87results about How to "Comprehensive forecast" patented technology

The present invention relates to a reliability prediction method for the power supply of a power distribution network. The method comprises the following steps: selecting a variety of original index factors which influence the power supply reliability; subjecting the original index factors to standardization treatment to obtain standardized index factors; calculating a correlation coefficient between each standardized index factor and a preset reliability evaluation index, and screening out a core index factor which obviously influences the power supply reliability from all index factors according to the correlation coefficient; according to the core index factor, constructing a radial primary function neural network; obtaining the optimal center vector, the optimal base width vector and the optimal output weight of the hidden layer of the radial primary function neural network; according to the optimal center vector, the optimal base width vector and the optimal output weight, obtaining a power supply reliability prediction model; and predicting the power supply reliability of the power distribution network according to the power supply reliability prediction model.

A method, device and equipment for constructing a merchant classification model and merchant classification are disclosed. A method for constructing a merchant classification model includes obtaininga plurality of merchant samples, wherein each merchant sample includes historical transaction information and business model type of that merchant; extracting eigenvectors of each merchant sample; themerchant classification model being trained by a machine learning algorithm according to the business model types of several merchant samples and the extracted eigenvectors. A merchant classificationmethod based on the merchant classification model comprises the following steps: acquiring historical transaction information of the merchant to be classified; extracting a feature vector of the merchant to be classified; the extracted feature vector of the merchant to be classified being input to the merchant classification model to predict the business mode type of the merchant to be classified.

The invention belongs the virtual simulation technical field, in particular to a macroscopic, mid-scope and microscopic multilevel urban parking demand prediction model integrated system, which comprises a system data module, an urban overall parking demand macroscopic prediction module, a comprehensive development sharing parking demand mid-scope prediction module and a parking garage entrance service level microscopic analysis module, wherein the system data module is used for importing and storing parking demand prediction data; the urban overall parking demand macroscopic prediction module is used for predicting the overall parking demand; the comprehensive development sharing parking demand mid-scope prediction module is used for predicting the largest parking demand of each block and is connected with the urban overall parking demand macroscopic prediction module; the parking garage entrance service level microscopic analysis module is used for predicting a parking garage entrance service situation; and the three prediction modules are respectively connected with the system data module. The macroscopic prediction module not only considers the parking demand of traveling vehicles, but also considers the parking demand of the vehicles which are not on trip, the mid-scope prediction module considers the shared parking demand of multi-nature buildings under the reachability situation of buses, bi-directional correction of the prediction results of the macroscopic, mid-scope and the microscopic modules can be realized, the system quantitatively predict the parking demand of different cities of different levels so as to provide important support for different parking researches.

The invention discloses a numerical control machine tool operation state health diagnosis system and diagnosis method. The system comprises an edge data acquisition module, a cloud platform and a client, the cloud platform is connected with the edge data acquisition module and the client. The cloud platform comprises a predictive diagnosis module, an information management and storage module and an application server; and the predictive diagnosis module comprises a real-time diagnosis module, a post-processing diagnosis module and a comprehensive diagnosis module. According to the system, a cloud platform with a diagnosis function is used for replacing an upper computer, the expandability is greatly improved, the diagnosis and prediction tasks can be completed only by deploying corresponding sensors on the machine tool and connecting the sensors to the cloud platform, the real-time state data of the machine tool are managed in a centralized mode through the cloud platform, and the health condition of the machine tool is evaluated and predicted through the diagnosis technology based on the neural network. The diagnosis method is simpler, and the health diagnosis accuracy is high.

The invention discloses a drilling well risk prediction method based on a Markov chain and a Bayesian network, which employs the Markov chain and Bayesian network to perform comparatively comprehensive analysis and prediction on drilling risks from vertical and horizontal aspects, and overcomes the deficiency of treating lack of indicators by the Markov chain. The Markov chain is a vertical prediction method to be used for detecting variable probability distribution determined by samples in future time. The Bayesian network is a horizontal prediction method and displays an index mutual influence relation. The combination of horizontal prediction and vertical prediction methods can solve the problem of lack of non-underlying index data of a multilayer index system to realize risk prediction of macroscopical meaning. The backstepping function of the Bayesian network also provides a basis for risk control.

