JP2023547729A - Systems and methods for scalable automatic maintenance optimization - Google Patents

Abstract

A scalable automated maintenance optimization system for managing the replacement of parts within a portfolio of assets is described. A plurality of maintenance records related to one or more replaced parts are received. The received maintenance records are analyzed to generate an asset history that includes information regarding part replacements. Based on asset history, an age at replacement distribution is generated for each part type. A parts replacement strategy for each part type is determined based at least on the calculated age at replacement distribution. A user interface is controlled to display a list of parts and a respective determined part replacement strategy. The displayed list automatically updates parts whose determined part replacement strategy differs from the current part replacement strategy by moving them closer to the top of the displayed list of parts in the user interface. Reconfigured.

Description

cross reference

This application claims priority to U.S. Provisional Patent Application No. 63/110,428, filed on November 6, 2020, U.S. Patent Application No. 17/165, filed on February 2, 2021, Claims priority to U.S. patent application Ser. No. 17/484,022, filed September 24, 2021, which is a continuation-in-part of No. 045. This application also claims priority to U.S. Provisional Patent Application No. 63/255,546, filed on October 14, 2021. The entire disclosure of each of the documents cited in this section is fully incorporated herein by reference.

Aspects of the present disclosure generally relate to systems and methods for using transaction data from a maintenance management system to improve maintenance strategies applied to a portfolio of assets in a capital-intensive industry, as well as for leveraging expert maintenance domain expertise. Concerning data science applications that encapsulate and automate. More specifically, but not exclusively, the present invention provides a method for determining the age of parts across a portfolio of assets based on extracting and integrating maintenance records using natural language processing, asset ontologies, and automated statistical analysis. Regarding decisions.

For example, capital intensive industries such as, but not limited to, mining, freight railroads, shipping, power generation, and oil and gas operate complex machinery around the clock in remote locations and difficult conditions. Operations may be limited to a single site or may span multiple sites across a geographic region, continent, or globe. Site operations, including asset management and parts replacement, may be managed locally at each site. However, different sites of the same type (e.g. located in It is more common and useful to be able to exchange data between

When a piece of equipment is replaced as part of planned or unplanned maintenance, replacement work is requested in the notification. The task description is recorded in an associated work order, which may be fed into the operation's maintenance management system and stored locally. The work order may include data included in the notification. Information from work orders informs future part replacement strategies to cost-effectively maximize uptime. Each local site's operational security management system may provide transaction data to a central server that acts as a client to the global operational security management system.

In a typical capital-intensive organization, reliability engineers are tasked with extracting data from an operation's maintenance management system, performing analysis, and determining optimal maintenance strategies. The analysis generally focuses on a specific part at a time, identified by its type and location within the asset, and collects all work order records in which that part was replaced to calculate total failure statistics. It consists of things. This analysis is further complicated when multiple parts of a single part type are installed on an asset and only some of the multiple parts are replaced. Additionally, work orders are often incomplete and lack critical information to identify the location of the part being replaced or the cause of the replacement that can be located.

These discrepancies and inconsistencies can occur due to operational pressures that lead to work orders being completed prematurely and incorrectly. Further, functionally equivalent parts may be identified by different part number identification codes, for example, because they are sourced from different manufacturers. Due to these challenges, it can take months to manually reconstruct the history of one particular part type that is matched to a portfolio of assets. A portfolio of assets may include fixed factory assets and a fleet of similar assets. Even if the history of a part type can be manually reconstructed, inconsistent and incomplete data can prevent accurate determination of the age of each instance of that part at the time of replacement across a particular operation's portfolio of assets.

Determining age is important for generating predictive parts maintenance and replacement strategies and requires tracking part replacement dates by location for each asset across the portfolio. The resulting age calculation determines the replacement rate or percentage of parts replaced at any given service age for that part type in the portfolio. Age function statistics can then be used to determine optimal part replacement strategies as well as to account for suboptimal maintenance processes within a site. For large organizations with many different portfolios of assets, each with different parts, traditional manual processes for reliability engineering are only capable of analyzing a very small percentage of parts. Moreover, manually processing work orders to determine the age function is error-prone, and the sheer number of parts to be monitored means that the derived maintenance strategy can be does not allow to be scaled or approached holistically.

Due to the diversity of work order quality and types within and across industries, part history can be automatically replayed across a portfolio of assets to persistently determine the age function for each single part at any given time. No solution has been developed to build it.

One alternative option to the manual reliability engineering process described above is to extract maintenance insights from equipment sensors or telemetry data and use predictive maintenance techniques to optimize maintenance and replacement strategies. One example is Uptake®, which uses machine learning models and asset sensor data to predict when the next failure is likely to occur, so corrective maintenance can be performed. obtain.

In current predictive maintenance systems, sensor data is analyzed to detect anomalies in sensor data trends that indicate asset failure. A few of these systems can isolate defect conditions for individual parts and their failure patterns and provide predictions of how far to the point of failure as the condition of the parts deteriorates. Accordingly, predictive maintenance may enable organizations to plan and pre-deploy resources for corrective maintenance. However, a major drawback of these predictive maintenance solutions is that, to be effective, they are highly dependent on assets or machines having sufficient sensors and access to their data that is frequently sampled. Given the high cost of installing sensors, typically only a subset of parts and machines within an asset fleet are instrumented. Therefore, these traditional solutions are unable to provide a comprehensive parts maintenance strategy across a deployed portfolio of assets.

A second problem with conventional predictive maintenance systems is that they cannot account for sudden or unexpected failures. Current predictive maintenance solutions rely on parts gradually deteriorating from the onset of failure to the point of failure. However, many parts fail suddenly without warning and are not amenable to current predictive maintenance analysis. Therefore, current predictive maintenance solutions, at best, can only address a subset of parts within a portfolio of assets and cannot be used to fully optimize and manage the complete portfolio of parts maintenance.

Therefore, for each set of parts in an asset portfolio at scale to improve the quality of maintenance process insights from transactional maintenance records and provide comprehensive maintenance and replacement solutions for all parts in the asset portfolio. It must be possible to efficiently calculate the age function of .

At least the needs described above are addressed and a technical solution is achieved in the art by various embodiments of the present invention.

According to a first embodiment of the invention, a scalable automated maintenance optimization system for managing the replacement of parts within one or more assets of a portfolio includes at least one system configured to store instructions. a computer-accessible storage device and a plurality of program modules communicatively coupled to the at least one computer-accessible storage device and, when executed, including a data acquisition module, a data integration module, and an age calculation module. at least one processor configured to execute instructions. The data capture module is configured to receive work orders or notifications related to one or more parts being replaced within one or more assets of the portfolio. The data integration module is configured to analyze a plurality of received work orders or notifications to generate an asset history, where the asset history includes information regarding replacement of parts within one or more assets of the portfolio. . The age calculation module is configured to calculate the age at replacement for each part type in the portfolio.

In another embodiment of the system, the plurality of program modules analyze the calculated age at replacement for each part type in the portfolio to determine one or more failure patterns associated with each part type. The method further includes a failure pattern analysis module configured to perform a failure pattern analysis module.

In another embodiment of the system, the plurality of program modules are configured to determine a part replacement strategy for each part type based at least on the determined one or more failure patterns associated with each part type. further includes a parts replacement optimization module.

In another embodiment of the system, the plurality of program modules provide a user interface configured to provide a user with recommendations for managing parts replacement schedules and inventory based at least on the determined parts replacement strategy. Including further.

In another embodiment of the system, the data capture module extracts at least one of article movement information, bill of materials information, sensor measurement readings, part repair information, or part cost information from the plurality of received work orders or notifications. further configured to extract one.

In another embodiment of the system, the data integration module determines whether multiple parts of the same part type in the asset are replaced when the asset includes multiple parts of the same part type and less than all of the multiple parts are replaced. further configured to determine the location of the replaced part of the parts.

In another embodiment of the system, the data integration module is configured to group functionally equivalent parts as the same part type when the asset includes multiple functionally equivalent parts with different identifiers. further configured.

In another embodiment of the system, the data integration module is further configured to update a parts replacement schedule for the replaced part when the part is replaced with a functionally equivalent part. In another embodiment of the system, the data integration module is further configured to determine the functional importance of each part within the asset to the operation of the asset upon failure of the part.

In another embodiment of the system, the age calculation module calculates a separate replacement for each part of the plurality of parts based on the position of each part within the asset when the asset includes multiple parts of the same part type. Further configured to calculate time age.

In another embodiment of the system, the calculated age function includes a statistical distribution of ages at replacement of a plurality of parts of each part type within the one or more assets of the portfolio. The statistical distribution of age can be fitted to a Weibull function.

In another embodiment of the system, the failure pattern analysis module is further configured to determine a dominant failure pattern from the one or more failure patterns associated with each part type based on the calculated current age. configured. The one or more failure patterns for each part type include one or more premature failure patterns, random failure patterns, or wear-out failure patterns.

In another embodiment of the system, the parts replacement optimization module is configured to perform one or more of an on-condition maintenance process or determining a part replacement strategy for each part type in the wear failure pattern. Further configured.

In another embodiment of the system, the part replacement optimization module calculates the cost of replacement parts for each part type based on the Weibull output indicating that the failure pattern is a wear-out failure. Further configured to determine a parts replacement strategy.

In another embodiment of the system, the part replacement optimization module determines the expected downtime of an asset due to a failure of a part of a part type within the asset based on the Weibull output indicating that the failure pattern is a wear-out failure. , further configured to determine a part replacement strategy for each part type.

In another embodiment of the system, the parts replacement optimization module performs one of the following: root cause analysis, modification of previous part replacement strategy, or on-condition maintenance process for each part type in the premature failure pattern. or further configured to perform more than one.

