62results about How to "Enables real-time forecasting" patented technology

The invention discloses a traffic flow prediction method of a divergence convolution recurrent neural network based on a space-time diagram. The traffic flow prediction method is characterized in thata directed weighted graph of a road network is constructed based on spatial features of a traffic network, then a traffic flow prediction model of a graphic divergence convolution recurrent neural network is constructed by taking the directed weighted graph as a basic unit of prediction, deep learning is carried out by means of time-space characteristics of the traffic network, time-space prediction is carried out on the traffic flow of the traffic road network, a final traffic flow prediction model is constructed, and real-time prediction of the traffic flow is realized. The traffic flow prediction method has the advantages of precise prediction and high fitting degree.

The invention provides a method for constructing a photovoltaic power station generation capacity short-term prediction model based on multiple neural network combinational algorithms and belongs to the technical field of photovoltaic power generation, power grid connection technology and solar energy photovoltaic forecasting. The method overcomes the problem that a usually-used algorithm for constructing the photovoltaic power station generation capacity short-term prediction model is single and is likely to fall into local optimization, further resulting in big measurement error of the prediction model. The technical construction method of the invention is realized as follows: firstly using four different neural network algorithms to construct sub-models for neural network prediction; secondly screening and classifying weather information and analyzing the suitability of the various sub-models for neural network prediction; giving weighted parameter values of the sub-models in a combined model according to the suitability to further make the combined neural network model for prediction suitable for different weather conditions and then completing the construction of the photovoltaic power station generation capacity short-term prediction model. The method is mainly used for photovoltaic power station grid connection short-term prediction.

The embodiment of the invention discloses a method and a device for predicting a congested road segment, equipment and a storage medium. The method comprises the following steps of enabling a server to obtain the position correlation information of an abnormal vehicle sent by at least one motor vehicle terminal, wherein the position correlation information comprises position information of the abnormal vehicle and abnormal time information; enabling the server to predict the congested road segment in a map according to the obtained position correlation information; enabling the server to execute a corresponding congested road segment processing strategy according to the predicting result of the congested road segment. By adopting the technical scheme, the method has the advantages that the massive data processing and large-scale computing are realized by the server, so that the congested road segment can be predicted in real time; according to the predicting result of the congested road segment, the number of vehicles being driven into the congested road segment is reduced before the road is heavily congested, the traffic congestion is effectively relieved, and the passing efficiency of automobiles and the use experience of a user are improved.

The invention discloses a photovoltaic power station generation power prediction method comprising the steps that six meteorological characteristics are daily extracted by using the historical meteorological data of a photovoltaic power station so that a meteorological characteristic library is established; the daily characteristic data in the meteorological characteristic library are clustered through a KFCM algorithm so as to realize weather type classification, and class marking is performed on the daily power data and the meteorological data; an SVR sub-model is established for each classof power data and meteorological data according to the class mark; the weather type of the target day is identified by using the SVM through the target day weather characteristics provided by numerical weather prediction and the corresponding SVR sub-model is selected; an ARIMA model is established by using the real-time monitoring data of the target day, and real-time prediction of the irradiation intensity and the temperature can be realized by using the rolling prediction model; and the prediction values of the irradiation intensity and the temperature are inputted to the selected SVR sub-model so that the photovoltaic power station power prediction result can be obtained. The photovoltaic power station generation power prediction accuracy can be enhanced.

The invention provides a multivariate time series abnormal mode prediction method and a data acquisition monitoring device. The method comprises the steps of obtaining an optimal k value of an MMOD algorithm based on historical data according to a natural neighbor principle; carrying out online expansion on the MMOD algorithm to achieve online identification of a multivariate time sequence abnormal mode; and according to an incremental fuzzy adaptive clustering algorithm, achieving conversion from the multivariate time series sub-sequence to the observation sequence, constructing a hidden Markov model based on a Baum-Welch algorithm and all the observation sequences, and achieving online prediction of the multivariate time sequence abnormal mode based on the constructed hidden Markov model. Through the multivariate time series data acquisition system of the cloud platform, related data needing to be mined can be better acquired, and real-time prediction of the abnormal mode of the multivariate time series can be achieved by utilizing an online density difference anomaly detection algorithm and a Markov prediction model algorithm. A monitoring system APP is constructed, so that real-time monitoring is facilitated.

