# US 12,761,643 B2 · Systems and methods for identifying and predicting industrial machine maintenance events > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,761,643 B2 - Document ID: US12761643B2 - Status: Granted - Kind: B2 - Application number: 18/733,798 - Filed: 2024-06-04 - Published: 2025-12-04 - Granted: 2026-10-13 - Earliest claimed: 2024-06-04 - Assignees: Caterpillar Inc. - Applicants: Caterpillar Inc. - Inventors: Daniel J. Reaume; Sadia Khalil - Web page: https://patentgrep.com/patent/US12761643B2 ## CPC - G05B 23/0248: {Causal models, e.g. fault tree; digraphs; qualitative physics} - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) ## Abstract Systems and methods are disclosed herein for identifying and predicting maintenance events with respect to assets, such as mobile machinery. A computing platform can include control circuit(s) (on-board and/or remote) configured to acquire machine fault data and machine utilization data. A feature set can be generated by transforming the machine fault data (e.g., by fusing the machine fault data with machine utilization data), normalizing the data, generating embeddings, and/or executing imputation algorithms to fill in missing values. A classifier model can be trained using the transformed machine fault data in conjunction with labeled maintenance event data to enable the trained classifier model to learn to recognize utilization-specific fault code patterns. The trained classifier model can generate inferences and predictions regarding machinery maintenance events without the use of maintenance data. ## Claims ### Claim 1 A system for predicting maintenance events for industrial machines, the system comprising: a set of condition monitoring sensors; at least one processor; at least one memory; and one or more non-transitory, computer-readable storage media storing instructions, which, when executed by the at least one processor, cause the system to: generate a training dataset for a machine learning classifier model by: acquiring, using the set of condition monitoring sensors, a first fault code dataset relating to operation of an industrial machine, wherein the industrial machine includes one or more of earth-moving machinery, construction machinery, or power-generation machinery; applying a transformation to the first fault code dataset to fuse fault code data with a first utilization dataset for the industrial machine, wherein the transformation includes two or more of (i) a fault-to-utilization ratio, (ii) a fault-to-output ratio, or (iii) a ratio change metric, wherein the training dataset comprises the transformed fault code data; train the machine learning classifier model using the training dataset and a maintenance dataset labeled with maintenance event data; acquire a second fault code dataset and a second utilization dataset; execute the machine learning classifier model on the second fault code dataset and second utilization dataset to generate a maintenance event prediction set; and using the maintenance event prediction set, generate a maintenance plan. ### Claim 2 (depends on 1) The system of claim 1, wherein the instructions cause the system to selectively generate the second fault code dataset to include data for a predetermined set of components associated with an item in the second utilization dataset. ### Claim 3 (depends on 1) The system of claim 1, wherein the industrial machine is a first industrial machine, and wherein the second fault code dataset and the second utilization dataset pertain to a set of industrial machines that includes one or more industrial machines different from the industrial machine. ### Claim 4 (depends on 3) The system of claim 3, wherein the maintenance event prediction set comprises at least one inference regarding an automatically determined occurrence of a past maintenance event, the inference comprising a past maintenance event descriptor and a past maintenance event time. ### Claim 5 (depends on 3) The system of claim 3, wherein the maintenance event prediction set comprises at least one inference regarding an automatically predicted occurrence of a future maintenance event, the inference comprising a future maintenance event descriptor and a future maintenance event time. ### Claim 6 (depends on 3) The system of claim 3, the instructions further comprising automatically generating and causing a computing device to display a notification regarding the maintenance plan, wherein the computing device comprises at least one of an on-board computing system, an on-board navigation system, and a mobile computing device communicatively coupled to the one or more industrial machines. ### Claim 7 (depends on 6) The system of claim 6, wherein the notification comprises a user-interactive control to enable a user to subscribe to the maintenance plan or modify the maintenance plan. ### Claim 8 One or more non-transitory, computer-readable media having instructions encoded thereon, which, when executed by at least one data processor of a computing system, cause the computing system to perform operations comprising: generate a training dataset for a machine learning classifier model by: acquiring, using a set of condition monitoring sensors, a first fault code dataset relating to operation of an industrial machine, wherein the industrial machine includes one or more of earth-moving machinery, construction