Inspection system and method

Abstract

To provide an inspection system that, in an event of a system failure, reports a future tentative point in time when the failure is expected to occur.SOLUTION: An inspection system and an operation method comprise steps of receiving sensor data for a component of a powered system, and determining, on the basis of at least in part on the sensor data, a predicted failure time for the component at which the component is predicted to fail. Predicted failure time appearing on a time axis and blank time zone start time can be determined after current time on the time axis and before the predicted failure time. The blank time zone start time and the predicted failure time can define a blank time zone range that spans between the blank time zone start time and the predicted failure time on the time axis. One or both of repair or maintenance work for the powered system can be scheduled at estimated arrival time within a blank time zone range and before the predicted failure time on a time axis.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The subject matter described herein relates to inspection systems and methods. [Background technology]

[0002] The inspection system may be used to determine the status of other systems. These statuses may be determined based on sensor data connected to the other systems. The inspection system may monitor the sensor data of the other systems to determine when the other systems require maintenance and / or repair. For example, the inspection system may monitor an engine parameter from time to time to determine whether the sensor data indicates that the engine parameter violates a threshold condition. If the inspection system determines that the engine parameter violates a threshold condition, the inspection system may trigger a repair or maintenance action to repair the engine system. For example, the inspection system may determine that the engine system requires maintenance or repair if the inspection system determines that the parameter indicates a fault in the engine system.

[0003] Therefore, there may be a need for an inspection system or method that, unlike existing systems and methods, will provide advance notice of whether other systems will fail, and, if so, a tentative time in the future when the failure is expected to occur. Summary of the Invention

[0004] According to one embodiment or aspect, a method can include receiving sensor data for a component of a powered system and determining a predicted failure time for the component at which the component is predicted to fail based at least in part on the sensor data. The predicted failure time occurs on a timeline. A window of absence start time can also be determined on the timeline after a current time and before the time at which failure is predicted. The window of absence start time and the predicted failure time can define a window of absence range on the timeline that spans between the window of absence start time and the predicted failure time. One or both of repair and maintenance activities for the powered system can be scheduled with a scheduled time falling within the window of absence range and prior to the predicted failure time on the timeline.

[0005] According to one embodiment or aspect, an inspection system can include a controller including one or more processors that can receive sensor data for a component of the powered system. The processor can determine a predicted failure time of the component at which the component is predicted to fail based at least in part on the sensor data. The predicted failure time can occur on a time line. The controller can determine a gap time slot start time on the time line that is after a current time and before the predicted failure time. The gap time slot start time and the predicted failure time can define a gap time slot range that spans between the gap time slot start time and the predicted failure time. The controller can schedule one or more repair or maintenance operations for the powered system at a scheduled time that falls within the gap time slot range and that is before the predicted failure time on the time line.

[0006] According to one embodiment or aspect, the method may include determining a timeline failure time at which the powered system is predicted to fail based at least in part on sensor data of the powered system. The sensor data may be acquired at a gap time start time on the timeline. The predicted failure time may occur after the gap time start time. The predicted failure time and the gap time start time define a gap time range on the timeline. One or more repair or maintenance operations on the powered system may have a scheduled repair time on the timeline that is within the gap time range. The scheduled repair time may be based on one or more of operating conditions of the powered system, environmental conditions of the powered system, or one or more operational requirements of the powered system. [Brief description of the drawings]

[0007] The subject matter of the present invention can be understood by reading the following description of non-limiting embodiments with reference to the accompanying drawings, in which:

[0008] [Figure 1] FIG. 1 illustrates an example of an inspection system according to one embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an outline of an example of a control system of the inspection system shown in FIG. [Diagram 3] FIG. 3 is a flow chart of an example method for determining a repair or maintenance activity schedule for a powered system according to one embodiment. [Figure 4] FIG. 4 illustrates an example of a timeline for scheduling repair or maintenance work on a powered system according to one embodiment. [Diagram 5] FIG. 5 is a graph for determining the predicted failure time of a powered system. [Figure 6] FIG. 6 illustrates an example of a timeline for scheduling repair or maintenance work on a powered system according to one embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Embodiments of the subject matter described herein relate to an inspection system and method of operation. The inspection system can include a powered system and a control system configured to monitor or inspect a condition of the powered system. In one embodiment, the control system can receive sensor data from one or more sensors coupled to or located proximate to the powered system. The sensor data can relate to the powered system, one or more various components of the powered system, the environment in which the powered system is in use, operating conditions of the powered system, etc.

[0010] The inspection system can determine a predicted failure time of one or more components of the powered system based at least in part on the sensor data. The predicted failure time can be a time on a timeline when a component is predicted to fail, require repair action, require maintenance action, etc. The predicted failure time can be determined to a window of absence start time on the timeline. The window of absence start time and the predicted failure time can define a window of absence range that spans between the window of absence start time and the predicted failure time. The window of absence range can span a length of about 30 days, about 60 days, about 120 days, about 240 days, etc. For example, the control system can determine a prediction of a failure of the powered system about 240 days before the prediction.

[0011] The inspection system may schedule repair and / or maintenance work for the powered system at a scheduled time within the gap time range. For example, the scheduled time for the repair and / or maintenance work (e.g., scheduled repair time) may occur on a timeline before the predicted failure time and after the gap time start time. For example, the control system may schedule repair and / or maintenance work for the powered system at a time ahead of the predicted failure time based on the determined predicted failure time of the powered system. In one or more embodiments, the inspection system may determine a plurality of different predicted failure times for a plurality of different components of the powered system. The control system of the inspection system may schedule the repair and / or maintenance work for one or more of the plurality of different components at a scheduled time based on the earliest predicted failure time.

