Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

1338 results about "Information layer" patented technology

The information layer is where the functional algorithms that handle information exchange between a data layer and a delivery layer site. The information layer is where mission-critical business problems are solved.

Digital twin system of an intelligent production line

The invention relates to a digital twin system of an intelligent production line, which comprises a physical space layer, an information layer and a virtual space layer. The physical space layer is composed of a physical production line, intelligent sensing devices and an industrial control network. The information layer includes a data conversion module, a data analysis module and a production line information database. The virtual space layer can adapt to a variety of platforms and environments including personal computers and handheld devices, is used for generating a virtual production line consistent with the physical production line by a 3D visual engine through online real-time and offline non-real-time rendering under the driving of the production line information database of the information layer, and has the functions of multi-angle of view visual display, natural interaction, state monitoring and so on. The real-time state information of the physical production line is collected by various intelligent sensing devices, and based on the information, a three-dimensional visual engine is driven to generate a virtual production line model consistent with the physical production line through rendering, thereby realizing the twin mirror image of the virtual production line and the physical production line.
Owner:CHINA ELECTRONIC TECH GRP CORP NO 38 RES INST

Deep neural network learning method, processor and deep neural network learning system

Embodiments of the present invention provide a deep neural network learning method. The method comprises: conducting, by a plurality of processors, forward processing on data distributed to the processors layers in parallel layer by layer from a first layer to a last layer, and acquiring error information when forward processing is finished; and conducting, by the plurality of processors, backward processing on the error information layer by layer from last layer to first layer, wherein each of the plurality of processors immediately transfers a parameter correction value to other processors after backward processing of a current layer of a corresponding deep neural network model generates the parameter correction value. With the method according to the embodiments of the present invention, time consumed by transfer of the parameter correction values is reduced, and efficiency of training the deep neural network models is effectively improved; and particularly under the conditions of a large volume of training data and a great number of layers of each deep neural network model, such manner can greatly reduce used time, and effectively save model training time. Further, the embodiments of the present invention provide a processor, and a deep neural network learning system.
Owner:HANGZHOU LANGHE TECH

Layered receiver structure

A method and apparatus is disclosed herein for receiving a layered transmission of data in a wireless communication system using an iterative layered receiver structure. In one embodiment, a receiver comprises a layer 1 demapper and a layer 1 outer decoder to iteratively decode layer 1 of the coded data, and a layer 2 demapper and a layer 2 outer decoder to iteratively decode layer 2 of the coded data, wherein the layer 1 demapper generates a layer 1 set of likelihood estimates only for bits of the first information layer of received signal data in each of one or more iterations and where the layer 1 set of likelihood estimates are generated in response to the received signal data and, in at least one of the one or more iterations, also in response to one or more of the likelihood estimates generated by the outer decoders in decoding schemes for at least one layer other than layer 1; the layer 1 outer decoder updates the layer 1 likelihood estimates from the layer 1 demapper and feedbacks the updated layer 1 likelihood estimates to the layer 1 demapper for use in another iteration of iterative decoding; the layer 2 demapper generates a layer 2 set of likelihood estimates only for information bits of the layer 2 of received signal data in each of one or more iterations, and where the layer 2 set of likelihood estimates are generated in response to the received signal data and, in at least one of the one or more iterations, also in response to one or more of the likelihood estimates generated by the outer decoders in decoding schemes for at least one layer other than layer 2; and the layer 2 outer decoder updates the layer 2 likelihood estimates from the layer 2 demapper and feedbacks the updated layer 2 likelihood estimates to the layer 2 demapper for use in another iteration of iterative decoding.
Owner:NTT DOCOMO INC

