Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

234 results about "Moving-average model" patented technology

In time series analysis, the moving-average model (MA model), also known as moving-average process, is a common approach for modeling univariate time series. The moving-average model specifies that the output variable depends linearly on the current and various past values of a stochastic (imperfectly predictable) term.

Digital twinborn modeling and predictive analysis system for oil and gas well

The invention relates to the technical field of prediction algorithms, in particular to an oil and gas well digital twinborn modeling and prediction analysis system which comprises an underground dynamic data analysis module for extracting variables based on pressure, flow velocity and temperature data, performing data association calculation, analyzing the pressure change rate and the flow velocity trend, calculating the temperature fluctuation range and establishing time period variable analysis; and generating a dynamic parameter mode. According to the invention, through an autoregressive integral moving average model, the dynamic data of each time period is integrated and smoothed, the long-term trend of the data is captured, the subtle change in the production fluctuation is identified, the accurate future yield fluctuation trend is generated, a density clustering algorithm is adopted, key variables are analyzed, and the change mode of abnormal fluctuation is extracted. According to the method, potential fault types are screened, similar data points are classified through the density relation between data, dependence on parameter setting is reduced, abnormity is recognized more accurately under the unsupervised condition, and the fault recognition capability is improved.
Owner:BEIJING BOZHONGJIAHE PETRO TECH

Carbon emission calculation method based on deep learning

The invention relates to the technical field of computers, and discloses a carbon emission calculation method based on deep learning, which comprises the following steps: S1, collecting multi-source data through a sensor, satellite remote sensing, an intelligent electric meter and a monitoring system, carrying out cleaning, denoising and missing value filling on the collected data, and in addition, carrying out data processing on the collected data; the structured data and the unstructured data are integrated through a multi-source data fusion technology; s2, performing feature extraction on the original data by adopting a deep feature learning model, and screening out key features contributing to carbon emission prediction; and S3, performing real-time decomposition and anomaly detection on the data by combining an autoregressive integral moving average model and an online learning algorithm. By combining an autoregressive integral moving average model and an online Bayesian learning method, carbon emission calculation can dynamically adjust parameters according to real-time data to adapt to environmental changes, seasonal fluctuations and emergencies, so that the flexibility and real-time performance of a prediction model are remarkably improved.
Owner:STATE GRID NINGXIA ELECTRIC POWER CO LTD ECO TECH RES INST +1

Intelligent warehouse cargo scheduling device

The invention relates to the technical field of automatic logistics, in particular to an intelligent warehouse cargo scheduling device, which comprises a dynamic priority adjustment module, a self-adaptive classified storage module, a cargo flow optimization module, a resource allocation module, a fault analysis and maintenance module, a behavior monitoring module, an energy management module and a cost control module. According to the method, the cargo scheduling priority is optimized through a support vector machine algorithm and a decision tree method, the warehouse space utilization rate is improved by utilizing a convolutional neural network and a genetic algorithm, the cargo flow is optimized by adopting linear programming and a network flow analysis algorithm, and the cargo flow trend is estimated through an autoregressive integral moving average model and a recurrent neural network. The system utilizes a long short-term memory network to identify equipment faults and maintain, reduces the risk of accidental shutdown, improves the operation safety through a computer vision technology and a behavior identification algorithm, and utilizes an energy consumption mode analysis and cost-benefit analysis method to reduce the operation cost.
Owner:曾丽婷

Deep learning model based method for forecasting online ride-hailing short-term demand

A deep learning model based method for forecasting online ride-hailing short-term demand is provided. The deep learning model based method includes S1: collecting online ride-hailing demand data in a large transportation hub, and preprocessing original data, to form a data set; S2: performing time series decomposition, specifically, decomposing time series data processed in S1 through a variational modal decomposition (VMD) method, to obtain the certain number of intrinsic mode functions; S3: forecasting a decomposed model by means of a deep learning model Transformer; S4: performing sub-series integration, specifically, accumulating forecast results in S3, to obtain an integrated forecast result; and S5: performing forecast error correction, specifically, correcting a forecast error by using a time series forecast model, that is, an autoregressive integrated moving average model (ARIMA).
Owner:BEIJING UNIV OF CHEM TECH