[0012] In one embodiment, the motorized system may be a system of vehicle systems, such as a fluid system, a thermal system, a mechanical system, an electrical system, a propulsion system, etc. of a vehicle system. The vehicle system may be a rail car, an automobile, a truck (with or without a trailer), a bus, a marine vehicle, an aircraft, a mining vehicle, an agricultural vehicle, or other off-highway vehicle. If desired, the motorized system may be a device of a stationary or other non-vehicle type system. For example, the motorized system may be a stationary mechanical system in which a hot fluid is cooled using a cold flow, such as a mechanical system used in industrial applications. The vehicle systems described herein (rail car systems or other vehicle systems that do not run on rails or tracks) may be formed from a single vehicle or multiple vehicles. And, if desired, the motorized system may extend between two or more multiple vehicles. For multi-vehicle systems, the vehicles may be mechanically coupled to each other (e.g., by a coupler) or may be logically coupled but not mechanically. For example, the vehicles may be logically coupled but not mechanically when the individual vehicles communicate with each other to coordinate the movement of the vehicles with each other, such that the vehicles run together as a train. A group of vehicles may be called a convoy, consist, swarm, fleet, platoon, train, etc.

[0013] FIG. 1 illustrates an example of an inspection system 100 according to one embodiment. The inspection system includes a powered system 104 and a control system 102 that may be communicatively coupled to the powered system. For example, the control system may remotely control one or more operations of the powered system, such as changing a power setting to power the powered system on and / or off, changing settings of subsystems of the powered system that may change the performance of the powered system, etc. In one embodiment, the powered system may be a powered system of a vehicle system, a powered system of a non-vehicle and / or stationary mechanical system, a powered system of a power generation system (mobile or stationary), etc. As an example, the powered system may be an exhaust gas recirculation (EGR) system, a combustion control system, an emission control system, etc. As another example, the powered system may be a thermal management system, a fluid management system, etc.

[0014] The powered system may include one or more components 110, 112 and / or one or more subsystems 114, 116. One or more of the subsystems may include subsystem components. The components and / or subsystems may be fluid components or systems, thermal components or systems, mechanical components or systems, power generation components or systems, and the like. For example, the components and subsystems, and / or components of the subsystems may be engines, motors, alternators, generators, valves, conduits, manifolds, compressors, expanders, fans, blowers, pumps, heat exchangers, coolers, radiators, electrical components, and the like. Where appropriate, the components or subsystems may be and / or include static and / or dynamic components. In one or more embodiments, one or more of the components and / or subsystems may be and / or include electrical control components, manually controlled components, and the like.

[0015] In one or more embodiments, the powered system may include a controller 108 disposed within the body of the powered system (e.g., within the powered system housing, coupled to the powered system housing, disposed proximate to but outside the housing, etc.). A controller may represent a control module that may include one or more processors, microcontrollers, or other logic-based devices and / or associated software or instructions to perform one or more operations of the powered system.

[0016] In one or more embodiments, the powered system may include a memory 120 or other data storage device. The memory may store or preserve data related to the powered system, such as, but not limited to, operating conditions, operating settings, age of the powered system and / or age of the components and / or subsystems, type or model of each of the different components and subsystems, past maintenance and / or repairs performed on the powered system or one or more of the components and / or subsystems. In one or more embodiments, the powered system may include a communication system 118. A communication system may represent a transmitting and receiving circuit, one or more antennas, a modem, etc., and may be configured for one or both of wired or wireless communication. The communication system may communicate with the components and / or subsystems of the powered system, with a controller, a control system, a cloud storage device or system, other controllers separate from the powered system, etc. If desired, the powered system may lack all or one or more of the controller, memory, and communication system. For example, a powered system may be a mechanical system of the vehicle (e.g., a propulsion system, a braking system, etc.) and may be operatively coupled to a controller, memory, and / or communication system of the vehicle, where the controller, memory, and communication system may be used by other systems of the vehicle system (e.g., not dedicated solely to the mechanical system).

[0017] In one or more embodiments, the inspection system can include one or more sensors 106 disposed within, proximate to, coupled to, etc. the powered system. The sensors can detect and obtain sensor data related to the powered system, one or more components or subsystems of the powered system, environmental conditions related to the environment in which the powered system is disposed, etc. In one or more embodiments, one or more of the sensors can be thermal sensors that detect or sense thermal properties, etc. of one or more components, subsystems, fluids moving or disposed within the powered system. Optionally, one or more of the sensors can be optical sensors such as a camera that can capture still and / or video image data of the components and / or subsystems. Optionally, one or more of the sensors can be pressure sensors that can detect pressure of a fluid moving or disposed within the powered system. Optionally, one or more of the sensors can be accelerometers or other velocity detection sensors that can detect the movement, velocity, etc. of moving components and / or subsystems, fluids (e.g., gases, liquids, mixtures of gases and liquids) moving within the operational system, solids (e.g., debris, particles, etc.) moving within the powered system. Optionally, the one or more sensors may be a proximity sensor, an IR sensor, an ultrasonic sensor, a current sensor, an electromagnetic wave sensor, or the like.

[0018] Figure 2 is a diagram illustrating a schematic configuration of one example of the control system shown in Figure 1. The control system may include a controller 202, which may represent and / or include one or more processors, microcontrollers, or other logic-based devices and / or associated software or instructions for performing one or more operations described herein.

[0019] The control system can receive instruction signals from an input device 204, e.g., a touch screen, joystick, keyboard, switch, wheel, microphone, or other device that accepts input from an operator, and can be manually operated based on manual input from the operator on the input device. The output device 206 can provide the operator with sensor data received from the sensors (e.g., sensor data related to the powered system, sensor data related to the environment in which the powered system is operating, etc.), information related to the powered system (e.g., operating conditions and / or settings, type and / or classification of components and / or subsystems, age and / or amount of use of the powered system, health of components and / or subsystems, etc.), or similar information. The control system can include a memory 208 or other data storage device. In one embodiment, the memory may store or store the sensor data and other information related to the powered system, information related to other powered systems, etc. If desired, the control system can be communicatively connected to other storage databases (e.g., other memory devices of other systems, data storage cloud systems, etc.) that can store and / or store data related to the powered system, data related to other powered systems, etc.

