery health state prediction system and method based on multi-mode sensor fusion, and belongs to the technical field of lithium ion battery health management and intelligent monitoring crossing. Comprising a multi-modal data acquisition module, a data preprocessing module, a multi-modal feature extraction module, a physical constraint modeling module and a multi-time-scale hybrid neural network module, data dimension shortages are supplemented, the prediction precision and robustness are improved, voltage, current, temperature and strain data are synchronously acquired through a multi-modal sensor, and the prediction accuracy and robustness are improved. The defect that the traditional technology lacks mechanical dimension information is overcome, and the SOH prediction root-mean-square error is reduced to be within 1% by combining multi-modal feature extraction and multi-time scale modeling, which is far better than that of the traditional method; meanwhile, the multi-modal fusion design ensures that when a single sensor fails, the prediction function can be maintained through other modal data, the system robustness is outstanding, physical mechanism constraints are fused, and generalization and interpretability are enhanced.

The invention provides a grab bucket composite anti-swing control system based on angle feedback of a steel wire rope at the head of a trunk beam and a control method of the grab bucket composite anti-swing control system, and relates to the technical field of portal crane grab bucket anti-swing. The core problems of response lag, control strategy solidification and poor working condition adaptability of the open-loop anti-swing system are systematically solved. And on the basis of a closed-loop control strategy of swing angle prediction and multi-cycle compensation, the response delay of a traditional open-loop system is reduced, the swing trend is inhibited in advance through a feedforward prediction instruction, and the swing attenuation time of the grab bucket is reduced. Through cooperative compensation of the swing angle and the speed, the portal crane boom and the grab bucket are kept dynamically synchronous all the time, the repeated positioning precision is improved, the fineness of manual operation is matched, and meanwhile manual operation errors are avoided. Through a parameter self-adaption mechanism and a swing angle elimination frequency prediction function, the system can automatically adapt to various complex working conditions, the stable anti-swing effect can be kept without manually adjusting parameters, and the optimal balance of the portal crane between efficient operation and safety control is achieved.

The present disclosure relates to accelerating table lookups using decoupled lookup table accelerators in a system on a chip. In various examples, a VPU and associated components can be optimized to improve VPU performance and throughput. For example, the VPU can include a min / max collector, an auto store prediction function, a SIMD data path organization that allows inter-lane sharing, a transpose load / store with stride parameter function, a load with permute and zero insertion function, a hardware, logic, and memory layout function to allow two-point and two-point by one lookups, and a per memory bank load cache function. Further, a decoupled accelerator can be used to offload VPU processing tasks to improve throughput and performance, and a hardware sequencer can be included in a DMA system to reduce programming complexity of the VPU and DMA system. The DMA and VPU can perform a VPU configuration mode that allows the VPU and DMA to operate without a processing controller for performing dynamic region based data movement operations.

Systems and methods are provided for performing customizable machine prediction using an extensible software tool. A specification including features of a trained machine learning model can be received and an interface for the trained machine learning model can be generated. The trained machine learning model can be loaded using the interface, the loaded machine learning model including a binary file configured to receive data as input and generate prediction data as output. Predictions can be generated using observed data that is stored according to a multidimensional data model, wherein a portion of the observed data is input to the loaded machine learning model to generate first data predictions, and a portion of the observed data is used by a generic forecast model to generate second data predictions. The first and second data predictions can be displayed in a user interface configured to display intersections of the multidimensional data model.

The invention relates to the technical field of semantic analysis, in particular to a customer group evolution prediction method based on large model semantic analysis, which comprises the following steps: acquiring historical unstructured data of streaming media platform users, and executing semantic analysis at multiple time points through a large model to generate semantic vectors; processing the semantic vector through a loop module to generate a historical semantic sequence; training a semantic evolution model based on the sequence; the method comprises the following steps: in an offline batch processing stage, pre-calculating future semantic vectors of all users by utilizing an evolution model, and constructing a semantic index; when a seed customer group is received online, calculating a customer group centroid vector representing a future trend for the seed customer group; and performing approximate neighbor search on the centroid vector in a predictive semantic index, and outputting a predicted evolved customer group. According to the method, the prediction accuracy is improved through future matching, and low delay and feasibility of an evolution prediction function are ensured through an off-line pre-calculation framework.

