Onboard maintenance system configuration generation

Abstract

Systems, methods, and other embodiments described herein relate to developing a comprehensive set of rules for assessing the health of an aircraft system. In one embodiment, a method includes receiving text from one or more sources. Each of the sources describes operation of at least a portion of the system. The method includes generating one or more rule sets based on text using at least one natural language processing model. The method includes generating, using at least one generative model, one or more formatted rule sets based at least on the rule sets, relationships between the rule sets, and the selected format. The method further includes outputting at least a portion of the set of formatted rules to the aircraft maintenance system. The aircraft maintenance system operates based on at least a portion of the set of formatting rules.

Description

Technical Field

[0001] The subject matter described herein generally relates to systems and methods for developing a comprehensive set of rules for assessing system health. Background Art

[0002] A comprehensive condition monitoring rule set is used to provide health management or onboard maintenance capabilities for systems such as aircraft systems. Systems may include subsystems and components from a variety of manufacturers. Therefore, the format of instructions, manuals, and guides for systems, subsystems, and / or components may vary, making it difficult and cumbersome for operators to interpret the instructions, manuals, and guides. BRIEF DESCRIPTION OF THE DRAWINGS

[0003] The accompanying drawings that are incorporated into the specification and constitute a part of the specification illustrate various systems, methods and other embodiments of the present disclosure. It will be appreciated that the element boundaries (e.g., boxes, groups of boxes or other shapes) illustrated in the figures represent an embodiment of boundaries. In some embodiments, an element can be designed as multiple elements, or multiple elements can be designed as one element. In some embodiments, an element shown as an internal component of another element can be implemented as an external component, and vice versa. In addition, the elements may not be drawn to scale.

[0004] Figure 1 The diagram illustrates the data flow of the Onboard Maintenance System (OMS) configuration generation system.

[0005] Figure 2 One embodiment of an OMS configuration generation system is illustrated.

[0006] Figure 3 is a flow chart illustrating one embodiment of a method associated with OMS configuration generation. DETAILED DESCRIPTION

[0007] Systems, methods, and other embodiments associated with systems and methods for developing a comprehensive set of rules for assessing the health of a system, such as an aircraft system, are disclosed.

[0008] An onboard maintenance system (OMS) may be used to determine the health of an aircraft. An OMS provides the ability to analyze the overall health of an aircraft system, a subsystem of an aircraft system, and / or a subsystem or component in an aircraft system. An OMS may be used by an operator for various operations, such as central maintenance, asset management, and aircraft condition monitoring. For centralized maintenance, an OMS may be used to report failures, isolate faults, and / or diagnose faults. For asset management, an OMS may be used for software loading, configuration reporting, and / or time-on-wing reporting. For aircraft condition monitoring, an OMS may be used for complete flight data recording, configurable analysis, and / or automatic wired or wireless data offloading. In general, an OMS may be used to determine the health status of an aircraft system, the configuration utilized on an aircraft system, built-in tests performed on an aircraft, and may be used for software loading and updating.

[0009] As an example, the configuration is a complex database consisting of a collection of interlinked files with integrity checks to ensure the completeness and appropriateness of the collection of files. The database can be updated partially or completely, and the OMS ensures that the overall contents of the database are configured correctly. If an error occurs within the database, the OMS can declare a fault / failure within itself, thereby triggering maintenance actions. Configuration tools on the ground can be used to build a loadable database, and can further provide validity testing to ensure that the database is valid when it is created.

[0010] As an example, an OMS database may include three files, each with a version number. During an update, the OMS may perform a version number check to ensure that the most appropriate data file version is being utilized. In such an example, the OMS database may have previously included three files - File 1 is File 1 version 1.1, File 2 is File 2 version 1.1, and File 3 is File 3 version 1.1. A new OMS database with three files (File 1 is still File 1 version 1.1, File 2 is File 2 version 1.2, and File 3 is still File 3 version 1.1) may be loaded into the aircraft. The OMS may perform a version check on the three files in the new OMS database, and upon identifying that the version of File 2 has changed, the OMS may unpack and update File 2, and then use the resulting configuration to perform maintenance operations.

[0011] OMS technology has greatly improved aircraft-related maintenance practices, such as correctly identifying critical issues early and in a timely manner. Systems in aircraft may originate from different suppliers. However, aircraft operators must understand how each of the systems, subsystems, and components within the aircraft operates. Aircraft operators may have different priorities, which may lead to prioritizing maintenance in different ways. As an example, different aircraft industries prioritize maintenance differently. In such an example, private business aircraft prioritize the availability of flights on customized schedules, airlines prioritize compliance with published schedules without interruptions due to maintenance, and military aircraft prioritize operational availability rather than downtime maintenance. The technology disclosed herein can provide customization so that all three of these industries use more data types to have more coverage of their priorities.

[0012] Aircraft systems may include various systems, subsystems, and / or components. These systems, subsystems, and components may be manufactured by various entities at various times. Thus, as an example, instructions, manuals, and guides for operating these systems, subsystems, and components may vary in format based on the manufacturer and / or time of manufacture.

[0013] Currently, a great deal of time and labor is spent reviewing various manuals and guides, extracting relevant information, and developing a comprehensive set of rules known as an OMS configuration. The OMS is configured using the OMS configuration, and tests and other tasks can be run based on the OMS configuration to assess the health of the aircraft.

[0014] Thus, systems, methods, and other embodiments associated with developing a comprehensive set of rules for assessing system health are disclosed. Other embodiments may include a non-transitory computer-readable medium including instructions for developing a comprehensive set of rules for assessing system health. As previously mentioned, the comprehensive set of rules is used to configure an OMS and is referred to as an OMS configuration. The disclosed OMS configuration generation system may develop an OMS configuration based on text from various sources, including manuals available in digital form and in physical form, and (one or more) pre-existing OMS configurations. The OMS configuration generation system may include one or more generation models, such as a natural language processor and an OMS configuration generator. The OMS configuration generation system may digitally capture (one or more) manuals, such as a fault isolation manual for an aircraft or (one or more) aircraft systems, and may feed the text of (one or more) manuals to a natural language processor. The natural language processor may generate a set of rules, such as condition monitoring rules and fault isolation logic based on text from (one or more) manuals and logic associated with the text. The OMS configuration generation system may then feed (one or more) rule sets from (one or more) natural language processors to the OMS configuration generator. The OMS configuration generator can generate a comprehensive formatted rule set based on the rule set(s) received from the natural language processor(s) and a format compatible with the OMS and the health assessment process. The OMS configuration generation system can then output the comprehensive formatted rule set to the OMS. As an example, the OMS configuration generation system can populate a database with the comprehensive rule set, and the database can be accessed by the OMS.