In another embodiment of the system, the parts replacement optimization module is further configured to perform an on-condition maintenance process for each part type of the random failure pattern.

In another embodiment of the system, a method for determining an inventory optimization strategy for the replacement of parts within one or more assets of a portfolio, the method comprising: receiving a plurality of work orders or notifications relating to one or more parts; and analyzing the plurality of received work orders or notifications to generate an asset history, the asset history being a portfolio item. and calculating an age at replacement for each part type in the portfolio.

In another embodiment of the system, the non-transitory computer-readable storage medium is a computer-implemented computer-readable storage medium for a scalable automated maintenance optimization system for managing the replacement of parts within one or more assets of a portfolio. The program is configured to store a program including a data acquisition module, a data integration module, and an age calculation module. The data capture module is configured to receive work orders or notifications related to one or more parts being replaced within one or more assets of the portfolio. The data integration module is configured to analyze a plurality of received work orders or notifications to generate an asset history, where the asset history includes information regarding replacement of parts within one or more assets of the portfolio. . The age calculation module is configured to calculate the age at replacement for each part type in the portfolio.

Additionally, any or all of the methods described herein and their associated features may be implemented in whole or in part in any of the systems, devices, or machines described herein, or in any combination or part thereof. may be implemented or performed by all or part of a device system, apparatus, or machine, such as a combination of devices.

It is to be understood that the accompanying drawings are intended to illustrate aspects of various embodiments and may include elements that are not to scale. It should be noted that like reference numbers in different figures refer to the same object.

1 is a diagram illustrating an example of a computing device system, according to an embodiment of the invention. FIG.

FIG. 3 illustrates another example of a computing device system, according to an embodiment of the invention.

1 is a block diagram illustrating an asset age calculation and predictive maintenance management system according to one embodiment of the invention. FIG.

1 is a flowchart illustrating a method for automatically calculating asset age and generating conservation and replacement recommendations, according to one embodiment of the invention.

1 is a block diagram illustrating an asset age calculation and failure analysis system according to one embodiment of the present invention. FIG.

1 is a flowchart illustrating a part failure maintenance decision-making method for a maintenance management system, according to an embodiment of the present invention.

FIG. 2 is a block diagram illustrating an example of an optimal replacement strategy capability of a predictive maintenance management system, according to an embodiment of the present invention.

FIG. 2 is a block diagram illustrating a warranty eligibility module of a predictive maintenance management system, according to one embodiment of the invention.

FIG. 2 is a block diagram illustrating data integration-based optimal parts inventory management capabilities in accordance with one embodiment of the present invention.

FIG. 2 is a block diagram illustrating maintenance plan revision capabilities of a predictive maintenance management system, according to one embodiment of the present invention.

FIG. 2 is a block diagram illustrating an objective benchmarking system extension of a predictive maintenance management system, according to an embodiment of the present invention.

1 is a block diagram illustrating a part risk score calculation system according to one embodiment of the present invention. FIG.

FIG. 7 illustrates an example of an age function associated with block 316 for a part, according to an embodiment of the invention.

FIG. 4 illustrates an example Weibull probability distribution for the part type associated with block 317, according to an embodiment of the invention. FIG. 7 illustrates an example Weibull cumulative distribution function for the part type associated with block 317, according to an embodiment of the invention.

1 illustrates an example graphical user interface for a predictive maintenance management system, according to an embodiment of the invention. FIG.

FIG. 3 is a diagram illustrating an example of a report generation screen of a graphical user interface for a predictive maintenance management system, according to an embodiment of the present invention.

FIG. 3 illustrates an example of a maintenance strategy modification screen of a graphical user interface for a predictive maintenance management system, according to an embodiment of the present invention.

FIG. 3 illustrates an example of a survey options screen of a graphical user interface for a predictive maintenance management system, according to an embodiment of the invention.

FIG. 2 is a diagram illustrating an example of a fishbone diagram used for root cause analysis in a predictive maintenance management system according to an embodiment of the present invention.

1 is a diagram illustrating an example of a graph-based root cause analysis technique used in a predictive maintenance management system according to an embodiment of the present invention. FIG.

FIG. 3 illustrates another example of a maintenance strategy modification screen of a graphical user interface for a predictive maintenance management system, according to an embodiment of the invention.

FIG. 3 illustrates an example of a maintenance analysis screen of a graphical user interface for a predictive maintenance management system, according to an embodiment of the invention.

FIG. 3 is a diagram illustrating an example of a task list management screen of a graphical user interface for a predictive maintenance management system, according to an embodiment of the present invention.

FIG. 3 illustrates an example of a global site view for a predictive maintenance management system, according to an embodiment of the invention.

FIG. 3 illustrates an example of a client site view for a predictive maintenance management system, according to an embodiment of the invention.

1 is a diagram illustrating an example of a client-server architecture for a predictive maintenance management system, according to an embodiment of the invention. FIG.

The present invention provides a system and method for efficiently integrating maintenance management records, automatically calculating the age of each part across a portfolio of assets at scale, and generating predictive maintenance schedules and inventory management strategies. . Note that the invention is not limited to these or any other examples provided herein, which are referred to for illustrative purposes only.

In this regard, in the description herein, certain specific details are set forth in order to provide a thorough understanding of the various embodiments of the invention. However, one of ordinary skill in the art will understand that the invention may be practiced on a more general level without one or more of these details. In other instances, well-known structures have not been shown or described in detail to avoid unnecessarily obscuring the description of various embodiments of the invention.

Throughout this specification, references to "one embodiment," "an embodiment," "exemplary embodiment," "illustrated embodiment," "particular embodiment," etc. means that a particular feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment. Thus, the terms "in one embodiment", "in an embodiment", "in an exemplary embodiment", "in this illustrated embodiment", "in one embodiment", "in one embodiment", "in an embodiment", "in an exemplary embodiment", "in the illustrated embodiment", The appearances of the phrase "in this particular embodiment" and the like are not necessarily all referring to one or the same embodiment. Additionally, the particular features, structures or characteristics of different embodiments may be combined in any suitable manner to form one or more other embodiments.

Unless explicitly stated otherwise or required by context, the word "or" is used in this disclosure in a non-exclusive sense. Further, unless explicitly stated otherwise or required by context, the word "set" shall mean one or more. For example, the phrase "set of things" means one or more of the things.

In the following description, some embodiments of the invention may be implemented, at least in part, by a data processing device system configured by a software program. Such a program may be equivalently implemented as multiple programs, and part or all of such software program may equivalently be constructed in hardware.

Additionally, the phrase "at least" is or may be sometimes used herein merely to emphasize the possibility that other elements may be present besides those explicitly listed. However, unless expressly stated otherwise (such as by the use of the term "only") or required by context, the non-use herein of the phrase "at least" nevertheless expressly including the possibility that other elements may be present in addition to those listed. For example, the phrase "based on at least A" includes the possibility of A as well as one or more other additional elements other than A. Similarly, the phrase "based on A" includes the possibility of A as well as one or more other additional elements other than A. However, the phrase "based only on A" includes only A. Similarly, the phrase "configured to perform at least A" includes configuration for performing A, as well as the possibility of one or more additional actions other than A. Similarly, the phrase "configured to do A" includes configuration to perform A, as well as the possibility of one or more additional actions other than A. However, the phrase "configured to only do A" refers to a configuration for performing only A.

The word "device," the word "machine," the word "system," and the phrase "device system" all refer to one or more physical devices or systems that interact to perform one or more functions. Sub-devices (eg, several pieces of equipment) are intended to be included, regardless of whether such devices or sub-devices are located within the same housing or different housings. However, according to various embodiments, the devices or machines or device systems reside entirely within the same housing, to exclude embodiments in which each device, machine, system, or device system resides across different housings. may be explicitly specified. The word "device" may be equivalently referred to as "device system" in some embodiments.

The term "program" in this disclosure refers to instructions or modules that may be executed by one or more components in a system, such as a controller system or a data processing device system, to cause the system to perform one or more operations. should be construed to include one or more programs, including as a set of programs. The set of instructions or modules may be stored by any type of memory device, such as those described below with respect to memory device systems 130, 251, or both, shown in FIGS. 1 and 2, respectively. . Further, this disclosure describes or may similarly describe that instructions or modules of a program are configured to cause performance of actions. The phrase "configured to" in this context refers to at least (a) instructions or modules (e.g., instructions or modules) that are currently in an executable form by one or more data processing devices to cause performance of an action; is in a compiled, unencrypted form ready for execution), and (b) is in a form not currently executable by the data processing device or devices, but to cause the performance of an action. instructions or modules that can be converted into an executable form by one or more data processing devices (e.g., instructions or modules that are encrypted in a non-executable manner but prepared for execution through performance of a decryption process) ). Such a description should be considered equivalent to describing that the instructions or module are configured to cause the performance of the action. The word "module" may be defined as a set of instructions. The words "program" and "module" can each be interpreted to include multiple subprograms or multiple submodules, respectively. In this regard, references to programs or modules may be considered to refer to multiple programs or multiple modules.

Additionally, it is to be understood that information or data may be influenced, manipulated, or converted into different forms as it moves through various devices or workflows. In this regard, unless explicitly stated otherwise or required by context, references herein to information or data shall include modifications to that information or data. For example, "Data X" may be encrypted for transmission, and references to "Data shall include both. Additionally, the phrase "graphical user interface" as used herein shall include a visual representation presented via a display device system, including computer-generated text, graphics, animation, or any one thereof. and a combination of one or more, which may include one or more visual representations initially generated, at least in part, by an image capture device.

