International Business Machines Corporation

Noodle Analytics, Inc.

Ying Tat Leung

Matthew Denesuk

Axel Hochstein

Hyung-il Ahn

Menachem Levanoni

Gyana Ranjan Parija

Aliza Rivka Heching

Sanjay Elathur Ramaswamy

Raman Harishankar

Jorge L C Sanz

Edward H B Giesen

Samir Sharma

Ramesh Inaganti

Juhnyoung Lee

Jayant R Kalagnanam

Ahamed Jalaldeen

Kerrie Lamont Holley

Ashish Mungi

Ying Huang

Kumar Bhaskaran

Kishore Channabasavaiah

Siddharth N Purohit

Ignacio Gabriel Terrizzano

Shuvanker Ghosh

Andrew J Davenport

Graham P Bate

Muthulakshmi Bhandari

Allison Baines Botros

Jayashree Jaishankar

Samuel Antoun

Nitin R Nayak

Harshini Mogili

Joe Caruso

Dinah W Cheng

Philip G Rains

Thomas Franklin Guinan

Joseph David Kramer

Kelly Anne Lyman

Guillermo Gallego

Nayan Ketak Dharamshi

Rohan Jha

A system is presented for predicting the amount of energy required by a manufacturing plant over a period of time, and then providing a recommendation on the best amount of energy to sell at each period, taking into consideration the energy requirements based on the production schedule, the price of energy, possible penalties for over selling energy, and other factors. A user interface is provided to present relevant information to a user, allow the user to plan the use of energy, and determine the energy offering for sale in each period. Based on a known future production schedule of a steel mill, implementations provide a forecast of electrical energy usage per hour over the same time horizon as the production schedule. Based on the forecast and electricity selling and billing rules, a recommended amount of energy to be sold to the market by the hour is presented with the corresponding offer price.

Reducing the cost of electrical energy in a manufacturing plant

Methods, systems, and computer program products for generating estimates of failure risk for a vehicular component are provided herein. A method includes splitting an input time series pertaining to a vehicular component across a fleet of multiple vehicles into multiple sub-time series, wherein each sub-time series comprises multiple data points of the input time series that correspond to measurements derived from the vehicular component; determining a weight applied to each of the sub-time series based on a pre-determined weight associated with the input time series; applying a failure or non-failure classification label to each of the sub-time series and the input time series; calculating a performance measure for the input time series; determining an updated weight associated with the input time series; and generating an estimate of failure risk for the vehicular component based on the classification label applied to each input time series and the updated weight.

Generating estimates of failure risk for a vehicular component

Methods, systems, and computer program products for generating estimates of failure risk for a vehicular component in situations of high-dimensional and low sample size data are provided herein. A method includes splitting a first input time series comprising multiple data points derived from a vehicular component across a fleet of multiple vehicles into multiple sub-time series; generating a first failure status predicting function of a first selected sub-time series; deleting, from the first input time series, the portion of the data points that corresponds to the first selected sub-time series; repeating the preceding two steps for a second selected sub-time series; generating a second failure status predicting function of each selected sub-time series; applying each second failure status predicting function to a second input time series to calculate prediction of failure values; and identifying the largest prediction of failure value as an estimate of failure risk for the vehicular component.

Generating estimates of failure risk for a vehicular component in situations of high-dimensional and low sample size data

Methods, systems, and computer program products for generating wear-based indicators are provided herein. A method includes assigning a failure label to each data point associated with a component associated with a failure-caused component replacement within a pre-specified number of runtime hours of the failure-caused component replacement; assigning a non-failure label to each data point associated with a failure-caused component replacement and not within the pre-specified number of runtime hours; assigning a non-failure label to each data point associated with a scheduled component replacement; assigning a non-failure label to each data point associated with an actively running instance of the component as yet to be replaced; estimating a failure probability for the component over a pre-specified future runtime; determining a cumulative hazard function for the component based on the failure probability; and generating a cumulative wear-based indicator for the component by executing a regression function based on the cumulative hazard function.

Generating cumulative wear-based indicators for vehicular components

Methods, systems, and computer program products for generating a vehicular component replacement policy are provided herein. A method includes, for each of multiple lifetime wear indicator functions associated with a vehicular component, wherein each lifetime wear indicator function comprises a transformed time scale plotting wear indicator values over a period of time, determining multiple corresponding candidate threshold values on the transformed time scale; calculating: a survival probability function for the vehicular component based on each transformed time scale, an average runtime of the vehicular component prior to failure, and an average runtime of the vehicular component prior to a scheduled replacement; calculating an economic criterion value for each given threshold value based on the above calculations and one or more economic parameters; generating the replacement policy to include (i) the lifetime wear indicator function that optimizes the economic criterion value and (ii) the corresponding threshold value.

