70results about How to "Predict failure" patented technology

An arrangement includes a utility meter housing that contains or supports a first sensor, a second sensor, and a processing circuit. The first sensor is configured to measure a first parameter, the first parameter relating to an environmental condition within the meter housing. The second sensor is configured to measure a second parameter. The processing circuit is operably connected to the first sensor and to the second sensor, and is configured to record information relating to one or more events, each event corresponding to a detection of an out of range condition by each of the first sensor and the second sensor.

A method for predicting bearing failure, wherein the bearing includes an inner race, an outer race, and a plurality of rolling elements between the inner and outer race. The method includes coupling a sensor assembly to the outer race, the sensor assembly including at least one temperature sensor and at least one acoustic sensor, generating a bearing performance model based on an initial signal received from the sensor assembly, receiving a second signal from the sensor assembly, and comparing the second signal to the bearing performance model to predict a bearing failure.

A method for predicting the failure of a data storage device having a slider heater is disclosed. For slider heaters exhibiting a decreasing resistance aging characteristic, a failure warning is produced when heater resistance suddenly increases 2 to 5%, or dR/dt changes sign from negative to positive. For slider heaters exhibiting an increasing resistance aging characteristic, a failure warning is produced when the heater resistance suddenly drops 2 to 5%, or dR/dt changes sign from positive to negative. Additionally, random changes in heater resistance exceeding nominal measurement error may also be utilized to produce a failure warning. This method provides advance warning of potential data read/write errors well before the open circuit failure of the slider heater occurs.

An optical transceiver and methods for using the same are disclosed. The optical transceiver and methods may be useful for providing more accurate information regarding trends in operation of the optical transceiver, predicting an impending failure of the optical transceiver, and providing details of the optical transceiver prior to failure. The optical transceiver generally includes (1) at least one of (i) a receiver configured to receive optical information and (ii) a transmitter configured to transmit optical information, (2) circuitry configured to sample data for one or more operational parameters of the receiver and/or transmitter, (3) logic configured to perform one or more statistical calculations on the sampled data to generate statistical information, and (iv) one or more memories configured to store the sampled data and the statistical information.

The invention discloses a high-voltage breaker mechanical characteristic fault probability monitoring method and system based on on-line monitoring. The method comprises the steps that (1) the mechanical characteristic curve of the breaker is read by an on-line monitoring system under the normal circumstance of the breaker; (2) when the breaker is put into operation in the field, the mechanical characteristic curve of the breaker is read by the on-line monitoring system under the operation circumstance of the breaker; (3) fault probabilities, of energy storage motor fault probability, tripping fault probability and closing fault probability, showed by all characteristic values are respectively calculated by the on-line monitoring system; (4) the total on-line monitoring fault probability, namely, the sum of the fault probabilities worked out according to the third step: F=FM+FF+FH, of the breaker is calculated; (5) whether alarming should be conducted or not is judged by the on-line monitoring system according to the fault probabilities, and a fault alarming signal is generated by the on-line monitoring system when the fault probability is equal to or larger than an threaded alarming value and is not generated by the on-line monitoring system when the fault probability is smaller than the threaded alarming value.

An early warning system and method for predicting a failure of a backlight of any display that uses internal illumination, such as a liquid crystal display (LCD), digital light processing™ (DLP), or liquid crystal on silicon (LCoS). This display could be a flat screen type or a projector type. A display indicating that failure is imminent within a certain period of time is provided. A countdown display of life remaining may also be provided. Color temperature of the backlight is monitored and compared over time to form the prediction of failure. Measurements may also include measurements of individual components of light, such as the red, green, and blue components. Components may be compared individually over time to detect a color shift that reaches a threshold of prediction failure.

A method and a system are presented for monitoring a battery in a motor vehicle. In the method, a first module ascertains operating quantities of the battery. Variables that represent the operating quantities are compared with a load capacity model in order to ascertain quantities characterizing the reliability of the battery, so that a future behavior of the battery can be predicted.

The invention discloses a pipeline fault prediction method and apparatus. The method is applied to a pipeline to be predicted, and the method comprises the following steps: obtaining current state data of the pipeline by prediction device at first, determining a current probability of generating faults of the pipeline at present according to the state data by a pre-established diagnostic model, and determining a predicted probability of generating faults of the pipeline within a set time period in the future according to the current probability and a historical probability of generating faults of the pipelines determined in the history. By adopting the method, the faults of the pipeline can be predicted, and corresponding maintenance and management of the pipeline can be carried out according to the prediction result.

The invention discloses a wind turbine generator main shaft bearing fault prediction method. According to the method, based on historical fault maintenance data of a main shaft bearing of a draught fan, statistics and a machine learning method are combined, multiple monitoring indexes of the draught fan serve as input variables, the state of the main shaft bearing serves as a prediction output variable, statistical analysis is conducted on a prediction value of the output variable, and a threshold value is set for fault prediction. The method has high accuracy and stability, and can predict the fault of the main shaft bearing one week in advance and discover early abnormality as soon as possible.

The invention discloses a large pump unit on-line monitoring and diagnosis system. The large pump unit on-line monitoring and diagnosis system comprises an air gap sensor, an electric eddy sensor, an acceleration sensor, a temperature sensor, a signal conditioner, a signal processor, a WEB server, a data server, a user client, a fire wall, a router and a remote expert sub-system. Information collected by the four sensors is conditioned through the signal conditioner and then sent to the signal processor, data processed through the signal processor are transmitted to the WEB server, the data server and the user client, the data of the user client are checked by a user, and the data of the WEB server are sent to the remote expert sub-system through the fire wall and the router; the remote expert sub-system provides corresponding maintenance measures according to the operation state of a unit. The large pump unit on-line monitoring and diagnosis system can monitor the operation conditions of the unit in real time, monitor the changes of the air gap and the magnetic flux of a motor, predict faults of the unit, shorten the stop time and reduce the overhaul cost.

