Using Sensor Data for the Development of Digital Twins in Support of Condition-Based Maintenance
Bibliographic record
Abstract
This article examines how operational data obtained from sensors interacting with the Royal Canadian Navy (RCN) Halifax Class Frigates onboard Integrated Platform Management System (IPMS) could be used to support a shift from schedule-based maintenance to condition-based maintenance. The idea is to use a few years of IPMS data logged by the L3Harris Equipment Health Monitoring (EHM) software tool to aid in the development of EHM rules (or Digital Twins) that will indicate the current health status of various equipment. The process of EHM rules development consists of several steps. First, the targeted failure modes were selected by carrying out equipment failure modes and effects analysis (FMEA) and reviewing existing operational and maintenance records collected from the resource management system. For each targeted failure mode, relevant IPMS integrated sensors data was identified (when available), extracted, and checked for missing values, low signal to noise ratio and outliers. An equipment digital twin was created using L3Harris EHM built-in functions and/or Python programming language. Utilization of Python programming language functions allowed implementing EHM approach for wider range of equipment failure modes. Once the EHM rule was developed, it was tested using a different set of IPMS data. The results were analyzed and the digital twin model was reworked until a satisfactory response was confirmed. Numerous Digital twins (DTs) were created for critical equipment on board including propulsion diesel engine, drive train components, pumps, remotely controlled valves, and sensors. This development process demonstrated how sensors meant to support operational needs and benefit CBM. More value to be expected should the specific needs of CBM be considered early in the ship design. L3Harris IPMS was proven a valuable source of information to support the development of EHM rules necessary for CBM. In the course of this study, L3Harris DT engineering process was also validated by Lloyd’s Register and received “Digital Twin Ready Approval in Principle” certification. The performance of EHM rules still has to be validated in the field and its value to be confirmed by the end-users, but the work performed so far is promising.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".