The invention discloses a fault predication and service life evaluation system of a wind power main bearing. The fault predication and service life evaluation system comprises a data acquisition unit,a data storage unit, a fault predication unit and a service life evaluation unit, wherein the data acquisition unit comprises a plurality of sensors for detecting a vibration component and a temprature signal of the wind power main bearing and a pressure signal in a cavity of the main bearing, and a data acquisition module connected with the plurality of sensors; the data storage unit is used forreceiving data and storing; the fault predication unit is used for carrying out principle component analysis on the data transmitted by the data storage unit, so as to realize fault predication of the wind power main bearing; the service life evaluation unit is used for predicating a residual service life of the main bearing through carrying out the principle component analysis on the data transmitted by the data storage unit. The invention further discloses a fault predication and service life evaluation method of the wind power main bearing. According to the fault predication and service life evaluation system, after the data is acquired, the data is subjected to PCA (Principal Component Analysis) processing; bearing faults are predicated based on a neural network model; the service life of the bearing is predicted based on a similarity principle, and real-time lubricating adjustment of the bearing is also realized based on a predication result.

The invention belongs to the technical field of network traffic prediction, and particularly relates to a combined network traffic prediction method based on ensemble empirical mode decomposition, which comprises the following steps: obtaining original traffic data and preprocessing the original traffic data; decomposing the network flow into IMF components with single frequency on different timescales through ensemble empirical mode decomposition; determining the stationarity of the IMF component sequence through autocorrelation and partial autocorrelation analysis; predicting the stable IMFcomponent by using a linear ARMA model; predicting the non-stationary IMF component by using a nonlinear Elman neural network; summing the predicted values of the IMF component sequences to obtain apredicted value of the network traffic; According to the method, the actual network flow is described and predicted more accurately and comprehensively, so that the prediction precision is improved, and the prediction reliability is improved.

The invention relates to a facial paralysis patient acupuncture treatment effect detection visual system and method based on surface electromyogram (sEMG). The system consists is constructed by connecting a sEMG signal acquiring electrode, a sEMG signal amplifier, a sEMG signal AD (Analog to Digital) converter, a sEMG signal analyzing device and a display in sequence. The method comprises the following steps: acquiring a sEMG signal; amplifying the sEMG signal through the sEMG signal amplifier; transmitting the amplified sEMG signal to the sEMG signal analyzing device through the sEMG signal AD converter for preprocessing; extracting time domain and frequency domain features to construct a feature vector; reducing the dimension of the feature vector by adopting a PCA (Principal Component Analysis) method; calculating a type center distance between a health side and a patient side by using a kmeans clustering method; fitting the type center distance to obtain an AR model; predicting the recovery trend of the patient. By adopting the facial paralysis patient acupuncture treatment effect detection visual system and method, the recovery degrees of muscles on both sides of the face of a facial paralysis patient can be detected accurately under the conditions of freeness from wounds and convenience, the recovery trend of the patient is further predicted, and an auxiliary reference index is provided for clinical treatment of doctors and the rehabilitation effect evaluation of the patient.