[0015] Generally speaking, the OMS configuration generation system may be used to develop a logic-based set of rules from a digitized human language data source by using a natural language processor.

[0016] More generally, the disclosed system may be an onboard maintenance system, an offboard maintenance system, or a combination of an onboard maintenance system and an offboard maintenance system. The onboard maintenance system analyzes the health of the aircraft based on resident aircraft data and condition-based rules, and provides results related to the health of the aircraft to a user such as an operator or personnel. The offboard maintenance system analyzes the health of the aircraft based on real-time data transmission, streaming data, or post-flight data from the aircraft and associated condition-based rules.

[0017] The embodiments disclosed herein present various advantages over current methods. First, the embodiments can be used for systems with subsystems and / or components that do not have a standard format across systems, subsystems, and components. As an example, this system can be used by legacy aircraft, aircraft with legacy systems, and any other aircraft with systems with non-confirmed formats. Second, the embodiments eliminate a large amount of engineering time to develop a set of rules for retrofitting an OMS that assesses the health of older aircraft; therefore, the maintenance costs of older aircraft are reduced and the life of older aircraft is extended. In general, the cost of retrofitting a system with one or more non-confirmed formats is reduced. Third, the embodiments reduce the expenditure of time and resources. Fourth, the embodiments improve the accuracy of the OMS and reduce the probability of human error. Fifth, the embodiments encourage more complete, comprehensive, and robust testing of systems, subsystems, and components therein. Sixth, the embodiments provide rules based on a combination of events occurring at various components and / or systems within an aircraft. As an example, when there is multi-system damage in an aircraft, these rules can help users identify (one or more) components or (one or more) systems with (one or more) faults. Therefore, cross-system analysis of various systems, subsystems, and components within the aircraft facilitates accurate identification and resolution of faults in a timely manner.

[0018] Detailed embodiments are disclosed herein; however, it is to be understood that the disclosed embodiments are intended to be examples only. Therefore, the specific structural and functional details disclosed herein are not to be construed as limiting, but merely as a basis for the claims, and as a representative basis for teaching those skilled in the art to variously employ the aspects herein in virtually any appropriate detailed structure. In addition, the terms and phrases used herein are not intended to be limiting, but rather to provide an understandable description of possible implementations. Various embodiments are shown in the drawings, but the embodiments are not limited to the illustrated structures or applications.

[0019] It will be appreciated that for simplicity and clarity of illustration, reference numerals have been repeated in different figures to indicate corresponding or similar elements where appropriate. In addition, numerous specific details are set forth in order to provide a thorough understanding of the embodiments described herein. However, it will be understood by those of ordinary skill in the art that the embodiments described herein may be practiced without these specific details.

[0020] Figure 1 The data flow of an onboard maintenance system (OMS) configuration generation system 100 is illustrated. The OMS configuration generation system 100 generates a comprehensive set of rules for configuring an OMS for assessing system health. The OMS configuration generation system 100 may include various elements that may be communicatively linked in any suitable form. As an example, Figure 1As shown in , the components can be connected. Figure 1 Some of the possible elements of the OMS configuration generation system 100 are shown in FIG. 1 and will now be described. It will be understood that the OMS configuration generation system 100 does not necessarily have Figure 1 All elements shown in or described herein. The OMS configuration generation system 100 may have Figure 1 In addition, the OMS configuration generation system 100 may have any combination of the various elements shown in FIG. Figure 1 In some arrangements, the OMS configuration generation system 100 may not include additional elements beyond those shown in FIG. Figure 1 One or more of the elements shown in .

[0021] The OMS configuration generation system 100 includes one or more natural language processors 110A, 110B (collectively referred to as 110), one or more OMS configuration generators 120, and one or more OMS configuration generation control (OMS CGC) systems 130. (One or more) natural language processors 110 and (one or more) OMS configuration generators 120 can be any suitable machine learning models. The natural language processor 110 (also referred to as a natural language processing model) is a generative model. A generative model is a type of machine learning model that can generate new data based on training data. Artificial intelligence (AI) training is a standard method for creating models, such as generative models that represent "intelligence" by providing a portion of an input data set to the model. The model receives and processes a set of input data, i.e., "training data", and compares the AI ​​results with the results generated by humans. Based on the results of the comparison, the model is updated until the performance of the model is comparable to the "ground truth" of humans. Once the model is trained, the model is fed with more data to confirm that the processed results are consistent with the version evaluated by humans. Over time, as new types of information increase, the model is frequently retrained. Training of the model can be performed off-board in the presence of a configuration generation tool.

[0022] As an example, the natural language processor 110 is capable of analyzing and understanding human language and generating human-like text. The training data may include human-like text, and more specifically, text from manuals such as operating manuals and maintenance manuals. In this example, the natural language processor 110 is trained on human-like text (such as a manual), and then is able to receive text 140A, 140B (collectively referred to as 140) from one or more sources describing the operation of at least a part of the system. The natural language processor 110 is also capable of generating one or more rule sets 160A, 160B (collectively referred to as 160) based on the text 140. In some embodiments, a single natural language processor 110 can receive text 140 from various sources and output multiple rule sets 160 associated with various sources. In other embodiments, a single natural language processor 110 can receive text 140 from a single source and output a rule set 160 associated with the single source. Therefore, the OMS configuration generation system 100 may include one or more natural language processors 110.

[0023] As mentioned previously, the source describes the operation of at least a portion of the system. As an example, the source may include one or more manuals for operating the system and / or at least a portion of the system. In one or more embodiments, the system may be an aircraft system. The aircraft system may be an integral part of the operation of the aircraft. Therefore, the health of the aircraft depends on the health, status, and / or condition(s) of the aircraft system within the aircraft. A portion of the aircraft system may include components and / or subsystems within the aircraft system, such as a flight control system, an engine control system, a fuel system, an electrical system, a pneumatic system, a hydraulic system, a landing gear system, and / or avionics. The purpose of designing components such as resistors, capacitors, connectors, air data probes, and systems such as air data computers, OMS, navigation computers, flaps, ailerons, oil pumps, engines, etc. is to understand safety. The design includes how the component and / or system fails (which may be referred to as a "failure mode"), the effect of the failure (which may be referred to as an "effect"), and the significance of the effect of the failure on safety. As an example, an LED light may fail due to a malfunction of the electronic control. The effect (or impact) of the failure of the LED light is that the indicator light does not turn on. However, the criticality of the indicator light not turning on varies, depending on whether the indicator light is signaling that the coffee pot is on or that an "autopilot failure" has occurred.

