17 results about "Machine diagnostics" patented technology

The invention provides a fan gearbox dynamic integration fault detection method and system based on feature fusion, and relates to the technical field of data processing, and the method comprises the steps: obtaining each preliminary feature set; performing feature-to-feature and feature-fault nonlinear relation quantization on each preliminary feature set to obtain each preliminary screening feature set; analyzing the contribution degree of each feature in each preliminary screening feature set, executing feature fine screening, and generating each fine screening feature set; and calling a multi-agent integrated fault detection system, executing multi-layer agent information sharing and collaborative decision from bottom to top based on each fine screening feature set, and generating fan gearbox fault detection information. According to the method and the device, the technical problem of low fault detection accuracy caused by lack of deep feature mining and dependence on a single-machine diagnosis system in the prior art is solved, and the technical effect of improving the fault detection accuracy is achieved by constructing the multi-agent integrated fault detection system, so that the false alarm rate and the missing report rate are remarkably reduced.

A system and method are disclosed for advanced multimodal-sensor systems integrating various sensing characteristics for machine condition monitoring, including thermal imaging cameras, ultrasonic, vibration, temperature, magnetic sensors, high-band microphones, electro-magnetic emission detectors and others. The system's architecture comprises edge computing capabilities for real-time anomaly detection and operational feedback, utilizing edge machine learning (ML) models trained in the cloud. The system supports flexible configuration and calibration to optimize measurements based on machine requirements, while a cloud-based analysis framework enables robust data fusion, training and condition assessment. The method comprises performing automated diagnostic workflows enabled by models at the edge, reducing or eliminating human intervention, and significantly enhancing operational performance, maintenance and efficiency across multiple machines in an industrial setting.

A system, and the like, capable of improving user-friendliness when a work machine is diagnosed in a form intended by a user using a terminal device having a wireless communication function, are provided. A second external request signal based on a designated attribute regarding a designated work machine 200 designated through a terminal input interface 101 and a unique identifier read in non-contact manner from a designated component 222 with a non-contact sensor mounted on a terminal device 100 is transmitted to a real machine communication station 210 mounted on the designated work machine 200. Then, a second external response signal representing information regarding the designated component 222 in response to the second external request signal is transmitted from the real machine communication station 210 to the terminal device 100, and the information that is a diagnostic result of the designated component is output to a terminal output interface 102.

A diagnostic method, executable for example from remote computing devices or onboard control units for machines having various systems, each system having associated electronic controllers. For a specified machine and configuration, a hierarchical list is automatically generated comprising systems associated with the machine and one or more expected electronic controllers for each system. At least pursuant to initiation of a diagnostic program via an onboard control unit of the specified machine, respective input signals are obtained from present electronic controllers in functional communication with the onboard control unit. For each of any expected electronic controllers for which respective input signals are not obtained, a status alert is generated corresponding to a determined missing status or failure status, wherein the determined missing or failure status is based on an optionality of the respective expected electronic controller for which respective input signals are not obtained and / or an optionality of the corresponding system.

A diagnostic system for electronic gaming machines (EGMs) includes a power supply, and a diagnostic device in electrical connection with the power supply, the diagnostic device configured for placement within a cabinet of an EGM. The diagnostic device includes an attachment device configured to couple the diagnostic device to the EGM, a sensor array including at least one sensor for sensing a condition associated with the EGM and configured to generate conditions data based on the sensed condition, a communications device configured to transmit the conditions data to a remote location, a memory configured to store the conditions data, and a processor configured to analyze the conditions data and determine a diagnostic evaluation based upon the analyzed conditions data.

A diagnostic system (1) comprises: a machining data acquisition unit (10) that acquires machining data from the start to the end of machining by a machine tool (2); a section extraction unit (11) that extracts, from machining sections of the machining data, a first section that is a section of cutting and a second section that is a section other than the first section; a feature amount calculation unit (13) that calculates a first feature amount in the first section of the machining data and a second feature amount in the second section of the machining data; a corrected feature amount calculation unit (14) that calculates a third feature amount corresponding to an actual cutting load that is a load of cutting by subtracting the second feature amount from the first feature amount; and a machining diagnostic unit (17) that executes a machining diagnosis on the basis of the third feature amount.

