A specimen processing system 100 which performs preprocessing and analysis of a specimen includes sensors 5a, 5b, . . . each detecting a driving state of a driving device installed in the system, an abnormality detecting part 3a determining from signal waveforms detected by the sensors 5a, 5b, . . . whether an abnormality occurs in the driving device, and a recording device sequentially recording the signal waveforms detected by the sensors 5a, 5b, . . . and storing a sensor signal waveform before or after the occurrence of an operation abnormality into an unerasable area when the abnormality is determined to have occurred in the abnormality detection part 3a. Consequently, there is provided a specimen processing system capable of realizing restoration from the time of the occurrence of an abnormality faster than in the past.

A fault finding support system is a fault finding support system for instructing a maintenance worker of an appropriate examination location and examination contents using fault knowledge data in which a causal relationship of fault of a target machine is described, the system including: an examination procedure creation unit that creates an examination procedure with respect to the examination location and the examination contents of the target machine using the fault knowledge data, an examination result storage unit that stores an examination history of performing examination using the examination procedure created by the examination procedure creation unit, an update target extraction unit that recommends an update location of the fault knowledge data using the examination history stored in the examination result storage unit, and a user interface that provides a function of displaying a location extracted by the update target extraction unit and updating the fault knowledge data.

A system and method for predicting the failure and estimating the health of the industrial equipment or industrial measurement equipment and diagnosing the root cause of the incipient failures is provided. The system and method are applicable to different types of flow meters used in flow measurement applications and other industrial equipment or industrial measurement equipment. A means to detect anomalies in the industrial equipment or industrial measurement equipment diagnostic signals is provided and thereby allowing incipient failure prediction. The system and method provides the means to calculate the current state of health of the industrial equipment or industrial measurement equipment. Leading indicator/failed component in the industrial equipment or industrial measurement equipment can be tracked down in the event of a failure. The system and method provides the means to label the normal and abnormal periods in the historical data based on the available diagnostic alarms and signals.

Systems and methods are provided for improving statistical and machine learning drift detection models that monitor computing health of a data center environment. For example, the system can receive streams of sensor data from a plurality of sensors in a data center; clean the streams of sensor data; generate, using a machine learning (ML) model, an anomaly score and a dynamic threshold value based on the cleaned streams of sensor data; determine, using the ML model and based on the anomaly score and the dynamic threshold value, a correctness indicator for a first sensor in the plurality of sensors; and using the correctness indicator, correct the first sensor.

A stress generated in each of a plurality of components is calculated during simulation using a machine including these components. A simulation device includes a storage that stores assembly data of a machine including a plurality of components and a program for control of a driver connected to machine, and a controller configured to execute a simulation of machine. The controller causes driver to operate in the simulation and calculates a stress generated in each of the plurality of components in the simulation in response to driver being driven.

An indicator generating method for generating an indicator which is suitable for maintenance prediction of a water heating system is proposed. A power state indication device generates a high power consumption signal if a heating device of the water heating system is activated. The time duration of the activation is such an indicator, if no water flow is present. Furthermore, the time interval between subsequent activations is such an indicator. A predictive maintenance method processes these condition-based indicators and determines a remaining useful lifetime according to a predictive maintenance model. The predictive maintenance device outputs a maintenance signal indicating required maintenance, if the remaining useful lifetime drops below a predetermined threshold. The methods may be performed by water heating systems or beverage makers.

A method for collecting error code history includes detecting a fault caused by errors in a machine, initiating a dispatch request from the machine to a service location, generating a first quick response code in response to a first input signal from a technician, where the first quick response code encodes first configuration items that describe the machine and first error codes that characterize the detected errors, presenting a first graphical image of the first quick response code on a display, performing a self-test in the machine in response to a second input signal, generating a second quick response code after the self-test has been completed, where the second quick response code encodes second configuration items that describe the machine and second error codes, and presenting a second graphical image of the second quick response code on the display.

Disclosed is a method and apparatus for inspecting defects in a washer based on deep learning. According to an embodiment of the present disclosure, a method for inspecting defects in a washer based on deep learning gathers learning data while the washer operates and trains a first ANN model for diagnosing the condition of the washer and a second ANN model for securing the reliability of the result of inspection of the condition of the washer. Thereafter, the washer may make a diagnosis of whether the washer is defective based on the two pre-trained ANN models and are thereby able to continuously monitor whether the washer has an abnormal condition. According to an embodiment, the artificial intelligence (AI) module may be related to unmanned aerial vehicles (UAVs), robots, augmented reality (AR) devices, virtual reality (VR) devices, and 5G service-related devices.

A field agricultural machinery test platform, comprising a field soil groove, traveling guide rails, traveling trolleys, a hitch trolley, a hitch device mechanism, and a test system. The two guide rails are provided on both sides of the field soil groove in parallel, and the traveling trolleys are located on the guide rails; a cross beam is provided between the two guide rails, and the two ends of the cross beam are respectively connected to the traveling trolleys; the hitch trolley is provided on the cross beam, and a hitch device is provided on the hitch trolley; the test system is provided on the hitch trolley and the hitch device; a test machine is connected to the hitch device; the test system comprises an image assembly, a force test assembly, and a control assembly which are mounted on the hitch trolley.

A method for diagnosing and predicting operation conditions of large-scale equipment based on feature fusion and conversion, including: collecting a vibration signal of each operating condition of the equipment, and establishing an original vibration acceleration data set of the vibration signal; performing noise reduction on the original vibration acceleration data set, and calculating a time domain parameter; performing EMD on a de-noised vibration acceleration and calculating a frequency domain parameter; constructing a training sample data set through the time domain parameter and the frequency domain parameter; establishing a GBDT model, and inputting the training sample data set into the GBDT model; extracting a leaf node number set from a trained GBDT model; performing one-hot encoding on the leaf node number set to obtain a sparse matrix; and inputting the sparse matrix into a factorization machine to obtain a prediction result.