[0024] Sources may include manuals for operating subsystems and / or components within subsystems. In more detail, as an example, (one or more) manuals may include information about fault isolation, maintenance, interface control, requirements, design, reliability analysis, failure mode effects and criticality analysis (FMECA) of corresponding systems, subsystems and / or components. FMECA data is based on detailed analysis, is applicable to well-known critical systems such as aircraft, and can be a data source directly related to OMS functionality. In addition, in the case of an aircraft experiencing a failure, the failure may be based on one or more of the components within the subsystem and / or subsystem. In such an example, (one or more) manuals may include information about how to identify and isolate (one or more) faults and / or (one or more) subsystems or components that experience a failure. (One or more) manuals may also include steps to correct the failure.

[0025] The source may be a digital document or soft copy, such as a Microsoft Word document or an Adobe Portable Document Format (PDF) document. In addition, and / or alternatively, the source may be a physical document or hard copy, such as a paper document or printout. In the case where the source is a physical document, the OMS configuration generation system 100 may include a sensor, such as a scanner, that is capable of scanning the physical document and generating a digital version of the physical document. The content of the source may include processes such as fault isolation logic in (one or more) systems, (one or more) subsystems, and / or (one or more) components. The content of the source may include text in a natural language, in machine code, or in any other machine-readable data format.

[0026] Upon receiving text 140 from a source, natural language processor 110 generates a set of rules 160, such as condition monitoring rules 160A and fault isolation rules 160B, based on text 140. In other words, natural language processor 110 receives text 140, determines a digital representation of logic associated with text 140, and then converts the logic into rules 160, such as fault isolation rules 160B and / or condition monitoring rules 160A.

[0027] Condition monitoring rules 160A inform users and / or automated systems such as OMS about rules to follow and logic to implement in order to sample, monitor and record information and parameters for system(s), subsystem(s) and component(s). Fault isolation rules 160B inform users and / or systems such as OMS about rules to follow and logic to implement in order to identify faults and isolate the systems, subsystems and / or components that caused the faults or errors.

[0028] As mentioned above, the OMS configuration generation system 100 includes one or more OMS configuration generators 120. The OMS configuration generator 120 receives rules 160 from (one or more) natural language processors 110. As an example and as mentioned above, the rules 160 may include fault isolation rules 160B and / or condition monitoring rules 160A for various systems, subsystems and / or components. (One or more) OMS configuration generators 120 then generate a set of formatted rules 170 to be included in the OMS configuration 180. The OMS configuration 180 may include rules such as system configuration and maintenance rules. The set of formatted rules 170 and the OMS configuration 180 may be in any suitable format. As an example, the set of formatted rules 170 and the OMS configuration 180 may be arranged in a format or layout that is easy for a user to understand and utilize. As another example, the set of formatted rules 170 and the OMS configuration 180 may be arranged in a machine-readable format or layout so that an automation system can capture the rules, analyze the rules, and perform actions based on the rules. In such an example, the set of formatting rules 170 and the OMS configuration 180 may be formatted so that the automation system can populate the user interface with information, such as the rules 170 in the OMS configuration 180. The set of formatting rules 170 and the OMS configuration 180 may be stored in a database, and the automation system may access the database and populate the user interface based on the information in the database. The database may be generated and populated inside the aircraft or external and outside the aircraft. The database may be updated at any suitable time. In the case where the database is generated external and outside the aircraft, when the generation and population of the database is complete, the database may be loaded onto the aircraft as a controlled item.

[0029] As previously mentioned, the OMS configuration generator 120 may be a generation model capable of receiving rules 160 from multiple sources, reformatting the rules 160 , and combining the rules 160 into a comprehensive set of formatted rules 170 .

[0030] In one example, the OMS configuration generator 120 may receive the rules 160 from one or more natural language processors 110. The OMS configuration generator 120 may also receive the rules from a pre-existing OMS configuration 150. The OMS configuration generator 120 may output a comprehensive set of rules 170 in a predetermined format. As an example, the OMS configuration generator 120 may select a predetermined format based on at least one of the texts 140 fed into the (one or more) natural language processors 110. In such an example, the OMS configuration generator 120 may receive and analyze the text 140 and / or the rules 160 from the (one or more) natural language processors 110 to determine the format in which the rules 160 are arranged. The (one or more) OMS configuration generators 120 may then output the formatted rules 170 based on the format. As another example, the OMS configuration generator 120 may select a predetermined format based on user input. In such an example, the OMS configuration generator 120 may receive user input including a preferred format. The OMS configuration generator 120 may then arrange and output the rules 170 based on the preferred format. As another example, the OMS configuration generator 120 may select a predetermined format based on historical information. In such an example, the OMS configuration generator 120 may simulate a format in a pre-existing OMS configuration 150. The OMS configuration generator 120 may receive and analyze a pre-existing OMS configuration 150. The OMS configuration generator 120 may then determine the format within the pre-existing OMS configuration 150 and apply the format while outputting the formatting rules 170. As another example, the OMS configuration generator 120 may select a predetermined format based on machine-readable information. In such an example, the OMS configuration generator 120 may request and receive machine-readable information from an existing database. The machine-readable information may be in various formats, such as html format and / or text format.

[0031] The OMS configuration generator 120 may receive one or more rule sets 160 from the natural language processor(s) 110 and / or pre-existing OMS configurations 150, and the OMS configuration generator 120 may utilize various large language models and / or machine learning methods to output a comprehensive rule set based on the received rules 160 and a predetermined format.

[0032] As mentioned previously, the OMS configuration generation system 100 includes one or more OMS configuration generation control (OMSCGC) systems 130. The OMS CGC system may control one or more natural language processors 110, one or more OMS configuration generators 120, and any other components within the OMS configuration generation system 100. The OMS CGC system 130 is described in detail below.

