1517 results about "State prediction" patented technology

The present invention provides an intelligent road facility system. The system comprises: a road side unit having perception, communication, control, driving area calculation functions; a traffic control unit and a traffic control center; a vehicle unit and a vehicle interface; a traffic operation center; and a calculation and information service center based on cloud. The road side unit is configured to provide real-time vehicle environmental perception and traffic state prediction and send an instant control command to a corresponding vehicle unit; the traffic control unit and the traffic control center and the traffic operation center are configured to provide short-item and medium-and-long-term traffic state prediction and management and planning decision and employ the calculation andinformation service platform based on cloud to collect and process traffic information to obtain an instant control command; and the vehicle unit is configured to collect data generated by the vehicles, send the data to the road side unit and receive information and a control command from the road side unit. The intelligent road facility system provides an efficient path for rapid achieving of grounding application such as unmanned driving and intelligent network connection traffic system.

A platoon model allows improved prediction of preceding vehicle future state. In this context, the preceding vehicle is a vehicle immediately ahead of the host vehicle, and the dynamic state of the preceding vehicle was predicted based on data received from one or more vehicles in the platoon. The intelligent driver model (IDM) was extended to model car-following dynamics within a platoon. A parameter estimation approach may be used to estimate the model parameters, for example to adapt to different driver types. An integrated approach including both state prediction and parameter estimation was highly effective.

A system for handling information requests from mobile devices (100) includes a memory (1100), a state prediction module (1200), and a push module (1300). The memory (1100) is operable to store data requests received from the mobile devices (100). The state prediction module (1200) is operable to access the memory (1100) to predict forecasted data requests for a mobile device (100) based on the stored data requests. The push module (1300) is operable to receive the forecasted data requests from the state prediction module (1200) and in response request and receive response data related to the forecasted data requests and prepare the response data for transmission to the mobile device (100) over a wireless network (105).

The invention relates to the dynamic resource scheduling technique in the cloud computing field, and provides a cloud computing dynamic resource scheduling method based on the feedback and a prediction mechanism. The method aims to overcome the defects of the cloud computing resource distribution and scheduling technique in the prior art, and can achieve balance use of various computer resources in a cloud computing environment, obtain satisfactory load balance under small pay expenses and improve comprehensive efficiency of system scheduling. According to the scheme, various performance indexes of virtual machines are monitored in real time in operation processes of the virtual machines, operation circumstances of all the current virtual machines within a next short period of time are predicted according to the monitored various current performance indexes of the virtual machines and a virtual machine state prediction model based on state feedback when a task request comes, and the most adaptive virtual machine is selected by combining a prediction result and a required task type and the required task is distributed. In addition, the invention further discloses a corresponding cloud computing dynamic resource scheduling system applicable to dynamic resource scheduling.

The invention discloses a city-level intelligent traffic simulation system. With multi-source heterogeneous data as input, the vehicle queue length of each lane at an intersection can be predicted, the evolution of the vehicle queue length is further dynamically simulated, and the simulation system comprises a data collection module, a multidimensional database, an algorithm module, a traffic state prediction module, a traffic simulation derivation module and an interaction visualization module. In the data collection module, the collected data comprise traffic dynamic data and static data. The multidimensional database is used for receiving various traffic dynamic information in real time and storing road infrastructure configuration information. In the algorithm module, a generated confrontation network is used for data generation and state prediction on the vehicle queue length, and the processing process comprises data feature extraction, data dimension processing, confrontation network generation, and hyperparameter optimization. The vehicle queue length of each lane at the intersection can be predicted, and the evolution of the vehicle queue length is further dynamically simulated.

The invention discloses a traffic state prediction method for the urban road network based on key road sections, which is characterized by comprising the steps of first, carrying out data preprocessing; second, establishing a spatial weight matrix of the road network; third, establishing a time correlation matrix; fourth, recognizing key road sections by using a time-space correlation matrix; andfifth, establishing a deep convolution neural network, predicting the state of the road network in the future, and carrying out evaluation on a prediction model. The traffic state prediction method predicts the urban traffic flow state from a level of the wide-range road network, thereby being conducive to guiding the traffic flow from a macroscopic perspective, and fully exploring time-space correlation characteristics of the traffic flow. The key road sections in the road network are recognized, so that the training time of the model can be greatly reduced compared with a method of taking historical states of all road sections as input data, and the prediction efficiency is improved; and the convolution neural network is adopted to serve as the prediction model, and the prediction resultis also more accurate.