Quality detection and evaluation method for terminal effluent carbon source of sewage treatment plant

The invention provides a sewage treatment plant terminal effluent carbon source quality detection and evaluation method, which realizes full-flow dynamic evaluation and regulation of carbon source quality through on-line monitoring and intelligent algorithm fusion. According to the method, an online water quality full-spectrum detector is used for collecting original spectrum data flow, and after preprocessing such as variational mode decomposition denoising and mutual information feature selection, organic matter content quantification, variation trend analysis and anomaly detection are completed in combination with algorithms such as a support vector machine and an autoregressive moving average model. An entropy weight method is introduced to dynamically adjust the weight of the evaluation model, model parameters are optimized based on a gradient descent algorithm, a process adjustment instruction is generated through reinforcement learning and fuzzy logic, and an automatic system is linked to execute regulation and control. According to the method, the problems of hysteresis and singleness of traditional offline analysis are solved, multi-dimensional real-time evaluation, abnormal quick response and process dynamic optimization of the quality of the carbon source are realized, the sewage treatment efficiency and the effluent quality stability are improved, and a technical support is provided for continuous standard reaching of the quality of the carbon source.
Owner:CHONGQING THREE GORGES ECO-ENVIRONMENTAL TECH INNOVATION CENT CO LTD +1

Mechanical arm control method based on multi-scale dynamic state estimation and error compensation

According to the mechanical arm control method based on multi-scale dynamic state estimation and error compensation, high-frequency and high-precision estimation of the state of a mechanical arm system is achieved through multi-sensor data fusion and an extended Kalman filtering algorithm, and the accuracy and reliability of state estimation are remarkably improved; on the basis, a multi-scale error analysis method combining a time domain and a frequency domain is provided, and an autoregressive moving average model is utilized to dynamically predict system errors, so that the sensing and pre-judging capability of the system on the errors is enhanced; a comprehensive control strategy including multiple links of feedforward, self-adaption and feedback is designed, a dynamic compensation and adjustment mechanism of errors is introduced, meanwhile, a real-time execution framework based on three-layer task scheduling is constructed, cooperative operation of all functional modules is coordinated, and the real-time performance and high efficiency of a control system are ensured. The method is suitable for multiple fields of industrial manufacturing, intelligent robots and the like, and provides technical support for precise control of mechanical arms in complex scenes.
Owner:GUANGDONG XINXIANPAI MODERN AGRICULTURAL GROUP CO LTD

Photovoltaic wind power energy storage intelligent management method and system for building

The invention provides a photovoltaic wind power energy storage intelligent management method and system for a building. The method comprises the following steps: acquiring operation parameters, environmental conditions and historical fault data records of system equipment, and preprocessing the acquired data; establishing health assessment indexes by using the comprehensive wind and light energy storage equipment performance model, and determining the health degrees of different equipment; the fault abnormity level is judged according to the fault alarm signal sending time and frequency of the system equipment; through combination of an autoregressive differential moving average model and a long-short-term memory model, the photovoltaic and wind power comprehensive electric quantity is predicted, and the loss abnormity level is judged; and in combination with the health degree, the fault abnormity level and the loss abnormity level of the equipment, making a patrol inspection and daily maintenance work plan, and sending out reminding and early warning. By analyzing and diagnosing key equipment and core performance of the system and early warning key events, energy waste and equipment damage caused by improper maintenance can be effectively avoided.
Owner:DALIAN VOCATIONAL & TECHNICAL COLLEGE (DALIAN OPEN UNIVERSITY)

Task simulation method and device of virtual simulation platform and computer equipment