machinery, or power-generation machinery; applying a transformation to the first fault code dataset to fuse fault code data with a first utilization dataset for the industrial machine, wherein the transformation includes two or more of (i) a fault-to-utilization ratio, (ii) a fault-to-output ratio, or (iii) a ratio change metric, wherein the training dataset comprises the transformed fault code data; train the machine learning classifier model using the training dataset and a maintenance dataset labeled with maintenance event data; acquire a second fault code dataset and a second utilization dataset; execute the machine learning classifier model on the second fault code dataset and second utilization dataset to generate a maintenance event prediction set; and using the maintenance event prediction set, generate a maintenance plan. ### Claim 9 (depends on 8) The media of claim 8, wherein the instructions cause the system to selectively generate the second fault code dataset to include data for a predetermined set of components associated with an item in the second utilization dataset. ### Claim 10 (depends on 8) The media of claim 8, wherein the industrial machine is a first industrial machine, and wherein the second fault code dataset and the second utilization dataset pertain to a set of industrial machines that includes one or more industrial machines different from the industrial machine. ### Claim 11 (depends on 10) The media of claim 10, wherein the maintenance event prediction set comprises at least one inference regarding an automatically determined occurrence of a past maintenance event, the inference comprising a past maintenance event descriptor and a past maintenance event time. ### Claim 12 (depends on 10) The media of claim 10, wherein the maintenance event prediction set comprises at least one inference regarding an automatically predicted occurrence of a future maintenance event, the inference comprising a future maintenance event descriptor and a future maintenance event time. ### Claim 13 (depends on 10) The media of claim 10, the instructions further comprising automatically generating and causing a computing device to display a notification regarding the maintenance plan, wherein the computing device comprises at least one of an on-board computing system, an on-board navigation system, and a mobile computing device communicatively coupled to the one or more industrial machines. ### Claim 14 (depends on 13) The media of claim 13, wherein the notification comprises a user-interactive control to enable a user to subscribe to the maintenance plan or modify the maintenance plan. ### Claim 15 A computer-implemented method comprising: generating a training dataset for a machine learning classifier model by: acquiring, using a set of condition monitoring sensors, a first fault code dataset relating to operation of an industrial machine, wherein the industrial machine includes one or more of earth-moving machinery, construction machinery, or power-generation machinery; applying a transformation to the first fault code dataset to fuse fault code data with a first utilization dataset for the industrial machine, wherein the transformation includes two or more of (i) a fault-to-utilization ratio, (ii) a fault-to-output ratio, or (iii) a ratio change metric, wherein the training dataset comprises the transformed fault code data; training the machine learning classifier model using the training dataset and maintenance dataset labeled with maintenance event data; acquiring a second fault code dataset and a second utilization dataset; executing the machine learning classifier model on the second fault code dataset and second utilization dataset to generate a maintenance event prediction set; and using the maintenance event prediction set, generating a maintenance plan. ### Claim 16 (depends on 15) The method of claim 15, further comprising selectively generating the second fault code dataset to include data for a predetermined set of components associated with an item in the second utilization dataset. ### Claim 17 (depends on 15) The method of claim 15, wherein the industrial machine is a first industrial machine, and wherein the second fault code dataset and the second utilization dataset pertain to a set of industrial machines that includes one or more industrial machines different from the industrial machine. ### Claim 18 (depends on 17) The method of claim 17, wherein the maintenance event prediction set comprises at least one inference regarding an automatically determined occurrence of a past maintenance event, the inference comprising a past maintenance event descriptor and a past maintenance event time. ### Claim 19 (depends on 17) The method of claim 17, wherein the maintenance event prediction set comprises at least one inference regarding an automatically predicted occurrence of a future maintenance event, the inference comprising a future maintenance event descriptor and a future maintenance event time. ### Claim 20 (depends on 17) The method of claim 17, further comprising automatically generating and causing a computing device to display a notification regarding the maintenance plan, wherein the computing device comprises at least one of an on-board computing system, an on-board navigation system, and a mobile computing device communicatively coupled to the one or more industrial machines.