TL;DR: In this paper, the authors proposed a failure prediction method using failure prediction apparatus, including: receiving time series data about measured performance parameters from a device under test, encoding the time-series data with a plurality of symbols corresponding to a predetermined range, calculating a transition probabilities between the symbols of the encoded time- series data, and generating a transition matrix according to the transition probabilities.
Abstract: Provided is a failure prediction method using a failure prediction apparatus, including: receiving time-series data about measured performance parameters from a device under test; encoding the time-series data with a plurality of symbols corresponding to a predetermined range; calculating a transition probabilities between the symbols of the encoded time-series data, and generating a transition matrix according to the transition probabilities; calculating an abnormal indicator, which is a difference between the transition matrix and a pre-stored database, and an increased value of the abnormal indicator; and comparing the increased value of the abnormal indicator and a predetermined threshold value, and if the increased value of the abnormal indicator is greater than the predetermined threshold value, predicting that failure of the device under test is to occur.
TL;DR: In this paper, the authors proposed a system to facilitate the maintenance by providing a detecting sensor of the opening/closing state and a water level sensor in a vacuum valve unit installed in a house inlet to judge abnormal conditions in accordance with the detected figure.
Abstract: PURPOSE: To facilitate the maintenance, by providing a detecting sensor of the opening/closing state and a water level sensor in a vacuum valve unit installed in a house inlet to judge abnormal conditions in accordance with the detected figure and indicate the result with a lamp when it is abnormal. CONSTITUTION: When a certain volume of sewage is kept in a sewage pit 3 in a building site, a vacuum valve 4 is opened and sewage is sucked to a sewage-collecting tank in a vacuum pump station and then transferred to a sewerage plant by a pump. In this system, a detecting sensor 16 of the opening/ closing state of the valve and a water level sensor 17 are provided in the vacuum valve unit 11 and further, a controller distinguishing an abnormal condition on the basis of the detected figure is provided. In case of an abnormal condition, it is informed by flickerring of a lamp on an abnormal indicator or other means to repair the abnormal part and make it normal before sewage overflows the pit 3. In this way, abnormal parts are detected in the early stages for effective maintenance.
TL;DR: In this article, the authors presented a method for recognizing abnormal indicator diagrams in the field of automatic oil extraction, which is characterized by comprising the following steps of: establishing a working motion model of a pumping unit, and simulating suspension point load and displacement to obtain the variation rule; carrying out comparison and judgment between the variation rules and the variation of the measured suspension point in a complete cycle, to recognize the abnormal indicator diagram.
Abstract: The invention relates to a recognition method of an abnormal indicator diagram, and belongs to the technical field of automatic oil extraction, and the method is characterized by comprising the following steps of: establishing a working motion model of a pumping unit, and simulating suspension point load and displacement to obtain the variation rule; carrying out comparison and judgment between the variation rule and the variation rule of the load and displacement of the measured suspension point in a complete cycle, to recognize the abnormal indicator diagram. Through establishing the workingmode of the pumping unit, the variation rule is obtained, the variation rule of the measured data in the same complete cycle is judged and analyzed to carry out the recognition of the abnormal indicator diagram, the abnormal indicator diagram can be effectively eliminated, and the foundation is laid for the data analysis of the indicator diagram of the oil field, the theory support is provided for the development of the indicator diagram acquisition equipment, so that the safe and efficient production of the oil field is guaranteed, the accuracy of judging the working condition through the indicator diagram can be greatly improved, the operation is simple, and the method is suitable for popularization and application.
TL;DR: In this paper, a method for detecting abnormality adapted to detect abnormal operations of an operating system is presented, which includes: calculating a safe range of usage of the operating system during one or more time periods according to a historical data stream; calculating abnormal ratios corresponding to the one or multiple time period according to current data stream and the safe range; selecting one or several abnormal time periods from the one and multiple time periods based on a threshold and the abnormal ratios; calculating an abnormal indicator for each of the one abnormal indicator; and ranking the abnormal indicators according to the abnormal indicator(
Abstract: A method for detecting abnormality adapted to detect abnormal operations of an operating system is provided. The method includes: calculating a safe range of usage of the operating system during one or more time periods according to a historical data stream; calculating abnormal ratios corresponding to the one or more time periods according to a current data stream and the safe range of usage; selecting one or more abnormal time periods from the one or more time periods according to a threshold and the abnormal ratios; calculating an abnormal indicator for each of the one or more abnormal time periods according to the historical data stream and the current data stream; and ranking the one or more abnormal time periods according to the abnormal indicator(s).
TL;DR: In this paper, a high-precision indicator diagram production counting correction statistical method is proposed for automatic oil extraction, which is characterized by counting the operation time of an oil well, extracting all indicator diagrams in the running time of the oil well; removing the abnormal indicator diagrams from allindicator diagrams in oil well operation time to obtain residual indicator diagrams; determining the effective operation time, corresponding to the residual indicator diagram; and summarizing the yield corresponding to each period of time in the effective operating time.
Abstract: The invention relates to a high-precision indicator diagram production metering correction statistical method, which belongs to the technical field of automatic oil extraction and is characterized bycomprising the following steps of: counting the operation time of an oil well; extracting all indicator diagrams in the running time of the oil well; removing the abnormal indicator diagrams from allindicator diagrams in the oil well operation time to obtain residual indicator diagrams; determining the effective operation time of the oil well corresponding to the residual indicator diagram; and summarizing the yield corresponding to each period of time in the effective operation time to complete high-precision indicator diagram production statistics. The method mainly comprises the steps of oil well startup and shutdown time confirmation; eliminating the abnormal indicator diagram in the startup time period; determining the time length represented by each remaining work map; according tothe high-precision indicator diagram production counting correction statistical method, carrying out daily production statistics according to the timeliness of each indicator diagram. Precision is high, and better and wider adaptability is achieved.