Furthermore, example methods are described herein with respect to FIGS. 4 and 6. Such figures are described as including blocks that relate to computer-executable instructions. Note that each instruction associated with such a block need not be a separate instruction, but may be combined with other instructions to form a combined instruction set. The same instruction set may relate to more than one block. In this regard, the block arrangements shown in method FIGS. 4 and 6 herein are not limited to the actual structure of any program or instruction set, or to the required ordering of method tasks, and are not limited to the actual structure of any program or instruction set, or to the required ordering of method tasks, and may be 4 and 6, the instructions are configured to carry out, e.g., when executed by a data processing device system in conjunction with interaction with one or more other devices or device systems. It just indicates the task.

Additionally, the block diagrams shown in FIGS. 3, 5, and 7-12 illustrate various program modules implemented by computer-executable instructions. Note that each instruction associated with such a program module need not be a separate instruction, but may be combined with other instructions to form a combined instruction set. The same instruction set may be associated with more than one program module. In this regard, the program modules of the block diagrams shown in FIGS. 3, 5, and 7-12 herein may differ from the actual structure of any program or instruction set or required ordering of method tasks. Such block diagrams shown in FIGS. 3, 5, and 7-12, according to some embodiments and without limitation, may be used, for example, with one or more other devices or device systems. It merely indicates the tasks that the instructions are configured to perform when executed by a data processing device system in conjunction with their interaction.

FIG. 1 schematically depicts a system 100, according to some embodiments. In some embodiments, system 100 may be computing device 100 (as shown in FIG. 2). In some embodiments, system 100 includes a data processing device system 110, an input/output device system 120, and a processor-accessible memory device system 130. Processor-accessible memory device system 130 and input/output device system 120 are communicatively coupled to data processing device system 110.

Data processing device system 110 may include one or more devices that, in conjunction with other devices, such as one or more of the devices in system 100, implement or execute control programs associated with some of the various embodiments. Contains multiple data processing devices. Each of the phrases "data processing device," "data processor," "processor," and "computer" refers to a central processing unit ("CPU"), desktop computer, laptop computer, mainframe computer, tablet computer, mobile computer, Processing data, whether implemented in terminals, mobile phones, and electrical, magnetic, optical, biological, or other components shall include any data processing device, such as any other device configured to run, manage, or handle data.

Memory device system 130 includes one or more processors configured to store information, including information needed to execute control programs associated with some of the various embodiments. Contains accessible memory devices. Memory device system 130 is a distributed processor-accessible memory device system that includes a plurality of processor-accessible memory devices communicatively coupled to data processing device system 110 via a plurality of computers and/or devices. could be. On the other hand, memory device system 130 need not be a distributed processor-accessible memory system, and thus may include one or more processor-accessible memory devices located within a single data processing device.

Each of the phrases "processor-accessible memory" and "processor-accessible memory device" may be volatile or nonvolatile, electronic, magnetic, optical, or limited. However, any storage device, whether otherwise, including registers, floppy disks, hard disks, compact disks, DVDs, flash memory, ROM (read-only memory), and RAM (random access memory) shall include a processor-accessible data storage device. In some embodiments, the phrases "processor-accessible memory" and "processor-accessible memory device" each include non-transitory computer-readable storage media. In some embodiments, memory device system 130 may be considered a non-transitory computer-readable storage media system.

The phrase "communicatively connected" shall include any type of connection, whether wired or wireless, between devices, data processors, or programs with which data may be communicated. Additionally, the phrase "communicatively connected" includes connections between devices or programs within a single data processor, devices or programs located within different data processors, and connections located entirely within the data processor. This shall include connections between devices that are not connected to each other. In this regard, although memory device system 130 is shown separately from data processing device system 110 and input/output device system 120, memory device system 130 may be separate from data processing device system 110 or input/output device system 120. Those skilled in the art will appreciate that it may be located entirely or partially within 120. Further, in this regard, although input/output device system 120 is shown separate from data processing device system 110 and memory device system 130, such systems may vary depending on the contents of input/output device system 120. , may be located wholly or partially within data processing system 110 or memory device system 130, as will be appreciated by those skilled in the art. Furthermore, data processing device system 110, input/output device system 120, and memory device system 130 may be located entirely within the same device or housing, or may be located separately between different devices or housings. but may be communicatively connected. When data processing device system 110, input/output device system 120, and memory device system 130 are located within the same device, system 100 of FIG. (ASIC).

Input/output device system 120 may include a mouse, keyboard, touch screen, another computer, or any other device by which desired selections, desired information, instructions, or any other data may be entered into data processing device system 110. May include a combination of devices. Input/output device system 120 may include any suitable interface for receiving information, instructions, or any data from other devices and systems described in various of the embodiments.

Input/output device system 120 may be an image generating device system, a display device system, a speaker device system, a processor-accessible memory device system, or may receive information, instructions, or any other information from data processing device system 110 . It may also include any device or combination of devices from which data is output. In this regard, if input/output device system 120 includes processor-accessible memory devices, such memory devices may or may not form part or all of memory device system 130. Input/output device system 120 may include any suitable interface for outputting information, instructions, or data to other devices and systems described in various of the embodiments. In this regard, the input/output device system may include various other devices or systems described in various embodiments.

FIG. 2 illustrates an example computing device system 200, according to some embodiments. Computing device system 200 may include a processor 250 that corresponds to data processing device system 110 of FIG. 1 in some embodiments. Memory 251, input/output (I/O) adapter 256, and non-transitory storage medium 257 may correspond to memory device system 130 of FIG. 1, according to some embodiments. User interface adapter 254, mouse 258, keyboard 259, display adapter 255, and display 260 may correspond to input/output device system 120 of FIG. 1, according to some embodiments. Computing device 100 may also include a communications interface 252 that connects to a network 253 for communicating with other computing devices 100.

Various methods 400 and 600 may be implemented by associated computer-executable instructions according to some example embodiments. In various exemplary embodiments, a memory device system (e.g., memory device system 130) is a data processing device system (e.g., sometimes referred to herein as "e.g., 110"). 110) and stores a program executable by the data processing device system to cause the data processing device system to perform various embodiments of methods 400 and 600. In these various embodiments, the program may include instructions that implement, or are configured to cause, various of the instructions associated with performing the various embodiments of methods 400 and 600. In some embodiments, methods 400 and 600 may include related blocks or additional subsets of blocks other than those shown in FIGS. 4 and 6, respectively. In some embodiments, methods 400 and 600 may include different sequences shown between various of the related blocks shown in FIGS. 4 and 6, respectively.

In some embodiments of the invention, transaction integrity records may be represented in work orders from an enterprise resource planning (ERP system) and stored in an integrity record storage system. Note, however, that the type of maintenance record is not limited to the type of ERP system or specific asset type or operating industry or geographic location.

FIG. 3 illustrates a predictive maintenance management system 300 that includes an asset age calculation system and a maintenance strategy optimization system 329, according to one embodiment of the invention. In some embodiments of the invention, maintenance records 302 from a client-based maintenance management system or other maintenance records storage system 301 are entered into an asset aging calculation system 329, also referred to as IronMan®, through a data ingestion process 304. may be provided.

In some embodiments, maintenance records 302 may include one or more of a description of work orders, notifications, task lists 904, repair records, article movements 305, measurement readings 306, or bills of materials 307. Item movement 305 indicates which asset parts have been removed from the asset for replacement. The measurement reading 306 is the number of units the asset was in service at the time of the part replacement (e.g., hours, miles, kilowatt-hours, fuel burn, or any other measurement that relates to duty cycle and has a dominant effect on age). value). Bill of materials 307 shows a detailed list of items used in replacing parts. However, it is noted that maintenance records 302 may include other information or data that may be used to calculate asset age.

In some embodiments, maintenance record data is data integrated to perform the preliminary calculations needed to accurately determine the age of various parts across a portfolio of assets using age function 316. It may be integrated via process 308. The age function is explained in detail in a later section of this specification. In some embodiments, these data integration functions include a part replacement event classification function (part replacement event classifier) 312, a part location detection function (part location detector) 309, and a functionally significant component (FSC). It may include one or more of a prediction function (functional importance predictor) 310 or a functionally equivalent item prediction function (functional equivalent predictor) 311.

In some embodiments of the invention, the system automatically creates a hierarchy of parts and assets within the portfolio in the form of an ontology 308B, from the asset level to subassemblies to functionally significant components (FSCs). To construct. This ontology is used for part assignment and by semantic rules for associating physical part locations with activities such as monetary payments, preventive maintenance, and corrective maintenance. When the system onboards a new customer with a new asset type, or an existing customer with a new asset type, the system will add to the system, up to the functionally critical components, into the assembly or subsystem, Automate the construction of physical dependency hierarchies of assets. The FSC may include parts that are subject to failure modes whose effects have safety implications, operational effects, or economic effects and may also be subject to preventive maintenance identified from work order data. The system automatically adjusts FSC components as new data is received, splitting the current FSC into sub-components or aggregating them into higher-level components to separate failure modes or perform preventive maintenance. You can set the most appropriate level for granting. Hierarchies are modeled as ontologies to provide levels of associated semantics that can assist in identifying the locations of parts where an asset may have two or more equivalent parts that are fitted to different locations.

In some embodiments, the part replacement event classification function 312 determines whether the part was replaced as part of a planned maintenance event, including whether the replacement event was a preventive or remedial action. Classify parts based on whether they were replaced as part of an unplanned maintenance event. In some embodiments, the part location function 309 determines the location of the replaced part based on information included in the bill of materials 307, article movement 305, or work order description, for example. For example, parts replacement event classifier 312 may identify an event in which two wheels were replaced on a six-wheel truck, and part location function 309 may identify which two of the six wheels were replaced. In some embodiments, part location detector 309 determines the location of the replaced part based on the description in the notification included in repair information 502 and historical replacement information.