An automated self-precision validation accelerometer is configured for machine diagnosis for efficient and accurate vibration readings from the machine. The accelerometer sensor system conducts self-precision validation test and diagnosis. The accelerometer sensor system comprises two accelerometer sensors for more data acquisition. The usage of two tri-axial accelerometers identify ill-health of the sensors through a self-precision validation test conducted by a firmware module configured in the microcontroller unit that triggers the accelerometers to conduct in built self-test at specific constraints. The system 300 for self-precision validation accelerometer sensor comprises a power supply unit 301, a self-test sensor assembly 302, a wireless interface unit 303, and an external device 304. The firmware module 302c further sends a report on the test to the external device 304 through a wireless interface unit 303 advising for the replacement of sensor.

A work machine diagnosis device includes: a display device that displays an operation procedure of a work machine; a controller that acquires a state quantity from a sensor that senses the state quantity of the work machine while the work machine is being operated with the operation procedure, and diagnoses actuation performance of the work machine based on the state quantity; and an output device that outputs a diagnosis result. The controller determines an actuation performance value representing predetermined actuation performance of the work machine and a plurality of causal parameters that influence the actuation performance value; computes a degree of influence of each of the plurality of causal parameters on the actuation performance value based on the plurality of causal parameters, and a reference value preset for each of the causal parameters; and causes the output device to output the actuation performance value and the degrees of influence.

Methods and apparatuses that utilize machine learning techniques to identify maintenance assets using sets of machine-health diagnostic images and link individual machine-health diagnostic images to the identified maintenance assets are described. The sets of machine-health diagnostic images may include a set of thermal images, a set of visible-light images, and / or a set of acoustic images. An identified maintenance asset may comprise an individual machine associated with a unique asset identifier. A diagnostic image linking system may acquire machine-health diagnostic images, apply object detection and other computer vision techniques to identify a particular machine within the machine-health diagnostic images, determine machine properties for the particular machine, generate a feature vector using the machine properties, select machine learning models corresponding with maintenance assets, generate predicted answers using the machine learning models, and generate an asset identifier for the particular machine based on the predicted answers.

Diagnostic aid system for a working machine (100), wherein the diagnostic aid system comprises: a display device (33); a controller (10) that specifies a diagnostic section in the working machine (100), based on candidate information about an abnormality candidate in the working machine (100), specifies a first sensor connection position of a diagnostic sensor (34) for diagnosis of the diagnostic section, and controls the display device (33) to display position information of the first sensor connection position; and a monitoring sensor (31) which is connected to a second sensor connection position of the working machine (100), wherein The controller (10) determines whether the first sensor connection position differs from the second sensor connection position, and If the controller (10) has determined that the first sensor connection position differs from the second sensor connection position, the controller (10) determines whether it is possible to reconnect the monitoring sensor (31) from the second sensor connection position to the first sensor connection position or not.

The invention relates to an analytical machine arrangement (100). A method comprises obtaining (A10) N time domain measurement samples at a time T (n), where n traverses the number of samples N, and the distance between adjacent samples in the time domain is T. The method further comprises determining (A12) updated, normalized time-domain measurement samples having a timing Tadapt (n) for each sample based on the associated T (n) and T adjustment, further based on an actual frequency factual (n) of the machine arrangement (100), and further based on an undesired behavior and / or error-related frequency F. The method further comprises determining (A12) the updated, normalized time-domain measurement samples having the timing Tadapt (n) for each sample based on the associated T (n) and T adjustment, further based on the actual frequency factual (n) of the machine arrangement (100). The method further comprises determining (A14) M reconstructed, normalized time domain measurement samples having a constant sampling period T2 at a time T (m), where m traverses the number M of samples. Furthermore, the method comprises performing (A16) a frequency analysis on the reconstructed time-domain measurement samples.

