Pages

Machine Tool Health Indicator

The primary role of a machine tool is to not only provide high up time but also produce good quality parts. Unfortunately, a machine tool goes through a process of degradation and wear, which will affect the accuracy and precision of machining and, consequently, the quality. With the overwhelming challenges facing US manufacturers and their struggle to decrease manufacturing costs and improve quality, monitoring the degradation of a machine tool and quantifying its health is a very important. Given the health of different components of a machine tool, the Machine Tool Health Dashboard is a framework for calculating and displaying the overall health of the machine tool termed as Machine Tool Health Index (MTHI). 

The Watchdog Agent, employs data driven methods, which use statistical tools and supervised learning algorithms to detect the degradation and wear of machine tool components and quantify their health status. The health values from different components of the machine tool are aggregated into an overall health value of the machine tool - Machine Tool Health Indicator (MTHI).


A machine tool is a complex system of components; the harsh machining environment poses as an accelerator of degradation and wear for the machine tool’s components. The Watchdog Agent tools are able to quantify the health of a component into a single Confidence Value (CV), which is a number between 0 (unhealthy) and 1 (healthy). MTHI is an indicator of the machine tool’s ability to produce quality parts. In addition, it can also be interpreted as a upcoming downtime. Machine failure or downtime is defined as the inability of the machine to produce desired quality parts. Therefore, the machine can be technically in a running state but still termed as "down" if it cannot fulfill the quality requirements.

The following steps constitute the approach for calculating the MTHI and displaying it with other important information on the Machine Tool Health Dashboard.

Step1: For each component, find the effect of degradation in a component (CV) on the various Machining Quality Indexes (MQIs): Surface Finish, Dimension Variation, Tool Life, Spindle Life, etc.

Step2: For each component, aggregate the Machining Quality Indexes (MQIs) to a single Machining Quality Value (MQV)  for the component. The MQV is a value between 1 and 0, indicating the effect of a component’s heath status on the overall machining quality.

Step3: Aggregate the Machining Quality Values (MQV) of different components into an overall Machine Tool Health Index (MTHI). MTHI is a single value between 1 and 0 that indicates the effect of a machine tool health on the overall machining quality (MTHI is 1 when the current health of the machine is not affecting product quality; 0 is when the health of the machine is causing the production to be completely out of tolerances(scrap/reject)).

The MTHI provides a single health value for the whole machine tool that enables the machine operator to easily monitor a single value as an indicator of the overall machine tool health and its direct effect on producing quality parts. The dashboard will also include other important information for the operator and maintenance personnel who will be able to: monitor the health values of different components (CV); monitor the effect of each component’s health on the machining quality (MQV); and take quick maintenance actions based on the real-time alarms displayed on the dashboard. 

Tool Holder Unbalance Monitoring

Unbalance in the tool assembly causes excessive loads on spindle bearings, tool wear, and increased vibration levels. As high-speed machining has become a common practice, situation is worse as unbalance force is proportional to square of the speed. Watchdog Agent provide data-driven methods, which use statistical tool and supervised learning algorithms to detect the presence of unbalance in a tool assembly relative to the tools with known balance levels. 
Firstly, Fourier analysis is performed to determine the vibration noise of the floor and uncover resonant frequencies. Total Indicator Run out (TIR) is quantified to determine spindle and tool run-outs. Other factors that may affect vibration readings are identified, which characterize the machine, thus coming up with a customized balance measurement technique for that machine. 
Secondly, after performing tests, features that are to be extracted from the vibration signals are identified. The gamut of features may include average (dc) value, RMS value, minimum and maximum peak levels, amplitudes of the fundamental and harmonics of the spindle service speed, 3rd and 4th order moments of the vibration signal, kurtosis etc... Fisher criterion are used to identify the features that influence the system performance. 
Finally, a supervised learning algorithm is selected to build the best-fitting model to quantify the relationship between the dichotomous characteristics of the dependent variable with a set of independent variables and estimate the unbalance present in the tool assembly. 



Trending and monitoring these values will give valuable insights and forecasting capabilities for the tool assembly in terms of its health and usability for a certain precision machining process.