[0033] As an example and Figure 1 As shown in , the OMS configuration generation system 100 includes two natural language processors 110A, 110B, an OMS configuration generator 120, and an OMS CGC system 130. The input to the OMS configuration generation system 100 includes published information that discloses the operation of a system, such as an aircraft system, a subsystem of an aircraft system, and / or a component within an aircraft system. As an example, the input may include a reliability analysis document 140A for an aircraft engine, a fault isolation manual 140B for an aircraft braking system, and a pre-existing OMS configuration 150 for an aircraft system. The input to the OMS configuration generation system 100 may include any suitable combination of published documents 140 and / or pre-existing OMS configurations 150.

[0034] The OMS CGC system 130 may activate the natural language processor 110, the OMS configuration generator(s) 120, and any other components. The OMS CGC system 130 may select a portion of a pre-existing OMS configuration 150 and / or published document 140 to be input into the natural language processor 110 and the OMS configuration generator(s) 120, respectively. The OMS CGC system 130 may further select a format as the OMS configuration generator(s) 120 output formatting rules 170.

[0035] The two natural language processors 110 include a first natural language processor 110A and a second natural language processor 110B. As an example, the first natural language processor 110A is receiving text 140A in a reliability analysis document. The first natural language processor 110A analyzes the text 140A, extracts the rules and logic disclosed in the text 140A, and generates a condition monitoring rule 160A based on the extracted rules and logic. The second natural language processor 110B is receiving text 140B in a fault isolation manual for an aircraft braking system. The second natural language processor 110B analyzes the text 140B, extracts the rules and logic disclosed in the text 140B, and generates a fault isolation rule 160B based on the extracted rules and logic.

[0036] The OMS configuration generator 120 receives the condition monitoring rules 160A, the fault isolation rules 160B, and the pre-existing OMS configuration 150. The OMS configuration generator 120 may determine a format for outputting the rules 170 based on at least one of the text 140, the user input, historical information such as the pre-existing OMS configuration 150, and / or machine-readable information. The OMS configuration generator 120 generates a comprehensive rule set 170 that includes condition monitoring rules for aircraft engines, fault isolation rules for the braking system, and various other rules related to other systems, subsystems, and / or components, some of which may be in the pre-existing OMS configuration 150. The OMS configuration generator 120 may output the comprehensive rule set 170 to a data storage unit such as a database.

[0037] refer to Figure 2 , further illustrating Figure 1 2. The OMS CGC system 130 is shown as including a processor 210. Thus, the processor 210 may be part of the OMS CGC system 130, or the OMS CGC system 130 may access the processor 210 via a data bus or another communication path. In one or more embodiments, the processor 210 is an application specific integrated circuit (ASIC) configured to implement the functions associated with the control module 230. Generally speaking, the processor 210 is an electronic processor, such as a microprocessor, that is capable of performing various functions as described herein.

[0038] In one embodiment, the OMS CGC system 130 includes a memory 220 that stores a control module 230 and / or other modules that can be used to support the development of a comprehensive set of rules for assessing system health. The memory 220 is a random access memory (RAM), a read-only memory (ROM), a hard drive, a flash memory, or another suitable memory for storing the control module 230. The control module 230 is, for example, machine-readable instructions that, when executed by the processor 210, cause the processor 210 to perform various functions disclosed herein. In a further arrangement, the control module 230 is logic, an integrated circuit, or another device for performing the functions including the instructions integrated therein.

[0039] Additionally, in one embodiment, the OMS CGC system 130 includes a data repository 270. In one arrangement, the data repository 270 is an electronic data structure stored in the memory 220 or another data repository and is configured with routines executable by the processor 210 for analyzing stored data, providing stored data, organizing stored data, etc. Thus, in one embodiment, the data repository 270 stores data used by the control module 230 in performing various functions.

[0040] For example, Figure 2 As depicted in , data repository 270 includes system information 240 and format parameters 250 , as well as other information used and / or generated by control module 230 , for example.

[0041] As previously mentioned, the system may include various systems, subsystems, and / or components. System information 240 may include information related to the system and the various systems, subsystems, and / or components. As an example, system information 240 may include identification information, such as the brand, type, model, year of manufacture, and / or version number of the system, subsystem, and / or component. System information 240 may be input by a user. Additionally and / or alternatively, system information 240 may be retrieved from a parts database.

[0042] Format parameters 250 may include information about the format of rules 170 in an OMS configuration. Format parameters 250 may be based on user preferences and user interfaces, related systems, subsystems and / or components, and / or pre-existing OMS configuration formats.

[0043] Although the OMS·CGC system 130 is illustrated as including various data elements, it should be appreciated that in various implementations, one or more of the illustrated data elements may not be included within the data repository 270 and may be included in a data repository external to the OMS·CGC system 130. In any case, the OMS CGC system 130 stores various data elements in the data repository 270 to support the functionality of the control module 230.

[0044] In one embodiment, the control module 230 includes instructions that, when executed by the processor(s) 210, cause the processor(s) 210 to receive text 140 from one or more sources. As previously disclosed, the one or more sources may describe the operation of at least a portion of the system. At least a portion of the system may refer to the entire system, a portion of the entire system, a subsystem within the entire system, and / or a component within the entire system and / or a subsystem.

[0045] The operation of at least a portion of the system may be related to fault isolation, maintenance, interface control, requirements, design, reliability analysis, and / or failure mode effects and criticality analysis (FMECA). Fault isolation includes monitoring the system, identifying when a fault occurs within the system, and identifying the type and location of the fault. Maintenance may include preventive maintenance and / or corrective maintenance. Preventive maintenance refers to the process used to keep the system in an operational state, while corrective maintenance refers to the process used to identify the need for replacement and / or repair, replace and / or repair the system before the failure of the system. Interface control refers to the connectivity between systems, subsystems, and components. Interface control may include messaging protocols between systems, subsystems, and / or components. Thus, interface control may disclose messaging types and / or message formats to be used for data transmission between systems, subsystems, and / or components. Requirements refer to how a system operates or is expected to operate. Design refers to how a system is designed and / or implemented. Reliability analysis refers to evaluating a system to determine whether the system provides consistent results, and therefore the system can be considered reliable. FMECA methods may be utilized during reliability analysis. FMECA is the process of reviewing systems, subsystems and / or components to identify potential failure modes and the causes and effects of potential failure modes. FMECA also includes determining the relationship between the probability of a failure mode occurring and the severity of its occurrence.