The invention relates to a task simulation method and device of a virtual simulation platform and computer equipment. The method comprises the following steps: a data synchronization management module performs data synchronization of each heterogeneous virtual simulation sub-platform according to a pre-controlled data synchronization frequency, and further needs to perform online evaluation and offline evaluation so as to optimize an autoregressive moving average model and a reinforcement learning model to perform simulation at the next moment. By adopting the method, the efficiency of data synchronization between heterogeneous simulation platforms can be improved.
Owner:CHINESE PEOPLES LIBERATION ARMY ARMY INFANTRY ACAD

Industrial circulating water system temperature prediction method based on BiLSTM-ARIMA-Attention

The invention provides an industrial circulating water system temperature prediction method which comprises the following steps: firstly, acquiring original data such as temperature, flow and pressure of a blast furnace system and a circulating water system, and preprocessing; a feature reduction method based on fuzzy inconsistency measurement is adopted to measure feature importance, redundant features are removed, and a key feature subset is obtained; dividing the data into a training set, a verification set and a test set, and performing training and evaluation by using a bidirectional long-short-term memory neural network model; predicting by using the verification set, and calculating a residual sequence; weighting the features in local and global dimensions by adopting an attention mechanism, and enhancing the difference of different time steps; then using an autoregressive comprehensive moving average model to correct a residual error, and integrating the residual error with a predicted value to obtain a final prediction result; a comprehensive model is established based on this, and prediction performance is evaluated by using a test set. The method can accurately predict the return water temperature and improve the system efficiency and the energy-saving effect.
Owner:XIANGTAN UNIV

Power consumption control method and device of power distribution network monitoring control chip and storage medium

The invention discloses a power consumption control method and device for a power distribution network monitoring control chip and a storage medium, and the method comprises the steps: carrying out the clock domain division of the power distribution network monitoring control chip, and obtaining a target clock domain; obtaining current load data and historical load data of the target clock domain; according to the historical load data, trend prediction processing is carried out by using an autoregressive moving average model to obtain predicted load data; according to the predicted load data and the power consumption state of the control chip, performing action evaluation processing by using preset reinforcement learning to obtain a state action function value; calculating a to-be-adjusted clock frequency and a to-be-adjusted voltage according to the current load data; determining a predicted clock frequency and a predicted voltage according to the state action function value; and performing power consumption control on the target clock domain according to the target clock frequency and the target voltage to obtain a power consumption control result. The power consumption control is realized, and the resource utilization rate and the control efficiency are improved. The method can be widely applied to the technical field of electric power engineering.
Owner:CHINA SOUTHERN POWER GRID COMPANY

Detection system and method for loop closing of power distribution network

The invention relates to the technical field of state detection, in particular to a detection system and method for loop closing of a power distribution network, and the system comprises a time sequence monitoring module which is used for collecting the change rate in real time based on electrical state parameters by adopting an autoregressive integral moving average model, comparing the fluctuation amplitude, extracting the abnormal fluctuation characteristics, and calculating the fluctuation difference; and generating a dynamic fluctuation detection result. According to the method, the system can accurately monitor the running state of the power distribution network and reduce the possibility of misjudgment and missed judgment through the autoregressive integral moving average model, by collecting and processing the change rate of the electrical state parameters in real time, generating the dynamic fluctuation detection result and effectively identifying and extracting the abnormal fluctuation characteristics; the gradient boosting tree algorithm is adopted to process the compressed feature data, the safety of a local system can be efficiently and accurately judged, local risks can be recognized, abnormity and faults in the power distribution network can be better recognized, predicted and processed, and therefore the safety and reliability of loop closing operation of the power distribution network are improved.
Owner:HUANGSHAN POWER SUPPLY COMPANY OF STATE GRID ANHUI ELECTRIC POWER

