42results about How to "Large amount of collected data" patented technology

The present invention belongs to the field of power plant security control systems, and particularly relates to an LSTM-based gas turbine online detection method and apparatus. The method is characterized in comprising the following steps: data collection; normalization processing; feature extraction; LSTM abnormality detection model training; and online abnormality detection: inputting to-be-detected data to a trained detection model, to obtain a model prediction value, calculating a difference between the prediction value and a sensor measured value to obtain an absolute value, and if the absolute value exceeds a given threshold, determining that abnormality occurs. The method is suitable for processing and predicting important events with a relative long interval and delay in a time series, and is suitable for analysis and fitting of the time series. A deep learning concept and technology is fully utilized to automatically select and extract hidden characteristics in data information detected by a device sensor, so as to implement online abnormality detection based on gas turbine real-time measuring point data. The LSTM-based gas turbine online detection method is large in collected data quantity, small in analysis error, and high in early warning result accuracy rate.

The invention discloses a leakage detection method and device for a vertical plastic-laying anti-leakage curtain. The leakage detection device comprises the vertical plastic-laying anti-leakage curtain, an accumulator, a plurality of electrodes, an electrode conversion box and direct current electrical prospecting apparatus. Two measuring lines are laid on the two sides of the anti-leakage curtaincorrespondingly; the electrode conversion box and the direct current electrical prospecting apparatus are arranged on the anti-leakage curtain and connected with the electrodes; and the multiple electrodes are embedded on the measuring lines sequentially with equal distances. The direct current electrical prospecting apparatus is controlled to emit currents to the underground according to the setsequence, so that potential differences are formed between the electrodes, accordingly, the current intensity and the potential differences are measured; and forward simulation is conducted accordingto the measuring results, and thus the resistivity profiles of the laid measuring lines can be obtained. The electrodes only need to be placed on the two sides of the anti-leakage curtain, therefore,construction is easy and convenient in actual engineering, detection can be conducted in the laying process of a vertical anti-leakage film, and thus hidden dangers can be treated more timely.

The invention discloses a Microstation v8i-based city rapid-modeling method, which comprises the following steps of: performing an aerial survey on a tested area according to a conventional aerial photogrammetric survey method by adopting an aerial photogrammetric survey system; and 2, performing analysis processing on aerial survey data in a Microstation v8i software environment by using a processor, namely, establishing a three-dimensional aerial photogrammetric survey model, performing land feature classification and marking, correspondingly establishing a land feature type layer-color mapping table, performing vector data acquisition, establishing models of houses, scattered trees and land features of other types respectively, processing all the land features in the tested area respectively, and obtaining three-dimensional geometric models of all the land features in the tested area.

The invention provides a communication iron tower deformation automatic detection device and detection method. The detection device comprises a base, a detection main frame, trackballs, springs, connecting rods and rheostats; the base is disc-shaped as a whole and is fixed on a beam of a communication iron tower. The upper surface of the base is provided with a number of tracks evenly distributed in the radial direction. The trackballs are arranged on the tracks, and the detection main frame is welded and fixed at the middle position of the upper surface of the base, and the sliding rheostats are arranged on the inner side of the detection main frame. Each sliding rheostat has a slipping sheet and a rheostat main body. The plurality of springs are separately installed in the corresponding tracks. One end of each spring is in fixed connection with the corresponding trackball, and the other end of the spring is fixedly connected to the detection main frame. The connecting rods, having the same number as the tracks, are installed in the same direction as the springs. One end of each connecting rod is fixedly connected to the corresponding trackball, and the other end of the connecting rod is fixedly connected to a corresponding sliding sheet. The device and method of the invention have advantages of being simple in structure, low in cost, high in measurement precision, being convenient and fast, etc.

The invention discloses a suspended overhead transmission line online monitoring system and method. The system comprises a suspended monitoring device and a master station system, wherein the suspended monitoring device comprises a mainboard module, a sensor module, a data storage unit, a suspension module, an electricity taking device, a communication module, a camera-shooting module and an innerdiameter adjustment mechanism; the mainboard module is connected with the sensor module, the suspension module, the camera-shooting module, the communication module and the data storage unit; and thesuspension module and the inner diameter adjustment mechanism are connected into a whole. The suspended monitoring device is used for collecting various meteorological conditions and conductor displacement of transmission conductors and transmitting data to the master station system through the communication module; whether a corresponding early-warning threshold is reached or not is judged through a model established according to a neural network in the master station system; and online monitoring is performed on galloping or icing of the transmission conductors under the various meteorological conditions. According to the suspended overhead transmission line online monitoring system and method, self-adaptive adjustment of the monitoring device during detection of transmission lines withdifferent outer diameters can be realized by adjusting the inner diameter change mechanism, the defect that traditional conductor fixing and monitoring equipment is unadjustable is overcome, and theuniversality of the device is enhanced.

