Machine Tool Spindle Fault Prediction Using Controller and Sensor Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional fault prediction methods for main shafts and motor-driven systems in machine tools are inefficient, leading to prolonged downtime due to labor-intensive manual measurements and inaccurate detection of faults, especially in complex environments, where ambient noise and vibrations complicate the identification of abnormalities.

Innovation Solution

A machine learning device and method that observes state variables from motor controllers, detectors, and measuring devices to learn fault prediction patterns, using a combination of data sets to determine fault occurrence and degree, and updates predictive models based on time-weighted determination data, enabling earlier fault detection and reducing downtime.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual vibration measurement is performed by operators, then fault detection can be conducted, but the operator burden increases significantly and measurement efficiency decreases

Engineering Contradiction:

Improvefault detection capabilityVSAvoidmeasurement efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system enables automatic fault detection by having the machine tool itself provide the measurement data through integrated sensors and controllers, eliminating the need for external operators to perform manual measurements. The control unit automatically collects vibration data from detectors during normal operation and performs fault analysis without human intervention.

Inventive Principle:

Principle #25Self-service

2Measurement precision

If vibration sensors are always attached to the main shaft for automatic measurement, then fault detection accuracy improves, but the machine tool cost increases

Engineering Contradiction:

Improvefault detection accuracyVSAvoidmachine tool cost

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system utilizes the existing control unit and detector infrastructure of the machine tool for dual purposes: normal operation control and fault detection. The control unit that already manages machine operations is also employed to collect and analyze vibration data, eliminating the need for separate dedicated fault detection hardware and reducing overall system cost.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The control unit serves as an intermediary that bridges the gap between simple detectors and fault detection functionality. It collects raw vibration data from detectors, processes the signals, and performs fault analysis without requiring direct complex sensor-main shaft connections, thereby reducing hardware complexity while maintaining detection accuracy.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Reliability

If conventional fault prediction methods are used, then some fault detection is possible, but downtime is prolonged due to labor-intensive manual measurements and inaccurate detection in complex environments

Engineering Contradiction:

Improvefault detection capabilityVSAvoiddowntime

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs continuous fault detection during normal machine operation without interrupting production. Vibration data is collected and analyzed in real-time throughout the operational cycle, enabling early fault detection without requiring separate measurement sessions or stopping the machine, thus minimizing downtime.

Inventive Principle:

Principle #20Continuity of useful action

Solution Approach 2:

The control unit continuously monitors vibration data and provides feedback on machine health status. When abnormal patterns are detected, the system can alert operators or automatically adjust operations, enabling proactive maintenance decisions that prevent complete failures and reduce unplanned downtime.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11521105B2Machine learning device and machine learning method for learning fault prediction of main shaft or motor which drives main shaft, and fault prediction device and fault prediction system including machine learning device

Publication Date: 2022.12.06 FANUC LTD

AI summary

A machine learning device which learns fault prediction of one of a main shaft of a machine tool and a motor driving the main shaft, including a state observation unit observing a state variable including at least one of data output from a motor controller controlling the motor, data output from a detector detecting a state of the motor, and data output from a measuring device measuring a state of the one of the main shaft and the motor; a determination data obtaining unit obtaining determination data upon determining one of whether a fault has occurred in the one of the main shaft and the motor and a degree of fault; and a learning unit learning the fault prediction of the one of the main shaft and the motor in accordance with a data set generated based on a combination of the state variable and the determination data.