The invention relates to a sensor-based odor monitoring system of an organic waste treatment facility. The odor monitoring system comprises a cloud platform and a plurality of odor gas data acquisition devices; the odor gas data acquisition devices are responsible for collecting basic data in an environment and uploading to the cloud platform; the cloud platform is responsible for inputting the received basic data into calculation models in the cloud platform for operation and feeding back a result to an environmental monitoring department; the cloud platform comprises a server and an odor pollution forecast module; the odor pollution forecast module calculates an odor gas concentration value according to data transmitted by the odor gas data acquisition device, performs evaluation, forecast and early warning on an odor pollution situation and feeds back a result to the environmental monitoring department; a plurality of odor gas concentration calculation models are preset in the odor pollution forecast module; and a pollutant diffusion model is further preset in the cloud platform. The system can accurately monitor an environmental odor concentration and odor strength in real time, judges and forecasts odor pollution diffusion and performs the early warning on odor pollution.

The present invention discloses a wind speed prediction method of a wind farm. Problems are mainly considered that spatial correlation among wind farms, unscented Kalman Filter optimization, and the like are not well considered in an existing method. The method mainly comprises: calculating a rank correlation coefficient between a target wind farm and the other 21 wind farms if 22 wind farms are given; determining a wind farm for prediction according to the correlation coefficient; and selecting a wind farm with a Kendall rank correlation coefficient greater than 0.55 and a Spearman rank correlation coefficient greater than 0.75; then establishing a non-linear state space model by using support vector machine regression, and performing unscented Kalman filter prediction by using the established non-linear state space model; optimizing a scale parameter of the unscented Kalman filter according to a principle of prediction error minimization; and finally, selecting wind speed data of a wind farm of a same time in four years, and performing grey correlation analysis by using the wind speed data and wind speed data of a target wind power turbine, No.9 wind power turbine, of the same time in the first year.

The invention discloses a flight delay real-time probability prediction method based on a Bayesian network algorithm, and the method comprises the steps: formulating a flight delay judgment standard,analyzing a delay wave and the impact on flight delay, and determining the release fairness of departure flights; analyzing the delay characteristics, determining flight delay factors, and creating aflight delay dynamic prediction model based on a Bayesian network; adopting a dynamic prediction technology based on a time sequence to predict the present transverse wave and measurement index to obtain a final flight delay prediction value, and generating a prediction set; and carrying out probability prediction on prediction set data by utilizing the flight delay dynamic prediction model obtained by training, and obtaining a prediction value of each flight delay level by adopting a probability maximum principle. According to the invention, real-time probability prediction can be carried outon the departure delay level of a single flight of an airport every day, the flight delay prediction precision is improved, a delay early warning notice is issued to passengers in time, an operationstrategy is adjusted in time, and various adverse effects caused by flight delay are reduced.

The invention discloses a demand prediction method and system for shared equipment. The method comprises: acquiring positioning data of a target area within a predetermined time period; inputting the positioning data to a preprocessing layer of a pre-established neural network model, and processing the positioning data according to a preprocessing rule to obtain sample data corresponding to the target area; inputting the sample data to a hidden layer of the neural network model to carry out sample training; and after a prediction instruction is acquired, receiving current positioning data and inputting the current positioning data to the trained neural network model to obtain a prediction result. According to the method, the neural network model is established using a neural network algorithm, a large amount of sample data is trained by deep learning, and after the current positioning data is input, a prediction result of demand corresponding to the target area can be obtained, so that real-time prediction is realized. In addition, after the positioning data is acquired, the positioning data is preprocessed, so that the accuracy of the prediction result can be improved.

The invention discloses an intranet attack early warning method. The method at least comprises the following steps: obtaining intranet attack event data regularly according to a first preset time interval; preprocessing the intranet attack event data to obtain a transaction data set, and storing the transaction data set in a database; generating an association rule from the transaction data according to an Apriori algorithm, storing the association rule in a database, and automatically updating the association rule; acquiring real-time attack event data regularly according to a second preset time interval, and preprocessing the real-time attack event data to obtain preprocessed data; matching the preprocessed data with the antecedent of the association rule through an exception analyzer toobtain a predicted unknown attack; and displaying the unknown attack and the association rule on a Web interface. According to the method, real-time prediction of the intranet attack event can be accurately realized, so that decision support can be provided for network information management personnel, and attack behaviors can be effectively prevented.

