CN107480095A - A kind of multi-modal decision system interface of O＆M based on multinuclear heterogeneous processor - Google Patents
A kind of multi-modal decision system interface of O＆M based on multinuclear heterogeneous processor Download PDFInfo
- Publication number
- CN107480095A CN107480095A CN201710623490.4A CN201710623490A CN107480095A CN 107480095 A CN107480095 A CN 107480095A CN 201710623490 A CN201710623490 A CN 201710623490A CN 107480095 A CN107480095 A CN 107480095A
- Authority
- CN
- China
- Prior art keywords
- heterogeneous processor
- multinuclear heterogeneous
- modal
- interface
- multinuclear
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/16—Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
- G06F15/177—Initialisation or configuration control
Abstract
The present invention discloses a kind of multi-modal decision system interface of O＆M based on multinuclear heterogeneous processor, O＆M environmental data is obtained using sensor and video camera, pass through input interface, signal is sent to multinuclear heterogeneous processor, multi-modal decision-making is carried out, by output interface, decision information is transmitted to control unit through bus, management platform and pre-alarm and prevention are controlled, to realize that accident automatic early-warning is taken precautions against.
Description
Technical field
The present invention relates to a kind of multi-modal decision system interface of O＆M based on multinuclear heterogeneous processor
Background technology
With cloud computing and virtualization, the features such as showing " extensive ", " high density ", " high energy consumption ", " complication ", build
If with developing New Generation of IDC, lifting data center infrastructure management will become increasingly important, the basis of data center
The new trend that framework fusion management will develop with intelligence as data center.
At present, O＆M lacks automation means, and passive O＆M, efficiency is low, and extensive IT facilities bring government pressure.Need
The automatically-monitored of data center is realized, improves the timely alarm ability of system and ambient parameter, system is improved and environment is different
The response speed and monitoring level often changed.Using sensor and first-class various means perception informations are imaged, can be achieved with unification
Service management software platform.
Multi-source Information Fusion obtains information by data caused by awareness tool.Information fusion is related to a variety of different senses
Know device and different actuators, different awareness apparatus can produce different types of data.How these multimodes are effectively merged
State data so correctly reflect O＆M state be highly important research topic.
Sensor subsystem is environmental detection device, acts on and detects environmental change and be data fusion subsystem in real time
Related data is provided；Decision support subsystem carries out situation estimation in time using the structure of data fusion, and the result is again sensing
Device management provides important evidence；Sensor management subsystem provides according to the feedback information that above several stages provide to sensor
Source adjust and optimize in real time.
Camera target detection is the original state using the state of target as tracking, while to Target Modeling, obtains phase
The descriptive model of latent structure target is closed, object module is then utilized in follow-up image, mesh is estimated by the way of filtering
Target current state, while utilize current state renewal object module.
The optimal estimation of fixed model collection is full hypothesis estimation, that is, etching system is possible to pattern when considering each.Its
Models Sets are predetermined, are time-varying in itself without tube model.Thus, it is necessary to utilize some hypothesis administrative skills
To establish more effective non-hypothesis tree algorithm, to ensure remaining hypothesis quantity within the specific limits.So-called broad sense puppet Bayes side
Method (GPB), it is exactly in moment k, carries out only considering the mesh that system is gone in limited individual sampling time interval during system state estimation
Mark model history.
Heterogeneous Computing is primarily referred to as the calculating using the computing unit of different type instruction set and architectural framework composition system
Mode.The common computing unit classification processor such as including CPU, GPU.Heterogeneous Computing is more paid close attention in recent years, mainly
Because encounter radiating and energy consumption bottle by lifting cpu clock frequency and number of cores to improve the traditional approach of computing capability
Neck.And although the dedicated computing unit working frequency such as GPU is relatively low, there is check figure and computation capability, bulking property in more
The ratio and performance/power dissipation ratio of energy/chip area are all very high, are but far from being fully used.
CPU design allows it to be relatively good at processing irregular data structure and uncertain access mode, Yi Jidi
Reduction method, branch's intensity code and single-threading program.This kind of program task possesses the instruction scheduling of complexity, circulation, branch, patrolled
Collect the step such as judgement and execution.And GPU is good at handling rules data structure and predictable access mode.Both length of set
Place, the optimization of overall performance is reached with Heterogeneous Computing.
