This document describes a predictive maintenance system for robots using real-time sensor data. A team of 4 engineers built a solution in 2 months using standard open source software like H2O and MapR. Sensors on a robot collected accelerometer, gyroscope and other data. This raw data was analyzed using anomaly detection algorithms in H2O to build a machine learning model that identified normal vs abnormal robot states. The model was deployed as a microservice to make real-time predictions on new sensor data and detect potential failures. The solution was able to analyze data from hundreds of robots and identify anomalies within 3 seconds, demonstrating an effective low-cost predictive maintenance system.
Industry 4.0 is all about digitization of the factory. Sensors everywhere. All this data makes possible new opportunities for automation, cost savings, higher productivity and higher quality.
Our talk will focus on Data & Analytics for improving the efficiency of operations of factories with lots of industrial robots.
We combine Smart sensors, DB Analytics (ML), Cloud computing and AR to power a real-world, state of the art predictive analytics system.
Predictive Maintenance generates value from the following
Requirements for such a system start with a clear view of business value before any work is done. Need to have an image of the impact of a successful system on the business.
Based on known real-world requirement of state of the art Japanese car-parts manufacturers.
Scale with number of sensors, robots and factories. GB a day quickly become many GB per hour or even minutes. This is comfortably on moderate sized clusters (5-25 nodes) using current big data platforms used by attendees of Strata.
Standard big data OSS has come a long way over the past 5 years and is now at a point where a state of the art project like this can be constructed by judicious assembly of projects:
Distributed storage
Distributed streaming
Distributed stream processing
Distributed machine learning
ありがとうございました
もう少し、デモについて詳しく説明します。
ロボットに動作検知をするためのセンサーがついています。
センサーはマシンの振動(しんどう)やノイズを検知しています。
このデータは Raspberry Pi に無線で送信されます。
Raspberry Pi がデータを収集して、MapRに送信します。
アナリティカルパートでモデルを作ります。
オペレーショナルなパートで作成したモデルで、robotの状態を可視化システムでoperatorがreal-timeで監視できます。
これは先ほどお話しした通りですね。
What do we even want?!
I.E.:
Data gathering
Feature selection, extraction, engineering and data transformation
3) Pick all potential algorithms
4) Build a model using your library/tool of choice
5) Evaluate according to previously defined metrics
6) If not good enough then either try a different approach, features or method parameters
7) Otherwise extract the model and put it into production!
Mention why we are doing it with machine learning at all!
No rules, automatically learn the best parameters for each application without new coding and not based on supervised techniques.
Especially good when we don’t know what we are looking for: machines can break in a variety of ways.
Mention why we are doing it with machine learning at all!
No rules, automatically learn the best parameters for each application without new coding and not based on supervised techniques.
Especially good when we don’t know what we are looking for: machines can break in a variety of ways.
Mention why we are doing it with machine learning at all!
No rules, automatically learn the best parameters for each application without new coding and not based on supervised techniques.
Especially good when we don’t know what we are looking for: machines can break in a variety of ways.
Peeking: ML modeling mistake where some data is used to train a model includes information about the answer
教師なし学習 => unsupervised learning
異常認識 => anomaly detection
The real data is very noisy
Why use ML at all? We don’t want to use rules for every type of robot and every situation
Don’t mention threshold, just say we did some parameter tuning of the ML algorithms or something
/
Keep?
Mention why we are doing it with machine learning at all!
No rules, automatically learn the best parameters for each application without new coding and not based on supervised techniques.
Especially good when we don’t know what we are looking for: machines can break in a variety of ways.
Mention why we are doing it with machine learning at all!
No rules, automatically learn the best parameters for each application without new coding and not based on supervised techniques.
Especially good when we don’t know what we are looking for: machines can break in a variety of ways.
Amazing evolution in last few years
Lots of learning material, Experts are out there
A minimal working model is easy to make (H2O)
Get more value: Improve it over time
Contract with experts as needed
Only one cluster, little configuration, ”it just works”