Abstract: A system that provides an improved approach for detecting and predicting failures in a plant or equipment process. The approach may facilitate failure-model building and deployment from historical plant data of a formidable number of measurements. The system implements methods that generate a dataset containing recorded measurements for variables of the process. The methods reduce the dataset by cleansing bad quality data segments and measurements for uninformative process variables from the dataset. The methods then enrich the dataset by applying nonlinear transforms, engineering calculations and statistical measurements. The methods identify highly correlated input by performing a cross-correlation analysis on the cleansed and enriched dataset, and reduce the dataset by removing less-contributing input using a two-step feature selection procedure. The methods use the reduced dataset to build and train a failure model, which is deployed online to detect and predict failures in real-time plant operations.

Abstract: A computer system provides improved classification of operating and scheduling plan data of a process plant. The system finds patterns in cases of the plan data and, based on the patterns, organizes the cases into a hierarchical structure of clusters representing distinct conditions. The system receives a dataset of cases of operating plan data represented by process variables. The system reduces a number of process variables representing operating plan data in the dataset by generating principal component(s) from values of the process variables for each case. The principal component(s) are latent variables generated to capture variation in conditions across the cases. For each case, the system determines a value for each generated principal component in the dataset. Using automated clustering or machine learning techniques, the system iteratively clusters the cases into a hierarchical structure based on the respective determined value of each generated principal component.

Abstract: Computer-implemented methods of characterizing chemical composition of a sample containing crude oil or a petroleum fraction are presented. The methods can include, in a processor, receiving assay data of the sample, and particularly molecular-level data obtained using advanced analytical techniques, and processing this data in view of a model library of compounds, including reconciling compound compositions, to form a characterization of the chemical composition of the sample.

Abstract: Computer-implemented methods and systems construct a calibrated operation-centric first-principles model suitable for online deployment to monitor, predict, and control real-time plant operations. The methods and systems identify a plant-wide first-principles model configured for offline use and select a modeled operating unit contained in the plant-wide model. The methods and systems convert the plant-wide model to an operation-centric first-principles model of the selected modeled operating unit. The methods and systems recalibrate the operation-centric model to function using real-time measurements collected by physical instruments of the operating unit at the plant. The recalibration may include reconciling flow and temperature, estimating feed compositions, and tuning liquid and vapor traffic flow in the model. The methods and systems deploy the operation-centric model to calculate KPIs (Key Performance Indicators) using real-time measurements.

Abstract: Embodiments are directed to computer methods and systems that build and deploy a pattern model to detect an operating event in an online plant process. To build the pattern model, the methods and systems define a signature of the operating event, such that the defined signature contains a time series pattern for a KPI associated with the operating event. The methods and systems deploy the pattern model to automatically monitor, during online execution of the plant process, trends in movement of the KPI as a time series. The methods and systems determine, in real-time, a distance score between a range of the monitored time series and the time series pattern contained in the defined signature. The methods and systems automatically detect the operating event in the online industrial process based on the determined distance score, and alter parameters of the process (e.g., valves, actuators, etc.) to prevent the operating event.

Abstract: A computer system and method optimize feedstock selection planning for an industrial process by evaluating first and second stages at separate intervals throughout the planning process. Evaluating the first stage determines a set of robust feedstocks to procure on long-term contracts. The computer system and method solve, in parallel, multiple simulation cases of a non-linear model generated with different expectation values for uncertain input parameters related to selecting feedstocks to procure on long-term contracts. Probabilistic analyses on the solutions from the simulation cases, including the application of chance-constraints, determine the set of robust feedstocks to procure on long-term contracts. Evaluating the second stage determines a set of robust feedstocks to procure in the spot market, using the information from the first stage.

Abstract: Computer-based methods and system perform root-cause analysis on an industrial process. A processor executes a hybrid first-principles and inferential model to generate KPIs for the industrial process using uploaded process data as variables. The processor selects a subset of the KPIs to represent an event occurring in the industrial process, and divides the selected data into time series. The system and methods select time intervals from the time series based on data variability and perform a cross-correlation between the loaded process variables and the selected time intervals, resulting in a cross-correlation score for each loaded process variable. Precursor candidates from the loaded process variables are selected based on the cross-correlation scores, and a strength of correlation score is obtained for each precursor candidate. The methods and system select root-cause variables from the selected precursor candidates based on the strength of correlation scores, and analyze the root-cause of the event.

Abstract: Embodiments are directed to systems that build and deploy inferential models for generating predictions of a plant process. The systems select input variables and an output variable for the plant process. The systems load continuous measurements for the selected input variables. For the selected output variable, the systems load measurements of type: continuous from the subject plant process, intermittent from an online analyzer, or intermittent from lab data. If continuous or analyzer measurements are loaded, the systems build a FIR model with a subspace ID technique using continuous output measurements. From intermittent analyzer measurements, the systems generate continuous output measurements using interpolation. If lab data is loaded, the systems build a hybrid FIR model with subspace ID and PLS techniques, using continuous measurements of a reference variable correlated to the selected output variable.

Abstract: A computer-implemented method of characterizing metal content and chemical composition of crude oil, including determining at least one respective organometallic class and subclass derived from physical and chemical property data for each organometallic class and crude oil physical and chemical property data and at least one segment type and segment number range of the segment type bound to each organometallic subclass. The method determines a relative ratio of each organometallic class and subclass that forms a chemical composition representative of the given crude oil, such that the determined relative ratio and the determined respective organometallic class and subclass, segment type, and segment number range form a characterization of the metal content and the chemical composition of the given crude oil, resulting in a display, as output to an end-user, of the formed characterization of the metal content and the chemical composition of the given crude oil.