The invention belongs to the field of safety production and early warming emergency of construction of water conservancy and hydropower projects and relates to an Internet of Things framework type system and method for monitoring and early warning of major accident potential safety hazards of a water conservancy and hydropower project. According to the Internet of Things framework type system and method for monitoring and early warning of the major accident potential safety hazards of the water conservancy and hydropower project, information of the potential safety hazards which can cause a potential accident in the area of the water conservancy and hydropower project is recognized and positioned to determine the types and levels of the potential safety hazards, and judging of the types and levels of the potential safety hazards and information statistics are carried out; meanwhile, the geographic position, spatial position, dynamic change, state change and state prediction of monitoring points in the area are analyzed by combining with the historical information of the area, early warning information can be generated automatically after potential safety hazard information in the monitoring area is beyond a set alarm value, and comprehensive data information of the potential safety hazards in the area and early warning of the major accident potential safety hazards of the project are provided through communication transmission.

The invention discloses a construction method for a lithium battery health life model, and the method is used for the recognition of the aging degree of a lithium battery. The method comprises the steps: firstly carrying out the health lift testing of the lithium battery; secondly constructing the health factor of the lithium battery according to the testing data; thirdly building the lithium battery health life model according to the constructed health factor, thereby achieving the prediction of the health state of the lithium battery; fourthly sequentially carrying out the testing of basic performances at four temperature points (25 DEG C, 40 DEG C, 10 DEG C and 55 DEG C) during the testing of the health life; fifthly carrying out the acceleration aging testing at the degree of 55 DEG C; and finally finishing the testing when the static capacity test value decreases to 75% of a rated capacity. The method carries out the direct obtaining of the performance parameters of the lithium battery based on testing data, carries out the research how to extract the health features to achieve the recognition of the aging degree of the lithium battery, and can be used for achieving the prediction of the health state of the lithium battery.

The invention discloses a day-dimension regional traffic index prediction method considering influences of multiple factors. The method comprises the steps that regions are divided and aggregated; regional traffic index original data preprocessing is carried out; the influences of multiple factors are considered, and regional traffic index prediction under the day dimension is carried out. According to the specific technical scheme of the method, on the basis of traffic cell division, traffic cells with the same aggregation property are aggregated, and regional traffic indexes are calculated;on the basis of road network operation early warning requirements, a prediction time period and a prediction cycle are determined; regional traffic data is extracted, made up for and removed, and preprocessing such as comprehensive building of a historical data factor attribute set from different angles is conducted on the data; on the basis of a decision tree theory, regional road network operation congestion state prediction is carried out; a final prediction result of the regional traffic indexes is determined by means of the square euclidean distance. By means of the method, on the one hand, monitoring and application of the urban road network operation state is deepened, and on the other hand, technical support is provided for early warning and forecasting work of the road network operation state.

A tire wear state estimation system estimates forces and sliding velocity generated in a tire contact patch, determines frictional energy from the tire force and sliding velocity, and generates an estimate of tire wear state based upon the frictional work done by the tire. A tire wear estimate, pursuant to the system and methodology, is made by determining the amount of frictional work performed by the tire through the integrated use of tire-mounted, GPS sourced, and vehicle-mounted sensor information.

The present disclosure belongs to the field of marine engineering, and in particular relates to a method and system for guaranteeing the safety of offshore oil well control equipment. The method comprises: identifying the state of a main structure of the offshore oil well control equipment, identifying the state of a hydraulic control unit of offshore oil well control equipment, identifying the state of an electronic control unit of offshore oil well control equipment, predicting the state of the offshore oil well control equipment and making a real-time decision based on existing information; and the system for guaranteeing the safety of the offshore oil well control equipment comprises a state identification subsystem of a main structure, a state identification subsystem of the hydraulic control unit, a state identification subsystem of the electronic control unit and a state prediction and real-time decision subsystem.

The invention claims for protection of a coordinated local path planning method based on V2X communication and binocular vision. An OBU acquires vehicle body information and environmental informationthrough a binocular preposed camera, OBD equipment and V2X communication and the information is transmitted to a coordinated local path planning controller; with a traffic object mixed state estimation model, state prediction is carried out on a traffic object state, spatio-temporal data fusion is carried out on the traffic object information and traffic rules after state estimation based on a multi-source data fusion algorithm, a traffic road map with high credibility is constructed by the fused traffic data according to a coordinate mapping model, an own vehicle state is calculated by combining own vehicle information according to an own vehicle state estimation model, and then an optimal smooth driving path of the current vehicle is calculated based on an improved local path planning algorithm; and then the path is transmitted to the OBU and the information is broadcasted to other vehicles through V2X. According to the invention, the accuracy of vehicle environment perception and local path planning is improved by combining visibility-range and non-visibility-range traffic object sense sensing.

