8 results about "Periodic maintenance" patented technology

The invention provides an intelligent rail smoothness adjusting method and system based on dynamic detection and big data analysis, and belongs to the technical field of railway engineering maintenance. The method comprises the steps that track geometric data, vehicle dynamics response data and environment data are collected in real time through a multi-dimensional sensor array installed on an operating train; uploading the data to a cloud big data platform for fusion and deep mining, constructing a track state degradation prediction model by using a machine learning algorithm, and accurately predicting the development trend of track irregularity; and based on the prediction result, automatically generating a targeted track fine adjustment scheme, and issuing the scheme to an intelligent maintenance robot deployed on the line or guiding a manual maintenance team. The system comprises a data acquisition layer, a cloud analysis layer and an intelligent execution layer. According to the method, the change of the track state from'regular maintenance 'to'predictive maintenance' is realized, the maintenance efficiency, the precision and the line smoothness are remarkably improved, and the maintenance cost of the whole life cycle is reduced.

The invention discloses an automatic generation method and system for a periodic maintenance work order of equipment, and relates to the technical field of automatic work order management control. The automatic generation method and system for the periodic maintenance work order of the equipment comprises the following steps: S1, constructing a periodic task basic data set; s2, based on the periodic task basic data set, identifying a periodic adaptability relationship between an equipment state and a plan configuration parameter; s3, according to the corresponding relation between the equipment operation behavior and the planned cycle configuration, judging a cycle adjustment requirement; s4, evaluating a task response offset condition in combination with a work order execution progress and an operation stability state; and S5, generating information content with node attributes, pushing the information content to the configuration object, and recording a corresponding sending state. The problem that the work order process data is not utilized due to the fact that a current system evaluates the execution state only after the work order is executed and does not recognize the running trend change of the execution process is solved.

The invention provides a comprehensive scheduling method for regular maintenance of flexible equipment. The method comprises the following steps of: firstly, adopting a strategy scheduling process of layer priority, short time and equipment priority; secondly, on the basis of a forest fire fighting model, according to the relation between the number of processed procedures and the number of unprocessed procedures and loss generated by the equipment in a maintenance period, the maintenance starting point and duration of the flexible equipment are determined; and finally, a dynamic adjustment strategy is adopted, so that maintenance of flexible equipment is realized, and the total time for product processing is reduced.

The invention provides a high-voltage isolation switch contact state intelligent verification and maintenance auxiliary method. Multi-dimensional parameters such as contact temperature, contact resistance, micro displacement and environment temperature and humidity are collected in real time through the integrated sensing module, after data preprocessing and spatial-temporal feature extraction are conducted through the edge calculation unit, the parameters are input into a CNN-LSTM fusion AI model for intelligent diagnosis, the degradation state of the contact is accurately recognized, and the accuracy of the contact degradation is improved. And secondary verification is implemented in combination with historical trends and environmental factors, so that false alarms and missing alarms are effectively reduced. The system supports local quick response and cloud linkage early warning, and realizes conversion from'periodic maintenance 'to'state maintenance'. In actual measurement of a 220kV transformer substation, the state recognition accuracy rate reaches 98.5%, the maintenance frequency is reduced by 40%, and the operation and maintenance safety and economy are remarkably improved.

The application discloses a vehicle information database perfecting method for automatic oiling, which integrates real-time, quasi-real-time and periodic maintenance and updating. The periodic maintenance and updating is triggered and completed manually; the real-time updating is triggered by events including new vehicle model design or market release of a vehicle manufacturer, and includes real-time automatic updating, real-time semi-automatic updating and / or real-time manual updating; and the quasi-real-time updating is triggered by events that a vehicle not matching the database information appears at a gas station, and includes quasi-real-time automatic updating, quasi-real-time semi-automatic updating and / or quasi-real-time manual updating. The application solves the problems of untimely information acquisition and unobtainable part of vehicle model feature point information by means of protocol pushing, automatic searching, manual surveying and mapping and autonomous surveying and mapping, and changes the past situation that vehicle information database perfecting mainly relies on manual periodic maintenance and sometimes cannot be perfected, and is more complete, flexible and practical.

The present application mainly relates to the technical field of aircraft maintenance. In order to solve the problem of low prediction accuracy of hinge wear under the scene of small sample, variable working condition, individual difference and equipment degradation, the present application provides a kind of aircraft door hinge wear prediction method based on dynamic wear coefficient, the core is based on real wear coefficient as training label, constructs physical information embedding type neural network, the working condition parameters of hinge are as input, the real wear coefficient is as training label and is trained to obtain the wear coefficient prediction model, after training, the working condition parameters collected in real time are input into the model to obtain the dynamic wear coefficient that changes with the working condition in real time, and the wear depth is recursively calculated based on the dynamic wear coefficient using discrete integration method;At the same time, the measured wear depth obtained by periodic maintenance is used to realize the adaptive correction of the model by weighting fusion and scaling update of the output layer weight of the model, and the high-precision adaptive prediction result of the wear depth of the aircraft door hinge is obtained.

The utility model discloses an inspection unmanned aerial vehicle protection structure in a hearth, which comprises a main body unit comprising a rack main body, four ends of the rack main body are respectively and fixedly provided with four connecting frames, and the main body unit further comprises a flight assembly; the protection unit comprises protection parts and an adjusting part, and the protection parts are located at the four ends of the adjusting part; the supporting unit comprises a supporting part and a power part, the power part is located on the top face of the supporting part, the adjusting part comprises two bidirectional hydraulic cylinders A fixed to the upper end face and the lower end face of the rack body, and the protection part comprises a sliding rod fixedly connected to the inner wall of the connecting frame. The bidirectional hydraulic cylinder A and the bidirectional hydraulic cylinder B are matched to work, so that the protection frame can contract, extend and move, can extend out to quickly shield and protect the flying blades when routing inspection work is carried out in a hearth, can contract when regular maintenance work is carried out, and is convenient to maintain. The flight blades are quickly disassembled and maintained, and the service life of the device is prolonged.

A device for planning the maintenance of a passenger elevator comprising an elevator car with a door equipped with an accelerometer for detecting door vibration, a data collection device designed to generate a vibration profile from the detection, a transmission device for transmitting the vibration profile to a server, and a server for analyzing the vibration profile, wherein the data collection device is spatially connected to the elevator car and is designed to determine the deviation of the vibration profile from a reference profile and, depending on the deviation from at least a threshold value or at least a range of values, cause the transmission device to transmit the deviation and / or the vibration profile to the server.and where the server is spatially separated from the passenger elevator and is designed to compare the deviation and / or vibration profile with at least one threshold value or at least a range of values ​​and, depending on the comparison, issue a signal indicating whether no action is to be taken, an action within the scope of the next regular maintenance, or an action before the next regular maintenance.