The invention discloses a vehicle-mounted mobile electrical resistivity detection system applicable to an urban environment as well as a working method. The invention can realize lossless ground electrical resistivity exploration, flexibly arranges exploration survey lines by utilizing a vehicle-mounted manner, so as to realize arrangement of the detection system, and reduces stray and electricalsignal interference, so as to adapt to an urban complex noise environment. The detection system disclosed by the invention combines and gives play to advantages of a mobile vehicle-mounted system specific to engineering requirements in urban underground space development and construction processes, fully utilizes an urban road surface environment and improves operation efficiency.

The invention discloses a bridge bearing capacity lightweight evaluation method based on impact load. Themethod comprises steps of loading the bridge by using a drop hammer simulation impact load, measuring a displacement time-history curve and an acceleration time-history curve of a bridge control section by using a displacement sensor and an acceleration sensor, performing comparative analysis on the extracted dynamic response and a theoretical calculation value, and establishing an evaluation index to evaluate the bearing capacity of the bridge. According to the method, the defects of longperiod, high cost and large influence on traffic in the conventional load test evaluation of the bridge bearing capacity are overcome, the evaluation uncertainty caused by the randomness of evaluationindexes and the fuzziness of the method is overcome in the evaluation method, and the method has the advantages of convenience, rapidness, large collected data volume, convenience and accuracy in evaluation and the like.

The invention discloses a big data processing system based on secure wireless transmission, relating to a data processing system. The system comprises a front end collection device (10), a 3G/4G wireless transmission device (20) and a cluster server device (30) which are successively in connection. The front end collection device (10) comprises a collection data module (11) and a data encryption module (12) which are embedded therein and have the front and back interacted; the cluster server device (30) comprises a big data decryption module (31), a big data storage module (32) and a big data analysis retrieval module (33) which are embedded therein and are successively interactive. The big data processing system has the characteristics of large data collection size and real-time uploading; in a transmission process, data is encrypted, and transmission security is high; the system employs wireless transmission, and is convenient to arrange nets and maintain; the cluster server processes big data.

The invention provides a user health management system based on a portable device. Currently, personal health is a hot topic. The invention aims to establish a personal health management system for performing comprehensive management on personal health danger factors. The system comprises a data collecting layer, a data transmitting layer and a data processing layer. Collection of health information (daily number-of-steps, heart rate, blood pressure and the like) is realized through establishing a board which is developed based on Arduino UNO, thereby extracting the user health data. Through adecision tree, a health condition score of a user in continuous time is obtained, thereby realizing tracking and evaluation to personal health condition. Through a microcontroller, various health information measuring modules are integrated, and a hardware platform is constructed for realizing health information collection of a hardware part. After the corresponding data are collected, a decisiontree model is established according the personal information such as age of the user. The health condition of the user is determined through an algorithm. Visual presentation to the user is performed, and a corresponding suggestion and reminding are generated.

The invention relates to a deep learning training inference system based on an FPGA. The deep learning training inference system comprises a cloud training device, a sensor device, a result comprehensive display device and an edge training inference device. The cloud training equipment, the sensor equipment and the result comprehensive display equipment are respectively connected with the edge end training reasoning equipment; the cloud training equipment is used for acquiring initial training parameters and transmitting the initial training parameters to the edge end training reasoning equipment; the sensor equipment is used for collecting data and transmitting the collected data to the edge end training reasoning equipment; the edge end training reasoning equipment performs reasoning and online training on the received initial training parameters and data; and the updated training parameters and reasoning results are output to a result comprehensive display device. The method has the advantages that high-speed and high-efficiency reasoning can be realized, the training requirement of edge end online learning can be met, meanwhile, the ability of reasoning training is achieved, and the method has the advantages of being completely autonomous, controllable, capable of being developed in a customized mode, low in power consumption and the like.