The invention discloses a multi-system dynamic PPP resolving method based on robust self-adaption Kalman smoothing. The method includes the steps that receiving machine outline coordinates and receiving machine clock bias of all systems are solved through selecting-weight-iteration pseudo-range single-point positioning, and accordingly all positioning error correction values are calculated according to an error correction model in combination with the satellite precise ephemeris and satellite precise clock bias; strict data quality control is conducted on observation data. Due to the fact that dynamic PPP accuracy is easily affected by undetected small cycle slips or the gross error and the like, an observation equation weight matrix is adjusted according to the observation value residual vectors, and the undetected small cycle slips or the gross error and other influence factors are removed; self-adaption factors are determined according to the state predictive information, and thus the influence on parameter estimation of the predictive information is controlled. By means of the method, when multi-system dynamic PPP is conducted through a single receiving machine, the feature that the number of multi-system satellites is increased greatly, on the basis that the stability of the satellite structure is guaranteed, the influence of the gross error is weaken effectively, the dynamic noise abnormity in dynamic positioning is improved, and finally the high-precision and high-stability multi-system dynamic PPP result is achieved.

The invention discloses a state prediction method and device. The method comprises the following steps of: sampling target users; respectively generating a negative sample, a positive sample and a verification sample according to account information of lost and unlost users according to a recognized sampling moment; training a decision-making tree which is used for predicting user loss state afterthe sampling moment; inputting the verification sample into the trained decision-making tree model to obtain a predicted loss state; and if a correct recall rate obtained through carrying out calculation according to the predicted loss state and a practical loss state is not smaller than a threshold value, determining that the training of the decision-making tree model is completed, and carryingout user loss state prediction. According to the state prediction method and device, the decision-making tree model is trained by a training sample generated through sampling the target users, and user loss state prediction is carried out according to the trained decision-making tree model, so that the technical problems of relatively recognition efficiency low and reusing difficulty caused by user loss state prediction carried out through artificial experiences or established rules in the prior art are solved.

The invention belongs to the technical field of traffic simulation, and provides a real-time online traffic simulation system comprising a detection data acquisition module, an initial matrix acquisition module, a dynamic path decision module, a mesoscopic traffic flow simulation module, a precision calculation module, a dynamic OD estimation module, a short-time traffic state prediction module, amesoscopic and microscopic fusion traffic simulation module and a real-time online module. According to the simulation system, the value of multi-source data can be fully utilized and mined, OD pathset more conforming to actual traffic conditions is generated, the timeliness of the simulation data is fully considered, and the accuracy of dynamic OD estimation is improved.

The invention discloses a road network state prediction method based on a depth space-time convolution circulation network. The method comprises steps of step 1, establishing a sample set and dividing a training set and a test set; step 2, modeling a road network state prediction model, wherein the road network state prediction module comprises a convolution neural network and a recurrent neural network, the convolution neural network is used for extracting space features of the road network and the recurrent neural network is used for extracting sequential rules of the evolution of the road network; and step 3, carrying out road network state prediction in a certain period in the future. According to the invention, through the depth convolution neural network, relations between sections in the road network are extracted; through the recurrent neural network, the sequential rules of the revolution of the road network are extracted; and quite precise prediction of road network traffic states can be obtained by fully considering the space-time information of the road network.

A computer system and method for extending parallelized asynchronous reinforcement learning for training a neural network is described in various embodiments, through coordinated operation of plurality of hardware processors or threads such that each functions as a worker agent that is configured to simultaneously interact with a target computing environment for local gradient computation based on a loss determination and to update global network parameters based at least on local gradient computation to train the neural network through modifications of weighted interconnections between interconnected computing units as gradient computation is conducted across a plurality of iterations of a target computing environment, the loss determination including at least a policy loss term (actor), a value loss term (critic), and an auxiliary control loss. Variations are described further where the neural network is adapted to include terminal state prediction and action guidance.

The present invention discloses an express way traffic state prediction method taking spatial-temporal correlation into account at different times. The method comprises: firstly, performing analysis period dynamic division of flow, speed and time sequences through adoption of a sequential cluster, and dividing the whole day into analysis periods with different traffic characteristics without disturbing traffic parameter time sequences; and selecting multivariable vector autoregression models aiming at different periods, comprehensively considering the spatial-temporal correlation of the upstream and downstream traffic flows, and predicting the flow or the speed of target places. The dynamic period division of the express way traffic state prediction method taking spatial-temporal correlation into account at different times provides a cheap, easy and substantially improved efficiency basic method for express way traffic state short-time prediction; and compared with a traditional method without considering the upstream and downstream traffic flow influence, the express way traffic state prediction method taking spatial-temporal correlation into account at different times considers the vector autoregression model of the spatial-temporal correlation after the periods are divided, so that the prediction results are obviously improved in precision.

