Predicting Machine failure
1300% Better at predicting Machine failure than random guessing.
Most Likely Yes:
Torque (Nm)<=59.92 and
Rotational speed (RPM)<=1366.72 and
Air temperature (K)>301.94 and
Process temperature (K)<=311.61
Most Likely No:
Torque (Nm)<=59.92 and
Rotational speed (RPM)>1366.72 and
Tool wear (min)<=171.83 and
Air temperature (K)<=302.01
Explored 8 factors over 10000 records in dataset Predictive Maintenance - Machine Failure.csv, in which 3.39% of records had Machine failure is Yes (339 of 10000)

Found 6 to be relevant, and ignored the remaining 2 irrelevant or redundant factors.
Key Factors

We analyzed each factor (column) in the data, looking for which factors matter and which are irrelevant when predicting Machine failure.

Key Factors - The most important factors and their values most likely to result in 'Yes' for Machine failure are:
Factor Likely Yes
1 Torque (Nm) Torque (Nm)>40.1
2 Rotational speed (RPM) Rotational speed (RPM)<=1503.0
3 Air temperature (K) Air temperature (K)>300.1
4 Tool wear (min) Tool wear (min)>108.0
5 Process temperature (K) Process temperature (K)>310.1
6 Type Type is L
Irrelevant Factors - The following factors in your data were not very important in predicting Machine failure:

There were no factors your model considered and deemed irrelevant

Expand to see more on Factors

Certain factors (or columns) are more important in the prediction of 'Yes' or 'No' than others. You can optimize your time and resources by prioritizing key factors across data gathering, data management, and decision-making.


For example, if data gathering is time-consuming or expensive, you might consider de-prioritizing irrelevant factors. Just be mindful that they may be important for other problems.


If you need help, set up a call with our Berrijam AI Coaches to brainstorm how you can adopt these insights from factors.

Key Segments

A combination of factors can be used to define a segment, giving deeper insights and making them easier to act upon.

We have automatically identified top segments for 'Yes' and 'No' predictions, by determining their importance based on the size of the segment and % Yes or % No within the segment. Alternatively, you can explore the segments below.

Most Likely Yes
Segment Segment Breakdown
Torque (Nm)<=59.92 and
Rotational speed (RPM)<=1366.72 and
Air temperature (K)>301.94 and
Process temperature (K)<=311.61
Torque (Nm)>59.92 and
Tool wear (min)>166.94 and
Rotational speed (RPM)>1193.72 and
Process temperature (K)<=311.45
Torque (Nm)>59.92 and
Tool wear (min)<=166.94 and
Air temperature (K)>301.93 and
Process temperature (K)<=312.71
Torque (Nm)>59.92 and
Tool wear (min)>166.94 and
Rotational speed (RPM)>1193.72 and
Process temperature (K)>311.45
Torque (Nm)>59.92 and
Tool wear (min)<=166.94 and
Air temperature (K)<=301.93 and
Rotational speed (RPM)>1418.32
Most Likely No
Segment Segment Breakdown
Torque (Nm)<=59.92 and
Rotational speed (RPM)>1366.72 and
Tool wear (min)<=171.83 and
Air temperature (K)<=302.01
Torque (Nm)<=59.92 and
Rotational speed (RPM)>1366.72 and
Tool wear (min)<=171.83 and
Air temperature (K)>302.01
Torque (Nm)<=59.92 and
Rotational speed (RPM)>1366.72 and
Tool wear (min)>171.83 and
Type is L
Torque (Nm)<=59.92 and
Rotational speed (RPM)>1366.72 and
Tool wear (min)>171.83 and
Type is not L
Torque (Nm)<=59.92 and
Rotational speed (RPM)<=1366.72 and
Air temperature (K)<=301.94 and
Tool wear (min)<=169.42
Explore More Segments
Click on the rings to drill down into sub-segments and click the center circle to navigate back up.

As you hover over a segment, you’ll see the factors that define the segment, the segment size as a percentage of all records, and the percentage of 'Yes' within that segment.
Expand to see more on Segments

Segments help identify important groups or populations where to invest time and effort. For example, a teacher could use segments to focus on students who are least likely to pass the course. They also identify which combination of the factors and values to focus on if you want to increase or decrease the percentage of ‘Yes’.


For example, a maintenance team might identify that machines operating above a certain temperature and load are more likely to break down. So they might set up temperature alerts and reduce the load at certain temperatures to keep the machine working.


If you need help, set up a call with our Berrijam AI Coaches to brainstorm some ideas on how to adopt the insights from segments to design strategies or policies that are relevant to you.

Model Results

We explored 194 different models to find which produced the best results.

Since there were no rows where Machine failure was empty, we did not make any predictions with these models.

The Best Explainable Model performed well on this dataset:

790%
Better than Random

The Best Non-Explainable Model performed very well on this dataset:

1300%
Better than Random
All Model Results
Credit

Explored by Avishkar Misra using Predictive Maintenance - Machine Failure.csv on 2023-10-14 with Berrijam. Try it yourself at Berrijam.com