Dynamic prediction of risk levels for manufacturing operations through leading risk indicators: dynamic risk analyzer engine

• US 10,268,962 B2
• Filed: 02/01/2016
• Issued: 04/23/2019
• Est. Priority Date: 10/10/2014
• Status: Active Grant

• Current Assignee: Near-Miss Management, LLC
• Original Assignee: Near-Miss Management, LLC
• Inventors: Pariyani, Ankur, Bespalov, Dmitriy, Oktem, Ulku G., Cielak, Luis
• Primary Examiner(s): La, Anh V
• Application Number:
  US15/012,109
• Publication Number:
  US 20160148107A1
• Time in Patent Office: 1,177 Days
• Field of Search: 340501, 340540, 340999, 702179, 702182, 702183, 345440, 345140
• CPC Class Codes: G05B 23/024 Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
• CPC Class Codes: G05B 23/0278 Qualitative, e.g. if-then rules; Fuzzy logic; Lookup tables; Symptomatic search; FMEA
• CPC Class Codes: G06N 5/04 Inference or reasoning models

Abstract

The dynamic risk analyzer (DRA) provided by the present invention periodically assesses real-time or historic process data, or both, associated with an operations site, such as a manufacturing, production, or processing facility, including a plant'"'"'s operations, and identifies hidden near-misses of such operation, when in real time the process data appears otherwise normal. DRA assesses the process data in a manner that enables operating personnel including management at a facility to have a comprehensive understanding of the risk status and changes in both alarm and non-alarm based process variables. The hidden process near-miss data may be analyzed alone or in combination with other process data and/or data resulting from prior near-miss situations to permit strategic action to be taken to reduce or avert the occurrence of adverse incidents or catastrophic failure of a facility operation.

Claims

1. A system for predicting risk levels for manufacturing operations with risk indicators comprising:

a server that receives automatically measured process data from a real-time data source and/or a historical archive data source and long-term process data for a period preceding the measured process data;

a processor that analyzes values of parameters P and/or groups G of said parameters P of said measured process data at time interval T and compares the measured process data to the long-term process data wherein the long term process data is automatically updated over time to identify operational risk and/or near-miss risk that would otherwise be unknown or concealed in parameters P, whereby said operational risk and/or near-miss risk may be used for strategic corrective action; and

a display that presents said operational risk and/or near-miss risk in a graphic that visually depicts a plotted value V of parameter(s) P of said operational risk and/or near-miss risk in time interval T relationally within a specified time period;

wherein said system continuously and autonomously operates contemporaneously with said manufacturing operation.

2. The system of claim 1, wherein the process data is either an analog signal or a two-state signal.

3. The system of claim 1, wherein the process data is not communicated outside the manufacturing operation.

4. The system of claim 1, wherein the system operates perpetually without an operator.

5. A method for dynamic prediction of risk levels in a manufacturing operation comprising:

collecting measured process data, comprising;

data automatically collected by a data collection component, located within said manufacturing operation, in either (a) real-time or (b) from an archive server or both;

collecting long-term process data for a period preceding the collecting measured data;

identifying risk and/or near-miss risk of said manufacturing operation that would otherwise be unknown or concealed in parameters P and/or groups G of said parameters P of process data, said process data by comparing the measured process data to the long-term process data, wherein the long term process data is automatically updated over time; and

displaying said risk or near-miss risk in a graphic that visually reports a plotted value V of parameter(s) P of said risk or near-miss risk relationally within time T period, whereby said plotted value V is displayed with a variable visual indicator corresponding with magnitude of said plotted value V;

wherein said method is performed continuously and autonomously.

6. A display system for risk indicators for a manufacturing operation comprising:

identifying risk and/or near-miss risk of said manufacturing operation that would otherwise be unknown or concealed in parameters P and/or groups G of said parameters P of measured process data, in real-time, periodically, and/or historically wherein the measured process data is obtained by using a data collection component located within said manufacturing operation;

plotting parameter P of said risk and/or near-miss risk on a circular or semi-circular chart of graphic visual indicators comprising;

a petal for P parameter at each T time interval;

said petal comprising an area plotted with a radius R having a maximum and minimum reportable length and an angle spread greater than 1 degree, wherein said length of said radius R corresponds with a magnitude of said parameter P at said T time interval and partially determines said area of said petal displayed on said chart; and

displaying said parameter P at a time interval on said chart over a predetermined time period.