The invention relates to the field of the intelligent transportation system, and especially relates to short-term traffic flow forecasting with use of a parameter value sequence of a road segment. A short-term traffic flow forecasting method based on a hidden Markov model comprises the following steps: collected data are processed and counted; a prediction window is set; a starting time measured value of the prediction window, and an average parameter value and a sequence contrast ratio in the prediction window are discretized, so as to form a hidden state and an observation state set of the hidden Markov model; and a Baum Welch algorithm combined with training data are used for learning the model parameter. Finally, for a certain prediction window, a Viterbi algorithm is used to obtain an optimal hidden state sequence based on a known observation state sequence, and a last state of the optimal hidden state sequence is a prediction state. The short-term traffic flow forecasting method based on the hidden Markov model can be used to predict the short-term traffic state in the future, and is an effective method of prediction of the short-term traffic state.

A terminal data storage section (18) of a portable communication terminal (10) stores the importance level of each piece of stored data. A connection state prediction judging section (12) predicts a change in the communication state of the connection to a server (20). A terminal processing level determining section (13) determines the terminal processing level of data based on the prediction result. When a data access becomes necessary, a data access managing section (15) determines whether a data access destination is the portable communication terminal (10) itself or the server (20) based on the importance level of the data and the then terminal processing level. When the terminal processing level is changed, a data hold managing section (14) deletes the data whose importance level is changed to an importance level which inhibits the data from being held at the changed terminal processing level from the terminal data storage section (18).

The invention discloses an automatic alarm method for preventing front crash of vehicles at a turning, comprising the following steps of: collecting coordinate data via an onboard GPS (Global Position System) device and providing the coordinate data to a filter unit for filtering treatment; calculating a road discrete curvature value according to the filtered data by a curvature calculation unit;judging whether a vehicle runs at the turning or not according to the road discrete curvature value by a turning identification unit; calculating a safe following distance according to a vehicle speed of the current vehicle, a relative distance between the current vehicle and a front vehicle and relative vehicle speed information provided by an onboard CAN (Controller Area Network) bus by a safe following distance calculating module if the current vehicle runs at the turning; calculating a following time interval and a collision avoidance time by a THW and TTC calculation module; calculating a risk state prediction value through a risk state prediction function based on the above parameters by a risk state prediction module; comparing the risk state prediction value with a pre-determined vehicle front crash alarm threshold by an alarm module; and sending a warning prompt to prompt the driver to reduce the speed by the alarm module if the risk state prediction value is equal to or greater than the vehicle front crash alarm threshold. The automatic alarm method can be widely arranged on all kinds of vehicles so that the driving safety of the vehicle is effectively improved.

The invention discloses a travel time fusion prediction and query method based on traffic big data, and the method comprises the steps: carrying out the offline calculation or training of data uploaded by all online vehicles to obtain various types of prediction models and parameters, and building and dynamically updating a data dictionary according to the prediction models and parameters; carrying out the call of the prediction models and parameters, and carrying out the prediction of the traffic state of a road network or a single vehicle through combining the real-time travel time data of a road segment and a path, wherein the data dictionary comprises a vehicle data dictionary, a road segment data dictionary and a path data dictionary, and the online vehicles are the vehicles which are registered to access to the network and automatically upload positioning and speed data. The beneficial effects of the invention are that the method solves problems that a road network or single vehicle traffic state prediction method in the prior art is poorer in instantaneity, universality and practicality, greatly improves the measurement precision, greatly improves the online prediction precision, and guarantees the instantaneity, practicality and universality in engineering application.

An onsite information preprocessing method of remote cooperative diagnosis includes an information collection step, a health state prediction step, a deep information processing step and a remote information transmission step. The information collection step collects working state information, control information, fault diagnosis information, working record information and working environment information. The health state prediction step predicates health state of equipment in one further period according to collection information and correspondingly conducting adjustment on an important monitoring point and monitoring frequency of the state monitoring in advance. The deep information processing step excavates fault sign information of relative time periods of the important monitoring point and conducting effective information extraction on common health state information according to certain standard. The remote information transmission step uploads preprocessing results. The onsite information preprocessing method compresses and extracts onsite original data of the equipment, reasonably expresses health state information of the equipment and converts the health state information into the knowledge expression mode required by an expert system or other decision making systems according to actual health state of the equipment.

A three-dimensional urban traffic road network global state prediction method under a large data environment is disclosed. Aiming at a coupling multi-layer large-scale urban traffic road network, a global traffic mode containing coupling information is defined, a method of extracting a main road network characteristic is provided, a high dimension state time sequence is converted into a discrete state type sequence, and difficulties of high dimension data in processing and prediction aspects are simplified. From aspects of traffic periodicity, delay performance and other characteristics, a historical state transfer information database containing a multielement traffic characteristic is constructed, mass data information and a data driving idea are fully used and a Markov transition probability theory is applied so as to realize multi-step global traffic state prediction. Through the global traffic prediction, a traffic state of each area can be acquired one time. Compared to an existing traffic prediction method, by using the method of the invention, a long-term prediction result is acquired rapidly and a good prediction output effect is possessed.