Key management system and method based on medical block chain

The invention relates to the technical field of information security, in particular to a key management system and method based on a medical block chain, and the system comprises a state evaluation module, a reverse tracking module, a foresight analysis module, an intelligent alarm threshold adjustment module, a resource priority scheduling module, a reliability analysis and fault tolerance module, and a process optimization and decision support module. According to the method, risk assessment and classification are effectively carried out and a key access control strategy is adjusted by adopting a support vector machine, a decision tree algorithm and a deep learning algorithm, a key use trend is predicted by utilizing an autoregression integral moving average model and a long-short-term memory network, and the key access control strategy is optimized through an isolated forest and a deep learning network. An alarm threshold value is dynamically adjusted, the early warning capability of the system for potential security threats is improved, a key management process is optimized through a genetic algorithm and a particle swarm optimization technology, a security decision and a response strategy are executed in combination with a rule engine and a machine learning model, and the response efficiency and the decision accuracy are improved.
Owner:XIANGJIANG LAB

Lithium battery residual life prediction method

The invention discloses a lithium battery residual life prediction method, and belongs to the technical field of lithium battery life prediction, and the method comprises the steps: constructing a capacity degradation data sequence according to the capacity degradation data of a lithium battery; decomposing the capacity degradation data sequence through fast ensemble empirical mode decomposition to obtain a fluctuation item and a trend item; predicting the trend term by adopting particle filtering to obtain a trend term prediction result; predicting the fluctuation item through a fractional autoregression moving average model to obtain a fluctuation item prediction result; and combining the trend item prediction result with the fluctuation item prediction result, constructing a prediction curve, predicting the failure cycle of the lithium battery, and realizing prediction of the residual life of the lithium battery. The nonlinear characteristic and the long-term correlation characteristic in the degradation process of the lithium battery can be considered at the same time, and the accuracy of battery life prediction is improved.
Owner:SHIJIAZHUANG TIEDAO UNIV +1

High-power charging pile self-adjusting method, medium and system for high-temperature environment

The invention provides a high-power charging pile self-adjusting method, medium and system for a high-temperature environment, and belongs to the technical field of electrical variable measurement, and the method comprises the steps: extracting time domain features and frequency domain features of an environment parameter, a charging temperature, an input parameter and an output parameter; a correlation matrix of each parameter is calculated through a Pearson's correlation coefficient and principal component analysis, and a stability matrix and a variability matrix are obtained through singular value decomposition. Based on the two matrixes, an autoregressive integrated moving average model and a conditional autoregressive model are respectively constructed, and the long-term trend and short-term fluctuation of each parameter are predicted. And then establishing a game model, and solving to obtain an optimal output parameter by taking the long-term stability and the short-term stability of the output parameter as a target, and taking the optimal output parameter as a charging pile output parameter in a next time period. The charging process is continuously optimized with the preset duration as the cycle period, and the technical problem that real-time optimization of charging adjustment is difficult to achieve due to the fact that an existing charging control technology is mainly based on a single temperature threshold value is solved.
Owner:QINGDAO HUASHUO GAOKE NEW ENERGY TECH

Noise suppression method and device for balanced photoelectric detector, equipment and storage medium

The invention provides a noise suppression method and device for a balanced photoelectric detector, equipment and a storage medium. The method comprises the following steps: acquiring a first sampling sequence of the balanced photoelectric detector; performing digital filtering processing on the first sampling sequence to obtain a second sampling sequence; performing autocorrelation analysis on the second sampling sequence, and constructing an autoregression model to obtain a first prediction sequence; according to the first prediction sequence, the second sampling sequence and an autoregressive model, constructing an autoregressive moving average model, and obtaining a second prediction sequence corresponding to the autoregressive moving average model in a preset time period; acquiring a third sampling sequence corresponding to a preset time period, and performing noise evaluation according to the second prediction sequence and the third sampling sequence to obtain a preliminary noise sequence; and acquiring a real-time sampling sequence of the balanced photoelectric detector, and in the autoregressive moving average model, performing weighted fusion on the real-time sampling sequence and the preliminary noise sequence to obtain a photoelectric differential signal.
Owner:SHENZHEN WEIDU TECHNOLOGY CO LTD

