Hefei University of Technology

Other

Shanlin Yang

Kaile Zhou

Shuai Ding

Xinhui Lu

Wenjuan Fan

Lulu Wen

Qiang Zhang

Qiang Fu

Li Sun

Zhanglin Peng

Xiaonong Lu

Lin Zhang

Zhen Shao

Zeyuan Wang

Jie Ma

Hao Wang

Xiaoxuan Hu

Huawei Ma

Guoqiang Wang

Wei Xia

He Luo

Jun Pei

Peng Jin

Xiang Fang

Chi Zhang

Moning Zhu

Wanying Wang

Xiao Sun

Hang Jin

Yeqing Li

Shaowen Lan

Pengtao Li

Zhengzheng Liang

Yanqiu Niu

Anning Wang

Minglun Ren

Feng Niu

Weidong Zhao

Jianling Jiao

Zenghui Zhang

Ling Li

Xiaojian Ding

Zijie Yue

Yuanhang Wang

Chunhui Wang

Xianghong Hu

Ting Huang

Zhifeng Guo

Jinxin Pan

Shikang Hu

Hui Huang

A deep learning fault diagnosis method includes the following steps: a fault diagnosis data set X is processed based on sliding window processing, to obtain a picture-like sample data set {tilde over (X)}, and obtain an attention matrix A of the picture-like sample data set {tilde over (X)}; and a 2D-CNN model is constructed to process the picture-like sample data set {tilde over (X)} to obtain a corresponding feature map F, and in the meantime, the feature map F is processed based on channel-oriented average pooling and channel-oriented maximum pooling to obtain an output Pof the average pooling and an output Pof the maximum pooling, and a weight matrix W is obtained based on the attention matrix A, the output Pof the average pooling, and the output Pof the maximum pooling, so that an output of the model is a feature map {tilde over (F)} based on an attention mechanism, where {tilde over (F)}=WF.

Deep learning method integrating prior knowledge for fault diagnosis

Provided are a method and a system for optimizing charging and discharging behaviors of a BESS based on a SOH, relating to charging and discharging optimization. The number of cycles of the battery pack and corresponding DODs are obtained based on the curve of the SOC of the battery pack. Then, the SOH of the battery pack is obtained. A charging index sequence and a discharging index sequence of battery packs are obtained based on the SOH, the SOC and a charging and discharging state of the battery pack. The optimal number of the charging and discharging battery packs and optimal DODs are determined. Charging and discharging tasks are carried out according to the charging and discharging index sequences of the battery packs based on the optimal number of the charging and discharging battery packs and the optimal DODs.

Method and system for optimizing charging and discharging behaviors of a battery energy storage system based on state of health

The present invention provides a method, system and storage medium for load dispatch optimization for residential microgrid. The method includes collecting environmental data and time data of residential microgrid in preset future time period; obtaining power load data of residential microgrid in future time period by inputting environmental data and time data into pre-trained load forecasting model; obtaining photovoltaic output power data of residential microgrid in future time period by inputting environmental data and time data into pre-trained photovoltaic output power forecasting model; determining objective function and corresponding constraint condition of residential microgrid in future time period, where optimization objective of objective function is to minimize total cost of residential microgrid; obtaining load dispatch scheme of residential microgrid in future time period by solving objective function with particle swarm algorithm. The invention can provide load dispatch scheme suitable for current microgrid and reduce operating cost of residential microgrid.

Method, system and storage medium for load dispatch optimization for residential microgrid

The disclosure provides a method, a system and a storage medium for predicting power load probability density based on deep learning. The method comprises: S, collecting power load data of a user, meteorological data and air quality data in a preset historical time period, and dividing the collected data into a training set and a test set; S, determining a deep learning model for predicting power load; S, inputting the test set into the deep learning model for predicting power load, and obtaining power load prediction data of the user at different quantile points in a third time interval; S, performing kernel density estimation and obtaining a probability density curve of the power load of the user in the third time interval.

Method, system and storage medium for predicting power load probability density based on deep learning

The present invention discloses a multimode mobile electronic medical record system and a working method thereof. The multimode mobile electronic medical record system comprises a plurality of mobile terminals, service server, push server, authentication server and cloud server. The mobile terminal comprises a medical record information collection module, a medical record generation module, a medical record synchronization module, a medical record parsing module and a medical record showing module. The service server comprises a medical record storage module and a medical record exchange module. The push server comprises a medical record push module. The authentication server comprises a medical record safety control module. The multimode mobile electronic medical record system can meet collection, integration and transfer of multimode electronic medical record information in a mobile medical environment, and can efficiently improve efficiency and convenience of mobile medical services.

Multimode mobile electronic medical record system and working method thereof

The present invention provides a method and system for synchronously storing multi-modal information of portable endoscope. The method includes: S1: when a mobile terminal acquires data collected by a portable endoscope and updates local data with the acquired data, acquiring update record of the local data of the mobile terminal; and, S2: when the mobile terminal is synchronized with a cloud, synchronizing data in the mobile terminal with data in the cloud by using the update record as information to be synchronized. By creating a table to be synchronized to store change information and location information of files and selectively performing synchronization from the mobile terminal to the cloud or from the cloud to the mobile terminal according to whether or not the table to be synchronized is null during synchronization, unnecessary synchronization operations, storage burden of the mobile terminal and synchronization time and traffic are all reduced.

Method and system for synchronously storing multi-modal information of portable endoscope

The present invention discloses an automatic loading system and method for service functions of a hydraulic machine. The loading system includes an acquiring portion for acquiring i service function component chains of a hydraulic machine, a determining portion for determining a demand sequence of the service function component chains used by a user within each preset time period in a measuring cycle based on the acquired service function component chains and a deciding portion for automatically loading a service function of the hydraulic machine in a next moment according to the demand sequence based on a current input operation command of the user. By adopting the automatic loading system or method provided by the present invention, response speed of intelligent services of the hydraulic machine can be improved.