The invention relates to a method for quickly detecting an extracting solution of Ganmaoling granules by utilizing near-infrared spectrometry. The method comprises the steps of linarin content determination and / or chlorogenic acid content determination and / or solid content determination. According to the method provided by the invention, linarin content, chlorogenic acid content and solid content near-infrared online analytical methods are established in an extraction process of the Ganmaoling granules, and are applied to online detection, so that automatic detection and real-time prediction of various index contents of the extraction process of the Ganmaoling granules are realized; an established model is high in prediction precision, and high in accuracy, and meets the requirement of quantitative analysis in actual production; by the method, quick and efficient real-time monitoring and control can be carried out on quality of the extraction process, so that the safety, stability and effectiveness of the final product quality are favorably ensured.

The invention discloses a method for monitoring the gas flow development process in the blast furnace material distribution period and predicting the gas utilization rate. The method comprises the first step of data collecting and processing, the second step of infrared image processing, the third step of image feature extraction, the fourth step of material distribution period gas flow distribution dynamic changing model construction, the fifth step of gas flow center feature extraction, the sixth step of image and material surface position calibration, the seventh step of material distribution period gas flow center dynamic change model construction and the eighth step of gas utilization rate prediction model construction. According to the method, collected furnace roof infrared images are treated, the clustering algorithm, the statistics method, the feature recognition technology and the mode recognition technology are utilized for achieving dynamic tracking of the material distribution period gas flow distribution state and falling point distribution of the gas flow center on the material surface, the neural network algorithm is utilized for finding the relation between the material distribution period gas flow development process and the gas utilization rate, real-time prediction of the gas flow utilization rate is achieved, and assistance is provided for intelligent production.

The invention discloses a health level evaluation method of a thermal power generating unit based on data analysis, belongs to the field of thermal power generation, The aim of invention is to providea health level evaluation method of a thermal power generating unit based on data analysis to evaluate the operation status. The main points of the technical scheme are as follows: S1, acquiring historical operation data for a period of time from the real-time information monitoring and management system of thermal power generating units, screening the historical operation data, and selecting thehealthy operation data; S2, determining the parameters to be measured, selecting the independent variables related to the parameters, and carrying out curve fitting on the parameters and the independent variables related to the parameters to establish a mathematical model of each parameter; S3: establishing the scoring rules based on the mathematical models of each parameter. The method can be used to realize the real-time prediction of parameters and to judge whether the predicted value is normal or not.

The invention provides a high-speed railway train operation late time prediction method. The method comprises the steps of obtaining a historical data set; selecting a training data set and a test data set by using a Bootstrapping strategy to obtain r weak learners integrated with a random weight neural network model; using a Weighted Voting combined strategy so that the strong learning device Bagging-RVFLNs prediction model is obtained; using the strong learning device Bagging-RVFLNs prediction model and predicting the predicted high-speed railway trains for a given late time and late station, and acquiring the delay prediction time; using the strong learning Bagging-RVFLNs prediction model to predict the late time of the next station or interval, and obtain a new late prediction time; ifyou need to further improve the operation speed of the late time prediction method, using online sequential integrated random weight neural network The network model replaces the strong learning device Bagging-RVFLNs prediction model. the invention uses the integrated learning random weight neural network to realize real-time prediction of the high-speed train late time, and the prediction accuracy is high, which provides assistance for the scheduling work of the high-speed railway dispatcher.