Abstract: A method, apparatus, and computer program product for increasing efficiency in a plant by creating a planning model for said plant comprising a plurality of runtime models stored in a database. Each runtime model corresponds to a reactor in the plant and mimics real world behavior of the reactor by identifying the mathematical relationships of the inputs and outputs of the reactor. Each runtime model further comprises a set of tuning factors, which allows the user to adjust the runtime model to more closely align with the user's desired output or otherwise account for real-life plant activity. By properly creating and utilizing a plurality of runtime models and implementing them into a planning model, a user can increase efficiency of the plant by optimizing product output, forcing the plant to balance materials-in and materials-out, or forcing the plant to stoichiometrically balance elements going in, and coming out of the plant or reactor.

Abstract: Process engineering software applications have respective proprietary in nature and disconnected model representations of a manufacturing or processing facility. The invention method and apparatus extract from the various applications topology of equipment and streams for a facility. From the extracted data, a convertor or adapter of the invention system derives a common canonical model. To support the common canonical model (e.g., a Flowsheet object in embodiments), the converter/adapter maps or associates one or more physical assets to a logical asset, and arranges a working hierarchy of assets that can be navigated, queried and filtered.

Abstract: Computer system and methods for optimally controlling the behavior of an industrial process, in accordance with plant operating goals, without requiring a complicated trial and error process. The system and methods enable configuring optimization preference and optimization priority for key manipulated variables (MVs) of the industrial process. The system and methods translate the configured optimization preference and optimization priority for each key MV into prioritized economic objective functions. The system and methods calculate a set of normalized cost factors for use in a given prioritized economic functions based on a model gain matrix of manipulated variables and controlled variables of the industrial process.

Abstract: Computer-based methods and system perform root-cause analysis on an industrial process. A processor executes a hybrid first-principles and inferential model to generate KPIs for the industrial process using uploaded process data as variables. The processor selects a subset of the KPIs to represent an event occurring in the industrial process, and divides the selected data into time series. The system and methods select time intervals from the time series based on data variability and perform a cross-correlation between the loaded process variables and the selected time intervals, resulting in a cross-correlation score for each loaded process variable. Precursor candidates from the loaded process variables are selected based on the cross-correlation scores, and a strength of correlation score is obtained for each precursor candidate. The methods and system select root-cause variables from the selected precursor candidates based on the strength of correlation scores, and analyze the root-cause of the event.

Abstract: A computer modeling apparatus and method optimize refinery operations. Included are an input module enabling user specification of inventory information including at least one rundown component, and user specification of refinery product commitments, and a processor routine executable by a computer and coupled to the input module. The processor routine, in response to the user specification, sequences refinery operations into a schedule that matches refinery commitments with inventory and unit rundown operations, wherein the refinery operations include refinery operations events, and provides on output a display of the schedule in a manner enabling optimized refinery operations.

Abstract: A computer method of characterizing chemical composition of crude oil and crude oil blends, includes determining respective segment type and segment number range of selected classes of hydrocarbon constituent molecules based on physical and chemical property data on each class of hydrocarbon constituent molecules and on crude oil physical and chemical property data. The method determines relative ratio of each class of hydrocarbon constituent molecules that forms a chemical composition representative of the subject crude oil, and therefrom characterizes chemical composition of the subject crude oil. The method/system displays to an end-user, the characterized chemical composition of the subject crude oil. Based on the identified distribution functions and the relative ratio of each class of hydrocarbon constituent molecules, the method estimates chemical composition of the crude oil. Estimates of physical and chemical properties of the crude oil are then based on the estimated chemical composition.

Abstract: A resource manager service, system, apparatus and method manages resources for a user group of at least one user by utilizing a resource adapter. The resource adapter serves as a smart proxy to mimic the user of a desktop software application preserving the interaction model with the application. Embodiments of the invention allow integration of desktop software in a distributed enterprise system, as a service, without requiring non-trivial modifications to the application code or to alter its workflows in any material way. A resource manager service, system, apparatus and method treat instances of the resource adapters, smart proxies, as finite but reusable resources that can be allocated and “bound” to a given user for an unspecified duration.

Abstract: A system and method of model predictive control executes a model predictive control (MPC) controller of a subject dynamic process (e.g., processing plant) in a configuration mode, identification mode and model adaptation mode. Users input and specify model structure information in the configuration mode, including constraints. Using the specified model structure information in the identification mode, the MPC controller generates linear dynamic models of the subject process. The generated linear dynamic models collectively form a working master model. In model adaptation mode, the MPC controller uses the specified model structure information in a manner that forces control actions based on the formed working master model to closely match real-world behavior of the subject dynamic process. The MPC controller coordinates execution in identification mode and in model adaptation mode to provide adaptive modeling and preserve structural information of the model during a model update.

Abstract: A method, apparatus, and computer program product for increasing closed-loop stability in a MPC controller controlling a process where there are significant uncertainties in the model used by the controller. This invention focuses on the improvement of the robustness of the steady-state target calculation. This is achieved through the use of a user defined robustness factor, which is then used to calculate an economic objective function giveaway tolerance and controlled variable constraint violation tolerance. The calculation engine uses these tolerances to find a solution that minimize the target changes between control cycles and prevent weak direction moves caused by near collinearity in the model. If the controller continues to exhibit large variations in the process, it can slow down the manipulated variable movement to stabilize the process.