Reduce rail disruptions through intelligent maintenance prioritization（通过智能维护优先级排序减少铁路中断）¶
Industry Sector: Transportation
Business Function: Maintenance & Reliability
A major freight railroad wanted to reduce a large number of service disruptions by reducing turnout failures.
With Foundry, the track maintenance team reduced disruptions through an integrated view of track components across all systems and by taking action in Foundry’s operational applications:
- Prioritized maintenance operations to high risk turnouts
- Designed capital plan based on needs instead of historical spend
- Improved maintenance crews’ trainings based on previous maintenance activities
Challenge¶
A major freight railroad was experiencing significant service disruptions caused by repeat failures of turnout components. However with 50k+ turnouts, they had difficulties tackling the problems over their entire network effectively.
Solution¶
- Integrated Ontology -- Foundry combines all information related to turnouts from engineering and transportations systems, as well as from IOT devices such as geometry and ballast quality measurements from telemetry-equipped railcars. The system provides full context for turnouts maintenance decisions and analysis of past failures.
- Turnout Risk Monitoring -- Foundry enables Track Engineering Analysts to build and manage heuristics-based risk models for turnouts failure in a point and click interface, leveraging metrics from the ontology.
- Integrated Capital Planning -- Foundry connects capital planning process with the unified view of turnouts to drive investments where it’s needed the most. Powerful scenario analysis helps the organization optimize between repairs and replacements given timelines and budget constraints.
- Data Quality Enhancement Process -- A programmatic feedback loop surfaces and fixes data quality issues from manual entry. Integration to the railroad’s ERP system enables the track maintenance crews to quickly submit corrections.
Users and stakeholders¶
- Track Engineering analysts
- Maintenance Crews
Impact¶
- Less than 6 months to implement data driven maintenance processes across all geographies.
- A significant percentage of failures took place at turnouts that were proactively flagged high risk.
- Those turnouts were triaged and those that were identified as high risk were prioritized for inspections, repairs, and replacements.
Implement a similar use case¶
This use case implements the following Patterns. Follow the links below to read more about a particular Pattern and learn how it is implemented within Foundry.
- Operational process coordination (used for 8 other use cases)
- Resource allocation & optimization (used for 3 other use cases)
Want more information on this use case? Looking to implement something similar? Get started with Palantir. ↗
中文翻译¶
通过智能维护优先级排序减少铁路中断¶
行业领域：交通运输
业务职能：维护与可靠性
某大型货运铁路公司希望通过减少道岔故障来降低大量服务中断事件。
借助 Foundry，轨道维护团队通过整合所有系统中的轨道组件视图，并在 Foundry 的操作型应用中采取行动，成功减少了中断事件：
- 将维护作业优先安排给高风险道岔
- 基于实际需求而非历史支出设计资本规划
- 根据过往维护活动改进维护团队的培训
挑战¶
某大型货运铁路公司因道岔组件反复故障而遭遇严重的服务中断。然而，面对超过 5 万个道岔，他们难以在整个网络范围内有效解决问题。
解决方案¶
- 集成本体（Ontology）——Foundry 整合了来自工程与运输系统，以及物联网设备（如配备遥测装置的轨道车所采集的轨道几何与道砟质量测量数据）中所有与道岔相关的信息。该系统为道岔维护决策和过往故障分析提供了完整的背景信息。
- 道岔风险监控——Foundry 使轨道工程分析师能够通过点击式界面，利用本体中的指标构建和管理基于启发式规则的道岔故障风险模型。
- 集成资本规划——Foundry 将资本规划流程与道岔的统一视图相连接，从而将投资引导至最需要的领域。强大的场景分析功能帮助组织在时间表和预算约束下，优化维修与更换之间的决策。
- 数据质量增强流程——通过程序化反馈循环，发现并修复手动录入带来的数据质量问题。与铁路公司 ERP 系统的集成使轨道维护团队能够快速提交修正。
用户与利益相关方¶
- 轨道工程分析师
- 维护团队
影响¶
- 在不到 6 个月的时间内，在所有地理区域实施了数据驱动的维护流程。
- 相当比例的故障发生在被主动标记为高风险的道岔上。
- 这些道岔经过分类处理，其中被识别为高风险的优先安排了检查、维修和更换。
实施类似用例¶
本用例实现了以下模式。点击下方链接可阅读特定模式的更多内容，并了解其在 Foundry 中的实现方式。
想了解更多关于此用例的信息？希望实施类似方案？立即联系 Palantir。↗