Abstract: Aspects of the technology described herein comprise a surrogate model for a chemical production process. A surrogate model is a machine learned model that uses a collection of inputs and outputs from a simulation of the chemical production process and/or actual production data as training data. Once trained, the surrogate model can estimate an output of a chemical production process given an input to the process. Surrogate models are not directly constrained by physical conditions in a plant. This can cause them to suggest optimized outputs that the not possible to produce in the real world. It is a significant challenge to train a surrogate model to only produce outputs that are possible. The technology described herein improves upon previous surrogate models by constraining the output of the surrogate model to outputs that are possible in the real world.

Abstract: Aspects of the technology described herein comprise a raw material valuation system that is able to quantify an outcome of various raw material management decisions. Raw material management decisions can include, but are not limited to, purchasing a raw material, selling a raw material, transferring a raw material within a chemical production system, and substituting a proposed purchase of a first raw material with the purchase of a second material. The raw material valuation system can quantify a contemplated changes to a raw material management plan by comparing an optimal reference usage plan to an optimal updated usage plan. The raw material valuation system can calculate a breakeven sale price for a raw material in inventory or a breakeven purchase price for a raw material to be purchased. The raw material valuation system used to generate the reference usage plan and the updated usage plan can use a multi-period optimization model.

Abstract: Aspects of the technology described herein comprise a surrogate model for a chemical production process. A surrogate model is a machine learned model that uses a collection of inputs and outputs from a simulation of the chemical production process and/or actual production data as training data. Once trained, the surrogate model can estimate an output of a chemical production process given an input to the process. Surrogate models are not directly constrained by physical conditions in a plant. This can cause them to suggest optimized outputs that the not possible to produce in the real world. It is a significant challenge to train a surrogate model to only produce outputs that are possible. The technology described herein improves upon previous surrogate models by constraining the output of the surrogate model to outputs that are possible in the real world.

Abstract: A raw material valuation tool to assist purchasing decisions in the operation of a facility. The decision support tool allows a user to apply a modeling and analysis framework for a raw material valuation process. This optimization model allows raw material purchasing decisions to be divided into scenarios ahead of time, thereby addressing operational and market uncertainties of events that occur between the initial planning/scheduling and the final arrival of the raw materials at the facility. Price and availability data of a set of raw materials are input into the optimization model, including probability of occurrence of such data. The model calculates an optimal raw material purchasing scenario, which extends up to a moment in time when the raw material is used at the facility. The flexibility of this optimization model increases revenue generated at the facility, decreases cost of the raw material and improves operational decisions.

Abstract: Methods and systems are provided for generating a development plan for a hydrocarbon asset. A high-fidelity computer model of a hydrocarbon asset is created. A low-fidelity computer model of the hydrocarbon asset is created. The low-fidelity computer model is iterated on to an interim solution. A comparison is generated of the interim solution to a solution obtained from a simulation of the high-fidelity computer model at the variables of the interim solution. The low-fidelity computer model is calibrated based, at least in part, on the comparison. The development plan for the hydrocarbon asset is generated based, at least in part, on a result from the calibrated low-fidelity computer model. The low-fidelity computer model is a mixed-integer nonlinear programming problem with complementarity.