[0046] In one embodiment, the system can be an aircraft system and / or a part of an aircraft system. In such an embodiment, the system can include a flight control system, an engine control system, a fuel system, a hydraulic system, an electrical system, a pneumatic system, an environmental control system, an emergency system, a rotor system, an advanced system and / or avionics technology. Each system can contribute to the operation of the aircraft. In the case of a failure in the aircraft, the failure can be attributed to one or more systems in the system in the aircraft. In other words, a failure in one or more aircraft systems in the aircraft system can lead to the failure of at least a portion of the aircraft. In addition, there can be interdependencies between the systems, such that, as an example, a failure in the engine control system can be caused by a failure or fault in the fuel system. Therefore, a failure that can occur in the engine control system in an aircraft can be due to a fault in the fuel system.

[0047] One or more sources may include documents, manuals, and / or guides that describe the operation of a system, a subsystem, and / or a component within a system or subsystem. Thus and by way of example, a source may include a fault isolation manual, maintenance manual, interface control document, requirements manual, design document, reliability analysis document, and / or FMECA document for a system, a subsystem, or a component having a system and subsystem. A source may be a combination of digital and physical documents. In some embodiments, the OMS configuration generation system 100 may include a scanner for converting the contents of a physical document into a digital document.

[0048] The source may also include a pre-existing OMS configuration 150. The pre-existing OMS configuration 150 may be human generated and / or machine generated. The control module 230 may activate the natural language processor(s) 110 to receive the text 140. Additionally, the control module 230 may activate the OMS CGC system 130 to receive the pre-existing OMS configuration 150.

[0049] In one embodiment, the control module 230 includes instructions that, when executed by the processor(s) 210, cause the processor(s) 210 to generate one or more rule sets 160 based on the text 140 using at least one natural language processor 110. The control module 230 may activate the natural language processor(s) 110 to generate one or more rule sets 160 based on the text 140 received by the natural language processor(s) 110. As previously disclosed, the natural language processor(s) 110 may utilize various methods, such as any suitable machine learning method and / or large language model learning process, to generate the rule set 160. The natural language processor 110 may output the rule set 160 to the OMS configuration generator(s) 120.

[0050] In one embodiment, the control module 230 includes instructions that, when executed by the processor(s) 210, cause the processor(s) 210 to generate one or more formatting rule sets 170 using at least one generative model, based at least on one or more rule sets 160, relationships between one or more rule sets, and a selected format. The control module 230 may activate the generative model to receive the rule set 160 generated by the natural language processor(s) 110. The control module 230 may also activate the generative model to receive a rule set from a pre-existing OMS configuration 150. An example of a generative model is the OMS configuration generator 120 described above. In some embodiments, the control module 230 may utilize the generative model or a second generative model to generate a relationship set between one or more rule sets. A relationship set refers to how two or more aircraft systems are related and / or interdependent. In other words, the failure of one aircraft system may be caused by the failure of another aircraft system. As an example, the generative model may be trained on data including relationships between aircraft systems and historical information. The generative model may receive a first rule set related to a flight control system and a second rule set related to an engine control system. The control module may then activate the generative model to generate a relationship set between the first rule set and the second rule set. As an example, the relationship set may include a fault in a first system associated with a first rule set that may result in a fault or failure in a second system associated with a second rule set. The relationship set may include a combination of conditions, faults, failures, and solutions for multiple aircraft systems.

[0051] In some embodiments, the control module 230 may determine the selected format. As an example, the control module 230 may determine the selected format based on text content, user input, historical information (such as the format of a pre-existing OMS configuration 150), and / or machine-readable information. When selecting a format, the control module 230 may activate the OMS configuration generator 120 to generate one or more formatting rule sets 170 based on the rule sets 160 received by the OMS configuration generator 120, the relationship between one or more rule sets, and the selected format. Additionally and / or alternatively, the control module 230 may activate the OMS configuration generator 120 to generate one or more formatting rule sets 170, which may include previously processed rule sets from (one or more) pre-existing OMS configurations 150. In some embodiments, the control module 230 may select different formats for different rule sets 170. Therefore, the OMS configuration generator 120 may format different rule sets 170 according to the corresponding selected formats. The OMS configuration generator 120 may then combine the different rule sets and the relationships between the rules and related systems into a comprehensive rule set 170 that constitutes the OMS configuration. The comprehensive rule set 170 may then be loaded onto the aircraft OMS system.

[0052] In one embodiment, the control module 230 includes instructions that, when executed by the processor(s) 210, cause the processor(s) 210 to output at least a portion of the one or more formatted rule sets 170 to an aircraft maintenance system. The aircraft maintenance system may be used to perform aircraft maintenance, such as monitoring the status and condition of systems, subsystems, and / or components within the aircraft. The aircraft maintenance system may also monitor failures and faults in systems, subsystems, and / or components within the aircraft. Even further, the aircraft maintenance system may identify and resolve faults and failures of systems, subsystems, and / or components within the aircraft. As previously mentioned, the aircraft maintenance system may include an onboard aircraft maintenance system and / or an offboard aircraft maintenance system.

[0053] The control module 230 may output the set of formatting rules in any suitable digital format, such as a digital file, a text file, or a spreadsheet. The control module 230 may electronically transmit the set of formatting rules and / or may display the set of formatting rules so that the set of formatting rules is visible and viewable by a human user or operator. The control module 230 may cause the OMS configuration generator 120 to output all of the rule sets 160 received by the OMS configuration generator 120. Alternatively, the control module 230 may cause the OMS configuration generator 120 to output a portion of the rule sets 160 received by the OMS configuration generator 120.

[0054] As an example, in a case where a health assessment is performed on a portion of a system, subsystem, and / or component, there may not be a need for a complete set of rules. In such an example, the set of rules related to a portion of a system, subsystem, and / or component may be the only set of rules required and output to the OMS by the OMS. As another example, in a case where an assessment related to a specific problem is performed on a portion of a system, subsystem, and / or component, there may not be a need for a complete set of rules. In such an example, the portion of the rule set related to the specific problem may be the only set of rules required and output to the OMS by the OMS. As an example, a portion of a rule set may include a process for monitoring conditions in a system, subsystem, or (one or more) components, a process for isolating faults in a system, subsystem, or (one or more) components, a process for diagnosing faults in a system, subsystem, or (one or more) components, a process for reporting faults in a system, subsystem, or (one or more) components, and / or a process for interacting with a system, subsystem, or (one or more) components. In some embodiments, the OMS interrogates the system reporting the fault, requesting additional information. As an example, the additional information may include a software part number, a system serial number, and / or an operating time.