Polycaryon processor refers to integrate two or more complete computing engines (kernel) in one piece of processor, now located
Reason device can support multiple processors on system bus, and all bus control signals and command signal are provided by bus control unit.
Multinuclear heterogeneous processor provides technical guarantee with for multi-modal decision-making.
Control the industrial I/O interface boards of configuration standard.The interface of control system has A/D converter, D/A converter, various
Motion control card, counter and digital quantity input-output equipment etc..Input interface is also referred to as input circuit, the signal from sensor
To be filtered by input circuit, shaping, after the processing such as amplification, can just be sent to processor and carry out computing.Due to sensor detection
Signal has analog- and digital- two class, and computer can only receive data signal, therefore with input interface circuit by analog signal
Data signal is converted into, i.e., A/D converter is used in input interface.
The electric signal of output is data signal, and some actuators need to export analog signal, therefore output interface needs
D/A converter.Simultaneously as output signal is weaker, it is impossible to actuator is directly controlled, therefore mostly using by big in output circuit
The output driver of power transistor composition, by the conducting and cut-off of output signal control transistor, so as to control actuator
Bonding loop.
The invention provides a kind of multi-modal decision system interface of O＆M based on multinuclear heterogeneous processor, sensor is utilized
O＆M environmental data is obtained with video camera, by input interface, signal is sent to multinuclear heterogeneous processor, carries out multi-modal determine
Plan, by output interface, decision information is transmitted to control unit through bus, management platform and pre-alarm and prevention are controlled, to realize thing
Therefore automatic early-warning is taken precautions against.
The content of the invention
It is an object of the invention to provide a kind of multi-modal decision system interface of O＆M based on multinuclear heterogeneous processor.This
Invention includes following characteristics：
Inventive technique scheme
1. a kind of multi-modal decision system interface of O＆M based on multinuclear heterogeneous processor, it is comprised the following steps that：
1) sensor and camera are utilized, obtains O＆M environmental data；
2) by input interface, signal is sent to multinuclear heterogeneous processor；
3) multinuclear heterogeneous processor is used, carries out multi-modal decision-making；
4) by output interface, decision information is transmitted to control unit through bus；
5) control unit is recycled, controls management platform and pre-alarm and prevention.
Brief description of the drawings
Fig. 1 is the multi-modal decision system interface schema of O＆M based on multinuclear heterogeneous processor.
Embodiment
The multi-modal decision system interface of this O＆M based on multinuclear heterogeneous processor, comprises the following steps：
1) sensor and camera are utilized, obtains O＆M environmental data；
2) by input interface, signal is sent to multinuclear heterogeneous processor；
3) multinuclear heterogeneous processor is used, carries out multi-modal decision-making；
4) by output interface, decision information is transmitted to control unit through bus；
5) control unit is recycled, controls management platform and pre-alarm and prevention.
Claims (1)
1. a kind of multi-modal decision system interface of O＆M based on multinuclear heterogeneous processor, it is comprised the following steps that：
1) O＆M environmental data is obtained using sensor and camera；
2) by input interface, signal is sent to multinuclear heterogeneous processor；
3) multinuclear heterogeneous processor is used, carries out multi-modal decision-making；
4) by output interface, decision information is transmitted to control unit through bus；
5) control unit is recycled, controls management platform and pre-alarm and prevention.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710623490.4A CN107480095A (en) | 2017-07-28 | 2017-07-28 | A kind of multi-modal decision system interface of O＆M based on multinuclear heterogeneous processor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710623490.4A CN107480095A (en) | 2017-07-28 | 2017-07-28 | A kind of multi-modal decision system interface of O＆M based on multinuclear heterogeneous processor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107480095A true CN107480095A (en) | 2017-12-15 |
Family
ID=60597060