The invention provides a failure predication method for a background operation and maintenance system of a bank. The method includes the steps: acquiring a bank data sample and extracting initial feature data from the bank data sample; subjecting the initial feature data to dimensionality reduction to obtain final feature data; using a random forest method for classified cleaning of the final feature data so as to carry out failure predication on the background operation and maintenance system of the bank according to classification results; when failures of the background operation and maintenance system of the bank is predicated, adjusting parameters of the background operation and maintenance system of the bank according to the final feature data to avoid failures of the background operation and maintenance system of the bank or lower failure occurrence probability of the background operation and maintenance system of the bank. According to the method, failures of the background operation and maintenance system of the bank can be effectively predicated, and the failures can be avoided or the failure occurrence probability can be lowered effectively by precaution. The invention further provides a failure predication system for the background operation and maintenance system of the bank.

The invention provides a sliding bearing fault diagnosis method based on a generative adversarial network and a convolutional neural network. The method comprises the steps of: collecting vibration signals and bearing bush temperatures of a sliding bearing under no fault and different fault conditions, and carrying out preprocessing; carrying out ensemble average empirical mode decomposition on the vibration signals to obtain an optimal intrinsic mode function and a characteristic frequency corresponding to the optimal intrinsic mode function; constructing state matrixes on the basis of the bearing bush temperatures, and respectively inputting the state matrixes into the generative adversarial network according to categories to generate samples; carrying out edge expansion on the data of an initial sample set, and setting fault state labels; constructing a sliding bearing convolutional neural network model, and training the model by using the data set and the corresponding fault labels; and collecting data of the current sliding bearing, constructing a state matrix, inputting the state matrix into the trained neural network model, and carrying out fault diagnosis and prediction. With the method of the invention adopted, the problems of unobvious vibration fault signals, poor diagnosis effect, insufficient bearing bush temperature utilization and insufficient sample size are effectively solved.

The present invention generally relates to a customer support methodology which can be enacted with a combination of automated support solutions and support technicians for industries where there are services which relate to a customer account(s). Its main purpose is the effective use and acquisition of data to better understand the customer, the product/service, and the support system in order to better handle support issues that have and could possibly happen. The innovation in customer support methodologies are established in key general areas: profiling, support session routing, authorization, verification, data convergence, data protection, communication, predictive analysis, government compliance, customer satisfaction, and preemptive actions.

Devices and methods for detecting operational parameters associated with a gas separator used in an electric submersible pump in a wellbore. A fiber optic sensing arrangement is used to detect the operational parameter and includes a fiber optic signal processor and an optic fiber that is associated with the gas separator to provide a signal indicative of the parameter to the signal processor.

Managing operation of a sealing element is described. In some aspects, failure of the sealing element of a pressure drilling system may be predicted. Deformation of the sealing element as a tool joint is pulled through the sealing element may be detected and tracked to determine if a deformation pattern of sealing element changes. Responses of sealing element due to one or more of stress, strain, temperature, mechanical load, and pressure using a network of sensors around sealing element can be detected. Responses may be tracked over time. Detected responses are compared to tracked responses to identify changes in the symmetry of responses over time or changes in magnitude of responses over time. Changes are associated with fractures occurring within sealing element. A remaining life of sealing element is predicted based on the changes and replacement may be scheduled based at least in part on the predicted remaining life.

An alerting method for fan failure first reads a target value of rotating speed of a fan motor. Predetermining values of each parameters of the fan motor is calculated according to the target value of rotating speed of the fan motor. If a current value of rotating speed of the fan motor is lower than the target value of rotating speed of the fan motor, the failure recorded in a counter is added one time. If a current peak value of the fan motor is higher than a first predetermining current value, the failure recorded in the counter is added one time. If the duration of the current which is higher than a second predetermining current value of the fan motor is higher than a predetermining duration, the failure recorded in the counter is added one time. An alarm signal is sent if the failure recorded in the counter is larger than a predetermining time.

The invention relates to an optical cable fault prediction method based on temperature and resistance, and relates to the technical field of optical cable communication state prediction, solving the problems that the current method only can process the occurred faults in the optical cable line and cannot analyze the grounding insulation resistance value of an optical cable protection sleeve. The optical cable fault prediction method based on temperature and resistance can predict the grounding insulation resistance of the optical cable protection sleeve through an improved Gauss Wolf Pack Algorithm-Extreme Learning Machine (GWPA-ELM) prediction algorithm, can predict the temperature of the optical cable protection sleeve through a difference autoregression moving average model (ARIMA) algorithm, and can evaluate the state of the optical cable protection sleeve through the predicted resistance value and temperature. The optical cable fault prediction method based on temperature and resistance can predict the possibly occurred fault of the optical cable in the future, and can make maintenance strategy in advance.

The invention discloses a fuel oil moisture on-line monitoring device, which can accurately measure the moisture content change of measured oil on line, display the moisture content value (ppm) of themeasured oil and the moisture change curve of a fuel oil system in different time periods in real time, and assist an operator in judging whether the oil needs to be replaced or not, so that the oilcan be saved, and the equipment failure can be predicted. The device is simple and practical in structure, and the measuring sensor is more convenient to maintain and replace due to the structural characteristics. the device can be easily and economically installed on a newly-built device to be tested or an original device to be tested,; the device can be widely applied to ships and other industries. The device is simple in structure, convenient to use, quick in response and low in price. The moisture content monitoring is fast and accurate. The structure is simple, and installation and maintenance are convenient; the adopted sensor has no movable part, is maintenance-free, is connected with the plunger probe and the tee joint, and has a simple industrial online installation form.