[0055] The control module 230 may select a portion of a rule set based on predetermined criteria. As an example, the control module 230 may receive user input, machine-generated input, and / or automatic input indicating a portion of a system, subsystem, and / or component to have a health assessment and / or assessment type. Thus, the predetermined criteria may be based on user input, machine-generated input, and / or automatic input. The control module 230 may utilize one or more different methods to identify a rule set required based on a portion of a system, subsystem, and / or component and / or the type of assessment to be performed. As an example, the control module 230 may utilize a machine learning process or a large language model approach to determine and select a rule set to output to the OMS. The control module 230 may utilize a lookup table or one or more different algorithms to determine and select a rule set 170 to output to the OMS.

[0056] As an example, the control module 230 can select the text 140 or source fed into the natural language processor 110 based on the type of test that the OMS is expected to perform. As another example, the control module 230 can select the rule set 160 that is input into the OMS configuration generator 120. As an example, the control module 230 can retrieve information indicating the type of test that the OMS is expected to perform from the OMS, and the control module 230 can utilize one or more methods, such as machine learning, large language models, lookup tables, algorithms, and / or formulas to identify the rule set associated with the test type. Therefore, the OMS configuration generator 120 can output a comprehensive rule set 170 that includes a selected rule set based on the test that the OMS is expected to perform.

[0057] Figure 3 is a flow chart illustrating one embodiment of a method 300 associated with OMS configuration generation. Figure 1-2 The method 300 is described from the perspective of the OMS CGC system 130. However, the method 300 may be suitable for execution in any of a number of different situations and is not necessarily performed by Figure 1-2 The OMS CGC system 130 is executed.

[0058] In step 310, the control module 230 may cause the processor(s) 210 to receive text 140 from one or more sources. As mentioned above, each of the sources may describe the operation of the system, subsystem, and component. More specifically, the control module 230 may activate the natural language processor(s) 110 and feed the text 140 from the source to the natural language processor(s) 110. In the case where the source is a physical document, the control module 230 may activate a scanner to convert the physical document into a digital document. In some embodiments, the control module 230 may feed all of the text 140 in the source to the natural language processor(s) 110. In some embodiments, the control module 230 may select a portion of the text 140 and feed the selected portion of the text 140 to the natural language processor(s) 110. The control module 230 may determine the selected portion of the text 140 using one or more methods. As an example, the control module 230 may receive information from a user. As another example, the control module 230 may receive information from the OMS indicating the type of test that the OMS is expected to perform.

[0059] The source may include a pre-existing OMS configuration 150. Thus, the control module 230 may activate the natural language processor(s) 110 and / or the OMS configuration generator 120 and feed the pre-existing OMS configuration to the natural language processor(s) 110 and / or the OMS configuration generator 120.

[0060] At step 320, the control module 230 may cause the processor(s) 210 to generate one or more rule sets 160 based on the text 140 using the at least one natural language processing model 110. Thus, the natural language processor(s) 110 may generate the rule sets 160 based on the text 140. The rule sets 160 describe the operation of a system, such as an aircraft system, a subsystem within an aircraft system, and / or a component within an aircraft system.

[0061] At step 330, the control module 230 may cause the processor(s) 210 to generate one or more formatting rule sets 170 using at least one generative model 120 based at least on one or more rule sets 160, relationships between the one or more rule sets, and a selected format. The control module 230 may activate a generative model, such as an OMS configuration generator 120. The control module 230 may feed the rule set 160 from the natural language processor(s) 110 and / or a pre-existing OMS configuration 150 to the OMS configuration generator 120. The control module 230 may activate a second generative model that determines relationships between rules associated with a plurality of systems, subsystems, and / or components. The second generative model may be trained on historical data including pre-existing relationships. The second generative model may be applied to one or more rules 160 to generate a set of relationships between the one or more rule sets. The control module 230 may determine one or more formats of output from the OMS configuration generator 120 based on the methods disclosed above. The OMS configuration generator 120 may format the rule set 170 based on the selected format(s). A formatting rule set 170 may include one or more rule sets 170 and information related to relationships between the one or more rule sets 170 .

[0062] At step 340, the control module 230 may cause the processor(s) 210 to output at least a portion of the one or more formatting rule sets 170. The OMS configuration generator 120 may then output the formatting rule sets 170 to the OMS. The OMS configuration generator 120 may output the formatting rule sets 170 to a database accessible by the OMS. More generally, the control module 230 may output at least a portion of the one or more formatting rule sets to an aircraft maintenance system. The aircraft maintenance system may include an OMS. As described above, the aircraft maintenance system monitors the status, condition, and overall health of the aircraft and the systems, subsystems, and components in the aircraft. The aircraft maintenance system also addresses failures and faults within the aircraft, the systems, subsystems, and components within the aircraft.

[0063] Detailed embodiments are disclosed herein. However, it is to be understood that the disclosed embodiments are intended to be examples only. Therefore, the specific structural and functional details disclosed herein are not to be construed as limiting, but merely as a basis for the claims, and as a representative basis for teaching those skilled in the art to variously adopt the aspects herein in virtually any appropriate detailed structure. In addition, the terms and phrases used herein are not intended to be limiting, but rather to provide understandable descriptions that may be implemented. Figure 1-3 Various embodiments are shown in the drawings, but the embodiments are not limited to the illustrated structures or applications.

[0064] The flow charts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functionality and operation of the system, method and computer program product according to various embodiments. In this regard, each box in the flow chart or block diagram can represent a module, a fragment or a code portion, which includes one or more executable instructions for implementing (one or more) specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may not appear in the order marked in the accompanying drawings. For example, the two boxes shown in succession can actually be executed substantially simultaneously, or the boxes can sometimes be executed in reverse order, depending on the functionality involved.

[0065] The systems, components and / or processes described above can be implemented with hardware or a combination of hardware and software, and can be implemented in a centralized manner in a processing system, or in a decentralized manner with different components distributed across several interconnected processing systems. Any type of processing system or another device suitable for executing the methods described herein is suitable. A typical combination of hardware and software can be a processing system with a computer-usable program code, which, when loaded and executed, controls the processing system so that it executes the methods described herein. The systems, components and / or processes can also be embedded in a computer-readable storage device such as a computer program product or other data program storage device, which can be read by a machine, tangibly embodying an instruction program executable by a machine to execute the methods and processes described herein. These elements can also be embedded in an application product, which includes all the features that enable the methods described herein to be implemented, and the application product, when loaded into a processing system, can execute these methods.

