Feature: AI
existing vision logic is recommended. The sparse modelling tool can be implemented as a standard installation within the customer’s software environments, or leverage a hypervisor- isolated virtual-machine cloud; even FPGA-based implementations on customised carrier boards are possible, to further reduce the required power envelope. Version 1.0 of the AI sparse-modelling
tool from Hacarus is now available as part of an instantly-deployable starter kit. A key highlight is that the platform is factory-ready, with support for industry-standard image-acquisition channels such as GigE or USB 3.x. Installation requires three simple steps: Connect with the installed image acquisition system via the tool’s API, capture images to train the algorithm, and tune the algorithm using human inspectors. No external cloud training is needed; all AI training and inference- system-based predictions run within edge-computing devices. Easily trained on vision-based intelligence like “door is open” or “switches are in wrong position”, it is much faster to train and implement than programmed solutions with many “if then else” lines of code, etc. In addition, sparse modeling is not only suitable for image-data analytics but also for analysing time-series data. Very useful for predictive maintenance purposes, this makes it highly suitable IoT and Industry 4.0 edge logic for machine builders, as well.
Starter kit with scaleable hardware platform The new starter kit has been compiled by Hacarus in cooperation with Japanese semiconductor trading company PALTEK, and can instantly be deployed and tested in any GigE and USB 3.x environment. It is designed on the basis of the palm-sized industrial box PC using standard computer-on-modules. The system measures only 173 x 88 x 21.7mm and, although slim, offers performance supported by the latest Intel Atom and Celeron processors (codename Apollo Lake). The system
AI will certainly help, but is not a panacea since it requires massive training data. Such data is currently rarely available, since quality production is not programmed to produce massive quantities of faulty parts to teach AI systems
is thus an ideal platform for best-in- class low-power, high-performance applications based on x86 processors. Despite its small size, the system has a
rich set of I/Os enabling many different setups on end-user factory floors. Standard interfaces are 2 x GbE ready for GigE Vison, 1 x USB3.0/2.0, 4 x USB2.0 and 1 x UART (RS-232). Extensions are possible with 2 x Mini-PCIe with USIM socket, 1 x mSATA socket and 16-bit programmable GPIO. DC input voltage is 9V-32V. Based on the Qseven COMs from Congatec, the system offers flexibility in terms of CPU selection and upgradeability on the basis of Intel’s CPU generations. One of the key benefits of the
computer-on-module standard specified by the SGET standardisation body for embedded computing technologies is that it supports both ARM and x86 platforms. Tis makes the low-power form-factor module futureproof, since it is also suitable for sparse-modelling setups as new applications evolve.
The first Conga-QA5 COMs supporting sparse modelling software are based on Intel’s latest low- power microarchitecture codenamed Apollo Lake
www.electronicsworld.co.uk November/December 2020 57
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68