In some embodiments, the functional importance prediction function 310 determines whether a replaced part is important (from the asset's perspective) based on whether the asset can continue to operate despite part failure. Determine whether there is. For example, an oil leak may not prevent the vehicle from operating, but a steering arm failure may prevent the vehicle from operating. In some embodiments, the functionally equivalent prediction function 311 reconciles work orders 302 where equivalent parts are sourced from different manufacturers and therefore have different codes. Note that equivalent parts from the same manufacturer may also have different codes. The functionally equivalent predictor 311 prevents functionally equivalent parts from being grouped separately in the parts grouping process (parts grouper) 313, which leads to inaccurate asset part age calculations. and can result in incorrect parts replacement schedules and strategies.

The data integration function was stored in the maintenance record 302 so that all replacement events for a given part type can be aggregated by the data aggregator 315 prior to calculation of the asset part age distribution by the age calculation function 316. Connect and enrich maintenance event information. This process is not trivial due to the complexity of the asset and therefore the number of interconnected parts that must be tracked in separate maintenance records 302. Moreover, this task is complicated by the fact that the result of the age calculation function 316 only makes sense if it is calculated for a part type and by its location on the asset. When a single part is attached to an asset, determining the location of the replaced part can be simple. However, when there are many instances of a single part type installed on an asset, determining the location is often difficult because the work order 302 may refer to the number of parts being replaced but not their location. Have difficulty.

After one or more of the data integration functions 309, 310, 311, 312 are applied to the data, part replacement events are combined into a parts grouping process 313 to form a complete asset history 314 of the parts within the asset. The asset history 314 is then aggregated via data aggregator 315 into an entire portfolio of assets. While the age of each asset within the portfolio may be determined via measurement readings 306, the age of each part that may be exchanged within the asset must be inferred based on historical exchange dates, which may be due to It will only be accurate if the position is accurately determined by the part position detection function 309. In some embodiments of the invention, information regarding the current age of parts that have not been replaced may also be obtained to more accurately determine the status of parts within the portfolio. In some embodiments, information regarding parts that have not been replaced is included in asset history 314.

In some embodiments of the invention, age calculation function 316 calculates the distribution of age at replacement of each part by part type across the portfolio of operating assets collected by data aggregator 315. In some embodiments, age calculation function 316 first generates an age profile for each part. FIG. 13 shows an example of an age profile for parts. As the asset is used, the age of the part increases. It is possible that parts may not age when the asset is idle, but this may not be the case in all cases. When a part is replaced, the age of the part is reset to 0. In some embodiments, the age calculation function generates an age profile for each part of the assets in the portfolio. The age profile also indicates the current age of the part.

In some embodiments of the invention, age calculation function 316 further generates a distribution of ages at replacement of all parts of the same part type within the asset. In some embodiments of the invention, the same part type may refer to a broad category of parts, such as truck wheels. In some embodiments of the invention, the same part type may refer to a narrower category of parts, such as a left front wheel of a truck. In some embodiments of the invention, the same part type may refer to a narrower category of parts, such as the left front wheel of a truck driven on a dirt road. In some embodiments of the invention, the system allows "part types" to be broadly or narrowly defined to accommodate different use cases for similar parts or assets within a portfolio.

In some embodiments, a fitter, such as Weibull fitter 317, may be applied to the age-at-replacement distribution of all parts of a defined part type obtained from age calculation function 316. Figures 14a and 14b show examples of fitting the Weibull probability distribution function or the Weibull cumulative distribution function to the distribution of ages at replacement of all parts, respectively. The calibrated Weibull function from fitter 317 may then be used to determine failure patterns for the part using failure pattern analysis module 322. It will be clear to those skilled in the art that order probabilities or statistical functions can be used to generate fits to the age-at-replacement distribution of all parts. Failure metrics may be calculated using metric calculator 323 based on the failure pattern of the part. Note that other functions instead of the Weibull function may be used to generate the age-at-replacement distribution 317 for part types.

In some embodiments of the invention, Weibull fitting involves one or more of three parameters that may be used to construct probability and cumulative density functions associated with failure patterns: shape, scale, and location. can bring about In some cases, if multiple failure patterns for the same part are identified, IronMan® may build multiple parameter sets, each with their own failure pattern. Shape parameters allow identification of three basic failure patterns: premature failure, random failure, and wear-out failure. In some embodiments, the system provides maintenance intervention recommendations related to failure patterns. For example, in the case of premature failure, a root cause analysis (RCA) may be performed if a previously determined replacement or maintenance strategy is stopped and it is practical to stop unexpected premature failure until the cause is eliminated. If so, on-condition maintenance may be considered. In the case of random failures, on-condition maintenance processes are applied when practical and cost effective. For wear-out failures, both scheduled replacement and on-condition maintenance are applicable, but scheduled replacement may be more advantageous when the geometric parameters strongly indicate a wear-out failure pattern.

In some embodiments, failure metrics calculated by metric calculator 323 may be used to determine an optimal replacement strategy using strategy optimization process 324 for each part type. In some embodiments, the task list rationalization process 325 may streamline the task list 904 so that each part is optimally stocked and replaced cost-effectively. Insights and recommendations from the strategy optimization process 324 and task list rationalization process 325 may be integrated by an output integration and write function 326 into an update form 303 stored in the client's maintenance management system, for example. In some embodiments, insights and recommendations generated by output aggregation function 326 may be presented to client user 328 via a user interface.

In some embodiments, the calibrated Weibull function 317 provides reliability, availability and maintainability (RAM: (Reliability, Availability and Maintainability) simulation 319. By adding cost elements to RAM simulation 319 and Weibull function 317, lifecycle cost simulation 318 predicts future costs based on existing maintenance processes and suggests alternative outcomes via what-if analysis. It is possible. Output from RAM simulation and analysis 319 and lifecycle cost simulation 318 may be used to generate future parts replacement strategies (forward-looking plans) 321 using equipment modification and replacement forecasting process 320. In some embodiments, strategy optimization process 324 may utilize information generated by equipment modification and replacement prediction process 320. Forward planning 321 can supplement or augment the insights and recommendations generated by output integration function 326.

IronMan® system 329 is an exemplary asset part age calculation and predictive maintenance management system that includes an implementation of the processes and functions 304-326 shown in FIG.

FIG. 4 illustrates a method 400 for integrating maintenance records and automating age function calculations, according to some embodiments of the invention. In some embodiments, in step 405,
Data capture process 304 is used to capture security record data 302 . In step 410, work instruction data regarding article movement 305 or parts list 307 is extracted from maintenance record data 302. At step 415, measurement data 306 is extracted from maintenance record data 302. The extracted data is then analyzed using a data integration function. The analysis and data integration step 430 performs the data integration process 308 using various data integration functions 309 , 310 , 311 , 312 and uses the parts grouping process 313 to generate an asset history 314 . group. The data is then aggregated across the portfolio in step 425 using data aggregator 315. At step 430, age calculation function 316 is used to calculate the age at replacement distribution of each part type across the portfolio. At step 435, a failure metric is derived by performing failure pattern analysis module 322 and metric calculation 323 on the derived age at replacement distribution. At step 440, an optimal maintenance strategy is calculated using strategy optimization function 324 and task list rationalization function 325 based at least on the derived failure metrics. At step 445, maintenance process recommendations are generated.

FIG. 5 depicts a block diagram of a data integration and failure analysis system 500 as applied to a single work order 302, according to one embodiment of the invention. In some embodiments, the age calculation function 316 is initialized using information from the client maintenance management system or other maintenance database system 301, including all historical maintenance or work order records 302. In this regard, system 500 provides an example overview of the analysis performed by IronMan® system 329 at the level of a single work order 302. Detection of replaced parts by part location detector 309 and classification of replacement as planned or unplanned by part replacement event classifier 312 are based on notifications contained in repair information 502. It may be derived using natural language processing algorithms, and this may be recorded as plain text by the field worker performing the repair. In some embodiments, functionally equivalent parts are identified (using a predictor 311) based on article movement 305 as well as the cost of the part 501 (because the costs of functionally equivalent parts often tend to be similar). ) can be predicted.

In some embodiments, functionally important parts (using function 310) are determined from article movement 305 and bill of materials 307, which, for example, excludes consumables from age calculation function 316 analysis. In some embodiments, the age 503 of parts replaced in work order 302 is calculated using measurement readings 306. If the measurement readings do not include part operating time, which is often entered manually, part age 503 may be estimated based on the age of the asset and date of last replacement. In some embodiments, measurement readings for one or more parts may be provided by a sensor and the values included in the analysis. In some embodiments, the aggregator 313 may aggregate all replacement ages 503 of functionally equivalent parts across a portfolio of assets to generate a respective age calculation function 316. In some embodiments of the invention, a Weibull distribution 317 is then fitted to the age function 316 to determine failure patterns.

Premature failures 506, random failures 504, and wear-out failures 505 are each subjected to root cause analysis 508 to determine the cause of the failure, as well as on-condition analysis 509 to support the investigation conducted by root cause analysis 508. may be received. These analyzes can be used to detect early failures, especially if they are unexpected or predicted to be premature or random.
06 and random faults 504 were correctly diagnosed. However, in some embodiments, if failures are identified as premature or random, they may be excluded from future calculations by exclusion filter 507 because they require a different analysis. Often, maintenance processes are ineffective against random failures 504 and premature failures 506 that may be caused by the manufacturer 609 or maintenance team that installed the part. The results of exclusion filter 507 help inform inventory requirements used by task list rationalization process 325. For wear-out failures 505, root cause analysis 508 may assist in recommending an optimal time-based replacement strategy using strategy optimization process 324.

