Automated functional understanding and optimization of human/machine systems
AssigneeMetric Masters Ltd.
InventorsJoseph Dalton, Will Bauer, Lindsay Haag
Life of this patent
Estimating the term…
Abstract
A method of analysing and tracking machine systems has the steps of sensing operational data from equipment, the operational data comprising at least location, time, and one or more operational condition data related to the equipment; analysing the operational data to identify data patterns; logging the data patterns as events in a database; comparing the events to a database of predetermined patterns to classify each data pattern as a known event or an unknown event; updating the database to include a new data pattern related to any unknown events; and alerting a user to further classify the unknown events manually.
Claims30
A method of analyzing and tracking a plurality of waste hauling trucks in a geographic area, wherein each waste hauling truck of the plurality of waste hauling trucks includes a sensor mounted to peripheral equipment, the method comprising:
- receiving operational data from the peripheral equipment of each waste hauling truck in the plurality of waste hauling trucks via the sensor, the operational data includes:
- a location measured by a GPS receiver,
- a time, and
- sensor data related to operation of the peripheral equipment of each waste hauling truck;
- analyzing the operational data to identify a data pattern of the plurality of waste hauling trucks;
- storing the data pattern in a database;
- classifying the data pattern as a gesture based on a set of gesture definitions with a first machine learning technique;
- identifying a system behaviour based on a plurality of gestures, wherein the plurality of gestures includes the gesture, and wherein the system behaviour is identified with a second machine learning technique, wherein the second machine learning technique is different from the first machine learning technique;
- and
- generating a report, the report to associate the system behaviour of the plurality of waste hauling trucks to determine an efficiency of an aggregated operation of the plurality of waste hauling trucks across the geographic area,
- wherein analyzing the operational data to identify the data pattern comprises:
- comparing the operational data to values in the set of gesture definitions,
- processing raw signals representative of the operational data to generate processed signals, and
- further processing the processed signals to identify the data pattern.
A system for analyzing and tracking a plurality of waste hauling trucks in a geographic area, the system comprising:
- sensors mounted to peripheral equipment in each waste hauling truck of the plurality of waste hauling trucks, the sensors sensing operational data from the peripheral equipment comprising:
- a location measured by a GPS receiver,
- a time, and
- one or more additional operational condition data related to operation of the peripheral equipment;
- and
- a processor in communication with the sensors of each waste hauling truck of the plurality of waste hauling trucks, the processor being programmed to:
- identify data structures using sets of data structure definitions, the data structures being ordered hierarchically in a first order data structure with a first machine learning technique and a second order data structure with a second machine learning technique, wherein the first order data structure comprises data patterns identified from the operational data, and the second order data structure comprises the first order data structure in combination with an additional first order data structures to determine an efficiency of an aggregated operation of the plurality of waste hauling trucks across the geographic area.
A method of analyzing and tracking a plurality of waste hauling trucks in a geographic area, wherein each waste hauling truck has peripheral equipment, the method comprising:
- receiving operational data from the peripheral equipment of each waste hauling truck of the plurality of waste hauling trucks, the operational data comprising:
- a location measured by a GPS receiver,
- a time, and
- sensor data related to operation of the peripheral equipment;
- identifying a data pattern from the operational data of the plurality of waste hauling trucks;
- identifying data structures from the data pattern using sets of data structure definitions, the data structures being ordered hierarchically, wherein first order data structures include the data pattern, and higher order data structures comprises a combination of two or more lower order data structures, wherein at least one lower order data structure comprises an immediately lower order data structure, and wherein a first machine learning technique is used to identify the first order data structures and a second machine learning technique is used to identify the higher order data structures to describe system behaviours;
- and
- generating an operational analysis based on a plurality of identified data structures from the plurality of waste hauling trucks across the geographic area, wherein the operational analysis comprises an efficiency analysis of a duration of one or more data structures, and a time interval between selected data structures, and wherein the operational analysis further comprises an estimated cost of the one or more data structures based on one or more maintenance costs, material costs, labour costs, and equipment costs,
- wherein analyzing the operational data to identify the data pattern comprises:
- comparing the operational data to values in a set of gesture definitions,
- processing raw signals representative of the operational data to generate processed signals,
- processing the processed signals to identify the data pattern, and
- using machine learning techniques to classify the data pattern as a gesture based on the set of gesture definitions, and
- wherein the operational analysis is to optimize a routing of the plurality of waste hauling trucks within the geographic area.
Dependencies are inferred from the claim text.