[0020] The control system may include a communication system 210 that may be configured for one or both of wired and wireless communication. For example, a communication system may refer collectively to a transmission and reception circuit, one or more antennas, a modem, a communication cable, and the like. The communication system may communicate (e.g., receive and / or provide data signals) with a communication system, such as a powered system. In one embodiment, the communication system may provide bidirectional communication with the powered system and / or other systems in one or more communication formats. Suitable communication formats may include, but are not limited to, cellular networks (e.g., Global System for Mobile Communications (GSM)), mesh networks using Ethernet standards, wireless communication protocols (e.g., Bluetooth), radio communication types, and shortwave communication types, and the like. In one or more embodiments, when two or more communication types are present, the communication system may partially or fully convert the data stream from one type to another type. Similarly, different data protocols may be used. Such conversion may enable the communication system to act as a transfer point for data transmission. The conversion may enable the use of different types of equipment (e.g., a first vehicle system and a second vehicle system may each use a different communication type to communicate with each other via the communication system). The communication system may switch types, protocols, and / or communication paths in response to signal delegation or failure of one communication path. This may provide redundancy for communication by the communication system. In one embodiment, the communication system may decode, decompile, or decompose the information, analyze the information, and transmit all or part of the message (e.g., alone or in combination with new data or in combination with encryption, or both) in turn. The communication system may be the same as or similar to other communication devices or systems described herein.

[0021] In one or more embodiments, the control system may function as a back office server or dispatch center, such as a positive vehicle control (PVC) system. A PVC system is a control system in which a vehicle is permitted to move (e.g., above a specified, penalized speed limit) only in response to receipt or continued receipt of one or more signals (e.g., received from an off-board vehicle system) that meet specified criteria, the signals having specified characteristics (e.g., specified waveforms and / or content) and / or being received at a specified time (or according to other specified time criteria) and / or under specified conditions. This is in contrast to a "passive" vehicle control system that allows the vehicle system to move unless a signal (restriction of movement) is received. The back office server may be a critical or non-critical system, such that the data stored, contained, maintained, communicated, etc. may be critical (e.g., protected) and / or non-critical (e.g., non-protected) data. Alternatively, an off-vehicle control system represents other computerized systems that communicate with the vehicle and / or non-vehicle systems described herein.

[0022] FIG. 3 illustrates an example flowchart 300 of a method for determining a repair or maintenance schedule for a powered system, according to one embodiment. One or more of the steps illustrated in the flowchart of FIG. 3 may be omitted or completed in a different order. If desired, the method may include additional and / or alternative steps for determining a repair and / or maintenance schedule for the powered system. Additionally, FIG. 4 illustrates an example timeline 400 for scheduling repair or maintenance activities for a powered system, according to one embodiment. FIGS. 3 and 4 are now described in conjunction.

[0023] In step 302, sensor data acquired by one or more sensors coupled to or located proximate to the powered system may be received by a control system, a controller of the powered system, or the like. The sensor data may be communicated to the control system via a communication system of the powered system, or, if desired, the sensors may communicate sensor data directly to the control system. The sensor data may be received at scheduled intervals (e.g., every 30 seconds, 60 seconds, 60 minutes, 24 hours, 7 days, etc.). If desired, the sensor data may be received in response to sensed data exceeding a threshold, falling outside a threshold range, the sensed data changing by a threshold percentage (e.g., within a given time period), etc. If desired, the sensor data may be received in response to a request for the sensed data from the control system.

[0024] In one or more embodiments, a sensor (e.g., as shown in FIG. 1 ) can detect or otherwise sense data related to the powered system. The sensor data may be related to one or more components of the powered system, one or more subsystems of the powered system, one or more components of a subsystem, or the like.

[0025] At step 304, the control system may determine, based at least in part on the sensor data, a predicted failure time 408 (shown in FIG. 4) of one or more components and / or one or more subsystems at which the powered system is predicted to fail. Additionally, at step 306, a gap time slot start time 404 (shown in FIG. 4) may be determined. The gap time slot start time may be a time in the timeline that is later than the current time and earlier than the predicted failure time. If desired, the gap time slot start time may be approximately the same as the current time.

[0026] In one or more embodiments, the predicted failure time may be determined based on historical data associated with components and / or subsystems of the powered system, based on the type, modality, classification, etc. of components of the operating system, based on historical usage data of the powered system (e.g., the length of time the system has been operated), the environmental conditions in which the powered system is in use and / or operated, etc.

[0027] In one or more embodiments, the predicted failure time may be determined by the control system examining and / or manipulating the sensor data (e.g., with additional characteristics or information of the powered system) according to one or more mathematical formulas. In one or more embodiments, the powered system may be a thermal system, such as an exhaust gas recirculation (EGR) system, disposed within or coupled to the system. One or more of the sensors may be a thermal sensor that may be used to detect thermal characteristics of a fluid moving within the EGR system. For example, the sensor data communicated from the sensor to the control system may be thermal sensor data associated with one or more fluids moving within the EGR system. Equation 1 may be one example of how the control system may calculate the efficiency of the EGR system based on the thermal sensor data received.

[0028]

number

[0029] In response to the powered system reaching a gap time period start time on the time axis, a predicted failure time for the powered system can be calculated based on the mathematical model shown in Equation 2.

[0030]

number

[0031] As an example, a constant c value may be calculated in response to determining the effectiveness of the EGR system (e.g., the η value in Equation 2) after a 60-day period of use of the EGR system (e.g., a blank time period start time). For example, Equation 3 shows one example for determining the c value, which is the constant in Equation 2.

[0032]

number

[0033] 5 illustrates an example of a graph 500 comparing calculated EGR efficiency data (e.g., predicted or expected EGR efficiency) with actual EGR efficiency data for an EGR system. The graph includes a horizontal axis 502 indicating time and a vertical axis 504 indicating EGR efficiency. The graph includes a first distribution 506 of data that corresponds to the actual EGR efficiency data for the EGR system. For example, the first distribution of data may be determined based on sensor data during a previous operating session of the EGR system.