Welding seam strength detection method

The invention relates to the technical field of welding detection, in particular to a welding seam strength detection method, which comprises the following steps of: based on welding process monitoring, monitoring welding seam temperature, welding speed and load pressure, recording and screening data, eliminating abnormal data points, generating a primary screening data set, applying an autoregressive moving average model to the primary screening data set, and adjusting model parameters, and generating a model tuning result. According to the method, the accuracy is improved by monitoring the welding process in real time, screening data, eliminating abnormal points, improving data quality and analysis precision, applying an autoregressive moving average model, improving prediction capacity, predicting weld temperature change and failure time points, comparing with historical data to verify the model and finely adjusting parameters; and a fault early warning mechanism and a threshold value are set to automatically trigger maintenance reminding, so that the maintenance efficiency is remarkably improved, the downtime is shortened, fault early warning logic is updated in real time, the response speed of a monitoring platform is increased, welding parameters are continuously optimized, and the welding seam strength and the service life prediction accuracy are improved.
Owner:JIANGSU JIDING METAL PROD CO LTD

Autonomous region division method based on random model predictive control under opportunity constraint

The invention discloses an autonomous region division method based on random model prediction control under opportunity constraint. The method comprises the following steps: predicting wind power photovoltaic output by using a differential autoregressive moving average model; considering the uncertainty of wind and light output, and establishing an autonomous region division opportunity constraint system by taking the minimum load loss risk rate of the autonomous region as a target; generating a distributed output scene set in a specified reasonable output interval by adopting a scene analysis method in combination with photovoltaic and fan prediction error probability models, and solving opportunity constraints by applying a stochastic simulation technology; a novel power distribution system autonomous region division optimization model based on random model prediction control is constructed, and continuous forward rolling optimization is carried out through rolling optimization and feedback correction. The method is used for solving the problem that in the prior art, the control dimension is too high due to the fact that distributed energy is connected into a distribution network, it can be guaranteed that the load loss risk probability is kept at a low level under a certain confidence level, and consumption of distributed new energy and the stability of an autonomous region are improved while the power supply reliability is guaranteed.
Owner:NANJING UNIV OF SCI & TECH +1

Dynamic collaborative optimal selection control method for denitration of garbage incinerator

The embodiment of the invention discloses a dynamic collaborative optimal selection control method for denitration of a garbage incinerator, and relates to the technical field of garbage incineration treatment. The method comprises the steps that operation parameters, collected in real time, of the garbage incinerator are obtained and preprocessed; based on the mechanism of waste incineration and denitration reaction and in combination with historical operation data, a dynamic model of the denitration process of the waste incinerator is established, and the denitration process is described by adopting an autoregressive moving average model; according to the preprocessed operation parameters and the established dynamic model, the working conditions of the garbage incinerator are recognized and classified in real time; multivariable model predictive control is adopted to make a cooperative control strategy; and outputting the formulated cooperative control strategy to execution mechanisms of the denitration system and the incineration system. According to the method, the denitration efficiency can be improved, nitrogen oxide emission can be accurately controlled, and the ammonia escape rate and the denitration cost can be reduced.
Owner:北京中科润宇环保科技股份有限公司

Non-abandoned inheritance display method and system based on artificial intelligence

The invention discloses a non-abandoned inheritance display method and system based on artificial intelligence, and particularly relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring dynamic detail time sequence data from a capture system in real time, analyzing track smoothness by using Fourier transform, generating a lossless reference model by using ultrahigh-resolution 3D scanning and image equipment, and performing texture consistency analysis on a difference salient region by combining point cloud registration and a difference heat map to evaluate spatial deviation of a track. Judging the fidelity of dynamic details, comprehensively evaluating the capture accuracy in combination with the smoothness and the fidelity, dividing capture results into accurate capture and inaccurate capture, and archiving the accurately captured data to realize efficient reuse; for data which are not accurately captured, track dynamic complementation is carried out through an autoregression integral moving average model, the accuracy and integrity of non-abandoned dynamic detail capturing are remarkably improved, it is ensured that the display effect is real and coherent, and accurate inheritance and wide propagation of non-abandoned cultural connotation are facilitated.
Owner:NANJING SUPERMIND INFORMATION TECHNOLOGY CO LTD

