System Integrator
Algorithmica Technologies - Machine Learning Assisted Applications
We are proud to partner with algorithmica technologies for machine learning applications for mechanical drive systems.
ADVANCED FAILURE PREDICTION
Rotating Equipment Life Extension
Unplanned outages in the industrial world are always undesirable, and can sometimes even be disastrous. They cause bottlenecks, significant labor overhead, more scrap production, and even loss of business opportunities. And unplanned downtimes are very expensive. According to recent statistics, plants in the oil and gas, chemical, and power industries routinely suffer 5 to 7% unplanned downtime losses due to poor maintenance practices. And in the automotive industry, it has been shown that one minute of unplanned downtime costs an avg. $22,000, or $1.3 million per hour.
Advanced Failure Predictor (AFP) by algorithmica technologies is a ground-breaking solution to this expensive problem. It uses historical data and advanced machine learning algorithms to understand the dynamics of your plant. At the same time it monitors the plant it in real time, and projects current trends into the future. AFP can forecast and alert you to problems days in advance.
Case studies
Prediction of Turbine Failure
Dr. Patrick Bangert, algorithmica technologies GmbH
In this study we will demonstrate that it is possible to predict a known turbine failure using historical data...
Failures of Wind Power Plants
Dr. Patrick Bangert, algorithmica technologies GmbH
It is possible to model dynamic evolving mechanisms of aging in a mathematical form so that a reliable prediction of a future failure can be computed...
Predicting the Dynamometer Card of a Rod Pump
Prof. Chaodong Tan (China University of Petroleum), Guisheng Li (Plant No. 5 of Petrochina Dagang Oilfield Company), Yingjun Qu (Plant No. 6 of Petrochina Changqing Oilfield Company), Xuefeng Yan, (Beijing Yadan Petroleum Technology Co., Ltd.), Dr. Patrick Bangert (algorithmica technologies GmbH)
In conclusion, we note that a recurrent neural network can reliably predict a future fault of a rod pump system via predicting the future model parameters of a mathematical formulation of the dynamometer card.
Optimizing Chemical Processes
Dr. Patrick Bangert, algorithmica technologies GmbH
Here, we compute the action required to achieve optimal yield at any time using machine learning.
Head Office
USA Office