[0066] In addition, the arrangements described herein may take the form of a computer program product embodied in one or more computer-readable media, on which a computer-readable program code is embodied (e.g., stored). Any combination of one or more computer-readable media may be utilized. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The phrase "computer-readable storage medium" means a non-transitory storage medium. A computer-readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer-readable storage media would include the following: a portable computer disk, a hard disk drive (HDD), a solid-state drive (SSD), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium may be any tangible medium capable of containing or storing a program used by or in conjunction with an instruction execution system, device, or apparatus.

[0067] In general, a module as used herein includes routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific data types. In other aspects, a memory generally stores the modules. The memory associated with a module can be a buffer or cache, RAM, ROM, flash memory, or another suitable electronic storage medium embedded in a processor. In further aspects, the module contemplated by the present disclosure is implemented as an application specific integrated circuit (ASIC), implemented as a hardware component of a system on a chip (SoC), implemented as a programmable logic array (PLA), or implemented as another suitable hardware component embedded with a defined configuration set (e.g., instruction) for performing the disclosed functions.

[0068] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber, cable, RF, etc., or any suitable combination of the foregoing. The computer program code for performing operations of aspects of the present arrangement may be written in any combination of one or more programming languages, including languages ​​such as Java. TM, Smalltalk, C++, and traditional procedural programming languages ​​such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (e.g., through the Internet using an Internet service provider).

[0069] The terms "a and an" as used herein are defined as one or more than one. The terms "plurality" as used herein are defined as two or more than two. The term "another" as used herein is defined as at least a second or more. The terms "include" and / or "have" as used herein are defined as comprising (i.e., open language). The phrase "at least one of ... and ... " as used herein refers to and includes any and all possible combinations of one or more items in the associated listed items. As an example, the phrase "at least one of A, B, and C" includes only A, only B, only C, or any combination thereof (e.g., AB, AC, BC, or ABC).

[0070] The aspects herein may be embodied in other forms without departing from its spirit or essential attributes. Accordingly, reference should be made to the following claims, rather than to the foregoing specification, as indicating the scope of the invention.

[0071] Disclosed are systems, methods, and other embodiments associated with developing a comprehensive set of rules for assessing the health of an aircraft and systems, subsystems, and components within the aircraft. The comprehensive set of rules is used to configure an aircraft maintenance system. The aircraft maintenance system may include one or both of an onboard maintenance system (OMS) and an offboard maintenance system. The OMS configuration generation system may develop an OMS configuration based on text from various sources, including manuals available in digital form and in physical form, and (one or more) pre-existing OMS configurations. The OMS configuration generation system may include one or more generation models, such as a natural language processor and an OMS configuration generator. The OMS configuration generation system may digitally capture (one or more) manuals, such as a fault isolation manual for an aircraft or (one or more) aircraft systems, and may feed the text of (one or more) manuals to (one or more) natural language processors. The natural language processor may generate a set of rules, such as condition monitoring rules and fault isolation logic based on text from (one or more) manuals and logic associated with the text. The OMS configuration generation system may then feed (one or more) rule sets from (one or more) natural language processors to the OMS configuration generator. The OMS configuration generator can generate comprehensive formatted rules based on the rule set(s) received from the natural language processor(s), the relationships between the rule sets, and a format compatible with the OMS and the health assessment process. The OMS configuration generation system can then output the comprehensive formatted rule set to the OMS. As an example, the OMS configuration generation system can populate a database with the comprehensive rule set, and the database can be accessed by the OMS.

[0072] Generally speaking, the OMS configuration generation system may be used to develop a logic-based set of rules from a digitized human language data source by using a natural language processor.

[0073] The embodiments disclosed herein present various advantages over current methods. First, the embodiments can be used for systems with subsystems and / or components that do not have a standard format across systems, subsystems, and components. As an example, this system can be used by legacy aircraft, aircraft with legacy systems, and any other aircraft with systems with non-compliant formats. Second, the embodiments eliminate a large amount of engineering time to develop a set of rules for retrofitting an OMS that assesses the health of older aircraft; therefore, the maintenance costs of older aircraft are reduced and the life of older aircraft is extended. In general, the cost of retrofitting a system with one or more non-confirmed formats is reduced. Third, the embodiments reduce the expenditure of time and resources. Fourth, the embodiments improve the accuracy of the OMS and reduce the probability of human error. Fifth, the embodiments encourage more complete, comprehensive, and robust testing of systems, subsystems, and components therein. Sixth, the embodiments provide rules based on a combination of events occurring at various components and / or systems within an aircraft. As an example, when there is multi-system damage in an aircraft, these rules can help users identify (one or more) components or (one or more) systems with (one or more) faults. Therefore, cross-system analysis of various systems, subsystems, and components within the aircraft facilitates accurate identification and resolution of faults in a timely manner.

[0074] Further aspects are provided by the subject matter of the following clauses.

[0075] A configuration generation system includes a processor and a memory. The memory stores machine-readable instructions that, when executed by the processor, cause the processor to: receive text from one or more sources, each of the one or more sources describing the operation of at least a portion of a system; generate one or more rule sets based on the text using at least one natural language processing model; generate one or more formatting rule sets using at least one generation model based at least on the one or more rule sets, relationships between the one or more rule sets, and a selected format; and output at least a portion of the one or more formatting rule sets to an aircraft maintenance system. The aircraft maintenance system operates based on the at least a portion of the one or more formatting rule sets.

[0076] A configuration generation system according to any of the preceding clauses, wherein the one or more sets of formatting rules include at least one of the following: a process for monitoring conditions in the system; a process for isolating faults in the system; a process for diagnosing faults in the system; a process for reporting faults in the system; or a process for interacting with the system.

[0077] The configuration generation system according to any of the preceding clauses, wherein the aircraft maintenance system comprises at least one of: an onboard aircraft maintenance system and / or an offboard aircraft maintenance system.

[0078] A configuration generation system according to any of the preceding clauses, wherein the operation of at least a portion of the system is related to at least one of: fault isolation; maintenance; interface control; requirements; design; reliability analysis; or failure mode effects and criticality analysis (FMECA).

