Abstract: Provided are techniques for global context explainers for Artificial Intelligence systems using multivariate timeseries data. Predictions for multivariate timeseries data are received. Feature importance weights are generated from the predictions using a feature-based local explainer, where each of the feature importance weights is associated with a time period and a corresponding data source of timeseries data of the multivariate timeseries data. A dataset is generated using the feature importance weights, where the dataset includes, for each time period and the corresponding data source, a label indicating whether the feature importance weight is one of positive and negative. One or more global explanations are generated using the dataset and a directly interpretable rule-based explainer, where the one or more global explanations indicate how the predictions change at particular times in the multivariate timeseries data based on values from the corresponding data source.

Abstract: Methods, computer program products, and/or systems are provided that perform the following operations: obtaining asset data; determining an asset class associated with the asset data; initializing a new neural network model, wherein the new neural network model is initialized based on a pretrained model associated with the asset class; training the new neural network model based, at least in part, on the asset data to obtain a trained remaining useful life model; and deploying the trained remaining useful life model to generate prediction data for one or more assets as output of the trained remaining useful life model.

Abstract: Disclosed is a system for automatic sampling and detection of on-line gas by high-temperature and high-pressure simulator and a detection method thereof. A vacuum manifold I is successively connected to a pressure controller, a gas-liquid separator, a gas automatic metering collector, a first trace quantitative gas collector, and a mechanical pump. On a vacuum manifold II, a high-low pressure convertor, a second trace quantitative gas collector, a gas transferring device, a heavy oil trap, a filtering trap, and a pressure gage head are connected successively. In the present invention, discharged simulation products, enter an empty gas chromatograph at a normal temperature and a normal pressure after treatment, completing on-line detection of an accumulated gas and a stage gas, and improving accuracy of gas composition measurement.

Abstract: Disclosed is a simulation device for interaction between deep reservoir rock and fluid in a basin and a use method thereof. The simulation device for interaction between deep reservoir rock and fluid in basin includes an automatic control unit, a heating unit, a pressurizing unit, an analysis metering unit, and a peripheral auxiliary unit. An output end of the automatic control unit is electrically connected to input ends of the heating unit, the pressurizing unit, and the peripheral auxiliary unit in a one-way direction, respectively. An output end of the analysis metering unit is electrically connected to an input end of the automatic control unit in a one-way direction. Combining the automatic control unit, the heating unit, the pressurizing unit, the analysis metering unit, and the peripheral auxiliary unit, the present disclosure solves problems of unreasonable evaluation on the interaction between the deep reservoir rock and fluid in a basin.

Abstract: Disclosed is a simulation device for interaction between deep reservoir rock and fluid in a basin and a use method thereof. The simulation device for interaction between deep reservoir rock and fluid in basin includes an automatic control unit, a heating unit, a pressurizing unit, an analysis metering unit, and a peripheral auxiliary unit. An output end of the automatic control unit is electrically connected to input ends of the heating unit, the pressurizing unit, and the peripheral auxiliary unit in a one-way direction, respectively. An output end of the analysis metering unit is electrically connected to an input end of the automatic control unit in a one-way direction. Combining the automatic control unit, the heating unit, the pressurizing unit, the analysis metering unit, and the peripheral auxiliary unit, the present disclosure solves problems of unreasonable evaluation on the interaction between the deep reservoir rock and fluid in a basin.

Abstract: Disclosed is a system for automatic sampling and detection of on-line gas by high-temperature and high-pressure simulator and a detection method thereof. A vacuum manifold I is successively connected to a pressure controller, a gas-liquid separator, a gas automatic metering collector, a first trace quantitative gas collector, and a mechanical pump. On a vacuum manifold II, a high-low pressure convertor, a second trace quantitative gas collector, a gas transferring device, a heavy oil trap, a filtering trap, and a pressure gage head are connected successively. In the present invention, discharged simulation products, enter an empty gas chromatograph at a normal temperature and a normal pressure after treatment, completing on-line detection of an accumulated gas and a stage gas, and improving accuracy of gas composition measurement.