The embodiment of the invention discloses a soil and rock stratum hidden danger information evaluation system based on same-hole measurement. The soil and rock stratum hidden danger information evaluation system comprises a multi-source information statistical analysis and storage unit, a same-hole monitoring device and a real-time prediction and early warning platform. Soil and rock stratum indexes obtained by the same-hole monitoring device are transmitted to the multi-source information statistical analysis and storage unit to be analyzed and processed, hidden danger information of the soiland rock stratum is evaluated through the real-time prediction and early warning platform, and collapse risk prediction and early warning are achieved. The method comprises the steps that a stratum core sample is drilled, a monitoring hole and an auxiliary detection hole radiating outwards with the monitoring hole as the center are formed, quantitative indexes of the physical property and the mechanical property of the soil body core sample are obtained, and a soil body soft stratum distribution model is constructed in combination with adjacent well geological survey data. The same-hole monitoring of geological, hydrological and deformation multi-source information is realized, the space-time four-dimensional dynamic information of the underground water level, the in-hole osmotic pressure, the deep displacement and the hole wall inclination angle can be acquired in real time for a long time in an unattended operation environment, the hidden danger monitoring cost of a soil layer and astratum is saved, the monitoring accuracy is improved, and the monitoring efficiency is improved.

The invention discloses an intelligent detection method for the water permeation rate of a membrane bioreactor MBR, and belongs to the field of online detection of water quality parameters of sewage treatment. Five process variables with high relativity to the water permeation rate are provided by using a feature analysis method based on biochemical reaction features in an MBR membrane sewage treatment process, a water permeation rate soft measurement technology is designed, and the water permeation rate soft measurement technology is inserted into an intelligent detection system, thus developing operation-facilitating human-machine interaction software; meanwhile, based on a functional requirement, the intelligent detection system for the MBR membrane sewage treatment process is designed; an intelligent water permeation detection system hardware platform, operation software and the water permeation rate soft measurement technology are integrated so as to form a complete intelligent water permeation detection system. The intelligent detection method can quickly and accurately forecast the size of the water permeation rate in the membrane sewage treatment process, and fills the blank of real-time detection of the water permeation rate in the MBR membrane sewage treatment process home and abroad.

The invention belongs to the field of control science and engineering, belongs to the field of environmental science and engineering, and relates to a soft sensing method of out-of-water TP (total phosphorus) for sewage treatment based on a reservoir network. Out-of-water TP concentration is an important monitoring index for urban sewage treatment plants and important index for water quality evaluation. In order to solve the problems, for example, out-of-water TP measurement process in current sewage treatment is complex, instrumentation and equipment are high in manufacture cost and high in maintenance cost and measurement results accuracy is low, the method of the invention employs principal component analysis to determine input variables of a soft sensing model; a reservoir structure optimizing algorithm based on contribution rate is designed, network structure is optimized, and network performance is improved; a soft sensing model of out-of-water TP is established based on a modified reservoir network to provide quick, effective and accurate measurement of out-of-water TP in sewage treatment, the level of real-time water quality monitoring is increased for urban sewage treatment plants, and normal treatment of urban sewage is guaranteed.

The present invention relates to a rib spalling real-time prediction method. A data processing main station, an electromagnetic wave receiving and transmitting device, a signal collector and a three-dimensional scanner are provided. The data processing main station is electrically connected with the three-dimensional scanner and the signal collector; the electromagnetic wave receiving and transmitting device is electrically connected with the signal collector; the three-dimensional scanner is configured to perform surface crack scanning and identification of the rib spalling and transmit the surface crack scanning and identification information to the data processing main station, and the data processing main station obtains the surface crack scanning and identification. The rib spalling real-time prediction method is reasonable in design, compact in structure and convenient to use.

The invention provides a brain disease prediction system, which comprises a mobile terminal, wherein the mobile terminal comprises an electroencephalogram signal acquisition device and a disease prediction module; the electroencephalogram signal acquisition device acquires the characteristic data of the electroencephalogram signal of a patient and sends the characteristic data to the disease prediction module; the disease prediction module receives the parameters of a prediction model of brain diseases of a patient, establishes the prediction model of the brain diseases of the patient according to the parameters, inputs the characteristic data of the electroencephalogram signal into the prediction model of the brain diseases of the patient, and performs real-time prediction on the brain diseases of the patient. The complex training task of the disease prediction model is completed outside the mobile terminal, the mobile terminal only receives the parameters of the disease prediction model and establishes the prediction model of the brain diseases of the patient according to the parameters, the requirements of low complexity and portability of the mobile terminal can be met, beforethe disease condition of the patient occurs, the system can quickly respond and remind the patient so as to greatly reduce the probability of the disease condition of the patient.