In some embodiments, wear-out failures 505 may also be used to simulate future maintenance and operating costs with lifecycle cost simulation 318, which also influences optimal replacement strategy process 324. The optimized replacement strategy process 324, in conjunction with random failing part identification 507, determines optimal inventory requirements and generates insights and recommendations for the user. In this regard, the predictive maintenance management system 300 reduces cost of ownership by optimizing parts maintenance and replacement while increasing asset availability for beneficial use, increasing reliability and reducing disruptions. Generate an exchange strategy that aims to

FIG. 6 illustrates a method 600 for a decision-making process that guides analysis of part failures, according to some aspects of the invention. A flowchart of method 600 illustrates how warranty claims, part failures, and maintenance actions may be coordinated according to some embodiments of the invention. At step 601, part failures are recorded. At step 602, it is determined whether the part qualifies for a warranty claim. If so, the original equipment manufacturer (OEM) is contacted at step 620 to file a warranty claim. If the part is not eligible for warranty (No at step 602), an initial analysis is performed at step 603 to determine failure patterns. In some embodiments, the failure pattern in step 603 is determined by performing failure pattern analysis process 322. If the failure pattern is determined to be random in step 603, it may not affect the planning of the replacement strategy. In some embodiments, at step 615, inventory is optimized to have a sufficient number of replacement parts based on historical failures determined by task list rationalization process 325. If the part failure is determined to be due to wear in step 603, then the functionally significant parts process 310 is performed in step 604 to determine whether the asset can still be put into service. If the asset cannot be put into service (No at step 604), replacement is scheduled immediately at step 606. If the asset can be placed into service (Yes in step 604), then in step 605 it is determined whether the planned replacement has already been scheduled. If no replacement is planned (No in step 605), a replacement is scheduled in step 606. Otherwise (Yes in step 605), the replacement clock for the part is reset in step 607 to prevent the part from being replaced prematurely as part of a scheduled maintenance plan.

At step 608, once the replacement is scheduled, a root cause analysis process 508 may occur. In some embodiments, the root cause analysis process 508 may be performed if the failure pattern is identified as early in step 603 or if the frequency and impact of failures is determined to be significant in step 603. At step 609, it is determined whether the root cause analysis 508 leads to any conclusions that may impact maintenance schedules or failure prediction. At step 610, the results of the root cause analysis process 508 performed at step 608 are implemented. In some embodiments, the OEM may be contacted at step 620 in the case of a potential warranty claim.

FIG. 7 illustrates a block diagram of a system for determining an optimal replacement strategy based on a generated age-at-replacement function, according to some embodiments of the invention. A predictive maintenance management system 300, such as the IronMan® system 329, extracts, integrates, and processes transactional and sensor data to create a part replacement history for each part on an asset. In some embodiments, transaction data may be provided by security records 302 and sensor data may be provided by measurement readings 306. In some embodiments, maintenance records 302 may include information regarding what maintenance events have occurred or will occur, such as article movements 305 and repair information 502. Maintenance records 302 may also provide context about maintenance events (e.g., if the engine fails, a new engine part is replaced, an oil leak from the cylinder head at number 5, or a bearing failure at the connecting rod at number 10, etc.) (can be ordered with a description of the defect). In some embodiments, the measurement readings 306 may include the duty cycle of the part derived from sensor data onboard assets (e.g., the fuel burn rate is the pulse width from each fuel injector that supplies fuel to the engine). (or the time the engine is running may be calculated using an engine speed sensor relative to a reference clock within an electronic control unit on the asset). Maintenance records 302 and measurement readings 306 provide supplemental information (maintenance events and context from maintenance records 302 and duty cycle information from readings 306) that are integrated to obtain age function 316.

In some embodiments of the invention, predictive maintenance management system 300 evaluates current part replacement and maintenance strategies against a generated part replacement history to determine an optimal replacement strategy. Determining the age at part replacement using the age calculation function 316 is important for generating an optimal replacement strategy in the strategy optimization process 324. A failure pattern analysis module 322 within the metric calculator 323 utilizes the age at replacement of parts across a portfolio of assets to derive failure metrics that determine whether the part type is eligible for a planned maintenance strategy. 704 is required. If the part type qualifies for a planned maintenance strategy, failure pattern analysis module 322 determines potential replacement time. Optimization of replacement timing in the strategy optimization process 324 may be based on recognition of maintenance and downtime costs 703. In some embodiments, maintenance and downtime costs 703 may be determined from site operational characteristics 701 and cost metrics 501 and maintenance downtime metrics 702 derived from asset history 314.

FIG. 15 shows an example graphical user interface 1500 for displaying a determined optimal exchange strategy, according to some embodiments of the invention. In some embodiments of the invention, a user can select and view one or more assets for which he or she is responsible. In some embodiments of the invention, the first screen of user interface 1500, shown in FIG. 15, displays a list of parts for a particular asset (eg, trial truck). In some embodiments, the displayed list of parts includes one or more of part number 1510, part description 1520, part cost 1530, current maintenance strategy 1540, recommended maintenance strategy 1550, and user action 1560. include.

Part number 1510 is a unique identifier for each part, which may be set by the user and available in maintenance record 302 or set by IronMan® system 300. Part description 1520 describes the part type and may include other information such as OEM name and OEM part number. Part cost 1530 may include the cost of a part from a particular supplier or the average cost of a part over a period of time or across multiple suppliers. Current maintenance strategy 1540 reflects the current part replacement and maintenance strategy for each part type in the system. Recommended maintenance strategy 1
550 reflects the optimal part replacement and maintenance strategy determined by predictive maintenance management system 300 for each part type in the system. A user can use graphical user interface 1500 to take several actions for each part type.

In some embodiments, graphical user interface 1500 uses part risk scores 1205 and information from Weibull fitter 317 to determine the order in which parts are displayed in the table shown in graphical user interface 1500. and functionally important parts 310. This feature assists the user in prioritizing tasks for action within the graphical user interface 1500. For example, system 300 may first identify all parts that have maintenance strategy change recommendations. Of these identified parts, the system may then further identify hazardous or functionally important parts and associate them with higher priority for display in the top row of the table. Often, an asset can have thousands of parts, and using information such as part risk score 1205, information from Weibull fitter 317, and functionally important parts 310 is useful in a graphical user interface. Usability can be greatly improved. Users can filter, search, and sort the list of parts with recommendations for changing maintenance strategies. The user can also select a single part to view a more detailed list of recommendations for that part (each part can have more than one recommendation), as shown in Figure 16. ). Data within the table can be exported for offline analysis. System 300 can also generate load sheets that can be sent to client worksite 1101 to update maintenance strategies stored in local or central maintenance transaction systems. The report may be fed back to a transaction system (eg, security record storage system 301 ) to update its master data, including task list 904 .

FIG. 16 illustrates an example report generation screen 1600 of user interface 1500, according to some embodiments of the invention. Report generation screen 1600 allows a user to generate a report that shows how recommendations are derived from part event history to provide technical justification and an audit trail for downstream decisions. do.

In some embodiments, user actions 1560 include approvals 1561, modifications 1562, and investigations 1563. If the user agrees with the recommended parts replacement and maintenance strategy 1550, the user can accept it by clicking the accept button 1561. For example, as shown in FIG. 15, the current maintenance strategy 1540 for the first part on the displayed list, part number 88891519, is to replace the part when it fails. The recommended maintenance strategy 1550 from the predictive maintenance management system 300 is to change this part at 13,000 hours of use. If the user finds this change acceptable, the user can click on the accept button 1561 for this part and the predictive maintenance management system 300 will change the current maintenance strategy for this part to "until failure". It is possible to automatically change from "operation" to "replace after 13,000 hours". In some embodiments, selecting the accept button 1561 displays a report generation screen 1600 for the selected part.

Alternatively, the user can click the modify button 1562 or the investigate button 1563 to potentially change the system's part replacement and maintenance recommendations. FIG. 17 illustrates an example maintenance strategy modification screen 1700 of user interface 1500, according to some embodiments of the invention. Maintenance strategy modification screen 1700, in some embodiments, includes a strategy modification interface 1710, information about replacement events 1720, age at replacement distribution 317, and strategy optimization results (cost function) 1730. In some embodiments, the strategy modification interface 1710 includes details describing the characteristics of the failure pattern and the justification for the recommended part replacement and maintenance strategy 1550, information about the recommended part replacement and maintenance strategy 1550, and information about the recommended part replacement and maintenance strategy 1550. and various options for modifying the maintenance strategy 1550. For example, if the recommended part replacement and maintenance strategy 1550 is to replace the part at 20,000 hours based on estimated downtime costs 1730, the user may want to replace the part at 30,000 hours instead of the recommended 20,000 hours. The recommendation may be modified to replace the part at any time, or a different replacement strategy may be selected, such as run-to-failure or on-condition maintenance.

In some embodiments, the graphical user interface allows the user to determine the exchange events 1720 that will be used to generate the distribution 317 through some mechanism, such as outlier detection or user-selectable date ranges. allow it to be corrected. This interactive filtering of the timeline of exchange events 1720 allows the user to perform what-if functions that may be used to identify value opportunities for root cause analysis. For example, in the exchange event 1720 shown in the example of FIG. 17, the user may elect to exclude old events prior to April 2017 from the analysis. In response, system 300 automatically reruns the age calculation function to generate a new theoretical Weibull cumulative distribution to exclude old events, and reruns strategy optimization results 1730. Therefore, users can easily simulate the effects of various filtering criteria. Another what-if function allows the user to modify some inputs to the strategy optimization 1730, such as the cost of downtime 703 or the time it takes to complete the work, maintenance, and downtime metrics 702. It can be provided by Using different inputs or factors changes the optimal strategy in terms of associated curves and costs. The user bases the user's decision to modify the recommended parts replacement and maintenance strategy 1550 on one or more of information about replacement events 1720, age at replacement distribution 317, and strategy optimization results 1730. obtain. Information about replacement events 1720 indicates when historical part replacements were performed, the current strategy, the new strategy, and when predicted part replacements will be performed under the new strategy. In some embodiments, information about replacement events 1720 includes information about new strategies and predicted maintenance events when a user modifies a new strategy (recommended parts replacement and maintenance strategy 1550) using strategy modification interface 1710. It will be updated automatically as shown. In some embodiments, the age-at-replacement distribution 317 is a calculated distribution indicated by the shaded space around the predicted function curve 317 in addition to the cumulative failure distribution of the part over the life of the part. A Weibull function is fitted that represents a reliability measure. Strategy optimization results 1730 shows optimization results for selected parts based on factors such as replacement part cost and downtime.