The invention provides a gestation diabetes risk monitoring system based on dynamic physics and physical and chemical factors and belongs to the field of medical instruments in the department of obstetrics and gynecology. The gestation diabetes risk monitoring system is characterized by comprising a computer, a toggle switch array, a resistor array and a gestation diabetes pathogenesis risk LED alarming module; a pregnant women information input module of dynamic physics check and physical and chemical factors, a logic switch array module of pregnant women gestation diabetes pathogenesis risk factors and logic regression value computation module of pregnant women gestation diabetes pathogenesis risk are arranged in the computer; a voltage comparison module and an LED array are arranged in the gestation diabetes pathogenesis risk LED alarming module. According to the invention, the logic switch value is utilized to control the make-and-break state of the toggle switch; a risk factor value in the logic regression manner is utilized to control the resistance value of the resistor array, so as to indicate the relative risk degree; the resistance value of the resistor array is utilized to control a voltage comparator, so as to output electrical level and light the LED alarm. According to the invention, the risk degree of the dynamic gestation diabetes can be comprehensively evaluated from multivariate physical and chemical factors and the real-time alarm can be conducted.

The invention provides an information discrimination method and system. The method comprises the steps of based on a web crawler technology, retrieving and collecting webpage information corresponding to hotspot information of a traditional media and a social media, and processing the collected webpage information to obtain traditional and social media data sets marked with categorical data and divided into training set data and test set data; based on the training set data, performing topic modeling to obtain topic and keyword documents, and establishing a topic characteristic set corresponding to traditional media data and a keyword characteristic set corresponding to social media data; and training a classifier by utilizing the topic characteristic set and the keyword characteristic set, and performing classification discrimination on the test set data through the obtained traditional media classifier and social media classifier to obtain traditional media data capable of triggering social media reports and/or social media data capable of triggering traditional media reports. By monitoring a plurality of medias, the trend of public sentiment development can be analyzed and predicted more comprehensively and more quickly.

The invention provides a paper currency form detection method, and belongs to the financial equipment field. The paper currency form detection method includes the steps: by means of two first sensorswhich are symmetrically arranged at two sides of the transmission surface of the first transmission path, acquiring the first state information of the paper currency transmitted on the first transmission path; and based on the first state information, acquiring the form of the paper currency. The paper currency form detection method can determine whether the paper currency are in the inclined state or the state that the neighboring paper currency are connected together, can make relatively more comprehensive prediction of the state of the paper currency, and can improve the determination accuracy. The invention also provides a paper currency form detection device. The paper currency form detection device includes a first transmission path, first sensors and a processor, wherein the two first sensors are symmetrically arranged at two sides of the transmission surface of the first transmission path in the transmission direction being perpendicular to the first transmission path; and thedistance between the two first sensors is not more than the standard length of paper currency. The paper currency form detection device has the advantages of being simple in structure, being convenient to use, being high in detection efficiency and being high in accuracy. The invention also provides self-service depositing and withdrawing equipment. The self-service depositing and withdrawing equipment includes the paper currency form detection device, and has higher usage stability.

The invention discloses a CGRU-based strong space-time characteristic radar echo proximity prediction method, which comprises the following steps: (1) obtaining a continuous radar echo image related to weather proximity prediction, preprocessing the continuous radar echo image, and constructing tensor data with unified time dimension and space dimension; (2) constructing and training a 3DCNN-CGRUnetwork training model to obtain a 3DCNN-CGRU coding prediction network model; (3) inputting the tensor data of the continuous radar echo image sequence for weather proximity prediction in the step (1) into the 3DCNN-CGRU network model to generate a weather proximity prediction result; according to the invention, the 3DCNN-CGRU network model is provided, the transmission capability of spatial-temporal features is enhanced, the spatial-temporal feature correlation of continuous radar echo images is captured and learned more effectively, and the problems that spatial-temporal information is easyto lose and the prediction accuracy is low are solved.

The invention relates to the field of education big data mining, graph neural network and learner behavior modeling, and provides a knowledge tracking method based on test question heterogeneous graph representation and learner embedding, the method adopts a heterogeneous graph neural network technology in the deep learning field to represent multi-dimensional features of test questions, and meanwhile, complex learner characteristics are modeled in combination with a project reaction theory, and ability characteristics of learners are captured by adopting a clustering mode and the like; finally, the test question and learner mixed features are fused to a traditional knowledge tracking model, and knowledge tracking and learner performance prediction for different learner groups are achieved. According to the invention, the learning condition of the learner can be scientifically and comprehensively predicted, and the purpose of assisting the teacher in precise teaching is achieved.