The invention discloses an agricultural machinery structure residual deformation prediction method based on a welding component linkage effect. The agricultural machinery structure residual deformation prediction method comprises the following steps: S1, determining a dangerous area of a welding part in an agricultural machinery structure; s2, determining a linkage factor between damage areas under harmonic response impact; s3, measuring the residual stress of the damaged area after welding; s4, determining a linkage progressive function of different damage areas; and S5, predicting the residual deformation of the agricultural machinery structure based on the linkage effect. The method is high in prediction precision and can accurately and efficiently predict the residual deformation of the agricultural machinery structure.

The invention relates to the technical field of agricultural equipment, in particular to an automatic counting device for pests causing plant diseases and pest disasters to medlar. The device includesa support, a wind direction transducer, a wind speed transducer, a light intensity transducer, an air humidity transducer, a rain amount transducer, a control box, a solar cell panel and a pest counting mechanism are fixedly installed on the support, the control box is internally provided with a collecting system, and the pest counting mechanism includes a pest entrapping box; a door plate is hinged to one side of the pest entrapping box, a camera is installed at one end of the interior of the pest entrapping box, a sliding track is installed in front of the camera and provided with a slidingblock, a supporting base is installed on the sliding block and provided with a fixing plate, the top of the fixing plate is provided with a storage roller, the bottom of the fixing plate is providedwith a winding-up roller, the storage roller is wound with a pest entrapping cloth, and the end, away from the storage roller, of the pest entrapping cloth bypasses a guiding roller and is connected to the wind-up roller. The automatic counting device can achieve automatic counting of medlar pests, and improve the accuracy of pest counting.

The invention belongs to the technical field of circuit power-off, and discloses an intelligent circuit and a method for controlling power-off. The intelligent circuit for controlling power-off comprises a power supply module, a current detection module, a voltage detection module, a main control module, a circuit monitoring module, a power-off test module, an alarm module and a display module. The circuit comprises a power supply module, a current detection module, a voltage detection module, a main control module, a circuit monitoring module, a power-off test module and a display module. Theinvention solves the problem that the existing single instruction power-off test can not detect whether the power-off protection mechanism is correct when the card executes data recovery or not through the power-off test in the execution process of writing data instructions to the smart card by the power-off test module and the power-off test in the execution process of the data recovery instructions. At the same time, through the circuit monitoring module, the alarm module can detect circuit faults in time, and send out a warning sound to remind the staff to do a good job of protective measures.

The invention relates to a method for rapidly detecting a preparation process of Qizhi Weitong granules with NIRS (near infrared spectroscopy) and an application. An NIRS online analysis method for a water extraction process, a volatile oil extraction process and an extracting solution concentration process of the preparation process of the Qizhi Weitong granules is established and applied to online detection, so that automatic detection of the preparation process of the Qizhi Weitong granules and real-time prediction of content of each quality control index are realized; an established model is high in prediction precision and accuracy and meets the requirement for quantitative analysis in actual production; compared with a traditional pharmacopeia method, the method has the advantages that on the premise that the accuracy is guaranteed, the analysis efficiency is increased greatly, the quality of the extraction processes can be monitored and controlled in real time rapidly and efficiently, and accordingly, guarantee of safety, stability and effectiveness of the quality of final products is facilitated.

The invention relates to a method for quickly detecting a water extraction process during the preparation of Qizhiweitong granules by use of near-infrared spectroscopy and application. According to the invention, a near-infrared spectroscopy online analysis method is established for a water extraction process during the preparation of Qizhiweitong granules and applied to online detection, and automatic detection of the water extraction process during the preparation of Qizhiweitong granules and real-time prediction of various quality control index content are realized; the established model has high prediction precision and high accuracy and meets the requirements of quantitative analysis in practical production; and compared with a traditional pharmacopeia method, the method has the advantages that the analysis efficiency is greatly improved on the basis of guaranteeing accuracy, and the quality of the water extraction process can be quickly and efficiently monitored and controlled in real time, so that the safety, stability and effectiveness of the final product quality can be guaranteed.