[0079] A configuration generation system according to any of the preceding clauses, wherein the selected format is based on at least one of: the text; user input; historical information; or machine readable information.

[0080] The configuration generation system of any of the preceding clauses, wherein the machine-readable instructions further comprise instructions that, when executed by the processor, cause the processor to: select the portion of the one or more sets of formatting rules based on a predetermined criterion.

[0081] The configuration generation system of any preceding clause, wherein the portion of the one or more formatting rule sets comprises one or more previously processed rule sets.

[0082] A method includes receiving text from one or more sources, each of the one or more sources describing the operation of at least a portion of a system; generating one or more rule sets based on the text using at least one natural language processing model; generating one or more formatting rule sets using at least one generation model based at least on the one or more rule sets, relationships between the one or more rule sets, and a selected format; and outputting at least a portion of the one or more formatting rule sets to an aircraft maintenance system. The aircraft maintenance system operates based on the at least a portion of the one or more formatting rule sets.

[0083] A method according to any of the preceding clauses, wherein the one or more sets of formatting rules include at least one of: a process for monitoring conditions in the system; a process for isolating faults in the system; a process for diagnosing faults in the system; a process for reporting faults in the system; or a process for interacting with the system.

[0084] The method according to any of the preceding clauses, wherein the aircraft maintenance system comprises at least one of: an onboard aircraft maintenance system and / or an offboard aircraft maintenance system.

[0085] A method according to any of the preceding clauses, wherein the operation of at least a portion of the system is related to at least one of: fault isolation; maintenance; interface control; requirements; design; reliability analysis; and failure mode effects and criticality analysis (FMECA).

[0086] A method according to any of the preceding clauses, wherein the selected format is based on at least one of: the text; user input; historical information; and machine-readable information.

[0087] The method of any of the preceding clauses, further comprising selecting the portion of the one or more sets of formatting rules based on a predetermined criterion.

[0088] A method as in any of the preceding clauses, wherein the portion of the one or more formatting rule sets comprises one or more previously processed rule sets.

[0089] A non-transitory computer-readable medium comprising instructions that, when executed by a processor, cause the processor to: receive text from one or more sources, each of the one or more sources describing the operation of at least a portion of a system; generate one or more rule sets based on the text using at least one natural language processing model; generate one or more formatting rule sets using at least one generation model based at least on the one or more rule sets, relationships between the one or more rule sets, and a selected format; and output at least a portion of the one or more formatting rule sets to an aircraft maintenance system, the aircraft maintenance system operating based on the at least a portion of the one or more formatting rule sets.

[0090] A non-transitory computer-readable medium as described in any of the preceding clauses, wherein the one or more sets of formatting rules include at least one of: a process for monitoring conditions in the system; a process for isolating faults in the system; a process for diagnosing faults in the system; a process for reporting faults in the system; and a process for interacting with the system.

[0091] The non-transitory computer-readable medium of any of the preceding clauses, wherein the aircraft maintenance system comprises at least one of: an onboard aircraft maintenance system and / or an offboard aircraft maintenance system.

[0092] A non-transitory computer-readable medium as described in any of the preceding clauses, wherein the at least a portion of the system is related to at least one of: fault isolation; maintenance; interface control; requirements; design; reliability analysis; or failure mode effects and criticality analysis (FMECA).

[0093] The non-transitory computer-readable medium of any of the preceding clauses, wherein the selected format is based on at least one of: the text; user input; historical information; or machine-readable information.

[0094] The non-transitory computer-readable medium of any of the preceding clauses, wherein the instructions further comprise instructions that, when executed by the processor, cause the processor to: select the portion of the one or more sets of formatting rules based on a predetermined criterion.

Claims

1. A configuration generation system, comprising: processor; as well as a memory storing machine-readable instructions that, when executed by the processor, cause the processor to: receiving text from one or more sources, each of the one or more sources describing the operation of at least a portion of the system; generating one or more rule sets based on the text using at least one natural language processing model; generating, using at least one generative model, one or more formatting rule sets based at least on the one or more rule sets, relationships between the one or more rule sets, and the selected format; as well as At least a portion of the one or more sets of formatting rules is output to an aircraft maintenance system, the aircraft maintenance system operating based on the at least a portion of the one or more sets of formatting rules.

2. The configuration generation system according to claim 1, wherein: The one or more sets of formatting rules include at least one of the following: a process for monitoring conditions in said system; a process for isolating faults in said system; a process for diagnosing faults in said system; a process for reporting faults in said system; as well as Processes for interacting with the system.

3. The configuration generation system according to claim 1, wherein: The aircraft maintenance system includes at least one of the following: Onboard aircraft maintenance systems; and Offboard aircraft maintenance systems.

4. The configuration generation system according to claim 1, wherein: The operation of at least a portion of the system is related to at least one of: Fault isolation; maintain; Interface control; Require; design; Reliability analysis; as well as Failure Mode Effects and Criticality Analysis (FMECA).

5. The configuration generation system according to claim 1, wherein: The selected format is based on at least one of the following: said text; User input; Historical information; and Machine readable information.

6. The configuration generation system according to claim 1, wherein: The machine-readable instructions further include instructions that, when executed by the processor, cause the processor to: The portion of the one or more sets of formatting rules is selected based on predetermined criteria.

7. The configuration generation system according to claim 1, wherein: The portion of the one or more formatting rule sets includes one or more previously processed rule sets.

8. A method comprising: receiving text from one or more sources, each of the one or more sources describing the operation of at least a portion of the system; generating one or more rule sets based on the text using at least one natural language processing model; generating, using at least one generative model, one or more formatting rule sets based at least on the one or more rule sets, relationships between the one or more rule sets, and the selected format; as well as At least a portion of the one or more sets of formatting rules is output to an aircraft maintenance system, the aircraft maintenance system operating based on the at least a portion of the one or more sets of formatting rules.

9. The method according to claim 8, wherein: The one or more sets of formatting rules include at least one of the following: a process for monitoring conditions in said system; a process for isolating faults in said system; a process for diagnosing faults in said system; a process for reporting faults in said system; as well as A process for interacting with the system.

10. The method according to claim 8, wherein: The aircraft maintenance system includes at least one of the following: Onboard aircraft maintenance systems; and Offboard aircraft maintenance systems.

Images