Machine Learning for Auto Optimization
What is Machine Learning? Definition: “ Machine learning refers to any system where the performance of a machine in performing a task improves by gaining more experience in performing that task ” . Experience refers to the data that we fed in to the algorithm and improvements refers to it output which is considered as an action. ML is intelligence acquired by a machine, which is similar to human natural intelligence. ML use existing data to forecast future behaviors, outcomes, and trends. ML involves using statistical / mathematical techniques.
Examples of Machine Learning A computer program is said to learn from experience E with respect to task T and performance gauge P. Future Traffic pattern(P) Performance measuring(P) ML Algorithm Traffic pattern(T) Task (T) Historic Traffic pattern(E) Experiences (E) Optical Character Recognition: categorize images of hand written characters by the letters represented. Face detection: Find faces in Image. Spam Filtering: identify email messages as spam or non spam.
Applying Machine Learning to CNC Machines Performance Improvement using Machine Preventive Maintenance using Machine Learning: Learning: Prediction of Failures Thermal Displacement Compensation Data Analysis using AI - Pattern Analysis/ Automatic Servo Tuning Adaptive Control for optimizing cycle time. Waveform Analysis Minimizing Downtime using AI Learning control for achieving high performance machining. Inertia Estimation, for higher acceleration to reduce cycle time. Smart Program Analysis – Acc/dec decided dynamically
Thermal Displacement Compensation Conventional Method ： Temperature sensor Data ： Displacement sensor Collection Temp. Analysis, Formulation Heat transfer analysis Software development Thermal fluid analysis. etc. Disp . It is not easy to derive the relationship between temperature and displacement necessary for thermal displacement compensation
Thermal Displacement Compensation Using machine learning Thermal Displacement Compensation option Model development tool ： Temperature sensor ： Displacement sensor Model Temp. Data Development TDC Thermal Temp. Learning Software Collection Displacement Model Data Compensation Software Machine Comp. Disp. Learni arning Machine learning can derive the relations from the data of temperature and displacement and can create thermal displacement model.
Automatic Servo Tuning • Auto-tuning of servo gain and Acc/Dec time constant according to target work piece • Useful for machining optimization Workpiece 1 SERVO Tuning Data 1 Manage Workpiece 2 SERVO Tuning Data 2 : Restore Collect Collect Ethernet SERVO SERVO SERVO Tuning Data 1 Tuning Data 2 Tuning Data 1 Workpiece1 Workpiece2 Workpiece1 Machine tools
Inertia Estimation, For higher acceleration to Reduce Cycle Time • Can automatically estimates the inertia when Job changes. • Can achieve optimum positioning time.
Adaptive Control for Optimizing Cycle Time • Automatic Feed rate control according to spindle load and temperature. • Controlling feed rate according to spindle load strikes a good balance between shorted cycle time and longer life time of cutting tools.
Adaptive Control for Optimizing Cycle Time
Learning Control for Achieving high performance machining Servo learning Control • Suppress periodic machining disturbance.
Learning Control for Achieving high performance machining Servo learning Oscillation • Avoid chip Entanglement by oscillation cutting for chip shredding using servo learning. • Contribution to productivity improvement by continuous operation. • Reduction of production costs by elimination of chip removal system.
Smart Program Analysis-Acc/Dec decided dynamically • Artificial Intelligence Contour Control Function for reading small segments of program in advance and will create smooth profile.
Prediction of Failures- AI Spindle Monitor • Anomaly monitoring of spindle by machine learning. • Can predict the spindle failure in advance. Calculation of Anomaly score Acquisition of servo data Model creation at normal state
Data Analysis Using AI- Pattern Analysis/Waveform Analysis Collection of various sensors data and servo data • Collect data from various sensors Motor speed (temperature, shock etc.) via CNC Machine Acc. by using i/o units. • Collect servo data with high speed Operation Management Servo software data VIEWER software sampling (1ms) and to store with Database file format Sensor data Servo data • Displays collected data for analysis. . . . Analog External sensor interface module MULTI SENSOR Applications Shock sensor Temperature sensor I/O UNIT • Monitor the servo and spindle loads and establish pattern(Signature) for the component.
Minimizing Down time using AI • Manages diagnosis information of Trouble Diagnosis and Machine Alarm Diagnosis with final solutions when alarm occurs. • When newly alarm occurs, indicate solution from similarly diagnosis information Normal Trouble Diagnosis AI Trouble Diagnosis Actually Measures/ Collect Add Treatments Indicate Alarm! • • Operator implement diagnosis according to AI indicate higher probability solution from past history data. CNC guidance/Manual. • Automatic judgment from countermeasure / treatment information in case of • Operator needs to diagnose when multiple multiple estimation causes remained. estimation causes finally to be left Rapidly restoration at trouble
Applying Machine Learning for Robotic Automation . Faster Bin Picking application : • Robots automatically learns the picking sequence of work piece. • Drastically reduces the time for manual setting and tuning. AI Bin picking Application
Applying Machine Learning for Robotic Automation . Learning Vibration Control : Learning robot realizes high speed smooth motion with suppression of vibration by LVC (Learning Vibration Control). W/O LVC W/ LVC Learning Control + Sensor Technology Accelerometer Vibration Suppressed!! Learning robot merit This function has Cycle time can be reduced by high overcome vibration speed motion. issues of high speed (i.e. realization of higher performance motion, which has not be for each ) used before.
Prediction of Failures- Mechanical Failures To eliminate unplanned downtime . Process Health Vision detection result Reducer to be exchanged Welding current monitor next weekend. Mechanical Health Servo gun status monitor Operational status proceed proceed proceed proceed production production production production System Health Increasing Memory usage vibration of J2! Alarm information Maintenance health Grease replacement Replace grease ! Battery replacement Greasing to the balancer bush Alarms
Machine Learning on Standalone Vs network of Systems Stand alone Machine with networking Server with ML Learning with experience is confined to Learning will be vast since all machines one machine. will be sharing there data and solution can be immediately found.
Machine learning With IOT IoT IoT- Conn nnects cts Thing ngs s – “Internet of Things” IOT provides a platform on which number of devices are connected and pushing down data in a centralized system. • IoT devices follow these five basic steps: measuring, sending, storing, analyzing, acting. • The collected datasets are fed into Machine learning algorithms to take active decisions.
Cloud Computing ON Premises • In IOT System, to save huge amount of data, 2017 2018 2016 known as Big Data, stack of storage devices are required. • IOT data will be increasing exponentially & hence will require frequent hardware up gradation. • To Run Machine learning/AI algorithms, high 2016 2017 2018 computation power processors are required and single processor is not sufficient. ON CLOUD
Advantages of Cloud Computing Disaster recovery Flexibility Automatic software updates Businesses of all sizes If your needs increase it’s should be investing in easy to scale up your cloud Suppliers take care of robust disaster recovery,. capacity, drawing on the servers for you and roll out service’s remote servers. regular software updates. Capital-expenditure Free Work from anywhere Cloud computing cuts out With cloud computing, if you’ve got an the high cost of hardware. internet connection you can be at work.
FOG Computing Data Segment Cloud Critical Data Non- Critical After processing data is saved in Data Non-Critical data sent directly cloud • FOG Computing is an intermediate layer between device and Cloud. FOG (T3 Time for processing) On- Premises T4 Sec T2 Sec IOT Devices (T1 time for data generation)
IOT/Cloud computing with ML The only way to analyze the data generated by the IoT is with machine learning/AI.
Recommend
More recommend