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710623490.4A Pending CN107480095A (en) | 2017-07-28 | 2017-07-28 | A kind of multi-modal decision system interface of O＆M based on multinuclear heterogeneous processor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107480095A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101110155A (en) * | 2007-08-27 | 2008-01-23 | 北京交通大学 | Built-in intelligent fault diagnosing device based on data inosculating pattern recognition and method thereof |
| CN104598109A (en) * | 2015-01-08 | 2015-05-06 | 天津三星通信技术研究有限公司 | Method and equipment for previewing application in portable terminal |
| CN106799991A (en) * | 2017-02-08 | 2017-06-06 | 张军 | A kind of intelligent travelling crane early warning system interface based on multinuclear heterogeneous processor |
| CN106809144A (en) * | 2017-02-08 | 2017-06-09 | 张军 | A kind of intelligent travelling crane early warning system interface based on polycaryon processor |
| CN106864404A (en) * | 2017-02-17 | 2017-06-20 | 张军 | A kind of intelligent travelling crane early warning sensory perceptual system based on multinuclear heterogeneous processor |
-
2017
- 2017-07-28 CN CN201710623490.4A patent/CN107480095A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101110155A (en) * | 2007-08-27 | 2008-01-23 | 北京交通大学 | Built-in intelligent fault diagnosing device based on data inosculating pattern recognition and method thereof |
| CN104598109A (en) * | 2015-01-08 | 2015-05-06 | 天津三星通信技术研究有限公司 | Method and equipment for previewing application in portable terminal |
| CN106799991A (en) * | 2017-02-08 | 2017-06-06 | 张军 | A kind of intelligent travelling crane early warning system interface based on multinuclear heterogeneous processor |
| CN106809144A (en) * | 2017-02-08 | 2017-06-09 | 张军 | A kind of intelligent travelling crane early warning system interface based on polycaryon processor |
| CN106864404A (en) * | 2017-02-17 | 2017-06-20 | 张军 | A kind of intelligent travelling crane early warning sensory perceptual system based on multinuclear heterogeneous processor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mittal | A survey on optimized implementation of deep learning models on the nvidia jetson platform | |
| CN113850363A (en) | Techniques for applying driving norms to automated vehicle behavior predictions | |
| EP3940665A1 (en) | Detection method for traffic anomaly event, apparatus, program and medium | |
| US20190050732A1 (en) | Dynamic responsiveness prediction | |
| CN107291597A (en) | A kind of multi-modal decision-making sensory perceptual system of O＆M based on multinuclear heterogeneous processor | |
| CN105391800A (en) | Internet plus-based medical equipment fault self checking and repairing system | |
| KR20200055828A (en) | Artificial Intelligence Platform Service System and Method | |
| CN109254895A (en) | A kind of high-performance server accident analysis prediction technique based on BMC | |
| Nagaraj et al. | Edge-based street object detection | |
| CN107329878A (en) | A kind of multi-modal decision system prototype of O＆M based on multinuclear heterogeneous processor | |
| US20200074213A1 (en) | Gpb algorithm based operation and maintenance multi-modal decision system prototype | |
| CN107480095A (en) | A kind of multi-modal decision system interface of O＆M based on multinuclear heterogeneous processor | |
| CN110221951A (en) | A kind of multi-modal decision system of O&M based on multi-data processing device | |
| KR20210147594A (en) | Edge computing devices and methods that provide optimization for energy data collection and management | |
| CN107300868A (en) | A kind of multi-modal decision system interface of O＆M based on polycaryon processor | |
| CN106799991A (en) | A kind of intelligent travelling crane early warning system interface based on multinuclear heterogeneous processor | |
| CN116645587A (en) | Image recognition model generation method, image recognition method, system and chip | |
| CN116469127A (en) | Method and device for detecting key points of cow face, electronic equipment and storage medium | |
| CN107332708A (en) | A kind of multi-modal decision-making sensory perceptual system of O＆M based on polycaryon processor | |
| CN107391451A (en) | A kind of multi-modal decision system framework of O＆M based on multinuclear heterogeneous processor | |
| CN107346110A (en) | A kind of multi-modal decision system prototype of O＆M based on polycaryon processor | |
| Miyagi et al. | Zytlebot: FPGA integrated ros-based autonomous mobile robot | |
| CN106864404A (en) | A kind of intelligent travelling crane early warning sensory perceptual system based on multinuclear heterogeneous processor | |
| CN108038046A (en) | A kind of O＆M pre-alarm and prevention decision system based on multinuclear heterogeneous processor | |
| CN107180162A (en) | A kind of multi-modal decision system framework of O＆M based on GPB algorithms |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171215 |
|
| RJ01 | Rejection of invention patent application after publication |