This invention provides a method for predicting the relative safety (RUL) of an aircraft system based on combined probability density. The specific steps are as follows: In the training module, preprocessed training data is input into an FFT model, and different quantile loss functions are set. After the loss functions converge, the predicted values ​​at each quantile are obtained. In the testing module, processed test data is input into a trained QRFFT model to obtain multi-quantile RUL prediction results. These results are then used as input to a KDE (Knowledge-Defined Allocation) model, and the RUL probability density distribution (PDF) is obtained through a Gaussian kernel function and optimal bandwidth. This model combines RUL point prediction, interval prediction, and probability density prediction functions. Experiments using real aircraft flight path data are conducted, and a new probability prediction evaluation index is introduced. Comparison with existing QR models in terms of point prediction accuracy and interval prediction performance shows that this invention has higher effectiveness and superiority.

The application relates to the technical field of semantic analysis, in particular to a customer group evolution prediction method based on large model semantic analysis, which comprises the following steps: obtaining historical unstructured data of users of a streaming media platform, performing semantic analysis on multiple time points by a large model to generate semantic vectors; processing the semantic vectors by a loop module to generate a historical semantic sequence; training a semantic evolution model based on the sequence; in an offline batch processing stage, calculating future semantic vectors of all users in advance by using the evolution model, and constructing a semantic index; when a seed customer group is received online, calculating a customer group centroid vector representing a future trend for the seed customer group; performing approximate neighbor search on the centroid vector in the predictive semantic index, and outputting a predicted evolved customer group. The application improves prediction accuracy through future-to-future matching, and ensures low delay and feasibility of the evolution prediction function through an offline precalculation architecture.

A system and method for learning a predictive function that can automatically learn different operating modes for a multi-modal system and predict the number of operating states for a multi-modal system and additionally the detailed structure for each state. Once learned, the predictive function (model) can be used to determine a mode of a new sample (an asset). Based on the determined components that maximize a log likelihood function, a mode of the new sample is detected into the model via dependency graphs. One aspect includes enforcing a lower bound for the number of sample points to form an operational mode for an asset. While a mode relates to sample points which maximizes like log-likelihood, an ability is provided to remove artifact modes due to noisy data by considering a sufficient sample data condition and maximizing log-likelihood. Domain knowledge can be incorporated into the model via dependency graphs.

The present application relates to the technical field of port supervision, in particular to a port multi-agent prevention and control information coordination system based on overall management, comprising: a compactness coordination unit for determining the coordination compactness of each supervision subject node in the standardized prevention and control knowledge graph, and constructing initial coordination strategies of a plurality of federal computing nodes based on the coordination compactness; the initial coordination strategies are evenly distributed to the plurality of federal computing nodes, and the plurality of federal computing nodes are trained in parallel through a mirror network to update the coordination reasoning network parameters and obtain a multi-agent joint prevention and control model. The present application identifies core supervision subjects through the use of fitting prediction function and supervision subject influence degree analysis based on coordination anomaly subgraph; this prediction capability enables the system to accurately grasp the influence of each subject, timely adjust resource input and prevention and control strategies, and achieve more efficient port management.

The invention relates to the technical field of tobacco leaf moistening, in particular to a method for predicting the water adding amount of a tobacco leaf moistening machine. The method comprises the following steps: acquiring actual values of current temperature and humidity from a workshop sensor through acquisition software, and determining a current production state according to the actual value of the temperature and the actual value of the humidity; determining acquisition points influencing the predicted value of the water adding amount and key parameters, and acquiring the parameters; a data set of the collected parameters is used as a data set of water adding amount prediction, and data cleaning is conducted on the data set through a program; carrying out data standardization and data segmentation processing; for the first batch production state, using a K-nearest neighbor algorithm to carry out linear regression model building prediction model, and optimizing the prediction model; if the production state is not the first batch production state, using a linear regression algorithm to build a prediction model, and optimizing the prediction model; the water adding amount is calculated according to a manual water adding amount calculation formula, the average value of the water adding amount and the water adding amount calculated through the optimized prediction model is calculated, and the final water adding amount value of the leaf moistening machine is determined. The intelligent prediction function of the water adding amount of the leaf moistening machine is achieved, the labor cost is reduced, water adding amount setting errors are avoided, the tobacco leaf production and processing quality is improved, and the working efficiency is improved.

