Abstract: Systems and methods (300) for offline/online performance monitoring of batch processes (BPs) involving obtaining archived data (AD) obtained during runs of BP and including information defining a batch quality attribute for each run. The method also involves forming clusters by classifying AD for the runs into classes based on the batch quality attribute(s) and building a first multivariate statistical model (MSM) using AD. The method can further involve building a wavelet analysis based feature matrix (FM) using AD, forming a first projection (1200) by projecting FM onto a first MSM, building a second MSM (1300) using information obtained from the first projection, and computing centroids (C902, . . . , C918) and boundary profiles for the clusters (902, . . . , 918). The method can involve performing an online/offline performance monitoring (700/800) using an integrated version of the first and second MSM, a classification algorithm, centroids, and boundary profiles.

Abstract: A method (300, 400, 500, 1200) for offline/online monitoring of batch processes. The method involves (312) decomposing a time domain of a batch process run (BPR) into several blocks and (334) building multivariate statistical models (MSMs) for each of them using archived data for a batch process (ABPD). ABPD comprises stored data obtained during BPRs. The method also involves (506, 1204) retrieving recently stored data (RSD) for a recent fully performed BPR run (FPRNEW) or current BPR run. The method further involves (520, 1210) building a feature vector matrix (FVM) using RSD. FVM contains feature vectors representing statistical measures of wavelet coefficients determined for variables (v0, . . . , vJ). A projection (1100, 1150, 1190) is formed by projecting feature vectors onto at least one MSM or a combined multivariate statistical model (CMSM). CMSM is a weighted average of at least two MSMs.

Abstract: A process for optimizing a portfolio of products produced from a crop includes the use of an objective function to determine optimized quantities of the products in the portfolio. The objective function, for example, includes quantity terms for the products. The objective function may also include additional terms such as an energy term and/or a storage term. The energy term, for example, relates to an amount of energy required to produce the products. The storage term, for example, relates to the cost of storing products. The crop, for example, may be sugarcane, and the products, for example, may be sugar, molasses, bagasse, biofuel, electricity, and/or carbon credits.

Abstract: Systems and methods (300) for offline/online performance monitoring of batch processes (BPs) involving obtaining archived data (AD) obtained during runs of BP and including information defining a batch quality attribute for each run. The method also involves forming clusters by classifying AD for the runs into classes based on the batch quality attribute(s) and building a first multivariate statistical model (MSM) using AD. The method can further involve building a wavelet analysis based feature matrix (FM) using AD, forming a first projection (1200) by projecting FM onto a first MSM, building a second MSM (1300) using information obtained from the first projection, and computing centroids (C902, . . . , C918) and boundary profiles for the clusters (902, . . . , 918). The method can involve performing an online/offline performance monitoring (700/800) using an integrated version of the first and second MSM, a classification algorithm, centroids, and boundary profiles.

Abstract: A method (300, 400, 500, 1200) for offline/online monitoring of batch processes. The method involves (312) decomposing a time domain of a batch process run (BPR) into several blocks and (334) building multivariate statistical models (MSMs) for each of them using archived data for a batch process (ABPD). ABPD comprises stored data obtained during BPRs. The method also involves (506, 1204) retrieving recently stored data (RSD) for a recent fully performed BPR run (FPRNEW) or current BPR run. The method further involves (520, 1210) building a feature vector matrix (FVM) using RSD. FVM contains feature vectors representing statistical measures of wavelet coefficients determined for variables (v0, . . . , vJ). A projection (1100, 1150, 1190) is formed by projecting feature vectors onto at least one MSM or a combined multivariate statistical model (CMSM). CMSM is a weighted average of at least two MSMs.

Abstract: A process for optimizing a portfolio of products produced from a crop includes the use of an objective function to determine optimized quantities of the products in the portfolio. The objective function, for example, includes quantity terms for the products. The objective function may also include additional terms such as an energy term and/or a storage term. The energy term, for example, relates to an amount of energy required to produce the products. The storage term, for example, relates to the cost of storing products. The crop, for example, may be sugarcane, and the products, for example, may be sugar, molasses, bagasse, biofuel, electricity, and/or carbon credits.

Abstract: Real time performance of a combustion process is evaluated by comparing sensor data with a template. Sensor data is derived from a passive infrared system and corresponds to specific heat capacity. Analysis of the real time performance can be used to control a parameter of the combustion process.