[0034] Additionally, the graph includes a second distribution 508 of data corresponding to the calculated predicted or expected effectiveness data of the EGR system. For example, the predicted or expected EGR efficiency data may be calculated according to Equation 2 for a number of different times in response to determining a value for the constant c in Equation 3. The graph illustrates that the second distribution of data corresponding to the predicted (e.g., calculated) effectiveness of the EGR system is similar (e.g., within a percentage threshold width) to the first distribution of data corresponding to the actual EGR efficiency data of the EGR system.

[0035] In one or more embodiments, the predicted failure time of the EGR system can be determined based on the determined threshold width 512 of the EGR efficiency. Also, the threshold width of the change amount can be determined based on the EGR efficiency at an initial time 514 of the calculated effects. In one or more embodiments, the initial time can be referred to as a gap time slot start time shown on the time axis shown in FIG. 4. In one embodiment, the gap time slot start time can be a predetermined amount of time, such as about 60 days after the current time (e.g., after the powered system has been in use for about 60 days, such as since the last maintenance and / or repair operation of the system, since the first use of the system, etc.). Optionally, the gap time slot start time can be based on a second threshold width change in EGR efficiency from the current time to the gap time slot start time.

[0036] The threshold range may be used to determine a failure time when a component and / or power system is predicted to fail. For example, the predicted failure time of an EGR system may be based on a change in EGR efficiency calculation data at a first time (e.g., a gap time period start time) by a percentage change of the threshold range. In the illustrated embodiment, the predicted failure time may be indicated by a second time 510. For example, the second time may be determined based on a change in calculated predicted or expected EGR effectiveness data by a determined percentage change of the threshold range.

[0037] In one or more embodiments, the predicted failure time may be a time in the future (e.g., within the next 60 days, within the next 120 days, within the next 240 days, etc.) that is predicted, expected, or anticipated that the powered system will fail, require repair action, etc. For example, the predicted failure time may indicate a future time that the powered system will require maintenance.

[0038] In one or more embodiments, a maintenance event may be a routine maintenance action (e.g., an expected or predicted action to maintain a powered system). Alternatively, a maintenance or repair action may be a non-routine maintenance action (e.g., an unforeseen or unexpected maintenance action). For example, a maintenance action may be cleaning one or more components of the powered system. A repair action may be repairing, adjusting, replacing, or otherwise fixing a broken, damaged, malfunctioning, etc. component of the powered system.

[0039] In one or more embodiments, the predicted failure time may be based on at least one of a degree or rate of deterioration of one or more components or subsystems of the powered system. For example, sensor data received by the control system from one or more sensors of the powered system may indicate that one or more components have reached or will reach a level of deterioration at a future time, and the predicted failure time may be determined based on an indication of the degree of deterioration indicated by the sensor data. If desired, the control system may determine that a rate of deterioration of one or more components of the powered system is greater than or exceeds an expected rate of deterioration. The predicted failure time may be determined based on the rate of deterioration of the one or more components.

[0040] In one or more embodiments, the predicted failure time can be displayed on a timeline as a time before or after the powered system is predicted to require maintenance. For example, the operating instructions and / or instructions for one or more components or subsystems, or historical data for the powered system, can provide a baseline schedule for maintaining the components of the powered system. The predicted failure time on the timeline can be different from the baseline detailed information for maintaining the powered system. For example, the predicted failure time can be a time on the timeline after the baseline detailed information for maintaining the powered system, such that a maintenance and / or repair event can be delayed from the baseline schedule provided time to the predicted failure time. Alternatively, the predicted failure time can be a time on the timeline prior to the baseline detailed information for maintaining the powered system, such that a maintenance and / or repair event can be scheduled for a predicted failure time that is prior to the baseline schedule provided time.

[0041] In one or more embodiments, the control system may determine a tolerance 416 for the predicted failure time. For example, the predicted failure time may be determined to be within a time window on the timeline that is within the determined tolerance. Different components and / or different subsystems of the powered system may have different or varying tolerance ranges. In one embodiment, the tolerance range may vary depending on the operating conditions of the powered system. For example, the powered system may be used in an environment where different components are subject to different strains or stresses than those caused by the powered system used in the different environment. Different environments may have different ambient conditions (e.g., temperature, humidity, pressure, etc.), different geographic regions (e.g., rural vs. urban) may have different air quality conditions, etc. If desired, the tolerances for different components of the system may be different based on the difference in the criticality of the components. For example, the health and / or functionality of a first component may be higher than the health and / or functionality of a second component of the powered system. If desired, the tolerance may be based on the number or severity of failures that the powered system (or components of the system) is expected to experience by the predicted failure time (e.g., whether the predicted failure time indicates possible inoperability due to predicted failure of one or more components, whether the predicted failure time indicates possible failure of the entire system, etc.).

[0042] Returning to FIG. 3 , at step 308, the control system can automatically schedule maintenance and / or repair work for the powered system. The maintenance and / or repair work may be scheduled for a gap time window range 410 spanning a timeline between a gap time window start time and a predicted failure time. For example, the gap time window range can indicate a lower limit 418 and an upper limit 420 on a timeline during which the maintenance and / or repair work may be scheduled. In one or more embodiments, the maintenance and / or repair work may be scheduled at a scheduled time 406. The control system may determine the scheduled time and can schedule the repair and / or maintenance work for the component at the scheduled time based on one or more operating conditions of the powered system, environmental conditions of the system, operating requirements of the powered system, etc.

[0043] In one or more embodiments, the scheduled time may be a time on a time axis that may fall within the gap time range. The scheduled time may be a time beyond the tolerance of the predicted failure time. Optionally, the scheduled time may be as close as the predicted failure time. Optionally, the scheduled time may be another predetermined amount of time away from the predicted failure time. For example, the scheduled time for repair and / or maintenance work may be about 60 days, about 120 days, about 180 days, about 240 days, etc., from the gap time start time. Optionally, the scheduled time may be about 1 day, 10 days, 50 days, etc., before the predicted failure time.