The invention discloses a portable gait information acquisition device and relates to an information acquisition device. The device consists of an electromyographic signal module, a gyroscope module, a laser diastimeter, a plantar pressure sensor, a microprocessor, an SD card module and a display screen, wherein the electromyographic signal module is provided with a differential amplifier, an analog multiplexer, an A/D converter and a digital controller; the input end of the differential amplifier is connected with an electromyographic signal detection electrode sheet, the output end of the differential amplifier is connected with the input end of the multiplexer, the output end of the multiplexer is connected with the input end of the A/D converter, the output end of the A/D converter is connected with the digital controller, the digital controller is connected with a channel selection signal input end of the multiplexer, and the output end of the digital controller is communicated with the first microprocessor and is connected with the first SD card module; the gyroscope module is connected with an I/O port of a second microprocessor, the diastimeter is connected with an A/D conversion interface of the second microprocessor, the sensor is connected with the A/D conversion interface of the second microprocessor, and an output port of the second microprocessor is connected with a second SD card module and the display screen.

The invention provides a path selection method, which is used for determining an optimal obstacle avoidance path from a plurality of candidate paths and can improve the path selection efficiency. The method comprises the following steps: acquiring road basic information of a target road area, position information of an obstacle in the target road area and a plurality of candidate paths of a target object in the target road area; determining an obstacle risk relationship of the target road area according to the road basic information and the position information of the obstacle, wherein the obstacle risk relationship is used for obtaining an obstacle risk of any position in the target road area; determining the comprehensive obstacle risk of each candidate path according to the obstacle risk relationship and the position distribution of each candidate path in the target road area; and determining a target path from the plurality of candidate paths according to the comprehensive obstacle risk of each candidate path.

The invention provides an automatic driving vehicle implementation method based on hybrid enhanced intelligence. Wherein the automatic driving vehicle is provided with a vehicle-mounted sensor and a navigation positioning map device so as to realize sensing, navigation, decision planning and control technologies on a road environment; an edge computing server and a roadside intelligent sensor areinstalled at the position, close to the automatic driving vehicle, of the roadside. According to the intelligent characteristics of the automatic driving vehicle, real-time perception of the road environment is mainly achieved through a vehicle-mounted sensor and a roadside sensor, data understanding and extracting work is conducted on perceived data information, and driving decision making and path planning work of the automatic driving vehicle is conducted; the hybrid enhanced intelligence makes full use of the respective advantages of the two kinds of intelligence, comprehensively realizesa relatively strong pushing function for the automatic driving vehicle, can realize perception in a complex road environment, and further realizes high-efficiency driving safety of the automatic driving vehicle.

The invention discloses a method for constructing a digital twin system, which comprises the following steps of determining a plurality of equipment types, and respectively establishing an equipment model corresponding to each type of equipment, namely establishing a component model corresponding to each structural component of the equipment; establishing a measuring point model corresponding to each structural component of each type of equipment; building a monitoring model corresponding to each type of equipment based on the working condition attribute and the environment attribute of the equipment; establishing a fault model corresponding to each equipment model, wherein the fault model comprises one or more fault indexes corresponding to the equipment model; and based on the equipment model, the corresponding measuring point model, the monitoring model and the fault model, constructing a digital twin system corresponding to the equipment so as to collect state data of each component model in the equipment model according to the corresponding measuring point model and the monitoring model, and determining fault information of the equipment according to the fault model. The invention also discloses corresponding computing equipment.

