Icon

2023-Valtorta-Serie Temporali Robot Antropomorfo

There has been no title set for this workflow's metadata.

Time series analysis of the measurement from an UR robotic arm.
The workflow generates a model and then applies it to forecast the robot performances.

URL: NIST dataset https://www.nist.gov/el/intelligent-systems-division-73500/degradation-measurement-robot-arm-position-accuracy

Data preparation. Data mining.Training the model. Model evaluation and deployment.Model deployed by forecasting the next 1 second series and then evaluated by comparison with actual values. Reading set 1.Reading headers.Adding headersto data.Headers to rows.Appending "Column"to row id to matchdata headers.Assigning newrows ID to matchdata headers.Trimming parenthesis.Converting trimmed strings to double.Preparing time seriesof 200 records.Training modelon 200 previous records.Testing the model.Scoring the model.Selecting onlyinterested cols.Getting first row.Converting firsttimestamp tovariable.Resetting timestamp.Sorting by row id.Creating thetime series.Forecasting the nextvalue.125 iterations = 1 second.Adding the forecastvalue to the previous 200.Renaming predictionvalue as actual,since we have to keepthe same col name.Node 27Choosing the 200most recent records.Selecting onlyforecasted rows.Appending forecast seriesto the actual.Creating an empty row.Adding empty row.Resetting row ids.Node 36Reading set 2.Merging sets.Scoring the forecastseries.Node 40Resetting timedomain.Node 42 CSV Reader Excel Reader Column Renamer(Dictionary) Table Transposer String Manipulation RowID String Manipulation(Multi Column) String To Number Lag Column Random Forest Learner(Regression) Random Forest Predictor(Regression) Numeric Scorer RecursiveLoop Start Column Filter Row Filter Table RowTo Variable Math Formula Sorter Lag Column Random Forest Predictor(Regression) Recursive Loop End Concatenate Column Renamer Column Filter Row Filter Row Filter Column Appender Table Creator Concatenate RowID Model Writer CSV Reader Concatenate Numeric Scorer Line Plot(JavaScript) Domain Calculator Line Plot Data preparation. Data mining.Training the model. Model evaluation and deployment.Model deployed by forecasting the next 1 second series and then evaluated by comparison with actual values. Reading set 1.Reading headers.Adding headersto data.Headers to rows.Appending "Column"to row id to matchdata headers.Assigning newrows ID to matchdata headers.Trimming parenthesis.Converting trimmed strings to double.Preparing time seriesof 200 records.Training modelon 200 previous records.Testing the model.Scoring the model.Selecting onlyinterested cols.Getting first row.Converting firsttimestamp tovariable.Resetting timestamp.Sorting by row id.Creating thetime series.Forecasting the nextvalue.125 iterations = 1 second.Adding the forecastvalue to the previous 200.Renaming predictionvalue as actual,since we have to keepthe same col name.Node 27Choosing the 200most recent records.Selecting onlyforecasted rows.Appending forecast seriesto the actual.Creating an empty row.Adding empty row.Resetting row ids.Node 36Reading set 2.Merging sets.Scoring the forecastseries.Node 40Resetting timedomain.Node 42 CSV Reader Excel Reader Column Renamer(Dictionary) Table Transposer String Manipulation RowID String Manipulation(Multi Column) String To Number Lag Column Random Forest Learner(Regression) Random Forest Predictor(Regression) Numeric Scorer RecursiveLoop Start Column Filter Row Filter Table RowTo Variable Math Formula Sorter Lag Column Random Forest Predictor(Regression) Recursive Loop End Concatenate Column Renamer Column Filter Row Filter Row Filter Column Appender Table Creator Concatenate RowID Model Writer CSV Reader Concatenate Numeric Scorer Line Plot(JavaScript) Domain Calculator Line Plot

Nodes

Extensions

Links

Download

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

Download Workflow
Created by: rikyv
Created at: 2023-09-21
On NodePit since: 2023-09-25
Last update: 2024-04-27
Created with KNIME version: v5.1.1
Tags: Time Series AnalysisRobotics

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

Try NodePit Runner!