Industrial chain situation prediction analysis system and method based on AIGC

The invention discloses an industrial chain situation prediction analysis system and method based on AIGC, and belongs to the field of data processing systems or methods specially suitable for the purposes of commerce, finance, management, supervision or prediction. An AIGC model based on the combination of a generative adversarial network (GAN) and a variational auto-encoder (VAE) is constructed; through adversarial training, KL divergence optimization and adaptive learning rate adjustment, a data rule is accurately captured, a moving average method, an autoregressive integral moving average model (ARIMA) and a random forest algorithm in situation prediction are cooperated, prediction stability and accuracy are enhanced, traditional defects are improved, in the aspect of analysis and management, polynomial fitting interpretation trend is deeper, and the prediction efficiency is improved. Risks and opportunity points are accurately identified through a comprehensive index system and a scientific method, decision making is assisted, on the whole, the industrial chain situation prediction analysis process is comprehensively innovated, scientific industrial development decision making is powerfully promoted, and enterprise competitiveness and industrial resource allocation efficiency are improved.
Owner:MINGWU SHUZHI TECH RES INST (NANJING) CO LTD

Air conditioning system load prediction method and device, medium and equipment

The invention discloses an air conditioning system load prediction method and device, a medium and equipment, and relates to the technical field of load prediction. The method comprises the following steps: firstly, acquiring historical load data of the air conditioning system and load influence factors of the historical load data in the same period, then constructing a preliminary load prediction model based on a seasonal difference autoregression moving average model according to the historical load data, and determining a prediction residual error of the preliminary load prediction model to the historical load data; then training the generalized regression neural network to obtain a residual error prediction model according to the prediction residual error of the load influence factors and the initial load prediction model on the historical load data, and finally inputting the load data to be predicted into the initial load prediction model to carry out initial load prediction, and correcting the load data through the residual error prediction model to obtain an initial load prediction result. And determining the predicted load of the air conditioning system at the target moment according to the initial load and the correction. According to the invention, the convergence speed, the prediction efficiency and the prediction accuracy are improved.
Owner:SHANGHAI HUAQI NEW ENERGY TECHNOLOGY CO LTD

Emotion regulation system based on multi-dimensional perception and evaluation method thereof

The invention discloses an emotion regulation system based on multi-dimensional perception and an evaluation method thereof. In the invention, through the emotion classification and intensity evaluation module using the support vector machine algorithm, the system not only can accurately divide the emotion of the user into different categories, but also can evaluate the intensity of the emotion, so that a more personalized emotion regulation scheme is provided for the user. The accurate emotion recognition enables the system to provide corresponding intervention measures according to the real-time emotion state of the user, such as music relaxation, breathing guidance or emotion catharsis games, so that the user is effectively helped to relieve negative emotion, and the emotion self-management ability is improved. The emotion trend analysis module predicts the emotion change trend by using an autoregressive moving average (ARIMA) model, so that the system can have perspectiveness, identify possible emotion fluctuation in advance and take preventive measures. The method can quickly respond when the emotion of the user is abnormal, and timely assistance is provided, so that the influence of emotion problems on the daily life and work of the user is reduced.
Owner:ZHEJIANG ECONOMIC & TRADE POLYTECHNIC

Heat supply equipment based on computing power and control method

The invention discloses heat supply equipment based on computing power and a control method, and belongs to the technical field of heat supply control. The method comprises the following steps: acquiring heat supply data, and performing anomaly detection on the heat supply data; when the heat supply data is not abnormal, the distribution condition of the hot water in the heat supply pipe network is analyzed, and a flow analysis result and a pressure analysis result are obtained; optimizing the operation parameters of the heat supply network, and calculating the heat recovery efficiency of the heat supply network; constructing and training an autoregressive integral moving average model, inputting current power utilization related data and heat recovery efficiency, and outputting a thermal load demand prediction value; influence weights of the indoor temperature and the outdoor temperature on the thermal load demand are determined, a temperature difference is calculated, a temperature correction coefficient is calculated according to the temperature difference, and a thermal load demand prediction value is adjusted by using the temperature correction coefficient; setting a power corresponding relation, and adjusting the power of the electric boiler by stages; the operation time and the stop time of the electric boiler are calculated according to the operation state data of the electric boiler, and the electric boiler is set according to the operation time and the stop time obtained through calculation.
Owner:JIANGXI FENGSHUO NEW ENERGY TECH CO LTD