[0044] For example, the scheduled time for repair and / or maintenance work to be performed may be scheduled several months in advance to ensure that the repair and / or maintenance work is performed at a time favorable to the powered system. In one or more embodiments, the scheduled time may be determined based on a predicted usage of the powered system. For example, the powered system may be predicted to be in use for at least 180 days from the void time start time, but the predicted failure time of the powered system may be 220 days from the void time start time. If the control system predicts that the powered system will no longer be in use after 180 days, the control system may schedule the repair and / or maintenance work to be performed before the predicted failure time. For example, the control system may plan to perform the maintenance work at a time after the powered system is predicted to no longer be in use to prevent the powered system from being taken out of use sooner than necessary. As another example, the repair and / or maintenance work may include exposing the powered system to a higher or lower fluid temperature (e.g., hot or cold cleaning fluid, etc.). The control system may schedule maintenance and / or repair operations to occur at times when the environment (e.g., weather forecast) is deemed suitable to expose the powered system to higher or lower fluid temperatures.

[0045] As another example, the control system may schedule maintenance and / or repair work at a time when maintenance equipment is predicted to be available to perform maintenance and / or repair work on the powered system. As another example, the control system may schedule repair and / or maintenance work after a reference information presentation time for maintaining a component of the powered system. For example, the operating instructions or instructions for a component of the powered system may state that the component is to be maintained for a certain period of time, a certain amount of usage, at certain time intervals, etc. Alternatively, the control system may determine that the powered system may continue to operate past the reference information presentation time indicated by the operating manual, in which case the control system may set the scheduled time to a time past the reference information presentation time, such as a time that is more convenient for the powered system.

[0046] In step 310, the control system may communicate a command message to an operator of the powered system. The command message may indicate to the operator a scheduled time for the maintenance and / or repair work. Optionally, the command message may include a predicted failure time. Optionally, the command message may include a blank time window range (e.g., a lower and / or upper limit of the blank time window range). Optionally, the command message may include instructions to instruct the operator to schedule the maintenance and / or repair work for a time on the timeline prior to the predicted failure time. Optionally, the command message may include instructions to have the operator manually control the powered system to move the powered system toward a location where the maintenance and / or repair work will be performed.

[0047] In one embodiment, the control system may communicate a first alert 412 to an operator of the powered system. Optionally, the control system may communicate a second alert 414 to the operator indicating that the current time is after the first alert and before the predicted failure time. In one embodiment, the first alert may have a lower priority level than the priority level of the second alert. For example, the priority of one or more alerts may be based on the amount of time from the predicted failure time until the alert is communicated, the amount of time from the predicted failure time to the scheduled time, etc. The control system may increase the tone of an alert message to the powered system as the predicted failure time of the powered system approaches. For example, a command message may indicate a high priority for a determination that the amount of time between the predicted failure time and the scheduled time on the timeline is less than the determined time range 422, and an alert may indicate a low priority for a determination that the amount of time between the predicted failure time and the scheduled time is greater than the determined time range. In the embodiment illustrated in FIG. 4, the scheduled time appears as a time on the timeline that is prior to the determined time range. A command message to an operator may indicate a low priority for a determination that the amount of time between the predicted failure time and the scheduled time is greater than the determined time range.

[0048] At step 312, repair and / or maintenance operations may be completed on components and / or subsystems of the powered system. In one embodiment, the repair and / or maintenance operations may be completed at a maintenance facility, at the current location of the powered system (e.g., the powered system may not need to travel to a maintenance facility to have the repair and / or maintenance operations completed), etc. One or more operations to repair and / or maintain the powered system may be completed manually, automatically, or a combination thereof.

[0049] At step 314, a notification or command message that the repair and / or maintenance action has been completed may be communicated to an operator of the powered system. In one embodiment, the notification may indicate the results of the maintenance and / or repair action and may include revised operational settings for the powered system, instructions for the operator of the powered system, etc. If desired, the notification of the completion of the repair and / or maintenance action and information related to the actions completed during the repair or maintenance action may be stored in a memory of the control system, communicated to a system on behalf of the control system, etc.

[0050] FIG. 6 illustrates a timeline 600 for scheduling repair and / or maintenance work for a system, according to one embodiment. The timeline includes a current time 602 and a gap time slot start time 604 that occurs after the current time on the timeline. Additionally, a first predicted failure time 606 and a second predicted failure time 608 are displayed on the timeline. The first predicted failure time may represent a time on the timeline at which the control system determines that a first component (e.g., component 110 shown in FIG. 1 ) is predicted to fail based, at least in part, on sensor data associated with the first component received from one or more sensors. The second predicted failure time may represent a time on the timeline at which the control system determines that a second component (e.g., component 112 shown in FIG. 1 ) is predicted to fail based, at least in part, on sensor data associated with the second component received from one or more sensors.

[0051] In one or more embodiments, the control system may perform repair and / or maintenance action on one or both of the first or second components at a scheduled time 612 based on the first and second predicted failure times. As an example, the control system may determine that repair of the first component is required before or prior to repair of the second component if the first predicted failure time occurs before the second predicted failure time on the timeline. The control system may perform the repair and / or maintenance action on at least the first component at a scheduled time that occurs before the first predicted failure time on the timeline.

[0052] In one embodiment, the control system can determine whether a second predicted failure of the second component occurs outside or inside the repair window 610. The repair window may extend on the timeline between the window start time and a second time 614 on the timeline. One or more components and / or subsystems of the powered system determined to have a predicted failure time that falls within the repair window may all be repaired and / or maintained prior to the earliest predicted failure time. Alternatively, components and / or subsystems of the powered system determined to have a predicted failure time that falls outside the repair window may not be repaired and / or maintained. For example, a component whose failure time falls within the determined repair window may be repaired and / or maintained earlier than necessary, but while the powered system is already being repaired or maintained. Alternatively, the control system may determine that it is too early to complete repair and / or maintenance work on a component whose failure time falls outside the determined repair window.

