230 results about "Train driver" patented technology

A train integrity network system comprises bogie units which monitor critical parameters relating to the condition of bogie components and the rail track they are travelling on, an onboard server which controls the bogie units and a wireless network which enables communication between the server and the bogie units. Each bogie unit is powered by an electrical generator which utilises the rotation of the bogie wheels and has a processor which compares the critical parameters against defined standards in order to issue alerts to the train driver. The wireless network utilises master/slave base band role switching, has store-and-forward nodes which convey quasi real time data to the server and utilises frequency hopping modes.

The invention discloses a method for detecting train driver behavior and fatigue state on line and a detection system thereof. The method comprises: adopting a camera to shoot a train driver; carrying out human face detection on pictures collected by the camera; judging whether the driver does not perform duty or nods off; then, using an eye open image detector trained by the AdaBoost algorithm to find an eye open image from the human face image so as to judge whether the driver opens eyes or not; and calculating the ratio of eye closing time to total testing time in real time, namely the PERCLOS value, for marking fatigue state. The system comprises a camera, an embedded host, an alarming device, a user press key and a memorizer, wherein, the camera, the alarming device, the user press key and the storage are respectively connected with the embedded host. The invention fills the gap of the field of monitoring train driver behavior and detecting fatigue state and can monitor train driver behavior and detect fatigue state under train environment.

The invention relates to a simulation driving system of trains, which comprises a master control device, a data collecting and output device and a vision simulation device, wherein, the collecting and output device receives and transmits the input data of simulation driving to the master control device; the master control device produces simulation data according to the input data of stimulation driving and sends the simulation data to the vision simulation device to set up simulation scenes of trains when running. The simulation driving system of trains can be used for training master operation skills of train drivers and drivers of city light rail or underground during transportation operation process so as to ensure that the workers have relatively high professional levels and relatively high ability for handling emergencies.

The invention provides a deep-learning-based driver's fatigue detection method, comprising: obtaining the images of a driver in different states as sample images; training the neural network with deep-learning-based to obtain a trained driver state recognizing model; acquiring the video images of the driver; employing a face detection algorithm to obtain the face area from each frame of the video images; utilizing the recognizing model for the state of the well-trained driver to recognize the face area from each frame of the video images and obtaining the state of the driver in each frame of the video images; and based on the state of the driver in the continuous frames of the video images and through eye blinking analysis, yawning analysis and comprehensive analysis, determining whether the driver is fatigued or not and outputting the detection result. Compared with the prior art, the method and apparatus are capable of accurately detecting whether a driver is fatigued or not.

The invention relates to a train collision prevention warning system. A train information collection module is used for collecting train status information, and the train status information comprises a train running line, a train location, a train speed, a safety level and the like; a wireless communication module is used for wirelessly broadcasting the train status information and wirelessly receiving the train status information broadcast by other trains; and a CPU (central processing unit) control processing module is used for receiving and processing the train status information of the train and other trains collected by the train information collection module and transmitted by the wireless communication module. The current train status information of the train can be broadcast wirelessly to other trains via the wireless communication module, the train status information wirelessly broadcast by other trains can be received by the wireless communication module, the running safety distance and speed can be judged by the CPU control processing module according to relationships between the train and other trains, and pre-warning signals can be sent to drivers and automatic train operation systems. The system has a simple and reliable structure and can be installed conveniently, the train drivers can promptly know running statuses of approaching trains, and the train running safety can be improved effectively.

The invention discloses a driver behavior recognition method based on a lightweight convolutional neural network, and the method comprises the steps: obtaining a driving behavior public data set, andobtaining pictures of different driving behavior classifications; preprocessing the pictures, randomly disturbing a data set, and dividing the data set into a training set and a test set; performing data enhancement on the training set; designing a lightweight convolutional neural network, and inputting the training set into a data input network for feature extraction; performing probability prediction of each driver behavior category on the extracted feature vector by using a classifier, calculating a loss function according to the predicted probability of the training set category label pair, and guiding the next training direction of the network through back propagation; and storing the trained driver behavior classification model after the training is completed. According to the method, the lightweight convolutional neural network is designed by adopting information circulation between the convolution module and the enhanced channel, the driver behavior classification model which is small in size, simple in operation and high in accuracy is trained, and the method is suitable for vehicle-mounted mobile terminals to recognize and classify the driving behaviors.

The invention provides a train curve prewarning system and prewarning method of a wireless sensor network. The prewarning system mainly comprises a MEMS accelerometer module, a data acquisition module, a GPS global positioning system, a wireless transceiving module, a hazard warning module and a display module. A wireless sensor node uses a MEMS accelerometer to detect a train centripetal acceleration, and the centripetal acceleration is compared with an acceleration threshold at a train curve; if the detected acceleration is higher than an alarm value or a preset value of a system, a lateral acceleration value is sent to a wireless sensor sink node, the sink node adopts the form of acousto-optical warning to warn the train driver to slow down and displays the current geographical position through the display module, the maximum lateral acceleration value and the limit running speed of the train at the curve on a liquid crystal display (LCD) module so as to prevent the train from generating rollover due to overspeed. The system has small volume and high reliability, can be applicable to ordinary trains or motor cars, and has an important role in improving the running safety for trains.