Intelligent operation and maintenance system and method for clean room based on digital twinning

The invention discloses a digital twinning-based clean room intelligent operation and maintenance system and method, and relates to the technical field of intelligent operation and maintenance, and the method comprises the steps: obtaining the state data of a clean room through arranging a sensor, obtaining the power data of clean room equipment through an external data source, and carrying out the preprocessing at an edge node, and generating a multi-source time series data set; constructing a multi-scale prediction model by integrating a long short-term memory network, an autoregressive integral moving average model and a graph neural network, and generating a multi-scale sequence data set based on the multi-source time sequence data set; performing analogue simulation on physical field coupling in the clean room through a quantum computing platform to generate a clean room digital twinborn simulation model; and loading the clean room digital twinborn simulation model to a cloud analysis platform, optimizing the running state of the clean room by using a gradient descent method, and generating an optimized operation and maintenance scheme. According to the invention, simulation is carried out on physical field coupling in the clean room through the quantum computing platform, and the authenticity and real-time performance of a simulation model are greatly improved.
Owner:SUZHOU SHUIMU TECH CO LTD

Energy scheduling optimization method for energy storage tunnel

The invention provides an energy scheduling optimization method for an energy storage tunnel, which comprises the following steps: collecting real-time operation data of all energy storage units in the energy storage tunnel, evaluating the health state of each energy storage unit based on a multi-dimensional health monitoring model, and identifying potential faults through a time sequence analysis and anomaly detection mechanism; constructing a multi-level distributed scheduling architecture; based on the historical load data, the external environment factor and the state of the energy storage unit, predicting a load demand through a weighted moving average model, and dynamically adjusting a prediction result of the load demand in combination with an adjustment factor; according to the prediction error of the load demand and the health state threshold value of the energy storage unit, designing an anomaly detection mechanism to judge whether to trigger fault detection, and after the fault detection is triggered, dynamically adjusting the electric quantity of the energy storage unit or switching a standby unit to realize automatic repair of the system; and integrating the health state, the electric quantity state and the load prediction result of the energy storage unit, and dynamically optimizing a global charging and discharging strategy by taking minimization of energy loss and health deterioration as a target.
Owner:TONGJI UNIV

Network bandwidth prediction method and system

The invention discloses a network bandwidth prediction method and system, and the method comprises the steps: collecting historical bandwidth data of a target network, carrying out the prediction through a deep reinforcement learning algorithm, and obtaining a reinforcement learning bandwidth prediction value at each moment; predicting by adopting a heuristic algorithm to obtain a heuristic bandwidth predicted value at each moment; carrying out weighted fusion on the reinforcement learning bandwidth prediction value and the heuristic bandwidth prediction value to obtain a fusion prediction bandwidth at each moment; carrying out serialization processing on the fusion prediction bandwidth at all moments to obtain a fusion prediction bandwidth sequence, and carrying out first-level moving smoothing processing on the fusion prediction bandwidth sequence by adopting an autoregression moving average model to obtain a prediction bandwidth first-level smoothing sequence; and performing secondary dynamic smoothing processing on the fused predicted bandwidth sequence by adopting a Kalman filtering algorithm to obtain a predicted bandwidth secondary smoothing sequence. According to the network bandwidth prediction method and system provided by the embodiment of the invention, the prediction accuracy of the network bandwidth is improved.
Owner:CHONGQING UNIV

Historical time sequence insufficiency-oriented violent snow disaster risk degree probability prediction method