[0053] In the illustrated embodiment, the control system may determine that the first predicted failure time occurs before the second predicted failure time, and that the second predicted failure time occurs outside the repair window. The control system may schedule the repair and / or maintenance work for the first component at the scheduled time, but may not schedule the repair and / or maintenance work for the second component at the same scheduled time as the first component in response to determining that the second predicted failure time occurs outside the repair window. For example, if the control system determines that it is too early to perform the repair and / or maintenance work for the second component, the control system may schedule the repair and / or maintenance work at a time on the timeline close to the second predicted failure time (e.g., outside the repair window). Alternatively, the control system may cause the repair and / or maintenance work for the first and second components to be planned based on the first and second predicted failure times occurring within the repair window. The repair and / or maintenance work for the first and second components may be completed at the same scheduled time.

[0054] In one or more embodiments, the control system may schedule repair and / or maintenance operations for the first component and / or the second component based on available assets (e.g., availability of a maintenance facility, availability of maintenance equipment, availability of replacement parts, available personnel, etc.). If desired, the control system can schedule repair and / or maintenance operations for the powered system based on the availability of alternative components that may replace current components of the powered system. If desired, the control system can schedule repair and / or maintenance operations, such as ahead of a scheduled time on a timeline or behind a scheduled time on a timeline, based on receiving one or more requests from an operator of the powered system to repair, maintain, or replace one or more components of the powered system.

[0055] In one embodiment, the control system may deploy a local data collection system that may use machine learning to enable derivation-based learning outcomes. The controller may learn and make decisions from a set of data (including data provided by various sensors) by making data-driven predictions and adapting according to the set of data. In an embodiment, the machine learning may include performing multiple machine learning tasks with the machine learning system, such as supervised learning, unsupervised learning, and reinforcement learning. Supervised learning may include presenting a set of example inputs and desired outputs to the machine learning system. Unsupervised learning may include a learning algorithm that structures its inputs by methods such as pattern detection and / or feature learning. Reinforcement learning may include the machine learning system performing in a dynamic environment and then providing feedback regarding accurate and inaccurate decisions. In an example, the machine learning may include multiple other tasks based on the output of the machine learning system. In an example, the tasks may be machine learning problems such as classification, regression, clustering, density estimation, dimensionality reduction, anomaly detection, and the like. In an example, the machine learning may include multiple mathematical and statistical techniques. In examples, many types of machine learning algorithms may include decision tree-based learning, association rule learning, deep learning, artificial neural networks, genetic learning algorithms, inductive logic programming, support vector machines (SVMs), Bayesian networks, reinforcement learning, representation learning, rule-based machine learning, sparse dictionary learning, similarity metric learning, learning classifier systems (LCS), logistic regression, random forests, K-means, gradient boosting, K-nearest neighbors (KNN), a priori algorithms, etc. In embodiments, certain machine learning algorithms may be used (e.g., to solve both constrained and unconstrained optimization problems that may be based on natural selection). In examples, algorithms may be used to address mixed integer programming problems, where some components are restricted to be integer-valued. Algorithms and machine learning techniques and systems may be used in computational intelligence systems, computer vision, natural language processing (NLP), recommendation systems, reinforcement learning, building graphical models, etc.In one example, machine learning may be used for vehicle performance and behavior analysis, etc.

[0056] In one embodiment, the controller system may include a policy engine that may apply one or more policies. These policies may be based at least in part on characteristics of a given item of equipment or environment. With respect to the control policies, the neural network may receive inputs of a number of environmental and task-related parameters. These parameters may include an identification of a trip plan determined for the group of vehicles, data from various sensors, and location and / or position data. The neural network may be trained to generate outputs based on these inputs, the outputs representing an action or sequence of actions that the group of vehicles should take to accomplish the trip plan. During operation of an embodiment, a decision may be made by processing the inputs through the parameters of the neural network to generate a value at an output node that designates the action as a desired action. The action may be translated into a signal that causes the vehicle to operate. This may be accomplished via backpropagation, a feedforward process, closed-loop feedback, or open-loop feedback. Alternatively, rather than using backpropagation, the machine learning system of the controller may use evolutionary strategy techniques to tune various parameters of the artificial neural network. The controller may use a neural network architecture with functions that may not always be solvable using backpropagation, e.g., functions that are non-convex. In one embodiment, the neural network has a set of parameters that represent the weights of its node connections. Multiple copies of this network are generated, and then various adjustments are made to the parameters and simulations are performed. Once the outputs from the various models are obtained, they can be evaluated based on their performance using a determined success metric. The best model is selected, and the vehicle controller executes a plan to achieve the desired input data to mirror the predicted best outcome scenario. Furthermore, the success metric can be a combination of optimized outcomes that can be weighted against each other.

[0057] According to one or more embodiments or aspects of the subject matter described herein, a method can include receiving sensor data of a component of a powered system and determining a predicted failure time of the component at which the component is predicted to fail based at least in part on the sensor data. The predicted failure time falls on a timeline. A window of absence start time may be determined on the timeline to be after a current time and before the predicted failure time. The window of absence start time and the predicted failure time may define a window of absence range on the timeline that spans between the window of absence start time and the predicted failure time. One or both of repair or maintenance operations for the powered system can be scheduled at a scheduled time falling within the window of absence range and before the predicted failure time on the timeline.

