Estimating Remaining Useful Life (RUL) from multi-sensor time series data is difficult through manual inspection. Current machine learning and data analytics methods, for RUL estimation require large number of failed instances for training, which are rarely available in practice, and these methods cannot use information from currently operational censored instances since their failure time is unknown. Embodiments of the present disclosure provide systems and methods for estimating RUL using time series data by implementing an LSTM-RNN based ordinal regression technique, wherein during training RUL value of failed instance(s) is encoded into a vector which is given as a target to the model. Unlike a failed instance, the exact RUL for a censored instance is unknown. For using the censored instances, target vectors are generated and the objective function is modified for training wherein the trained LSTM-RNN based ordinal regression is applied on an input test time series for RUL estimation.

The present invention provides a system and method for analyzing sensor data related to an irrigation system. According to a preferred embodiment, the system includes algorithms for analyzing real-time, near real-time and historical data acquired from sensors in communication with a mechanized irrigation machine. Further, the algorithms of the present invention system may analyze collected sensor data to determine if an event has occurred or is predicted to occur. Further, the algorithms of the present invention may provide commands to an irrigation machine and notifications to users. According to further aspects of the present invention, the algorithms of the present invention may preferably apply machine learning and other data analysis tools to detect maintenance patterns, geographic trends, environmental trends, and to provide predictive analysis for future events.

Systems and methods described herein can involve management of a system having a plurality of sensors, the plurality of sensors observing a plurality of process steps, which can involve selecting a subset of the plurality of sensors for observation; executing anomaly detection from data provided from the subset of the plurality of sensors; for a detection of an anomaly from a sensor from the subset of sensors, selecting ones of the plurality of process steps based on the detected anomaly; estimating a probability of anomaly occurrence for the selected ones of the plurality of process steps; and for the estimated probability of anomaly occurrence meeting a predetermined criteria, selecting ones of the plurality of sensors associated with the selected ones of the plurality of process steps for observation.

Method, apparatus and computer program product for detecting vulnerability and predicting maintenance in an industrial control system are described herein.

An integrated vehicle health management (IVHM) system to resolve equipment-fault related anomalies detected by cyber intrusion detection system (IDS). A benefit of the present system is that it can result in fewer alerts that need manual analysis. A combination of cyber and monitoring with integrated vehicle health management (IVHM) may be a high value differentiator. As a solution gets more mature through a learning loop, it may be customized for different customers in a cost-effective manner, something that might be expensive to develop on their own for most original equipment manufacturers (OEMs). An IVHM symptom pattern recognition matrix may link a pattern of reported symptoms to known equipment failures. This matrix may be initialized from the vehicle design data but its entries may get updated by a learning loop that improves a correlation by incorporating results of investigations.

A method for learning and detecting an abnormal part of a device through artificial intelligence comprises: an information collection step for collecting a current waveform of a current value that changes over time in a driving state of at least one device and collecting information about a faulty part of the device, together with current waveform information before a fault occurs in the device; a model setting step for learning, by a control unit, information collected in the information collection step and setting a reference model of a current waveform for each faulty part of the device; and a detection step for, when an abnormal symptom of the device is detected in a real-time driving state, comparing, by the control unit, a real-time current waveform of the device and the reference model, and detecting and providing an abnormal part regarding the abnormal symptom of the device.

The present disclosure relates to systems and methods for determining abnormal information associated with a vehicle. The systems may perform the methods to obtain real-time information associated with a bicycle and obtain reference information associated with the bicycle. The systems may also perform the methods to determine, based on the real-time information and the reference information, abnormal information associated with the bicycle, and transmit the abnormal information associated with the bicycle.

By accurately predicting industrial aging processes (IAP), such as the slow deactivation of a catalyst in a chemical plant, it is possible to schedule maintenance events further in advance, thereby ensuring a cost-efficient and reliable operation of the plant. So far, these degradation processes were usually described by mechanistic models or simple empirical prediction models. In order to accurately predict IAP, data-driven models are proposed, comparing some traditional stateless models (linear and kernel ridge regression, as well as feed-forward neural networks) to more complex stateful recurrent neural networks (echo state networks and long short-term memory networks). Additionally, variations of the stateful models are discussed. In particular, stateful models using mechanistical pre-knowledge about the degradation dynamics (hybrid models). Stateful models and their variations may be more suitable for generating near perfect predictions when they are trained on a large enough dataset, while hybrid models may be more suitable for generalizing better given smaller datasets with changing conditions.

A machine-learning-based prognostic and health management system comprises a machine sensor, an instruction receiver, a processor, and an annunciator. The machine sensor is configured to dynamically receive data of a machine under test associated with operations of the machine under test. The instruction receiver is configured to dynamically receive a model-assigning command. The processor is configured to dynamically apply a damage alert machine-learning model corresponding to the model-assigning command for processing the data of the machine under test to predict an anomaly probability of an anomaly occurrence of the machine under test. The processor also dynamically generates, according to the anomaly probability, a damage possibility warning on the machine under test, and determine whether to keep the machine under test running or not.

The invention relates to the field of operating, monitoring and controlling mills of the mining industry. It specifically relates to a system and a method for in-line determination of the characteristics of worn balls and pieces thereof, which have been ejected from a semi-autogenous mineral grinding (SAG) mill to the external classifiers.