Big data analysis
Make data analysis smarter
in edge computing.
What is big data analysis?
Big data is broadly divided into data generated by humans (on social networks, for example) and data generated by things (such as sensors placed on equipment). The amount of data generated by things in particular is increasing rapidly as IoT spreads. Much attention is focusing on edge computing as a way to process this data quickly. This is because it would be very difficult to keep up with the explosive growth in data by existing means that depend on the cloud for all data processing, because that increases the data communications load and lowers responsiveness.
Edge computing can minimize the communications load and speed up processing by placing servers around the device and dispersing the processing of the data. In addition to dispersed processing by edge computing, it is important to have high-level big data analysis technology like AI in order to use big data effectively.
Strengths of Mitsubishi Electric
Drawing on our machinery knowledge to efficiently analyze
time series data.
There are many ways to use big data, one of which is the preventive maintenance of infrastructure and the like. Promptly finding signs of irregularities in equipment requires fast and accurate analysis of vast amounts of time series data from sensors. Mitsubishi Electric has successfully used machine learning to reduce the number of calculation repetitions needed to detect signs of irregularities to just 1/40 the earlier count.
The technology until now would find signs of irregularities by comparing all the waveform data from sensors. Our technology makes it possible to find signs of irregularities quickly, with fewer calculation repetitions, by categorizing and learning waveform data in a number of typical patterns (clusters) and extracting only the differences (degree of deviation) in those patterns. Through AI and other analysis technology using Mitsubishi Electric’s machinery knowledge, we are helping to make time series data analysis faster and more efficient in edge computing.
The analysis technology uses our machinery knowledge to machine-learn typical time series data patterns and extract the degree of deviation.