Process for producing PET laser transfer membrane

The invention relates to a process for producing a PET laser transfer membrane. A PET membrane is used as a basement transfer membrane, and laser transfer pigment is coated and spread on the PET membrane. The method includes the following steps: a laser transfer pigment is coated and spread on the PET basement transfer membrane by an anilox roll at one step to form a coating layer, and a precoating membrane can be formed after the operation of drying is carried out; the precoating membrane is processed by the operation of laser mould pressing, and interference figures on a laser slab are printed on the coating layer of the precoating membrane by heat pressing so as to form a mould pressing membrane; and aluminum is coated on the mould pressing membrane, an aluminum layer is formed on an information layer, and the PET laser transfer membrane can be prepared, wherein the pigment includes thermoplastic acroid resin and cellulose acetate. The process has the advantages that the special singly coated laser transfer pigment and the unique manufacture process control are selected, and the entire process is simple, novel, stable and reliable. As the laser mould pressing transfer coating layer has the properties of easy mould pressing, favorable stripping, and the like, the operation of coating just needs to be carried out for one time, and therefore the production efficiency can be greatly improved. After being transferred and stripped, the aluminum coated membrane can be recycled to be repeatedly used for many times, and therefore cost can be greatly reduced; and the PET laser transfer membrane is the environmentally friendly anti-counterfeit laser material for packaging and printing.
Owner:上海宝绿包装材料科技有限公司

Three-dimensional assembling technology design system based on information physical fusion and operation method thereof

ActiveCN108388146AReal-time detection of problems that do not meet assembly design requirementsAvoid interferenceSimulator controlInformation layerProcess optimization
The invention discloses a three-dimensional assembling technology design system based on information physical fusion and an operation method thereof. The actual assembling environment and the virtualassembling system are combined by the system through the information physical fusion technology, the actually measured data of the critical elements/components/parts are acquired through the field equipment of the physical layer, the actually measured data are transmitted to the virtual information layer through the communication layer and used as the digital twin model data of product virtual-actual mapping to be used for virtual assembling three-dimensional technology planning and design, assembling precision prediction and the online correction instruction are given through virtual assembling simulation and process optimization and feedback control are performed on the field assembling activity so that the digital twin model can be continuously and dynamically updated to meet the product assembling design requirements, and finally the operator is guided to complete the product assembling task by three-dimensional technology demonstration. The trial assembling and repair time in theassembling activity can be reduced so that the product field assembling efficiency can be guaranteed and the product assembling accuracy and assembling accuracy can be enhanced.
Owner:SOUTHEAST UNIV

Workshop-grade smart manufacture system based on digital twins and configuration method thereof

Provided are a workshop-grade smart manufacture system based on digital twins and a configuration method thereof. According to the workshop-grade smart manufacture system, a system architecture composed of a physical layer, a network layer and an information layer is adopted. According to the configuration method of the workshop-grade smart manufacture system, digital twins of an article in process and a manufacture source are built, mapping relations between the digital twins and the article in process and between the digital twins and the manufacture source are also built, in this way, a workshop human-machine-article self-government interaction mechanism is formed, and workshop perception-calculation-execution-feedback-decision closed-loop manufacture logic is achieved. By the adoptionof the workshop-grade smart manufacture system based on the digital twins and the configuration method thereof, a digital twin technology is applied to workshop-grade smart manufacture system modelingand simulating, an optimized smart workshop production operation scheme is given, support is provided for improving the production flexibility, self-government capacity and dynamic response capacityof industry workshops, and certain references are provided for transforming and upgrading traditional manufacture workshops into smart manufacture workshops.
Owner:CHANGAN UNIV

Electrical fire warning system based on data fusion

The invention relates to an electrical fire warning system based on data fusion. According to the scheme, the electrical fire warning system comprises an information layer, a feature layer and a decision-making layer, and further comprises an electric arc detection device; when the electric arc detection device detects electric arc signals, the detected electric arc signals pass through a signal preprocessing device and a signal transmission device and then are transmitted to an early warning system to achieve system early warning, meanwhile, the feature layer is started to conduct fusion processing on fire feature signals collected by sensors, and when no electric arc is generated, the feature layer collects data of the information collecting layer in real time to carry out monitoring on electrical fires. In the electrical fire warning system, the phenomenon that electric arcs are generated before fire signals are generated in electrical fires is utilized, the early warning function of the system is achieved by detecting the electric arc signals, fuzzy logic is introduced while the neural network algorithm is adopted, the defect that the neural network is not easy to understand can be compensated for a large degree, accurate fitting can be carried out on existing fire data through the neural network, and fuzzy reasoning can be carried out through the fuzzy logic through a small amount of known fire data.
Owner:HENAN POLYTECHNIC UNIV