The invention discloses a sudden snow disaster risk degree probability prediction method oriented to insufficient historical time sequences. The method comprises the following steps: step 1), constructing a multi-index risk index based on related data such as historical snow disasters; 2) performing time sequence modeling on the violent snow disaster risk index by adopting an autoregressive integral moving average model, and capturing trend and periodic characteristics of the violent snow disaster risk index; 3) discretizing a continuous risk index of modeling production into a plurality of risk levels, and constructing a state transition probability matrix; step 4), introducing space neighborhood influence and carrier exposure constraint, and constructing a Markov space weighted state transition model; 5) coupling CMIP6 climate scene data, and dynamically adjusting future state transition probability, and 6) fusing ARIMA trend prediction and Markov state transition probability, and outputting future multi-period snowstorm disaster risk level probability distribution.According to the method, the accuracy of snowstorm disaster risk prediction and the modeling ability and prediction adaptability of future climate change scenes are improved.
Owner:INST OF DESERT METEOROLOGY CMA URUMQI

Battery temperature prediction method based on multi-model fusion

The invention belongs to the field of data science and machine learning, and constructs a prediction system fusing a convolutional neural network (CNN), a long-short-term memory network (LSTM), a seasonal autoregressive integral moving average model (SARIMAX) and a data-driven modeling method in order to solve the problem of battery temperature prediction. The system focuses on analyzing transient temperature change during fast charging of the battery and a temperature evolution rule caused by aging, an exclusive data feature extraction and fusion strategy is formulated for different working conditions, and model parameters are optimized. Key performance indexes such as prediction accuracy, model robustness and working condition adaptability are remarkably improved, and the method has a wide application prospect and an important practical value in thermal management of the battery of the electric vehicle.
Owner:TIANMU LAKE INST OF ADVANCED ENERGY STORAGE TECH CO LTD

Direct-current power distribution network fault positioning system and method based on neural network and optimization algorithm

The invention discloses a direct-current power distribution network fault positioning system and method based on a neural network and an optimization algorithm, relates to the field of direct-current power distribution network fault positioning, and designs a fault location strategy in combination with a generalized regression neural network and a grey wolf optimization algorithm. The method comprises the following steps: performing sample expansion on original fault voltage data by adopting an autoregression moving average model to obtain a large number of data samples, performing time-frequency domain feature extraction on a fault transient voltage signal by utilizing S transformation and permutation entropy, constructing a fault feature quantity, inputting the fault feature quantity into a GRNN for training, and optimizing parameters of the GRNN by adopting a GWO of an improved iteration strategy to obtain a fault transient voltage signal; and finally obtaining a fault positioning result. The fault location method designed by the invention is excellent in performance and strong in robustness, and realizes accurate fault location of the MMC type flexible direct-current power distribution network, thereby ensuring safe operation of the flexible direct-current power distribution network.
Owner:SUQIAN POWER SUPPLY COMPANY OF JIANGSU PROVINCE POWER +1

Water quality evaluation method based on data analysis

The invention relates to the technical field of water quality analysis, in particular to a water quality evaluation method based on data analysis, which comprises the following steps: based on a satellite remote sensing technology, analyzing water spectral characteristics by adopting a deep neural network algorithm, and generating water characteristic data. According to the method, the satellite remote sensing technology and the deep neural network are combined, the accuracy of water body spectral feature analysis is improved, particulate matter in water is classified through image recognition, the analysis speed is increased, the result accuracy is improved, environmental DNA sampling is used for evaluating the biological diversity, and basic data are generated for microbial activity analysis; a micro-fluidic chip and a fluorescence labeling method are used for improving the activity analysis sensitivity of microorganisms and algae, a support vector machine algorithm is used for improving the water quality detection accuracy, an autoregression integral moving average model and a random forest algorithm are combined for deep water quality change analysis, and a comprehensive risk assessment model is used for comprehensively assessing the water quality risk. And a basis is provided for accurate water quality management.
Owner:CHINA GEOLOGICAL SURVEY XINING NATURAL RESOURCES COMPREHENSIVE SURVEY CENT