Refining and petrochemicals producers face increased pressure to maximize margins while improving safety and sustainability. In this on-demand webinar, learn how Pan American Energy implemented a predictive maintenance solution powered by artificial intelligence to predict critical equipment failures – giving time back to production and reducing operational risk.

​It’s time to stop equipment breakdowns: but where and how should you start?

Saras拥有地中海最复杂的炼油厂，每天的炼油产能为30万桶。作为数字化项目的一部分，他们正在评估如何提高资本和资产密集型炼油厂运营的可靠性。他们选择了AspenMtell，基于一个竞争性试点项目选择过程，最初的重点集中在关键炼油设备上，比如大型压缩机和水泵。 Aspen Mtell通过挖掘历史和实时操作以及维护数据来发现资产性能下降和故障发生之前的精确特征，预测未来故障并制定详细的行动以缓解或解决问题。

Because traditional diagnostic methods weren’t preventing equipment failures or identifying root causes of historic failures, a U.S. refinery turned to Aspen Mtell prescriptive maintenance to improve internal data science resources. Download this case study to learn how this refinery's pilot program with Aspen Mtell was able to predict failures with nearly one month of lead time, enabling planning for maintenance and rescheduling production.

Conozca cómo se utilizó la tecnología de mantenimiento predictivo de Aspen Mtell para saber con 27 días de anticipación sobre fallas de la válvula central de una planta de plásticos especializada.

Discover how predictive maintenance and planned downtime can deliver positive results for your company when it comes to Safety, Sustainability and Productivity.

Descubra cómo un fabricante de termoplásticos de ingeniería descubrió la causa raíz de fallas recurrentes en sus calderas de tubos y calderas utilizando el mantenimiento prescriptivo de Aspen Mtell.

In production environments, changing conditions means increased risk. Operating companies have been shouldering more of this risk in recent years as insurance coverage becomes less readily available.

Get key insights from a 2019 ARC Advisory Group survey on asset performance management (APM) and learn what is most important to industry leaders implementing APM at their organizations.

Lea cómo esta compañía minera utilizó Aspen Mtell para predecir dos posibles fallas cuando se implementó en 12 activos durante un breve piloto en línea. Permitiendo así, un tiempo de inactividad planificado de equipos críticos, ahorrando dinero por cortes inesperados.