Electric power transmission line and disaster geographic information system

The invention discloses an electric power transmission line and disaster geographic information system. The electric power transmission line and disaster geographic information system comprises an electronic map part which is used for generating a basic geographic information layer and comprises a satellite imagery layer, a disastrous meteorological environment map information part comprising lightning, pollution area, wind area, ice area, bird trouble geographic information layers, a data base part for building and maintaining electric power transmission line information, electric power transmission line tower information, management unit information and tower dynamic operation information and a line corridor information part. For different line management line corridor information, different power transmission corridor parameters are set dynamically according to terrain environment of lines, and therefore evaluation of influence of various disastrous meteorological environment parameters on a power grid is refined. The electric power transmission line and disaster geographic information system can effectively support planning, design and stable and deep construction work development of a smart power grid and improve comprehensive monitoring and management efficiency of operating conditions of power transmission and transformation equipment.
Owner:SHAANXI ELECTRIC POWER RES INST +2

Small target detection method and apparatus in image based on depth learning

Embodiments of the present invention provide a small target detection method and apparatus in an image based on depth learning. The method comprises: obtaining a to-be-detected image; obtaining a target category of the to-be-detected image and location coordinates of the target category in the to-be-detected image based on the to-be-detected image and a pre-trained target detector model, wherein the process comprises: inputting the to-be-detected image into a target feature extractor to obtain a feature map, inputting the feature map into a target area to generate a network to obtain coordinates of a candidate box, inputting the coordinates of the candidate box into a context information layer, calculating by a preset calculation manner according to the coordinates of the candidate box toobtain coordinates of the vertical candidate box and coordinates of the horizontal candidate box; and inputting the coordinates of each candidate box and the feature map into a target area classification network to obtain the category and location coordinates of the target. According to the technical scheme of the embodiments of the present invention, even for the relatively small target in the image, more feature information is obtained due to the target area classification network, so that the accuracy when detecting the small target such as the traffic sign is improved.
Owner:BEIJING UNIV OF POSTS & TELECOMM

Mountain geological disaster monitoring and prewarning system and method based on digital twin driving

A mountain geological disaster monitoring and prewarning system based on digital twin driving comprises data acquisition sensors arranged on a physical layer, a DT monitoring module, a DT prediction module and a DT prewarning module arranged on an information layer, and clients on a visualization layer. A monitoring and prewarning method comprises the following steps: Step 1, investigation is carried out on a geological environment, and a monitoring plan is obtained for focused monitoring on a current area; Step 2, real-time data is obtained according to the monitoring plan obtained in Step 1,and historical geological disaster data are all stored in a geological disaster digital twin database and analyzed in the DT prediction module; Step 3, BP neural network analysis is carried out in the DT prediction module based on the historical geological disaster data to obtain a geological disaster prediction model; and Step 4, the monitoring data obtained in Step 2 is stored in the geologicaldisaster twin database to obtain prediction results, and the prediction results are sent to the clients for visualization. The system and method provided by the invention has the characteristics thatthe personal safety of residents, tourists and the like can be protected, and economic losses can be reduced.
Owner:XIAN UNIV OF POSTS & TELECOMM

Overlay convolutional network-based rolling bearing failure mode recognition method and device

The invention discloses an overlay convolutional network-based rolling bearing failure mode recognition method and device, and relates to the field of rolling bearing failure diagnosis. The method comprises the following steps of: extracting a time-frequency domain feature of a vibration signal of a state-known rolling bearing; normalizing the obtained time-frequency domain feature of the state-known rolling bearing into a feature pixel according to a CNN network input format; inputting the feature pixel into a CNN network, and adjusting a model parameter of the CNN network through carrying out forward self-learning and gradient descent-based counter-propagation on the CNN network so as to obtain a trained CNN network; and during the recognition of a practical rolling bearing failure mode, extracting high-order features capable of reflecting intrinsic information layer by layer by utilizing the trained CNN network by taking a time-frequency domain feature of a vibration signal of a state-unknown rolling bearing, and inputting results of the feature self-learning into a top classifier layer by layer, so as to realize failure mode recognition of the rolling bearings under multiple working conditions and strong noises.
Owner:北京恒兴易康科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products