Icon

RUL_​LAB_​Part2_​HealthIndex

RUL LAB Part 2 - health index from 36 pump sensors (KNIME 5.x, metanode version). Double-click a metanode to open it.
1 Prepare dataKeep cycles 0-6, drop RECOVERING hours.Drop sensor_50 and the redundant block -> 36 sensors.Fill gaps with the previous value (no look-ahead).Out: 2,034 rows x 36 sensors + timestamp, cycle, rul.
2 Health index per cycle (Group Loop over cycle)2a Baseline of THIS cycle: rolling 48 h median and MAD of every sensor, shifted +24 h -> hour t is judged against hours t-72 .. t-25.2b z = (x - median) / max(1.4826*MAD, 0.02*|median|) HI = number of sensors with |z| > 3 HI6 = 6 h mean of HI ALARM = HI6 > 9 for 2 consecutive hours (tau = 9)
3 Evaluate per cyclelead time = max rul while ALARM = 1 and rul <= 72 hfalse-alarm hours = ALARM = 1 while rul > 72 hResult (tau = 9 fixed): 2 of 7 failures caughtcycle 2: 63 h ahead, cycle 4: 56 h ahead13 false-alarm hours in 2,034 hours
Read pump_rul_hourly.csv(data folder of this workflow)
CSV Reader
Per cycle: max lead time,false-alarm hours, row count
GroupBy
hi_eval_per_cycle.csv
CSV Writer
features_knime.csv(same values as the Python reference)
CSV Writer
1 Prepare data
HI6 over time:does it rise before a failure?
Line Plot
2 Health index per cycle

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: anos
Created at: 2026-09-24
On NodePit since: 2026-09-25
Last update: 2026-09-27
Created with KNIME version: v5.12.0

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

Try NodePit Runner!