The invention discloses a cooking method and cooking equipment with a prediction function, and the method comprises the steps: obtaining food material parameters, and generating cooking schemes of different maturity according to the food material parameters for a user to select; obtaining the maturity selected by the user, and cooking the food materials according to the cooking scheme; monitoring the parameter change of the food materials, comparing the parameter change with the cooking scheme, and if the food material parameters are out of the error range of the parameter change curve in the cooking scheme, adjusting the parameters of the cooking equipment to enable the food material parameters to return to the error range of the change curve; the actual cooking process is stored in a database; according to the method, cooking schemes of different maturity degrees are generated through food material parameters, a prediction map is generated so that a user can visually select the desired maturity degree, the requirements of the user can be accurately obtained, and dishes satisfying the user can be better cooked for the user; in the cooking process, parameter changes are monitored in real time, the cooking parameters are adjusted in real time, it is ensured that the cooking result is closer to the expected effect, and dishes wanted by a user are cooked.

The application provides a neural network-based density prediction method and device, equipment and storage medium, including: data preparation: obtaining the depth domain measured depth domain P-wave velocity, depth domain S-wave velocity and density logging data of a study area; sample set construction: normalizing and preprocessing the depth domain measured depth domain P-wave velocity, depth domain S-wave velocity and density logging data, thereby forming a neural network training sample set; model training: constructing a density prediction model based on a depth feedforward neural network, and training the model using the training sample set, thereby obtaining a nonlinear relationship model between the depth domain P-wave velocity, depth domain S-wave velocity and density, and realizing a density prediction function; model application: normalizing and preprocessing the measured depth domain P-wave velocity and depth domain S-wave velocity prediction data, and then inputting the normalized and preprocessed prediction data into the nonlinear relationship model to predict the density.

The present application relates to the field of communications, and discloses a model monitoring method and apparatus, a device, and a readable storage medium. The method in the embodiments of the present application comprises: a terminal acquiring first information; and performing model monitoring on a first artificial intelligence (AI) model on the basis of the first information, wherein the first AI model is configured to execute a first prediction function; wherein the first information comprises at least one of the following: one or more prediction accuracy requirements; configuration information corresponding to the first prediction function; and a first parameter, used for determining a prediction accuracy requirement associated with the first prediction function, the one or more prediction accuracy requirements being associated with at least one of the following: a prediction window, a measurement reduction ratio (MRR), a frequency point, a cell, a beam, an AI function, and an AI model.

The invention provides an electric power spot market price prediction system and method based on artificial intelligence. The system comprises a market boundary prediction analysis module, a spot market price prediction module, an agent electricity purchase decision optimization module and a prediction result redisk analysis module. According to the system, a deep learning model fused with a CNN-MLP-Attention algorithm is adopted, kernel density estimation is combined to carry out electricity price interval prediction, meteorological data weighting processing, feature engineering, rolling training and multi-day prediction functions are integrated, and 1-7-day high-precision determinacy and uncertainty prediction of the electricity price of the electric power spot market is achieved. The method solves the problems of low electricity price prediction precision, large uncertainty, lack of scientific support of electricity purchasing strategies and the like in the existing electric power spot market, can effectively improve the decision scientificity of power grid enterprises in the spot market, reduces the transaction risk, and improves the efficiency of the power grid enterprises. And full-process data support and strategy simulation capability are provided for a power grid enterprise to participate in an agent power purchase transaction mode.

An intelligent dosing platform incorporating comprehensive predictive analytics and forecasting capabilities for injectable medication administration. The platform includes predictive analytics modules configured to generate forecasts for financial costs, medication demand patterns, and adverse event probabilities using machine learning algorithms and statistical modeling techniques. The system features financial modeling modules that analyze cost patterns associated with medication procurement, administration infrastructure, and insurance reimbursements, while demand forecasting modules predict medication needs based on seasonal trends, patient population changes, and treatment protocol modifications. Adverse event prediction modules identify risk factors using patient risk profiles and clinical outcome histories. The platform incorporates machine learning capabilities that continuously improve prediction accuracy using patient outcome data and administration patterns. Comprehensive reporting modules generate customized predictive reports for healthcare administrators, pharmaceutical suppliers, and insurance providers, while optimization modules recommend actions for cost reduction and patient safety improvement based on predictive insights.