[0058] Optionally, the gap time range may include an upper limit determined by the predicted failure time and a lower limit determined by the gap time start time. Optionally, the predicted failure time and the scheduled time of one or both of the repair or maintenance actions may be separated by a predetermined amount of time. Optionally, the predicted failure time may have a determined error. Optionally, the one or more characteristics of the component may be determined based on sensor data. The predicted failure time may be based on one or more characteristics of the component at the gap time start time on the time axis. Optionally, the sensor data may include thermal sensor data associated with one or more fluids moving within the powered system. Optionally, a command message may be communicated to an operator of the powered system indicating one or more of the predicted failure times or scheduled times of one or both of the repair or maintenance actions in the gap time range. Optionally, the command message may include a priority based on the amount of time between the predicted failure time and the scheduled time. Optionally, the command message may include a high priority in response to the amount of time between the predicted failure time and the scheduled time being determined to be less than the determined time range, and the alert may indicate a low priority in response to the amount of time between the predicted failure time and the scheduled time being determined to be greater than the determined time range. Optionally, one or both of the repair and maintenance actions may be performed at a scheduled time based on one or more of one or more operating conditions of the powered system, an environmental condition of the powered system, or one or more operating requirements of the powered system. Optionally, one or both of the repair and maintenance actions may be completed for the powered system and a command message may be communicated indicating that one or both of the repair and maintenance actions have been completed. Optionally, at least one of a degree of deterioration or a rate of deterioration of a component of the powered system may be determined based at least in part on the sensor data. One or both of the repair and maintenance actions for the powered system may be performed at the scheduled time based on at least one of a degree of deterioration or a rate of deterioration of a component and a predicted time of failure for the powered system.Optionally, the predicted failure time may be a first predicted failure time of a first component of the powered system. A second predicted failure time of a second component of the powered system may be determined. The first predicted failure time and the second predicted failure time may occur at different times on a timeline. Optionally, it may be determined that the first predicted failure time occurs before the second predicted failure time on a timeline, and that the second predicted failure time occurs during a repair window on a timeline. One or more repair or maintenance operations on the first component and one or more repair or maintenance operations on the second component may be scheduled at a scheduled time that is prior to the first predicted failure time on a timeline in response to determining that the first predicted failure time and the second predicted failure time occur within a repair window. Optionally, the first predicted failure time may be determined to occur before the second predicted failure time on a timeline, and that the second predicted failure time occurs outside of a repair window on a timeline. One or more of the repair or maintenance actions on the first component may be scheduled to occur at a scheduled time prior to a first predicted failure time, and one or more of the maintenance actions on the second component may not be scheduled at the scheduled time in response to a second predicted failure time being determined to fall outside the timeline repair window.

[0059] According to one or more embodiments or aspects of the subject matter described herein, an inspection system can include a controller including one or more processors that can receive sensor data for a component of a powered system. The processor can determine a predicted failure time of the component where the component is predicted to fail based at least in part on the sensor data. The predicted failure time can occur on a timeline. The controller can determine a window of opportunity start time on the timeline that is after a current time and before the predicted failure time. The window of opportunity start time and the predicted failure time can define a window of opportunity range that spans between the window of opportunity start time and the predicted failure time. The controller can schedule one or more repair or maintenance actions for the powered system at a scheduled time that occurs within the window of opportunity range and before the predicted failure time on the timeline.

[0060] According to one or more embodiments or aspects of the subject matter described herein, a method can include determining a failure time on a timeline at which the powered system is predicted to fail based at least in part on sensor data of the powered system. The sensor data can be acquired at a gap time start time on the timeline. The predicted failure time can occur after the gap time start time. The predicted failure time and the gap time start time define a gap time range on the timeline. For one or more repair or maintenance operations on the powered system, a time on the timeline within the gap time range can be a scheduled time of the repair operation. The scheduled repair time can be based on one or more of operating conditions of the powered system, environmental conditions of the powered system, or one or more operating requirements of the powered system.

[0061] Optionally, the predicted failure time may be a first predicted failure time of a first component of the powered system and a second predicted failure time of a second component of the powered system may be determined. The first predicted failure time and the second predicted failure time may occur at different times on the timeline. Optionally, the first predicted failure time may be determined to occur before the second predicted failure time on the timeline and one or more of the maintenance operations for both the first and second components may be scheduled at a scheduled repair time that occurs before the first predicted failure time on the timeline. Optionally, one or more of the repair operations or maintenance operations for both the first and second components may be completed at a scheduled repair time prior to the second failure time based on the first failure time occurring before the second failure time on the timeline.

[0062] As used herein, an element or step described in the singular and preceded by the word "a" or "an" should be understood not to exclude a plurality of such elements or steps, unless the exclusion is expressly stated. Moreover, reference to "one embodiment" of the invention does not exclude the existence of additional embodiments incorporating the recited features. Moreover, unless expressly stated to the contrary, an embodiment "comprising," "including," or "having" an element or elements having a particular characteristic may include additional such elements that do not have that characteristic. In the appended claims, the terms "including" and "in which" are used as the plain English equivalents of the respective terms "comprising" and "wherein." Moreover, in the following claims, the terms "first," "second," "third," etc. are used merely as labels and do not impose numerical requirements on their objects. Moreover, the following claim limitations are not written in means-plus-function form, and such claim limitations are not intended to be construed under 35 U.S.C. 352(f) unless and until the phrase "means for" is followed by an express description of the function, lacking further structure.

[0063] The above description is illustrative, and not limiting. For example, the above-described embodiments (and / or aspects thereof) can be used in combination with each other. In addition, many modifications can be made to adapt a particular situation or material to the teachings of the inventive subject matter without departing from its scope. The dimensions and types of materials described herein are intended to define the parameters of the inventive subject matter, but are exemplary embodiments. Other embodiments will be apparent to those skilled in the art upon review of the above description. The scope of the inventive subject matter should, therefore, be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.

[0064] This written description uses examples to disclose some embodiments of the inventive subject matter, including the best mode, and also to enable one of ordinary skill in the art to practice embodiments of the inventive subject matter, including making and using any devices or systems, and performing any incorporated methods. The patentable scope of the invention is defined by the claims, and may include other examples that occur to those of ordinary skill in the art. Such other examples are intended to be within the scope of the claims if they have structural elements that do not differ from the literal words of the claims, or if they include equivalent structural elements with differences that do not substantially differ from the literal words of the claims.