There may be multiple factors that can contribute to the user's decision to modify the recommended parts replacement and maintenance strategy 1550. In some embodiments, the recommended parts replacement and maintenance strategy 1550 may be based on the lowest total cost predicted by the strategy optimization results 1730. However, the wider confidence range (width of the shaded area around curve 317) may correlate with the sparsity of the historical parts replacement data. Human factors such as the availability of maintenance personnel to perform part replacements, safety concerns, or legal regulations may also influence a user's decision to modify recommended part replacement and maintenance strategy 1550.

In some embodiments of the invention, a user can test different optimization factors (cost and time) to find an appropriate maintenance strategy for a part based on his or her preference for risk. In some embodiments, after the user modifies and accepts the recommended part replacement and maintenance strategy 1550, a report generation screen 1600 for the selected part is displayed.

Returning to FIG. 15, in some embodiments, the user may select the investigate button 1563 to initiate root cause analysis (RCA) before approving or modifying the recommended maintenance strategy 1550. In some embodiments, upon selecting the survey button 1563, the graphical user interface displays the survey options screen 1800 shown in FIG. 18. In some embodiments, investigation options screen 1800 includes buttons to initialize the RCA and modify the current or recommended strategy using maintenance strategy modification screen 1700. In some embodiments, survey options screen 1800 is displayed in the form of a pop-up window.

In some embodiments of the invention, selecting the "Start RCA" button on the investigation options screen 1800 affects the determined failure patterns (early failures 506, random failures 504, and wear-out failures 505) for the part. A root cause analysis process 508 is initiated to determine if there is an unexpected or undesirable underlying problem that is causing the problem. FIG. 19 shows an example of a simple fishbone diagram 1900 that may be used to perform RCA. Cause and effect diagram 1900 includes various factors grouped into different categories that may be selected to identify the root cause of a failure. For example, in the example shown in FIG. 19, the root cause analysis may identify design and manufacturing issues and environmental issues as potential causes or contributing factors associated with the failure of the part. This process of identifying contributing factors may include decomposing the part to a further atomic level and understanding various design, usage, and operational contexts. For example, autonomous assets are less likely to have fatigue as a contributing factor because they are not driven by people. The user can navigate the fishbone diagram 1900 to add new branches that involve new groupings of contributing factors and add additional factors to each branch as the various fishbone chains are explored and navigated. It can be fixed.

In some embodiments, root cause analysis process 508 includes graphical data structures for identifying and storing information regarding conditions and evidence. For example, as shown in Figure 20, to facilitate and record more detailed RCA, including breaking down causes into conditions and actions, and allowing for the association of evidence and insights with RCA. , graph 2000 may be used. Evidence can include rich media, such as images, audio, or video. In the example shown in FIG. 20, a traction motor has been identified as having premature failure caused by a short circuit to ground. Evidence of the cause is provided by images of burnt out windings. The RCA process follows various characteristic factor chains to determine underlying conditions that may contribute to failure and potential remedial actions to eliminate these conditions or causes. In the example shown in FIG. 20, the RCA process may query a database to determine potential causes of the short circuit, ie, motor overload or electrical insulation breakdown. Further queries may be generated to obtain more detailed cause information, i.e. overloading of an individual motor may occur due to the unavailability of other motors in parallel or the absence of a warning system. . The RCA process can also identify remedial actions that can be taken to eliminate these causes, ie, adding automatic shutdown control systems, operator training, or warnings.

This information is automatically generated using a cause information database that stores associations between observed failures, evidence supporting those failures, conditions or causes that contribute to those failures, and remedial actions. can be generated. Transaction information, such as that stored in client ERP system 301 and sensor information 306, may be used to query and prune graphs to generate probable causes for observed failure patterns. In some embodiments, the root cause analysis process 508 may include determining whether an RCA has been previously performed on a similar part or a similar failure. Transactions related to a current failure of a part to determine whether the current failure has a similar cause to a previous failure or if a new RCA is required to determine potential new causes and sensor data may be compared to historical information regarding previous RCAs. Historical data may be filtered by timeline to observe new emerging trends in failure modes and percentage changes as improvements may be made to reduce undesirable causes of failure.

In some embodiments, a user may select a modify strategy button on investigation options screen 1800 to display maintenance strategy modification screen 1700 shown in FIG. 21. In the example shown in FIG. 21, system 300 determines a random failure pattern, for which the heuristic rule suggests that the correct action is to consider an on-condition maintenance strategy. However, the information regarding replacement events 1720 is sparse and includes two failure events that were very early in the life of the part. The thickness of the shaded confidence band in distribution 317 also indicates that the sample size is small and the random failure mode predicted by the Weibull distribution may be incorrect. These observations should be followed by an RCA process to determine if the premature failure had other causes that may have been improved, requiring modification of the recommended maintenance strategy 1550. It can be shown that For example, if the premature failure event was caused by operator error corrected by proper training, the new maintenance strategy 1550 would Rather than replacing parts every 20,000 hours.

In some embodiments, a user may elect to generate a temporary, mitigating on-condition maintenance strategy to stem the effects of premature failure while RCA discovery preventive or remedial actions are implemented. Once the root cause of premature failure has been eliminated or reduced, wear conservation and parts replacement strategies can be employed.

In some embodiments, graphical user interface 1500 includes various sorting and filtering criteria that a user can use to display a determined optimal replacement strategy for a part. The user can use the export button 1570 to export the displayed recommendations. You may choose to export to a file such as a csv (comma separated values) file. In some embodiments, predictive maintenance management system 300 sorts the listed parts to collate and prioritize representations of parts where current maintenance strategy 1540 and recommended maintenance strategy 1550 do not match. In some embodiments, the user interface 1500 may highlight parts where the current maintenance strategy 1540 and the recommended maintenance strategy 1550 do not match, use a different font, or otherwise indicate that there is no change in the recommended maintenance strategy. The part with the change recommendation may be displayed in a different part of the user interface than the part. In some embodiments, a user may filter or sort the displayed list of parts based on his or her criteria of priority of risk of the listed parts. Users may exercise their own judgment in what constitutes a priority in a changing business context.

In some embodiments, predictive maintenance management system 300 may include: To avoid wasting part life by unnecessarily changing parts when the part is replaced with a functionally equivalent part, The age of functionally equivalent parts is compared to the age required by the parts replacement schedule and the maintenance plan 1003 is updated. FIG. 22 shows an example of a maintenance analysis screen 2200 included in graphical user interface 1500. In some embodiments, the maintenance analysis screen 2200 is calculated using, for example, an age function 316 to collate and prioritize the display of maintenance items 2210 that may be unnecessary and result in waste. Sort the part replacement schedules by highest percentage of wasted life 2230 or by scheduled replacement date 2220. In some embodiments, the user may select an action 2240 to reset the age clock 1006 to skip the scheduled exchange or investigate further.

In some embodiments, predictive maintenance management system 300 determines the set of parts to be replaced from asset history 314. The set of parts to be replaced is compared to at least one of a parts task list, a parts inventory, or a parts replacement schedule to determine part utilization in the portfolio of assets. Task list rationalization process 325 adjusts the parts order schedule and task list based on the determined parts utilization to avoid over-ordering or under-ordering parts. FIG. 23 shows an example of a task list analysis screen 2300 included in the graphical user interface 1500. In some embodiments, the task list analysis screen 2300 uses, for example, a series of filters 2310 to collate and prioritize the display of parts 2320 that may or may not be included in the task list. Then, the parts usage rate 2330 is sorted. In some embodiments, the user may select an action 2340 to modify the quantity of parts on the task list.

FIG. 8 shows a block diagram for a warranty determination system 800 for determining warranty eligibility, according to some embodiments of the invention. Determining whether a failed part qualifies for a warranty claim due to lack of visibility in the client's maintenance management system 301 showing when the part was last replaced and therefore how old the part is now Therefore, the information generated by age calculation function 316 is important. Asset history 314 can provide useful information for making warranty recommendations 803 by accurately determining the age at replacement of parts flagged as failing 805 in asset history 314 . Warranty eligibility 810 may be determined by checking that warranty recommendation 803 has not yet been claimed by comparing to claimed warranty 804 . In some embodiments, warranty eligibility 810 is further based on warranty criteria 802 shown in OEM database 801.

FIG. 9 shows a block diagram for an optimal parts inventory determination system 900, according to some embodiments of the invention. In some embodiments, optimal parts inventory 903 is determined based on task list rationalization process 325. Parts inventory 901 is compared to current task lists 904 in task list rationalization process 325 and bill of materials 307 needed to satisfy those task lists. The parts and content usage consistency analysis process 902 determines which parts are over-used or under-used and therefore over- or under-ordered and over- or under-stocked based on the task list 904 maintained by the task list rationalization process 325. Identify what could be. If a part is not frequently needed or used and is overstocked, the IronMan® system 329 may, for example, recommend that the part be ordered less frequently or not at all. Conversely, if a part is used regularly and is understocked, then in accordance with task list rationalization process 325, IronMan® system 329 may recommend that more of that part be ordered. Recommendations generated by the IronMan® system 329 may be used to determine the optimal parts inventory 903 for the site and generate an optimal task list 905 even if a current task list 904 does not exist. .

