Search

DE-102025144616-A1 - SYSTEMS AND METHODS FOR PREDICTING THE WEAR CONDITION OF A MACHINE GROUND ENGINE TOOL

DE102025144616A1DE 102025144616 A1DE102025144616 A1DE 102025144616A1DE-102025144616-A1

Abstract

Systems and methods for determining the wear of one or more components of a machine (101) are disclosed. The method involves receiving sensor data from the sensor(s) associated with the machine. The sensor data is processed by a wear model (201) to determine a change in performance and/or a wear rate (217) of the component(s). The estimated wear of the component(s) is generated using the wear model (201) and based on the change in performance and/or the wear rate (217). A value representing the estimated wear of the component(s) is displayed on a user interface.

Inventors

  • Grant Kocher
  • Wenming Zhao
  • Cheng Yu
  • Daojie Zhang
  • David B. Parzynski
  • Thomas Congdon
  • Rammagy Yoeu
  • Pasita Pibulchinda

Assignees

  • CATERPILLAR INC.

Dates

Publication Date
20260513
Application Date
20251030
Priority Date
20241112

Claims (10)

  1. A computer-implemented method for determining the wear of one or more components of a machine (101), the method comprising: Receiving sensor data from one or more sensors (111) assigned to the machine (101); Processing the sensor data by a wear model (201) to determine a change in performance and/or a wear rate (217) of the one or more components; Generating an estimated wear of the one or more components using the wear model (201) and based on the change in performance and/or wear rate (217); and Displaying a value representing the estimated wear of the one or more components on a user interface.
  2. Computer-implemented method according to Claim 1 , where the sensor data includes one or more shield position data or load data.
  3. Computer-implemented method according to Claim 2 , furthermore encompassing: continuous or periodic monitoring of the position of one or more edges of one or more components and recording one or more of: deviations, angular positioning or height of one or more edges in relation to a ground surface.
  4. Computer-implemented method according to one of the preceding Claims 2 until 3 , furthermore comprehensively: monitoring, in real time or near real time, of dynamic load fluctuations and/or peak forces during the operation of the tool for an evaluation of the operating load of one or more components.
  5. Computer-implemented method according to one of the preceding Claims 1 until 4 , wherein the wear model (201) determines the wear rate (217) of one or more components based on at least one of: surface hardness of one or more components; machine learning algorithms for soil conditions; force applied to one or more components; or speed at which one or more components move over a soil surface.
  6. Computer-implemented method according to one of the preceding Claims 1 until 5 , wherein the processing of the sensor data by the wear model (201) further comprises: applying a set of predefined rules to the sensor data to determine the wear rate (217) of one or more components; comparing the wear rate (217) with historical performance data to determine a deviation from the historical performance data; analyzing the deviation to estimate the wear rate (217) of one or more components; and generating a quantitative wear prediction based on the estimated wear rate (217).
  7. Computer-implemented method according to one of the preceding Claims 1 until 6 , wherein generating the estimated wear comprises: generating a three-dimensional model (301) of the one or more components, wherein the three-dimensional model (301) visually represents predicted wear areas on a surface of the one or more components.
  8. Computer-implemented method according to Claim 7 , wherein the three-dimensional model (301) includes color-coded areas corresponding to different degrees of predicted wear, and wherein the three-dimensional model (301) is updated based on the sensor data in real time or near real time.
  9. Computer-implemented method according to one of the preceding Claims 7 until 8 , wherein displaying the estimated wear indicator further comprises: generating one or more notifications in the user interface of a device after determining that the estimated wear exceeds a predetermined threshold, wherein the one or more notifications include one or more recommended actions and wherein the recommended actions include ordering a new component based on the estimated wear.
  10. Computer-implemented method according to one of the preceding Claims 1 until 9 , wherein one or more sensors (111) include a linear displacement sensor, a rotary encoder, an accelerometer, a strain gauge, a load cell, a load sensing cylinder or a pressure sensor.

Description

Technical field The present disclosure relates generally to the field of monitoring and diagnostics and in particular to a monitoring system that combines a plurality of sensors and algorithm modalities to monitor the structural wear of one or more components (e.g. ground engaging tools, GETs) of an industrial machine. State of the art Machines equipped with working tools such as cutting edges for shields, shaft tips for rippers and scarifiers, and teeth for buckets are subject to significant wear due to continuous material handling. Wear monitoring is typically performed through physical inspection of the worn parts, which presents several challenges. This method is labor-intensive, time-consuming, and prone to human error, which can lead to inaccurate assessments of the degree of wear. For example, manual inspections often rely on visual analysis or camera images, which can be inaccurate due to environmental factors such as dirt, debris, or mud obscuring the components. These obstructions can result in an inaccurate analysis of the actual wear. As machines evolve toward remote control and autonomous operation, the need for advanced remote wear monitoring is becoming increasingly critical. Current manual methods are inadequate for continuous, real-time monitoring and do not provide accurate data for predicting wear patterns or maintenance schedules. In addition, without real-time data, unexpected failures can occur, leading to costly machine downtime, reduced efficiency, and potential safety risks. Published on February 16, 2023 US patent application no. 2023/0053154 A1 The '154 publication describes a method for determining the wear level of a GET by analyzing images from various sensors and calculating geometric parameters and pixels to assess wear. The '154 publication relies on image-based analysis for wear determination, which can lead to inaccuracies due to environmental factors such as contamination obscuring the tools. The '154 publication does not disclose a method for using modeling techniques for wear prediction. The system of the present disclosure can solve one or more of the problems listed above and/or other prior art problems. However, the scope of the present disclosure is defined by the attached claims, and not by the ability to solve any specific problem. Brief description In one aspect, a computer-implemented method for determining the wear of one or more components of a machine is disclosed. The computer-implemented method includes: receiving sensor data from one or more sensors associated with a machine; processing the sensor data using a wear model to determine a change in performance and/or a wear rate of the one or more components; generating an estimated wear of the one or more components using the wear model and based on the change in performance and/or the wear rate; and displaying a value representing the estimated wear of the one or more components on a user interface. In another aspect, a system for determining the wear of one or more components of a machine is disclosed. The system includes: one or more processors and at least one non-volatile, computer-readable medium on which instructions are stored which, when executed by the one or more processors, cause the one or more processors to perform operations, including: receiving sensor data from one or more sensors associated with the machine, wherein the sensor data includes one or more of: shield position data, load severity data, or ground condition data; inputting the sensor data into a wear model for calculating the wear rate and simulating predicted wear of the one or more components; and generating a three-dimensional model of the predicted wear, wherein the three-dimensional model specifies one or more of: wear geometry, wear volume, or wear rate of the one or more components. In yet another aspect, a non-volatile, computer-readable medium for determining the wear of one or more machine components is disclosed. This non-volatile, computer-readable medium stores instructions, which, when executed by one or more processors of a computer system, cause the one or more processors to perform operations, including: receiving sensor data from one or more sensors associated with the machine; processing the sensor data by a wear model to determine a wear volume rate of the one or more components; and generating an estimated wear of the one or more components based on the wear volume rate. Brief description of the drawings The accompanying drawings, which are incorporated into this patent specification and form part of this patent specification, illustrate various exemplary embodiments and, together with the description, serve to explain the principles of the disclosed embodiments. 1 is a representation of an exemplary machine according to aspects of the revelation. 2 is a schematic illustration of a system for determining the state of one or more components of the machine of 1 . 3A-3C are exemplary outputs of the system of 2 .