Integrating economic considerations to develop a component replacement policy based on a cumulative wear-based indicator for a vehicular component

Methods, systems, devices and computer program products for planning for failures of vehicular components are provided herein. A method includes obtaining a first set of data of maintenance events recorded for multiple vehicular components across multiple vehicles in a fleet; obtaining a second set of data of maintenance work orders performed on the vehicular components; obtaining a third set of data of measurements taken in connection with the vehicular components; analyzing (i) the first set of data and (ii) the second set of data to identify component failure events associated with the multiple vehicular components; determining failure indicators for each of the vehicular components in each of the vehicles in the fleet based on the second set of data, the third set of data, and the identified component failure events; and outputting the indicators in multiple visualized forms, each representing one of multiple levels of granularity.

Monitoring and planning for failures of vehicular components

Methods, systems, and computer program products for generating wear-based indicators for vehicular components are provided herein. A method includes assigning a failure class label to each data point, from multiple data points derived from measurements associated with a vehicular component across a fleet of vehicles, that is within a pre-specified number of runtime hours of a replacement; assigning a non-failure class label to each data point not within the pre-specified number of runtime hours of a replacement and each data point associated with a component yet to be replaced; estimating a failure probability at each data point over a pre-specified future runtime of the component based on the assigned class label; determining a cumulative hazard function for the vehicular component based on the failure probability; and generating a cumulative wear-based indicator for the vehicular component by executing a regression function at a given time based on the cumulative hazard function.

A system gathers real-time data about an enterprise over a network. A user device displays a dashboard showing a component business model map, a heat map, key performance indicators for components, key performance indicators for the enterprise, and gradients. The business is enhanced by making investments and changes to those operations having large gradients.

System for enhancing business performance

A business enterprise is assessed by a consultant using a computer implemented tool for practicing component business modeling techniques. The tool builds a map of components, filters the map to form a heat map and identifies collaborations. Key performance indicators are evaluated.

System for implementing business transformation in an enterprise

Equipment failures are diagnosed using an integrated approach of case-based reasoning (CBR) and statistical reliability analysis. The method outputs a single list of suggested failed components, ranked by an overall probability of failure, and their associated past solutions from the case base. The overall probability of failure is calculated using the combined logic of case based reasoning and statistical reliability analysis. The method is typically used in a real-time decision support system to aid equipment diagnosis by a maintenance technician working in the field.

Diagnosis of equipment failures using an integrated approach of case based reasoning and reliability analysis

A computer implemented system analysis and design method for use in a complex business environment characterized by a set of tightly linked business processes captures in a framework a world view of a business decision and/or a business application software system. A world view is defined by business objectives, constraints, assumptions, data, and underlying model used in business decision and/or the application software system. The framework is used to specify and document each business decision and/or business application software system in the complex environment. A BDML (Business Decision Markup Language) is used to implement the framework for specifying the world view of a business decision and/or a business application software system. A BDML processor comprises a syntax processor that checks the syntax correctness and syntax consistency within an individual and between different documents written in BDML, a logic processor that checks logical consistency between different documents written in BDML, in terms of the business objectives, constraints, assumptions, data, and underlying model among the different documents, and a knowledge-based processor including a knowledge base of business decisions, common choices for their decision support models and commercially available decision support systems, the knowledge-based processor providing suggestions for a set of BDML documents to improve consistency using the knowledge base.

Method and framework for model specification, consistency checking and coordination of business processes

A computer-implemented method determines current beliefs and/or behaviors of a population, and forecasts the behaviors and/or beliefs which this population is likely to have in the future. The method involves selecting a subset of members from a target population, obtaining survey responses from the members in the subset, generating point estimates of at least one population parameter, generating confidence bounds for the point estimates, and conducting a trend analysis on the survey responses and the point estimates of the at least one population parameter. Future behavior, beliefs, or other attributes of the population is then determined based on the trend analysis.

Computer method for using sample data to predict future population and domain behaviors

Method and apparatus suitable for demand forecasting. The invention can enable sales forecasting 'by item, by size, by location'. The invention features combining a demand profile and a demand model into a single encompassing model which is capable of projecting demand for an identified set of merchandise.

Method and apparatus suitable for demand forecasting

A computer system provides one or more lists of product combinations to one or more shoppers over one or more networks. The computer system comprises one or more central processing units (CPUs), one or more memories, and one or more network interfaces to one or more networks. An electronic shopping assistant process implemented on the computer system receives one or more inputs of constraints from shoppers, sends out the inputs to one or more shopping list generating processes in one or more stores, receives one or more lists of recommended product combinations that satisfy the given constraints, and allows shoppers to view and select one or more product combinations from received lists. A shopping list generating process implemented on the computer system receives one or more inputs from the electronic shopping assistant process by using an electronic shopping list protocol, searches products in an online product catalog stored in a product database, computes one or more lists of product combinations that satisfy the constraints given in the input, and sends lists of product combinations back to the electronic shopping assistant process again by using the electronic shopping list protocol.

Electronic shopping assistant and method of use

Growing community of inventors

Tarrytown, NY, United States of America

Ying Tat Leung