A machine diagnostic system (100, 600) is disclosed. The machine diagnostic system (100, 600) comprises at least one processor (506) coupled to a memory (508) in which computer-executable instructions are stored. When executed by the at least one processor (506), the instructions configure the at least one processor (406) to acquire first fault information (614) associated with a first set of machines; to train a first model (612) based on the first fault information (614) associated with the first set of machines; to simulate the injection of faults into a second set of machines using the first model (612) in order to generate second fault information (616); and to train a second model (622) based on the first fault information and the second fault information. A method for such a machine diagnostic system (100, 600) is further disclosed.

The invention relates to a method and a system for the secure retrieval of machine diagnostic data for an agricultural machine (1). The method comprises the following: receiving a service request from a machine operator of an agricultural machine (1) in a first computer unit (2) assigned to a service center; providing a request code associated with the service request in the first computer unit (2); transmitting the request code via a first data connection (10) from the first computer unit (2) to an output unit; outputting the request code to the machine operator by means of the output unit; transmitting the request code via a second data connection (12) and receiving the request code in a third computer unit (15) assigned to a service person;Transmitting the request code from the third computer device (15) to the first computer device (2) and providing a diagnostic access request to the first computer device (2); transmitting, receiving, and outputting the diagnostic access request to the machine user via the output device; receiving a response input from the machine user at the output device and providing a response message in response to receiving the response input; receiving the response message at the first computer device (2) and retrieving machine diagnostic data for the agricultural machine (1) via a data interface of the agricultural machine (1) when the response message indicates an acknowledgment by the machine user of the diagnostic access request.

The present application provides a method and system for dynamic integrated fault detection of wind turbine gearboxes based on feature fusion, which relates to the field of data processing technology. The method includes: obtaining each preliminary feature set; quantifying the feature-feature and feature-fault nonlinear relationships of each preliminary feature set to obtain each preliminary screening feature set; analyzing the contribution of each feature in each preliminary screening feature set, performing feature fine screening, and generating each fine screening feature set; calling a multi-agent integrated fault detection system, and performing bottom-up multi-layer agent information sharing and collaborative decision-making based on each fine screening feature set to generate wind turbine gearbox fault detection information. This application solves the technical problem in the prior art that the fault detection accuracy is not high due to the lack of deep mining of features and the reliance on a single-machine diagnostic system. By constructing a multi-agent integrated fault detection system, the false alarm rate and missed alarm rate are significantly reduced, achieving the technical effect of improving the accuracy of fault detection.

To obtain a diagnostic system that can achieve highly accurate machining diagnosis even when the changes in the feature quantities of machining data calculated from machining data are small in cutting processes. [Solution] The diagnostic system 1 includes a machining data acquisition unit 10 that acquires multiple machining data from a machine tool 2 for multiple machining operations performed under the same machining conditions from past machining operations to the present machining operation; a feature quantity calculation unit 13 that calculates feature quantities from the machining data; a change trend calculation unit 15 that calculates the change trend of the feature quantities; and a machining diagnostic unit 17 that performs machining diagnostics based on the change trend.

A system and method are disclosed for advanced multimodal-sensor systems integrating various sensing characteristics for machine condition monitoring, including thermal imaging cameras, ultrasonic, vibration, temperature, magnetic sensors, high-band microphones, electro-magnetic emission detectors and others. The system's architecture comprises edge computing capabilities for real-time anomaly detection and operational feedback, utilizing edge machine learning (ML) models trained in the cloud. The system supports flexible configuration and calibration to optimize measurements based on machine requirements, while a cloud-based analysis framework enables robust data fusion, training and condition assessment. The method comprises performing automated diagnostic workflows enabled by models at the edge, reducing or eliminating human intervention, and significantly enhancing operational performance, maintenance and efficiency across multiple machines in an industrial setting.

One approach to digital twin-enabled equipment diagnostics based on acoustic modeling includes receiving real-time audio inputs of an asset from a mobile device, analyzing the real-time audio inputs using one or more acoustic modeling algorithms to establish deviations from a baseline associated with the asset's digital twin, and, in response to determining that the deviations from the baseline are greater than a predetermined threshold, repeatedly prompting a user to move the mobile device until a stopping criterion is met.