Icon

Completed Workflow

Cleaning up of data

Classification (Decision Tree, Minimum Records per Node = 45)

Clustering k=5

Regression (Linear Regression – Target: Degradation level) Predictors: Process Temp + ToolWear

Classification( Decision Tree, Minimum Records per Node = 15)

Regression ( Linear Regression- Target: Degradation level) Predictors : Torque

Clustering k=3

Clustering k=2

Classification (Decision Tree, Minimum Records per Node=5

Regression (Linear Regression-Target: Degradation level) Predictors: Torque + tool wear + rotational speed

Classification (Decision Tree, Minimum Records per Node = 30)

Regression 9Linear Regression-Target: Degradation level) Predictors: Rotational Speed + Tool Wear

Clustering k=4

1st

3rd

Selected predictor variables and regression target.
Column Filter
k=3
k-Means (deprecated)
Split data into training (80%) & testing (20%) datasets.
Table Partitioner
Built a Linear Regression model to predict degradation level
Linear Regression Learner
Converts the target from numeric (0/1) to a nominal/string class.
Number to String
Train Model
Decision Tree Learner
Visualise clustersRotational speed vs Tool wear
Scatter Plot
Predict
Decision Tree Predictor
Compare clustersprocess temp+Torque+Tool wear
Parallel Coordinates Plot
Predicted degradation level using the trained linear regressionmodel
Regression Predictor
Evaluated regression performance using RMSE, MAE and R² metrics.
Numeric Scorer
Train/Test(80/20)
Table Partitioner
Train Regression Model(rotational speed + tool wear)
Linear Regression Learner
Evaluate
Scorer
select variables
Column Filter
Evaluate Model
Numeric Scorer
select features
Column Filter
Predict degradation
Regression Predictor
k = 2
k-Means (deprecated)
dataset witherror
CSV Reader
Remove Kfrom Air Temp
String Manipulation
Remove rpmfrom Rotational Speed
String Manipulation
Change Air Temp and Rotational Speed to Number
String to Number
Change Process Temp& Rotational Speedto Mean (Missing Values)
Missing Value
Selected numerical features for clustering
Column Filter
Normalised data
Normalizer
Branch 1- ClusteringNormalise data
Normalizer
Assign clusters
Color Manager
Visualize clustersAir temp vs Process temp
Scatter Plot
Evaluate
Scorer
Evaluate
Scorer
train model
Decision Tree Learner
Torque + Tool Wear + Rotational Speed
Linear Regression Learner
predict
Decision Tree Predictor
Branch 3 - Regression80% Training20% TestingSeed: 12345
Table Partitioner
Evaluate Model
Numeric Scorer
Predict degradation
Regression Predictor
Train/Test Split (80/20)
Table Partitioner
Normalise data
Normalizer
Converts the target from numeric (0/1) to a nominal/string class.
Number to String
select variables
Column Filter
Train/TestSplit (80/20)
Table Partitioner
Select variables
Column Filter
Assign clusters
Color Manager
Select variables
Column Filter
Select features
Column Filter
Duplicate Row Filter
Train/Test(80/20)
Table Partitioner
Branch 2 - Classification80% Training20% TestingSeed: 12345
Table Partitioner
Visualised cluster separation across selected features.
Parallel Coordinates Plot
Predict degradation
Regression Predictor
Predict
Decision Tree Predictor
Train Regression Model(Torque)
Linear Regression Learner
Min. No of Records per Node = 5
Decision Tree Learner
Evaluate Model
Numeric Scorer
rename machine tomachine failure
Column Renamer
perform clusteringk=5
k-Means
Assign clusters
Color Manager
k=4
k-Means (deprecated)
Assign colors to clusters
Color Manager
Converted Machine a categorical
Number to String
Compare clustersAll
Parallel Coordinates Plot
select features
Column Filter
Visualised cluster distribution using torque and rotational speed.
Scatter Plot
select variables
Column Filter
Converts the target from numeric (0/1) to a nominal/string class.
Number to String
Visualise clusters Torque vs Tool wear
Scatter Plot
Selected predictor variables and target variable.
Column Filter
Normalise data
Normalizer
Compare clusters
Parallel Coordinates Plot
Predicted machine failure
Decision Tree Predictor
Evaluated classification performance using the confusion matrix.
Scorer
Split data into training (80%) and testing (20%) datasets using stratified sampling.
Table Partitioner
select features
Column Filter
Built a Decision Tree classifier using Gain Ratio (minimum records per node = 45).
Decision Tree Learner

Nodes

Extensions

  • No modules found

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: joshl
Created at: 2026-07-30
On NodePit since: 2026-07-31
Last update: 2026-08-02
Created with KNIME version: v5.11.0

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!