Abstract: Planner insight analytics identifies orders and sizes customers can execute to achieve business and operational efficiency. Generating optimal trimming patterns for trimming raw rolls and/or sheets of a flat sheet stock/customer orders includes: (a) receiving customer orders, primary and secondary machine specifications, warehouse inventory, and trade constraints; and (b) generating solutions for (i) order quantity fulfillment, (ii) a primary cutting pattern for the primary machine, (iii) a secondary cutting pattern for the secondary machine, and (iv) inventory details, wherein the solutions are generated with consideration of the initial trade constraints; (c) executing a batch and generating suggestions; (d) generating modified solutions for the parameters in step (b) using revised trade constraints derived from the suggestions generated that override the initial trade constraints in (c); and (e) operating a cutting apparatus.

Abstract: Monitoring continuous repetitive web sheet defects to determine the causes of such defects by creating unique diagnostic patterns associated with selected components of a web-making machine and employing pattern recognition techniques to analyze and classify web-sheet dynamic and deterministic defect patterns, and identify their root causes. Corrective actions can be effected thereby enhancing machine run-time to minimize late deliveries and improves overall product quality. The technique which is integrated with quality control system can be applied to the manufacturer of paper, packaging, rubber sheets, plastic film, metal foil, and the like.

Abstract: A method for trim loss optimization for metal industries includes receiving a selection of one or more orders for metal trimming. The method also includes inputting the one or more orders and multiple machine parameters to a dimension conversion engine, the dimension conversion engine configured to determine a roll width and a roll length for optimally fulfilling each order using decomposition of a three dimensional problem into a two dimensional problem based on spatial decomposition. The method also includes identifying at least one metal forming or conversion machine for processing the one or more orders. The method also includes inputting one or more metal tolerances as edge trim parameters to a trim algorithm. The method also includes determining, using the trim algorithm, a number of parent rolls for fulfilling the one or more orders using the at least one metal forming or conversion machine.

Abstract: Integration of clothing performance into production planning, scheduling and execution of papermaking machines yields paper products with consistent acceptable quality with minimum downtime and inventory. Linking the selection and operation of papermaking machines to their respective clothing performances improves clothing life cycle. Selected operating parameters of a papermaking machine and historical clothing data are indicative of the machine's clothing condition. Order scheduling engine identifies manufacturing times for particular grades of product and generates order blocks. Papermaking machines are assigned to execute specific order blocks with provision that each machine completes execution of the assigned orders without any anticipated breakage of the wire or felts.

Abstract: Monitoring continuous repetitive web sheet defects to determine the causes of such defects by creating unique diagnostic patterns associated with selected components of a web-making machine and employing pattern recognition techniques to analyze and classify web-sheet dynamic and deterministic defect patterns, and identify their root causes. Corrective actions can be effected thereby enhancing machine run-time to minimize late deliveries and improves overall product quality. The technique which is integrated with quality control system can be applied to the manufacturer of paper, packaging, rubber sheets, plastic film, metal foil, and the like.

Abstract: Integration of clothing performance into production planning, scheduling and execution of papermaking machines yields paper products with consistent acceptable quality with minimum downtime and inventory. Linking the selection and operation of papermaking machines to their respective clothing performances improves clothing life cycle. Selected operating parameters of a papermaking machine and historical clothing data are indicative of the machine's clothing condition. Order scheduling engine identifies manufacturing times for particular grades of product and generates order blocks. Papermaking machines are assigned to execute specific order blocks with provision that each machine completes execution of the assigned orders without any anticipated breakage of the wire or felts.

Abstract: A advanced planning and scheduling (APS) application for processing business objectives in a process industry. A method of the APS uses a business priority provided by a user for each the business objectives, ranks the business priority for each of the business objectives from a top priority to a lowest priority, and identifies a set of desired solutions for the top priority business objective. The method selects solutions in the set of desired solutions whose percentage change in honoring a second highest priority business objective is more than a percentage change in the top priority business objective. The method iterates through the solutions in the set of desired solutions for each of the remaining business objectives to realize an output solution such that the business objectives are optimized through successive linear programming.

Abstract: Optimal charting patterns for charting of raw rolls/sheets from flat sheet industry are produced with a processing system and includes the steps of: (a) receiving user selected business objectives; (b) receiving user selected business preferences; (c) setting targets for user selected business preferences; (d) establishing charting constraint sets; (e) generating charting patterns based on user selected business objectives and targets for user selected business preferences; and (f) selecting charting patterns based on targets for user selected business preference using an objective function, wherein the objective function includes terms related to the user selected business objectives. Target driven charting assists users in knowing the bounds (upper and/or lower) of the values for various business objectives for an individual charting run.

Abstract: Optimal charting patterns for charting of raw rolls/sheets from flat sheet industry are produced with a processing system and includes the steps of: (a) receiving user selected business objectives; (b) receiving user selected business preferences; (c) setting targets for user selected business preferences; (d) establishing charting constraint sets; (e) generating charting patterns based on user selected business objectives and targets for user selected business preferences; and (f) selecting charting patterns based on targets for user selected business preference using an objective function, wherein the objective function includes terms related to the user selected business objectives. Target driven charting assists users in knowing the bounds (upper and/or lower) of the values for various business objectives for an individual charting run.