The invention discloses a rock-soil side slope geological disaster early warning system, and the system comprises a slope space displacement analysis module which is used for analyzing the space stability of a rock-soil side slope through collecting the surface displacement and deep displacement of the rock-soil side slope; the slope sound wave stability analysis module is used for analyzing the internal structure stability of the rock-soil side slope by collecting the wave velocity response value of the rock-soil side slope; the slope seepage stability analysis module is used for analyzing the water content stability of the rock-soil side slope under the conditions of different surface water levels and / or different underground water levels by collecting underground water movement conditions of the rock-soil side slope; the slope vibration stability analysis module is used for analyzing the seismic stability of the rock-soil side slope by collecting horizontal and vertical seismic waves of the rock-soil side slope; the geological disaster early warning module is used for predicting the probability of occurrence of geological disasters on the rock-soil side slope by collecting real-time environment data of the rock-soil side slope and generating an early warning signal; the technical support is provided for the address disaster prediction of the rock-soil slope.

The invention belongs to the field of control science and engineering, belongs to the field of environmental science and engineering, and relates to a soft sensing method of out-of-water TP (total phosphorus) for sewage treatment based on a reservoir network. Out-of-water TP concentration is an important monitoring index for urban sewage treatment plants and important index for water quality evaluation. In order to solve the problems, for example, out-of-water TP measurement process in current sewage treatment is complex, instrumentation and equipment are high in manufacture cost and high in maintenance cost and measurement results accuracy is low, the method of the invention employs principal component analysis to determine input variables of a soft sensing model; a reservoir structure optimizing algorithm based on contribution rate is designed, network structure is optimized, and network performance is improved; a soft sensing model of out-of-water TP is established based on a modified reservoir network to provide quick, effective and accurate measurement of out-of-water TP in sewage treatment, the level of real-time water quality monitoring is increased for urban sewage treatment plants, and normal treatment of urban sewage is guaranteed.

The invention provides a shield utilization rate prediction and operation parameter optimization method and system based on SVR and PSO. The method comprises the following steps of 1, screening load and operation parameters from machine operation data, and preprocessing the screened data; 2, constructing a data set by using the preprocessed data, the geological type and the utilization rate of each ring, and dividing the data set; 3, establishing a shield utilization rate prediction model by using the SVR and the data set; 4, constructing an optimization equation with the maximum construction progress as a target and operation parameter changes, load changes and geological types as constraint conditions; and 5, obtaining optimal operation parameters under a specific geological type by using an equation established by PSO optimization, so that the construction progress is maximum. According to the method, the utilization rate can be accurately predicted, shield operation can be optimized, safe and rapid tunneling can be achieved, and good engineering application value is achieved.

The invention discloses a method and a system for predicting a passenger rate benchmark, and the method comprises the following steps: determining a core original variable in basic data of a data source, wherein the basic data of the data source represents a basic data set affecting the change of the passenger flow rate; performing data preprocessing on the core original variable to obtain a target data variable; processing the target data variable by using a preset regression model to obtain a target prediction variable; performing parameter adjustment on the target prediction variable to obtain a fitting model, and analyzing the fitting model to determine a regression equation; and taking the actual passenger flow rate as an input value of a regression equation, and predicting the targetpassenger flow rate of the prediction time in real time to obtain a prediction value of the target passenger rate. According to the invention, the real-time prediction of the passenger rate change isrealized, and the accuracy of the passenger rate prediction is improved.

The invention discloses a large-span bridge vibration response prediction method under typhoon action based on data driving. The large-span bridge vibration response prediction method comprises the following steps: S1, calculating a plurality of typhoon characteristic parameters, and extracting bridge vibration response caused by typhoon from bridge vibration response monitoring data; S2, dividingthe typhoon characteristic parameters and the bridge vibration response caused by the typhoon into a training set and a test set; S3, inputting the training set into a quantile random forest (QRF), obtaining an optimal hyper-parameter of the QRF by adopting a Bayesian optimization algorithm, comparing the importance of each parameter of typhoon characteristics by combining the optimal QRF, and determining a final input characteristic; and S4, inputting the corresponding typhoon characteristic parameters in the test set into the QRF according to an input characteristic comparison result, and taking an output value as a typhoon-induced response probability prediction value. For the large-span bridge vibration response prediction method, the accuracy and efficiency of the prediction result are obviously higher than those of other parameter optimization methods or finite element model methods, and the uncertainty of the prediction process can be considered.