FIG. 10 shows a block diagram of a system 1000 for updating maintenance plans, according to some embodiments of the invention. A revised maintenance plan 1003 is required whenever a part failure 1010 is assumed to have occurred before the current scheduled maintenance plan 1002 and the part is replaced. If the age of the part is not reset by the age clock reset process 1006, the part will most likely be replaced prematurely under the current maintenance plan 1002. In some embodiments, the IronMan® system 329 supports this functionality and assists the user in prioritizing the age clocks that should be reset by the age clock reset process 1006 and from the asset history 314. A revised maintenance plan 1003 is generated based on the analysis of the current maintenance plan 1002 and part failures 1010. In some embodiments, the IronMan® system 329 includes detailed information (through data integration 308) in the parts database 1001 about how the parts are connected or are functionally equivalent 311. , thus the part failure 1010 can be matched with the current maintenance plan 1002.

FIG. 11 illustrates a system 1100 for objectively benchmarking multiple sites 1101, according to some embodiments of the invention. Without objective performance and reliability metrics generated by metric calculator 323, it is difficult for capital intensive operations to benchmark their sites. Objective benchmarking 1103 is the first step for continuous improvement and is important because it is difficult to perform at site 1101 due to quality issues with maintenance data 301 and fluctuating maintenance actions. In some embodiments, the IronMan® system 329 resolves quality issues in the maintenance data 301 for multiple sites 1101 and provides objective benchmarking 1103 among the sites 1101 for each site 1101. provides the same performance and reliability metrics 1110. Objective benchmarking 1103 allows sites 1101 to quickly identify where to focus efforts to improve performance and reliability metrics 1110, as well as learn best practices from successful sites. can.

FIG. 12 illustrates a system 1200 for calculating a part risk score 1205, according to some embodiments of the invention. Although the system identifies functionally critical components, part risk provides additional information that can be used to prioritize corrective actions. Hazard utilizes one or more of Weibull distribution 317, work order frequency 1201, parts cost 501, labor cost 1202, and cost of lost production and disruption 1203 to calculate a hazard score. . Several factors affect the risk score. The impact of a failure can be characterized by a mix of parts costs, labor costs for remedial work, and costs equivalent to lost production time while the asset is unavailable. The frequency of failure events may be a combination of the B-20 age from the Weibull distribution and the number of preventive or remedial work orders per unit time. The detectability of an occurring failure can be derived from asset history work orders and notifications, ranging from "the failure was sudden and with no prior warning to the operator or maintenance personnel" to "the failure exhibits many different failure symptoms as they slowly worsen over time, the symptoms are obvious to operations or maintenance staff, and, prior to final failure, they can plan and schedule remedial maintenance to minimize disruption to operations. There is a severity range from ``There was sufficient time to begin the process.'' An example of a failure symptom may be an increase in noise, heat, vibration, odor or other visual indication of an impending failure.

In some embodiments, the risk score function 1204 from the work order frequency 1201 for the part, the Weibull statistics generated using the Weibull fitter 317, the cost of the part 501, and the labor cost to service the work order. 1202 and the cost of lost production and disruption in case of failure 1203 may be used to generate a part risk score 1205. Work order frequency 1201 is determined from processed work order data 302 and asset history 314. In some embodiments, the calculation of risk score 1205 is weighted using B-20 information provided from Weibull fitter 317. The B-20 information relates to the age at which 20% of the part units in the population are likely to fail, which helps capture the negative effects of premature failure 506. Parts cost 501 is extracted from client ERP system 302. Part risk score 1205 is important because it adds a layer of risk management to the optimal parts inventory maintained by task list rationalization process 325 by considering the distribution, impact, and cost of failures in the inventory determination process.

FIG. 24 illustrates an example of a global site view for a predictive maintenance management system, according to one embodiment of the invention. Global site operations for one or more clients may be connected to the IronMan® system 329 using, for example, a client-server architecture. In the example shown in FIG. 24, there are four clients, each client having multiple sites 1101. In some embodiments, the sites (which may be mining areas, locomotive factories, etc.) are in different global and/or national geolocations. There may be many sites 1101 within the country. In some embodiments, data may be stored locally at each site or in a central client repository for each client. The arrows in Figure 24 represent data coming to the central repository. IronMan® system 329 connects to central repository 301 to perform maintenance analysis tasks. In some embodiments, there may be no central repository 301 and data is stored locally at each site. In these embodiments, IronMan® system 329 connects to local repository 301 to perform maintenance analysis tasks. In some embodiments, client data may be stored on an on-premises server or in the cloud, with the IronMan® system 329 working with either system. In some embodiments, client data remains isolated from other clients for security and intellectual property reasons, which may be specific client requirements, for example. However, it is also easy to share data across clients, for example to provide additional context or benchmarking analysis, which is a requirement from multiple clients.

FIG. 25 illustrates an example of a client site view for a predictive maintenance management system, according to an embodiment of the invention. The example site view of FIG. 25 shows at the top left two example assets 2510 (excavator and truck) that are operating and collecting sensor data while working. Sensor data is recorded and stored in client repository 301. Asset 2510 (eg, the truck at the bottom left of FIG. 25) may enter a maintenance yard for maintenance work, with old part 2520 coming off and new part 2530 moving. Transaction data icons indicate many things from triggering maintenance to actually performing maintenance (notifications, work orders, task lists). All of this information is then recorded in local client data 301 for that site. This client data 301 can then be provided to a global client data repository 301 or accessed directly by the IronMan® system 329. As mentioned above, the IronMan® system 329 can also access multiple instances of local data in the absence of a global system (dotted line in FIG. 25). All of this data is then fed into the IronMan® system for analysis and then fed back to client offices and sites to improve maintenance.

FIG. 26 illustrates an example of a client-server architecture for a predictive maintenance management system, according to one embodiment of the invention. More specifically, FIG. 26 shows an example of how client data 301 is transferred to IronMan® system 329 from a data communications perspective. Client data 301 is transferred to IronMan® system 329 via a secure connection, such as a secure file transfer via SFTP/HTTPS. ETL processes and data integration into the database occur within the IronMan® system 329. In some embodiments, the IronMan® system 329 is deployed via a cloud service, such as AWS, and is accessible by clients via a web portal. Client access is secure and authenticated. The IronMan® analysis screen in the upper right corner of FIG. 26 is the user interface for the client to interact with the IronMan® system 329.

While the invention has been illustrated by way of description of embodiments thereof and embodiments have been described in considerable detail, it is not intended that the scope of the appended claims be limited or in any way limited to such detail. This is not the intention of the applicant. Additional advantages and modifications will readily appear to those skilled in the art. The invention in its broader aspects is therefore not limited to the specific details, representative apparatus and method, and illustrative examples shown and described. Accordingly, departures may be made from such details without departing from the spirit or scope of applicants' general inventive concept.

Claims (40)