The invention provides a method and system for deducing a bonding site of oligonucleotide on a genome. According to the method, an index table of thermodynamics of arbitrary 7-mer oligonucleotide is built, a stable bonding sequence of the oligonucleotide to be deduced on the thermodynamics is acquired by using the index table, the position of the bonding sequence is positioned on the genome, thus, the bonding site of the oligonucleotide to be deduced can be efficiently deduced, and a basis is further provided for judging whether the oligonucleotide is high-quality oligonucleotide with regard to a target sequence in the genome. The invention also provides a system for the bonding site of the oligonucleotide on the genome. With the adoption of the above method by the system, the real bonding condition of the oligonucleotide and the target sequence in the genome can be efficiently reflected from the thermodynamics property, and an accurate basis can be provided for judging the quality of the oligonucleotide to be deduced.

The embodiment of the invention provides a traffic operation state prediction method, device and system. The method comprises the following steps: acquiring multi-source traffic data of a target intersection; and on the basis of the multi-source traffic data, establishing a traffic operation state model to obtain a road traffic state and a vehicle traffic state of the target intersection. According to the traffic operation state prediction method, device and system provided by the embodiment of the invention, the traffic flow characteristics of the three types of traffic data sources are integrated and extracted by adopting a multi-modal data fusion technology, and the road traffic state of the current intersection is obtained. Moreover, edge nodes process floating vehicle track data to obtain time sequence characteristics and state characteristics of motor vehicle track information. According to the embodiment of the invention, the traffic state of the intersection is described from two levels of vehicles and roads, the traffic operation state of the intersection can be accurately and comprehensively predicted, and the safety and efficiency of road traffic are improved.

The invention discloses a model and a method for predicting the occurrence of heat stroke based on machine learning. The method includes 1: establishing a database of high temperature events in typical high temperature cities 2, carrying out data matching and cleaning on that database; 3, applying the Boruta algorithm to carry out variable screening; 4, establishing a training data set and a verification data set of a random forest model; 5, determining that parameters of the random for and establishing a random forest model; 6, arranging that importance of variables; 7, evaluating that prediction result of the model; Step 8: using Bland- Altman consistency evaluation method to evaluate the model results. The method of the invention can better represent the adverse health effects of high temperature heat wave events; It can better fit the non-linear relationship variables and improve the effect of model fitting. Forecast the occurrence of heatstroke in a comprehensive way; It can reduce the population health damage and reduce the health-related economic losses.

The invention discloses a method for rapidly predicting heterosis based on genome size, and belongs to the technical field of crop breeding. The method includes the following steps: S1. selecting a hybrid combination parent according to the relative difference percentage of genome size and Nei genetic distance between crops; S2. emasculating and hybridizing the selected hybrid combination parent to obtain F1 generation; S3. carrying out heterosis analysis on target traits of the F1 generation; S4. analyzing the correlation between heterosis of the target traits of the F1 generation and Nei genetic distance between parents; S5. analyzing the correlation between heterosis of the target traits of the F1 generation and absolute value of genome size difference between parents; and S6. combiningthe above analysis results, selecting strong heterosis hybrid combinations and predicting heterosis of the F1 generation at the same time. The breeding method is beneficial to improving breeding efficiency and reducing breeding cost, and has the advantage of wide applicability.

The invention discloses a numerical simulation calculation method for a multi-layer and multi-pass welding process of a header tube socket. The method comprises the following steps: S1, establishing a three-dimensional thermal coupling calculation model of a tube socket, a header and a welding seam, and performing finite element mesh generation on a solid model of the header tube socket weldment to form a plurality of mesh units of the solid model; S2, setting initial conditions and boundary conditions of the welding model; S3, determining a heat source equation and welding parameters used by the saddle-shaped welding seam of the header pipe base; and 4, submitting and solving the task, and carrying out post-processing and analysis. According to the structural features of the saddle-shaped welding seam of the tube socket header, the entity model is established in a targeted mode, grids are divided in a regional mode, welding heat source parameters are corrected, the change rule of a post-welding temperature field and a stress-strain field can be predicted, and the actual saddle-shaped welding seam welding process is guided.