Abstract: A product recovery prediction model that models recovery of a product from a crop is generated by inputting training product recovery data by date, age, and variety. A first model that models season dependent effects on product recovery, and/or a second model that models age dependent effects on product recovery, and/or a third model that models other effects such as, for example, weather dependent effects on product recovery are generated. The first, second, and/or third models are combined, and the product recovery prediction model is generated based on the combined first, second, and/or third models and on the training product recovery data. The crop may be sugarcane, and the product may be sugar. The product recovery prediction model may be used to predict recovery of the product to use for harvesting or any economical decisions.

Abstract: Raw rolls and/or sheets of flat sheet stock are charted by a processing system that generates charting patterns using constraint logic programming, that matches the charting patterns and available raw rolls and/or sheets of flat sheet stock, and that selects the optimal patterns from those matching charting patterns and available raw rolls and/or sheets using mixed integer linear programming.

Abstract: A harvesting and/or planting schedule is generated based on a product recovery model and a crop yield model. The product recovery model models recovery of a product, such as sugar, from a crop, such as sugarcane. The crop yield model models yield of the crop from land. First, second, third, and fourth data are used to generate the harvesting and/or planting schedule. The first input data is pertinent to predicting the recovery of the product by use of the product recovery model. The second input data is pertinent to predicting the yield of the crop by use of the crop yield model. The third input data relates to capacity of a crop processing plant to process the crop to produce the product. The fourth input data relates to harvesting and/or planting practices for the crop.

Abstract: A combination of yield prediction models is usable to predict the yield of a crop, such as sugarcane, from land. The model combination includes at least first and/or second models. The first model may be a structured or unstructured model that models season dependent effects on yield. If structured, the first model may be a linear, non-linear, or polynomial representation. The second model may be a structured or unstructured model that models age dependent effects on yield. If structured, the second model may be a linear, non-linear, or polynomial representation. Additional models that model weather and/or soil dependent effects on yield may also be used in the model combination.

Abstract: Periodic communication of data packets between modules in time frames having a plurality of frame rates including a base frame rate through a bus is schedule by determining a first load schedule for data packets of base frame and half base frame rates using constraint logic programming techniques, by determining a second load schedule for data packets of other frame rates using mixed integer linear programming techniques, and by scheduling produce and consume loads for each of the modules based on the first and second load schedules.

Abstract: Cutting and skiving patterns to be used in the production of product rolls from a master roll are selected so as to optimize trim efficiency. The product rolls have widths ordered by customers. In selecting these cutting and skiving patterns, cutting patterns that can be used to trim master rolls of the same or different dimensions in order to fill customer orders for the product rolls are generated, skiving patterns for skiving auxiliary rolls that result from trimming the master roll in order to produce the product rolls according to the customer orders are generated, and those of the generated skiving and cutting patterns that optimize trim efficiency for the production of the product rolls are selected.

Abstract: A product recovery prediction model that models recovery of a product from a crop is generated by inputting training product recovery data by date, age, and variety. A first model that models season dependent effects on product recovery, and/or a second model that models age dependent effects on product recovery, and/or a third model that models other effects such as, for example, weather dependent effects on product recovery are generated. The first, second, and/or third models are combined, and the product recovery prediction model is generated based on the combined first, second, and/or third models and on the training product recovery data. The crop may be sugarcane, and the product may be sugar. The product recovery prediction model may be used to predict recovery of the product to use for harvesting or any economical decisions.

Abstract: Cutting and skiving patterns to be used in the production of product rolls from a master roll are selected so as to optimize trim efficiency. The product rolls have widths ordered by customers. In selecting these cutting and skiving patterns, cutting patterns that can be used to trim master rolls of the same or different dimensions in order to fill customer orders for the product rolls are generated, skiving patterns for skiving auxiliary rolls that result from trimming the master roll in order to produce the product rolls according to the customer orders are generated, and those of the generated skiving and cutting patterns that optimize trim efficiency for the production of the product rolls are selected.

Abstract: Raw rolls and/or sheets of flat sheet stock are charted by a processing system that generates charting patterns using constraint logic programming, that matches the charting patterns and available raw rolls and/or sheets of flat sheet stock, and that selects the optimal patterns from those matching charting patterns and available raw rolls and/or sheets using mixed integer linear programming.

Abstract: An intelligent information-mining system extracts desired intelligent information from unstructured text data in documents to categorize the unstructured text data based on the extracted desired intelligent information. This is accomplished by obtaining unstructured text data from documents in an electronic format. The obtained unstructured text data is then transformed into unstructured neutral format data. The transformed unstructured neutral format data is then converted into structured data based on desired intelligent information. Desired intelligent information is then extracted from the structured data by using a multilayer self-organizing maps (MSOM) algorithm.

Abstract: A pattern solution set for paper roll trimming to fulfill orders is generated using constraint programming and a heuristic. For every pattern generated, an objective function is evaluated based on the sum of waste factor and the variance of the quantity ordered for all widths in that pattern. The pattern that has the least objective function is chosen with the maximum number of sets possible. Orders are updated with the quantities left over and then the process continues, forming a solution tree, which serves as an initial solution set. The initial solution set is checked individually against the average loss of the solution set. Nodes in the solution tree having trim loss greater than the average loss are identified. Branches of the tree emanating from its parent are explored for better patterns. The process continues until all patterns are below the initial average loss.