Various aspects of the present disclosure relate to risk forecasting in a wireless network. A network equipment (NE) implements a risk forecasting function that receives multiple series of key performance indicator (KPI) values over a time duration. Each series of the KPI values correspond to a respective KPI that is a performance metric of a network aspect. The risk forecasting function generates a KPI representation based on a predicted KPI value and one or more previous KPI values of the respective KPI. The risk forecasting function generates a forecast embedded matrix (FEM) that includes the KPI representations of each KPI. The risk forecasting function detects whether a change has occurred between the FEM and one or more previous FEMs over the time duration.

The invention relates to the technical field of turnout grinding wagon operation, in particular to a zero-speed out-of-gear protection system under a network fault of a turnout grinding wagon, which comprises a network state monitoring module, a speed monitoring module, a gear monitoring module, a central control module and an out-of-gear execution module, wherein the network state monitoring module detects faults through multi-modal fusion and deep learning; speed detection is combined with laser and traditional sensing, and Kalman filtering is used; gear monitoring depends on the Hall effect and image recognition; central control is carried out to reinforce learning of comprehensive multi-factor decisions; the out-of-gear execution is driven by magnetorheological fluid and is monitored by an MEMS (micro-electromechanical system); the AR technology is used for alarming and displaying, and voice interaction is achieved. The system has the advantages that the network, the speed and the gear are accurately monitored, and the out-of-gear is intelligently decided; off-gear execution is reliable, and alarm display is visual. The system has the functions of data secure storage, remote efficient monitoring and fault prediction, and the security under a network fault is comprehensively improved.

The application discloses a network service quality prediction method and device, a network element and a storage medium. The network service quality prediction method is applied to a Qos prediction function network element, and the method comprises the following steps: receiving a prediction request, wherein the prediction request comprises a QoS prediction index of a user terminal; performing prediction on the QoS prediction index based on the prediction request, so as to obtain a first prediction value of the QoS prediction index; and sending early warning information to a network management device based on the first prediction value.

A distributed environmental control system comprises control nodes that communicate via wireless mesh networks to predict user movement and automate loads without centralized coordination. Each node executes a local inference engine (Markov model, HMM / DBN, or reinforcement learning policy) to predict occupancy patterns, broadcasts predictions to neighbors, and makes autonomous actuation decisions based on local and shared data. When multiple nodes control loads in a shared zone, a Runtime Actuation Authority mechanism designates a single decision-maker based on most recent manual interaction, with authority epochs and deterministic total order resolution ensuring distributed consistency. The system prevents feedback loops via causal action identifiers, logical timestamps, and recent action caches. Sensor data is transmitted as compressed waveform encodings. A deterministic policy layer enforces safety and comfort constraints. The reinforcement learning embodiment learns household preferences from user feedback, adapting actuation behavior to optimize satisfaction, comfort, and energy efficiency while maintaining safety guarantees.

The invention provides an industrial heating furnace temperature prediction method and device based on deep learning, and a storage medium, and belongs to the technical field of temperature prediction, and the method comprises the steps: collecting the operation data of an industrial heating furnace, and carrying out the preprocessing; constructing a temperature prediction network model, and standardizing input data; constructing an input projection layer extension feature number; two layers of gating circulation units are constructed, and two stages of GRU networks are arranged and are connected through residual errors; the first-stage GRU network learns a time dependency relationship of the input data, and outputs a hidden state sequence to a second-stage GRU network to extract key time sequence context information; an output layer is constructed, final temperature prediction and normalization are carried out, an output temperature increment is subjected to destandardization, and an actual temperature value is obtained; performing hyper-parameter training on the temperature prediction network architecture to obtain a temperature prediction network model with a temperature change prediction function; and predicting the temperature prediction network model by using actual data to obtain a temperature prediction result.