FEATURE DATA ACQUISITION MACHINE LEARNING AND DATA
In National Instruments’ Trend Watch 2018, the company has identified the ways in which machine learning is putting data to work and how it can offer practical business improvements
faulty sensor? Endless anomalies can cause defects, so setting up test limits for all of them is not practical (or possible). NI says that machine learning technology will alert manufacturing test engineers to defects missed in the design and test phases of product development.
N
ational Instruments (NI) has launched its Trend Watch 2018. The report
examines the technological advances propelling our future faster than ever before along with some of the biggest challenges engineers face next year. “As we advance through the 21st century, our customers demand higher quality devices, faster test times, more reliable networking and almost instantaneous computing to keep their organizations moving forward,” said Shelley Gretlein, NI vice president of corporate marketing. “Not only is NI prepared to help customers keep pace by exploring the trends impacting our industry, we also provide actionable insights backed with an open, software- centric platform to accelerate the development of any customer-defined test, measurement or control system.” NI Trend Watch 2018 considers how 5G
is to disrupt test processes. It also explores the three necessities for successfully managing the Industrial Internet of Things (IIoT), the effects of electrification and breaking Moore’s Law. Another key trend identified by NI
in the report is how machine learning puts data to work. NI reports that the investments of tech
giants in machine learning applications are drawing a lot of attention. For example, Google’s largest collection of developers outside its US headquarters is a research group dedicated to machine learning. Microsoft open sourced CNTK, Baidu released PaddlePaddle, Amazon decided to support MXNet on AWS, and Facebook created two deep learning frameworks. NI says the wave of machine learning applications in the consumer space will spill over into industry, which
16 NOVEMBER 2017 | INSTRUMENTATION
will help engineers and managers improve business operations with automated data analysis. In addition to driving innovation, machine learning offers practical business improvements such as operational uptime, production, yield and engineering efficiency.
MACHINE LEARNING FEEDS ON DATA The ability to network intelligent systems to improve data visibility is well- documented as both an Internet of Things (IoT) benefit and a Big Analogue Data challenge. Sensor and machine data from industrial equipment is expected to top 78 exabytes by 2020, and somewhere among all that data will be evidence of a machine failure, manufacturing defect, or critical validation test missed by today’s technology. NI says vast data sets will help train better models from machine learning algorithms and yield faster results, but only if they are available. Today’s system designers need to view organised data collection as the first step to implementing machine learning technology and develop more comprehensive DAQ and management strategies for connected systems.
IMPROVING YIELD Most manufacturers today screen for pass/fail conditions and save data for forensic analysis, calibration records and genealogy. Some manufacturers use more advanced automated test methods, but machine learning models can help them screen for product defects regardless of root cause. Did the silicon-level components on the current build come from a new fab? Does the design include counterfeit components? Is the wave- soldering temperature off because of a
One key element to watch for is the incorporation of machine learning in technology platforms that help developers focus on new problems
INCREASING UPTIME Many companies in process manufacturing have extensive databases of maintenance and operational data for their industrial assets. Maintenance engineers manually work with this data today, but future machine learning methods will process this data to classify operational states and detect anomalies. NI says that properly trained systems will identify irregularities that need attention.
TAKING ADVANTAGE OF THE EDGE NI explains that the convergence of rugged processing and sensor fusion with machine learning will help engineers build better systems that can interpret data at the edge without needing to communicate with the enterprise stack. Some technology can already train and run models at the edge. Pushing intelligence to the edge with real-world signals reduces the latency of decisions and the need for costly infrastructure, which helps as billions of new devices come online and compete for limited bandwidth.
PLATFORMS WILL HARNESS THE POWER OF MACHINE LEARNING According to NI, one key element to watch for is the incorporation of machine learning in technology platforms that help developers focus on new problems, save time stitching together adjacent technologies, and avoid getting lost in middleware. Engineers rarely want to spend time dealing with questions that have already been answered or deemed necessary only because of toolchains. Integrating machine learning into cloud, software and hardware platforms will provide precurated technology stacks so engineers can focus on new challenges. NI concludes that business leaders are
looking to engineers, platforms, and the next wave of machine learning to help find uptime, yield and efficiency in a sea of Big Analogue Data.
National Instruments
www.ni.com
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
