Condition-based Maintenance for High-speed Fleet
- 2. Contents Condition-based Maintenance for High-speed Fleet M2M approach to the CBM Solution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 2 References About Author . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 4
- 3. Condition-based Maintenance for High-speed Fleet Maintenance accounts for approx. 30% of the life-cycle costs of a high-speed train, making it the largest rolling stock operating cost factor besides energy. Life-cycle Costs • Besides energy and depreciation, maintenance is the largest cost factor of a high speed train • Over the life-cycle of a high-speed train, maintenance costs exceed depreciation • Approx. 60% of maintenance costs are personnel cost and 40% for material / spare parts • For a fleet in service, maintenance cost is the major cost position subject to optimization as depreciation and energy stay constant during the fleet’s life-cycle source: Oliver Wyman Predictive maintenance, also known as Condition Based Maintenance (CBM) aims to reduce these unnecessary costs by basing the maintenance need on the actual condition of the machine rather than on preset schedules or assumptions. For example, a typical periodic maintenance strategy demands automobile operators to change the engine oil after every 3,000 to 5,000 Miles traveled. No concern is given to the actual condition of vehicle or performance capability of the oil. If on the other hand, the operator has some way of knowing the actual condition of the vehicle and the oil lubrication properties, he/she gains the potential to extend the vehicle usage and postpone oil change until the vehicle has traveled 10,000 Miles, or perhaps pre-pone the oil change in case of any abnormality. Advancements in the Big data technologies and predictive analytics with M2M telematics are enabling deep insights into the machine operations by providing full functionality status in real time - giving rise to optimal maintenance schedules, improved machine availability and asset usage. Customer reports have indicated the following industrial average savings resulted from the initiation of a fully functional predictive maintenance program: • Reduction in maintenance costs: 25% to 30% • Elimination of breakdowns: 70% to 75% • Spare parts inventories reduced: 20% to 30% • Reduction in equipment downtime: 35% to 45% • Overtime expenses reduced: 20% to 50% • Asset life increased: 20% to 40% • Increase in production: 20% to 25% 1
- 4. CBM Benefits Improved worker and environment safety, increased component availability, better asset usage etc. are few compelling reasons why more and more manufacturers and operators are embracing CBM based fleet management. • Benefits for workers: – Work-life balance with predictable schedules – Turn-key solutions with zero paper work – Increased on-road safety – Navigation helpers and landmark guides • Benefits for Management: – Reduced maintenance costs with Predictive Maintenance – Increased asset usage with zero unplanned downtime – Reduced operational costs and eliminated idle times with smart scheduling – Improved customer loyalty with always on-time deliveries – Theft and misuse prevention with real-time asset tracking M2M approach to the CBM Solution A Condition-based Maintenance Management (CBMM) solution is enabled by three major technology enhancements over the traditional maintenance approach: 1. Remote Sensor Monitoring & Data Capturing 2. Real-time Stream Processing of Sensor Data 3. Predictive Analytics CBMM systems essentially operate by having sensors attached to remote assets (mobile or stationary) that send continuous streams of data about the assets’ operational conditions to a monitoring station that then analyzes them in realtime using predictive analytic models and detects any problems in the behavior or state of the asset. Once a problem is detected, appropriate pre-configured action is taken to notify the operator or manufacture for corrective action. The monitoring station in question can be on the same network as that of the sensors or it could be in a remote location far away from them, connected through wide area networks or satellite networks. Devices such as On-Train Monitoring Recorder(OTMR) for trains and Flight Data Recorder for flights record events in real-time from their corresponding vehicles. These event data, along with any additional sensor data attached to the vehicle, will be collected into a centralized processing system and processed in real-time to detect any current anomalies and predict any future failures.
- 5. CBM Functions CBM philosophy is: Detect failures in their early stages and prevent them from happening. In addition it facilitates one to, • Estimate the Failure Rate for assets • Find the Remaining Useful Life of assets • Schedule Predictive Maintenance • Maintain right levels of Inventory for spare parts • Schedule right skilled and sized workforce • Optimize Inspection routines • Evaluate What If alternate scenarios • Decide right Warranty period at design time • Compare different designs for reliability evaluation Nature of data collected and analyzed from vehicle sensors is as follows: • On-board Diagnostics (OBD) data: Vehicle speed, RPM, fuel level etc. • GPS data: Locations, routing, length of time vehicle is at certain location etc. • Driving Patterns: Acceleration patterns, braking patterns etc. • OTMR data: Door close status, Air suspension pressure, Brake dragging, HVAC failure etc. A major challenge in implementing a CBM system for high-speed fleet is: processing the enormous data streamed-in from sensors attached to the high-speed vehicle in real-time. This requires: • Parallel architectures capable of handling large volumes of real-time data, • Low payload data-structures that optimize sensor data bandwidth requirements, • Fault-tolerance capabilities that can deal with packet drops and fragile networks, • Adaptable ontologies capable of supporting varied data types and protocols in parallel, • Proof based security to ensure data privacy and anonymity. The latest advancements in the Big-data open-source family of technologies offer viable solutions for the above requirements. A full featured CBMM system requires integration and customization of multiple open-source frameworks as listed below. • Remote sensor monitoring & data capturing: OpenXc • Real-time stream processing: Storm, Kestrel, ZMQ, MQTT • Predictive analytics: R • Real-time anomaly detection: Esper CEP • Distributed fault-tolerant storage: Hadoop, HBase • Failure report dashboards: HTML 5 • Control center visualization: OpenGl, Vtk, Qt, HMI The value add in customizing and integrating these frameworks lies in achieving the required level of parallelism for the large volume data with adaptable ontologies all the while reducing the sensor data bandwidth. In their native form, individually, these open-source frameworks will not be able to achieve the afore-mentioned objectives in a manner suitable for enterprise customers.
- 6. References 1. Gopalakrishna Palem. M2M Telematics & Predictive Analytics. M2M White Paper, Available at: Research Gate, 2013. 2. Gopalakrishna Palem, Condition-Based Maintenance using Sensor Arrays and Telematics, International Journal of Mobile Network Communications & Telematics, 3(3):19-28, DOI: 10.5121/ijmnct.2013.3303. 3. Gopalakrishna Palem, Predictive Maintenance Demo Video, Available at: You tube, 2013. About Author Gopalakrishna Palem is a Technology Management & Strategy consultant specialized in Big data Predictive Analytics and M2M Telematics. During his 12+ year tenure at Microsoft and Oracle, he helped many customers build their high volume transactional systems, distributed render pipelines, advanced visualization & modeling tools, real-time dataflow dependency-graph architectures, and Single-sign-on implementations for M2M telematics. When he is not busy working, he is actively engaged in driving open-source efforts and guiding researchers on Algorithmic Information Theory, Systems Control and Automata, Poincare recurrences for finite-state machines, Knowledge modeling in data-dependent systems and Natural Language Processing. He can be reached at Gopalakrishna.Palem@Yahoo.com 4