A scalable automated maintenance optimization system for managing replacement of parts within one or more assets of a portfolio, the system comprising:
at least one computer-accessible storage device configured to store instructions;
communicatively connected to the at least one computer-accessible storage device and when executed;
a data ingestion module configured to receive a plurality of work orders or notifications related to one or more parts being replaced within the one or more assets of the portfolio;
a data integration module configured to analyze the received plurality of work orders or notifications to generate an asset history, the asset history being a part of the one or more assets of the portfolio; a data integration module containing information about the exchange of;
an age calculation module configured to calculate an age at replacement for each part type in the portfolio; and at least one processor configured to execute instructions for providing a plurality of program modules including: , a scalable automatic maintenance optimization system. The plurality of program modules are configured to analyze the calculated age at replacement for each part type in the portfolio to determine one or more failure patterns associated with each part type. further including a failure pattern analysis module,
The scalable automatic maintenance optimization system of claim 1. a parts replacement optimization module, wherein the plurality of program modules are configured to determine a part replacement strategy for each part type based at least on the determined one or more failure patterns associated with each part type. further including,
The scalable automatic maintenance optimization system of claim 2. The plurality of program modules further include a user interface configured to provide a user with recommendations for managing parts replacement schedules and inventory based at least on the determined parts replacement strategy.
The scalable automatic maintenance optimization system of claim 1. the data capture module extracts at least one of article movement information, bill of materials information, sensor measurement readings, part repair information, or part cost information from the received plurality of work orders or notifications; Furthermore, it is composed of
The scalable automatic maintenance optimization system of claim 1. The data integration module is configured to determine which of the plurality of parts of the same part type in the asset if the asset includes a plurality of parts of the same part type and less than all of the parts of the plurality of parts are replaced. further configured to determine the position of the replaced part of the
The scalable automatic maintenance optimization system of claim 1. The data integration module is further configured to group the plurality of functionally equivalent parts as the same part type if the asset includes a plurality of functionally equivalent parts with different identifiers;
The scalable automatic maintenance optimization system of claim 1. the data integration module is further configured to update a parts replacement schedule for the replaced part when the part is replaced with a functionally equivalent part;
The scalable automatic maintenance optimization system of claim 7. the data integration module is further configured to determine the functional importance of each part within the asset to the operation of the asset upon failure of the part;
The scalable automatic maintenance optimization system of claim 1. The age calculation module is configured to calculate a separate age at replacement for each part of the plurality of parts based on the position of each part within the asset when the asset includes a plurality of parts of the same part type. further composed of
The scalable automatic maintenance optimization system of claim 1. the calculated age function includes a statistical distribution of the ages at replacement of a plurality of parts of each part type within the one or more assets of the portfolio;
The scalable automatic maintenance optimization system of claim 1. said statistical distribution of age is fitted to a Weibull function;
The scalable automatic maintenance optimization system of claim 1. the failure pattern analysis module is further configured to determine a dominant failure pattern from the one or more failure patterns associated with each part type based on the calculated age at replacement;
the one or more failure patterns for each part type include one or more premature failure patterns, random failure patterns, or wear-out failure patterns;
The scalable automatic maintenance optimization system of claim 2. the one or more failure patterns for each part type include one or more of a premature failure pattern, a random failure pattern, or a wear-out failure pattern;
the parts replacement optimization module is further configured to perform one or more of an on-condition maintenance process or determining the part replacement strategy for each part type in the wear-out failure pattern;
4. The scalable automatic maintenance optimization system of claim 3. The part replacement optimization module determines the part replacement strategy for each part type based on a cost of replacement parts for each part type based on a Weibull output indicating that the failure pattern is a wear-out failure. further configured as,
15. The scalable automatic maintenance optimization system of claim 14. The part replacement optimization module determines for each part type based on the expected downtime of an asset due to a failure of a part of the part type within the asset, based on a Weibull output indicating that the failure pattern is a wear-out failure. further configured to determine the part replacement strategy of;
15. The scalable automatic maintenance optimization system of claim 14. the one or more failure patterns for each part type include one or more of a premature failure pattern, a random failure pattern, or a wear-out failure pattern;
and wherein the parts replacement optimization module performs one or more of a root cause analysis, a modification of a previous part replacement strategy, or an on-condition maintenance process for each part type of the premature failure pattern. Furthermore, it is composed of
4. The scalable automatic maintenance optimization system of claim 3. the one or more failure patterns for each part type include one or more of a premature failure pattern, a random failure pattern, or a wear-out failure pattern;
and wherein the parts replacement optimization module performs one or more of a root cause analysis, a modification of a previous part replacement strategy, or an on-condition maintenance process for each part type of the premature failure pattern. Furthermore, it is composed of
4. The scalable automatic maintenance optimization system of claim 3. A method for determining an inventory optimization strategy for replacement of parts within one or more assets of a portfolio, the method comprising:
receiving a plurality of work orders or notifications related to one or more parts being replaced within the one or more assets of the portfolio;
analyzing the received plurality of work orders or notifications to generate an asset history, the asset history including information regarding replacement of parts within the one or more assets of the portfolio; to analyze and
and calculating an age at replacement for each part type in the portfolio. A non-transitory computer-readable storage medium configured to store a program executed by a computer for a scalable automated maintenance optimization system for managing the replacement of parts within one or more assets of a portfolio. The program is:
a data ingestion module configured to receive a plurality of work orders and notifications related to one or more parts replaced within the one or more assets of the portfolio;
a data integration module configured to analyze the received plurality of work orders and notifications to generate an asset history, the asset history being a part of the one or more assets of the portfolio; a data integration module containing information about the exchange of;
and an age calculation module configured to calculate an age at replacement for each part type in the portfolio. A scalable automated maintenance optimization system for managing the replacement of multiple parts within one or more assets of a portfolio, the system comprising:
at least one computer-accessible storage device configured to store instructions;
communicatively connected to the at least one computer-accessible storage device and when executed;
a data capture module configured to receive a plurality of maintenance records related to the replacement of one or more of the plurality of parts within the one or more assets of the portfolio;
a data integration module configured to analyze the received plurality of maintenance records to generate an asset history, wherein the asset history includes the plurality of maintenance records within the one or more assets of the portfolio; a data integration module containing information regarding replacement of one or more of the parts;
an age calculation module configured to calculate an age at replacement distribution for each part type of the plurality of parts in the one or more assets of the portfolio;
a parts replacement optimization module configured to determine a part replacement strategy for each part type based at least on the calculated age at replacement distribution;
a user interface control module configured to control a user interface to display a list of the plurality of parts and the respective determined part replacement strategies, the user interface control module configured to display the list of the plurality of parts and the respective determined part replacement strategies; and configured to automatically move a part of the plurality of parts whose part replacement strategy differs from a current part replacement strategy to a position closer to the top of the displayed list of parts in the user interface. a scalable automatic maintenance optimization system comprising: at least one processor configured to execute instructions for providing a plurality of program modules including: a user interface control module; The plurality of program modules are configured to analyze the calculated age at replacement distribution for each part type in the portfolio to determine one or more failure patterns associated with each part type. further including a failure pattern analysis module,
22. The scalable automatic maintenance optimization system of claim 21. the part replacement optimization module is configured to determine the part replacement strategy for each part type based at least on the determined one or more failure patterns associated with each part type;
23. The scalable automatic maintenance optimization system of claim 22. The user interface control module includes:
displaying a parts replacement strategy modification screen that includes the generated asset history for a part of the plurality of parts, the calculated age distribution at replacement for the part, and a cost function for the part; the determined part replacement strategy for the part corresponds to a minimum value of the cost function;
receiving user input to modify one or more maintenance events in the generated asset history;
displaying an updated calculated age at replacement distribution and an updated cost function for the part;
updating the determined part replacement strategy to correspond to a minimum value of the updated cost function;
22. The scalable automatic maintenance optimization system of claim 21. the data acquisition module is further configured to receive a plurality of sensor measurement readings related to the replacement of the one or more parts of the plurality of parts;
the plurality of maintenance records include information regarding the maintenance event of the replacement of the one or more parts of the plurality of parts;
the plurality of sensor measurement readings include information regarding a duty cycle associated with the replacement of the one or more parts of the plurality of parts;
the data acquisition module is further configured to integrate the plurality of maintenance records and the plurality of sensor measurement readings to generate the asset history;
22. The scalable automatic maintenance optimization system of claim 21. The data integration module is configured to determine which of the plurality of parts of the same part type in the asset if the asset includes a plurality of parts of the same part type and less than all of the parts of the plurality of parts are replaced. further configured to determine the position of the replaced part of the
22. The scalable automatic maintenance optimization system of claim 21. The data integration module is further configured to group the plurality of functionally equivalent parts as the same part type if the asset includes a plurality of functionally equivalent parts with different identifiers;
22. The scalable automatic maintenance optimization system of claim 21. the data integration module is further configured to update a parts replacement schedule for the replaced part when the part is replaced with a functionally equivalent part;
28. The scalable automatic maintenance optimization system of claim 27. the data integration module is further configured to determine the functional importance of each part within the asset to the operation of the asset upon failure of the part;
The user interface control module selects the part of the plurality of parts, the determined part replacement strategy of which differs from the current part replacement strategy, from the user interface based at least on the functional importance of the part. further configured to automatically move parts in the displayed list closer to the top of the displayed list;
22. The scalable automatic maintenance optimization system of claim 21. The age calculation module calculates a separate age-at-replacement distribution for each part of the plurality of parts based on the position of each part within the asset when the asset includes a plurality of parts of the same part type. Further configured as,
22. The scalable automatic maintenance optimization system of claim 21. the calculated age at replacement distribution includes a statistical distribution of the ages at replacement of a plurality of parts of each part type within the one or more assets of the portfolio;
22. The scalable automatic maintenance optimization system of claim 21. said statistical distribution of age is fitted to a cumulative Weibull distribution;
22. The scalable automatic maintenance optimization system of claim 21. the failure pattern analysis module is further configured to determine a dominant failure pattern from the one or more failure patterns associated with each part type based on the calculated age at replacement;
the one or more failure patterns for each part type include one or more premature failure patterns, random failure patterns, or wear-out failure patterns;
23. The scalable automatic maintenance optimization system of claim 22. the parts replacement optimization module is further configured to perform one or more of an on-condition maintenance process or determining the part replacement strategy for each part type in the wear-out failure pattern;
34. The scalable automatic maintenance optimization system of claim 33. The parts replacement optimization module is further configured to determine the part replacement strategy for each part type based on a cost of replacement parts for each part type if the determined failure pattern is a wear-out failure. composed of,
34. The scalable automatic maintenance optimization system of claim 33. The parts replacement optimization module replaces the parts for each part type based on the expected downtime of an asset due to a failure of a part of the part type in the asset if the determined failure pattern is a wear-out failure. further configured to determine an exchange strategy;
34. The scalable automatic maintenance optimization system of claim 33. and wherein the parts replacement optimization module performs one or more of a root cause analysis, a modification of a previous part replacement strategy, or an on-condition maintenance process for each part type of the premature failure pattern. Furthermore, it is composed of
34. The scalable automatic maintenance optimization system of claim 33. The parts replacement optimization module is configured to replace the functionally equivalent parts in order to avoid wasting part life by changing parts unnecessarily when the parts are replaced with functionally equivalent parts. further configured to compare the age of the part to the age required by the parts replacement schedule;
29. The scalable automatic maintenance optimization system of claim 28. The data integration module includes:
determining from the asset history a set of parts to be replaced;
comparing the set of replaced parts to at least one of a parts task list, a parts inventory, or a parts replacement schedule to determine parts utilization;
and adjusting the parts ordering schedule and the task list based on the determined parts utilization to avoid over-ordering or under-ordering parts;
22. The scalable automatic maintenance optimization system of claim 21. A processor-implemented method for determining an inventory optimization strategy for the replacement of multiple parts within one or more assets of a portfolio, the method comprising:
receiving a plurality of maintenance records related to the replacement of one or more of the plurality of parts within the one or more assets of the portfolio;
analyzing the received plurality of maintenance records to generate an asset history, wherein the asset history includes one or more of the plurality of parts within the one or more assets of the portfolio; including and analyzing information regarding the replacement of multiple parts;
calculating an age-at-replacement distribution for each part type of the plurality of parts within the one or more assets of the portfolio;
determining a parts replacement strategy for each part type based at least on the calculated age at replacement distribution;
by automatically moving a part of said plurality of parts whose determined part replacement strategy differs from a current part replacement strategy to a position closer to the top of a displayed list of parts in a user interface; , controlling the user interface to display the list of the plurality of parts and the respective determined part replacement strategy.

Images