Claims

1. A method executed by at least one processor, comprising: receiving sensor data for a component of the powered system; generating predicted sensor data based in part on the sensor data received in the previous step; comparing the sensor data to the predicted sensor data to determine differences between the sensor data and the predicted sensor data; determining a predicted failure time of the component at which the component is predicted to fail based at least in part on a difference between the sensor data and the predicted sensor data outside a threshold range, the predicted failure time occurring on a time axis; determining a gap time slot start time on said time axis that is after a current time and before said predicted failure time, said gap time slot start time and said predicted failure time defining a gap time slot range on said time axis that spans between said gap time slot start time and said predicted failure time; scheduling a repair or maintenance operation or both of the powered system for a scheduled time that falls within the window of opportunity and that is prior to the predicted failure time on the timeline; A method comprising:

2. The method of claim 1 , wherein the gap time zone range includes an upper limit determined by the predicted failure time and a lower limit determined by the gap time zone start time.

3. The method of claim 1 , wherein the predicted failure time and the scheduled time of one or both of the repair action or the maintenance action are separated by a predetermined amount of time.

4. The method of claim 1 , wherein the predicted failure time is within a determined margin of error.

5. determining one or more characteristics of the component based on the sensor data; The method of claim 1 , wherein the predicted failure time is based on the one or more characteristics of the component at a gap time period start time on the timeline.

6. The method of claim 1 , wherein the sensor data includes thermal sensor data associated with one or more fluids moving within the powered system.

7. 2. The method of claim 1, further comprising the step of communicating a command message to an operator of the powered system indicating one or more of the predicted failure times or the scheduled times of one or both of the repair actions or the maintenance actions in the gap time range.

8. The method of claim 7 , wherein the command message includes a priority for warning messages based on the amount of time between the predicted failure time and the scheduled time.

9. 8. The method of claim 7, wherein the command message indicates a high priority in response to determining that the amount of time between the predicted failure time and the scheduled time on the timeline is less than a determined time range, and wherein the command message indicates a low priority in response to determining that the amount of time between the predicted failure time and the scheduled time on the timeline is greater than a determined time range.

10. 2. The method of claim 1, further comprising scheduling one or both of the repair action or the maintenance action for the component at the scheduled time based on one or more operating conditions of the powered system, an environmental condition of the powered system, or one or more operational requirements of the powered system.

11. The method of claim 1 , further comprising the step of communicating a command message indicating completion of one or both of the repair operation or the maintenance operation.

12. determining at least one of a degree or rate of deterioration of components of the powered system based at least in part on the sensor data; scheduling the repair action or the maintenance action, or both, of the powered system at the scheduled time based on at least one of the degree of deterioration or the rate of deterioration of the component and the predicted time of failure of the powered system; The method of claim 1 , further comprising:

13. the predicted failure time is a first predicted failure time of a first component of the powered system; The method further includes determining a second predicted failure time of a second component of the powered system; The method of claim 1 , wherein the first and second predicted failure times occur at different times on the timeline.

14. determining that the first predicted failure time occurs before the second predicted failure time on the time axis; determining that the second predicted failure time falls within a repair window on the timeline; 14. The method of claim 13, further comprising: in response to determining that the first predicted failure time and the second predicted failure time fall within the repair window, scheduling the repair or maintenance operation or both of the first component and the repair or maintenance operation or both of the second component at the scheduled time prior to the first predicted failure time on the timeline.

15. determining that the first predicted failure time occurs before the second predicted failure time on the time axis; determining that the second predicted failure time occurs on the time axis outside a repair window; 14. The method of claim 13, comprising: scheduling the repair or maintenance action or both of the first component at the planned time prior to the first predicted failure time, and not scheduling the repair or maintenance action or both of the second component at the planned time in response to determining that the second predicted failure time is outside the range of repair times on the timeline.

16. 1. An inspection system comprising: a controller including one or more processors configured to receive sensor data for a component of a powered system, the controller comprising: the one or more processors are configured to compare the sensor data to the predicted sensor data to determine a difference between the sensor data and the predicted sensor data based in part on the sensor data received by the controller; the one or more processors are configured to determine a predicted failure time of the component at which the component is predicted to fail, the predicted failure time of the component being predicted to fail based at least in part on a difference between the sensor data and the predicted sensor data that falls outside a threshold range, the predicted failure time occurring on a time axis; the controller is configured to determine a gap time slot start time on the timeline that is after a current time but before the predicted failure time, the gap time slot start time and the predicted failure time being configured to define a gap time slot range that spans between the gap time slot start time and the predicted failure time on the timeline; the controller is configured to schedule one or more repair or maintenance operations for the powered system at a scheduled time that occurs within the window of opportunity and that is prior to the predicted failure time on the timeline; The controller is configured to control a communication system to communicate a command message indicating completion of one or both of the repair operation or the maintenance operation.

17. A method executed by at least one processor, comprising: comparing sensor data of the powered system to predicted sensor data of the powered system to determine a difference between the sensor data and the predicted sensor data, the predicted sensor data being based in part on the sensor data; determining a predicted failure time on a timeline at which a powered system is predicted to fail based at least in part on a difference between the sensor data of the powered system and the predicted sensor data of the powered system that falls outside a threshold range, the sensor data being acquired at a gap time slot start time on the timeline, the predicted failure time occurring after the gap time slot start time, and the predicted failure time and the gap time slot start time defining a gap time slot range on the timeline; and scheduling one or more repair or maintenance operations for the powered system at a time on the timeline within the gap time range and at a scheduled repair time prior to the predicted failure time on the timeline, the scheduled repair time being based on one or more of one or more operating conditions of the powered system, environmental conditions of the powered system, or one or more operational requirements of the powered system.

18. the predicted failure time is a first predicted failure time of a first component of the powered system; The method further includes determining a second predicted failure time of a second component of the powered system; The method of claim 17 , wherein the first and second predicted failure times occur at different times on the timeline.

19. determining that the first predicted failure time occurs before the second predicted failure time on the time axis; scheduling one or more of the repair or maintenance actions for both the first component and the second component at a scheduled repair time prior to the first predicted failure time on the timeline; 20. The method of claim 18, further comprising:

Images