Automatic loading system and method for service functions of hydraulic machine

The present invention discloses a task scheduling system and method suitable for mobile health, the characteristics thereof including: a mobile health task distribution module, a plurality of mobile health task processing modules and a mobile health task callback module; the mobile health task distribution module comprises: a resource description unit, a resource scheduling unit, a resource matcher; each of the mobile health task processing modules comprises: a task decomposition unit, a task execution unit, a task evaluation unit. The present invention is capable of carrying out tasks with full use of the currently available task processing resources, thereby being capable of improving the efficiency and performance of the task scheduling processing in the mobile health environment.

Task scheduling system with a work breakdown structure and method suitable for mobile health

The present invention discloses a mobile health intelligent medical guide system and method thereof. The method comprises: collecting patient chief complaint by use of a mobile terminal, sending the patient chief complaint to a cloud server through the mobile phone device internet, analyzing and processing the patient chief complaint by use of the keyword extraction, text word segmentation, fuzzy matching and sorting recommendation technologies based on a medical knowledge base, automatically generating a disease examination result, and generating an intelligent medical guide result to be fed back to the mobile terminal in combination with the doctor information; and then optimizing the disease examination result and the intelligent medical guide result one by one until the patient ends the query or the diagnosis result achieves the optimum. The system can assist the patient to perform self-helped disease examination and medical guide in the mobile environment.

Mobile health intelligent medical guide system and method thereof

The present invention relates to a method and a system for compressing data from a smart meter. The method comprises: LZ-encoding electricity load data collected by the smart meter whenever the smart meter collects the electricity load data; storing the LZ-encoded electricity load data in a temporary database through a smart grid communication channel; reading the electricity load data from the temporary database every preset second duration, wherein the read electricity load data is electricity load data stored in the temporary database within the second duration before a corresponding reading time point; and LZ-decoding the read electricity load data, SAX-compressing the LZ-decoded electricity load data, and storing the SAX-compressed electricity load data in a data center. The present invention has high compression rate, reduces the transmission burden for communication lines and storage burden for the data center, and improves the efficiency of smart electricity data analysis and mining.

Method and system for compressing data from smart meter

The embodiments of the present invention disclose a method and apparatus for joint optimization of multi-UAV task assignment and path planning. The method comprises: obtaining the location information of a plurality of UAVs and a plurality of target points, the dispersion of groundspeed course angle, and motion parameters of each UAV and wind field; constructing an initial population based on the location information, the dispersion of groundspeed course angle and a preset genetic algorithm; determining the flight status of each UAV and the flight time taken by each UAV to complete a path segment of the corresponding Dubins flight path based on the initial population and the motion parameters, obtaining the total time taken by all the UAVs corresponding to each chromosome to complete the task based on the flight time of the path segment; and subjecting the chromosomes in the initial population to crossover and mutation based on the genetic algorithm and, when a predetermined number of iterations is reached, selecting the optimal Dubins flight path as the joint optimization result. In the embodiments of the present invention, the UAV flight path planning problem is combined with the actual flight environment of the UAV, so that the optimal flight path obtained is superior to the solution in which the UAV speed is constant.

Method and apparatus for joint optimization of multi-UAV task assignment and path planning

The present invention discloses an intelligent assistant judgment system for images of cervix uteri and a processing method thereof. This system comprises a colposcope device and an assistant judgment device. By combining the colposcope device and the assistant judgment device together to obtain the images of the cervix uteri to be detected by the colposcope device and to compare and analyze the images of the cervix uteri to be detected and its characteristic data by the assistant judgment device, the present invention can judge whether the current cervix uteri to be detected are normal cervix uteri, and can obtain, from the characteristic data of the images of the cervix uteri to be detected, the type of a lesion occurring in the current cervix uteri to be detected and characteristic parameters of the lesion. The doctors are assisted in making correct diagnosis and judgment.

Intelligent assistant judgment system for images of cervix uteri and processing method thereof

The present invention relates to a method and device for on-line prediction of remaining driving mileage of an electric vehicle. The method comprises: acquiring in-transit data and driving environment data of the electric vehicle which is driving; calculating the power consumption per mileage of the electric vehicle in the current case by using the in-transit data and the driving environment data in combination with a power consumption rate data model; predicting the remaining driving mileage of the electric vehicle based on the power consumption per mileage. The device provided by the present invention is implemented on the basis of the method above. The prediction result of the present invention is more accurate, to avoid the problem that the power is exhausted due to exceeding the mileage expected by a user so that the electric vehicle cannot continue to drive, thereby improving the driving experience of the user.

Method and device for on-line prediction of remaining driving mileage of electric vehicle

A charging and discharging scheduling method for electric vehicles in microgrid under time-of-use price includes: determining the system structure of the microgrid and the characters of each unit; establishing the optimal scheduling objective function of the microgrid considering the depreciation cost of the electric vehicle (EV) battery under time-of-use price; determining the constraints of each distributed generator and EV battery, and forming an optimal scheduling model of the microgrid together with the optimal scheduling objective function of the microgrid; determining the amount, starting and ending time, starting and ending charge state, and other basic calculating data of the EV accessing the microgrid under time-of-use price; determining the charge and discharge power of the EV when accessing the grid, by solving the optimal scheduling model of the microgrid with a particle swarm optimization algorithm.

Charging and discharging scheduling method for electric vehicles in microgrid under time-of-use price

Growing community of inventors

Anhui, China

Shanlin Yang