The present invention relates to an automatic driving system of locomotive. A signal information collection module is configured to collect locomotive information required by automatic driving of thelocomotive, transmit the locomotive information to a train ATO system and send the locomotive information through a man-machine interaction module to a train driver for monitoring and control; the train ATO system is configured to calculate and obtain an optimal console shift sequence of the locomotive control according to the locomotive information sent by the signal information collection module, send the locomotive control and console instruction sequence to the man-machine interaction module, and the man-machine interaction module notifies the train driver of manual/automatic operation forsafe switching according to the locomotive control instruction sequence; and the train ATO system is configured to receive the train driver's instruction through the man-machine interaction module and perform setting of a manual/automatic switch according to the instruction. The train ATO system has good fusion with a current vehicle system to obtain the optimal locomotive control and console sequence and achieve automatic driving of the locomotive according to the locomotive control and console sequence.

The invention discloses an anti-collision system for trains and a method thereof; driving information of the train is automatically and continuously reported to nearby trains by an on-board anti-collision system on the train; the method is opposite to the operation principle of radar; the radar operation detects what exists in the nearby environment; the radar is taken as the center and then the nearby objects passively reflect radar signals to the radar. In the invention, each train positively and continuously sends dynamic information of the train to the nearby trains, to tell the nearby trains the position, direction and driving speed of the train on a rail. In this way, in addition to driving according to orders sent by a controlling center, each train driver can also calculate the driving safety distance and maximal driving speed according to the information sent by the nearby trains through the on-board anti-collision system on the train, which helps the driver to make correct judgment and thus avoids collision accidents.

An on-board train brake safety monitoring and fault action system that compares actual train brake power with expected train brake power to provide real time reporting to the train driver of the margin between the actual brake power and a safe threshold. The system may be configured to automatically make a full service brake penalty if the actual brake system power is less than a safe brake power threshold, such as those required by government regulations, or to adjust the braking system to improve actual brake efficiency. The on-board train brake monitoring system may optionally receive data from wayside hot and cold wheel detector systems to augment the actual brake power measurements.

The invention provides a driver advisory system and method for a train. The driver advisory system arranged between a control center and a train driver at a functional position comprises a data acquisition and processing module, a control center, and a human-computer interaction interface. The data acquisition and processing module is used for collecting dynamic data of the train operation in real time when the train moves forwardly and continuously according to a predetermined operation curve and feeding the dynamic data to the control center by a mobile data communication interface; the control center carries out analyses and comparison on the dynamic information and a static database stored in advance, identifies a deviation between a current operation state and an expected operation state of the train, carries out optimization calculation on the train inter-station operation curve and generates a piece of training driving advice for decision making according to the optimized train inter-station operation curve, and the training driving advice is sent to a vehicle-mounted device by a data communication and recording interface; and the human-computer interaction interface is used for obtaining and displaying the train driving advice and information in the static database by a train driver auxiliary information human-computer interaction port. According to the driver advisory system and method provided by the invention, with the driving advice fed back to the train drive in an optimized mode, operability of the train driver based on the driving advice is improved.

The invention relates to a railway crossing safety protection early warning system. The railway crossing safety protection early warning system is characterized by consisting of a monitoring center subsystem, a track maintenance division subsystem, a site subsystem and a network which is connected with each subsystem, wherein the monitor center subsystem acquires the state and an operating plan of a signal device through a TDCS interface server and consists of a crossing safety protection module, a crossing management module and an emergency communication module; the track maintenance division subsystem acquires the real-time information of a crossing from the monitoring center subsystem and monitors the administered crossing in real time, and the track maintenance division subsystem consists of an external interface module, a crossing safety protection module, an identification module and an emergency communication module. By adopting the railway crossing safety protection early warning system, the precision, reliability, comprehensiveness and economical performance for locating a train can be improved, stable and reliable communication connection between a center and a site can be established, an alarming target not only contains motor vehicles and pedestrians, but also contains a train driver, the safety risk of the crossing can be maximally reduced, a closed-loop cooperative network is formed by relevant elements, and the poor interaction problem of the information in the safety management of the crossing can be fundamentally solved.

The invention provides a train running simulation system. The system comprises a vehicle parameter acquisition module, a running simulation initial model establishment module, a traction and braking characteristic information addition module, a circuit model establishment module and a simulation running module, wherein the vehicle parameter acquisition module, the running simulation initial modelestablishment module, the traction and braking characteristic information addition module, the circuit model establishment module and the simulation running module are in successive communication connection. The vehicle parameter acquisition module acquires vehicle parameters. The running simulation initial model establishment module establishes a running simulation initial model according to thevehicle parameters and running conditions. The traction and braking characteristic information addition module adds traction characteristic and braking characteristic information into the running simulation initial model to acquire a running simulation model. The circuit model establishment module establishes a circuit model based on the running simulation model. The simulation running module carries out simulation running on a train according to the running simulation model of the train and the circuit model. The train running simulation system provided by the invention has the advantages ofhigh reliability and complete function, is complete and highly simulative for a practice train driver, and provides an accurate research technology for the research of train traffic engineering.

The invention relates to an intelligent vehicle automatic driving control method and system and belongs to the field of intelligent driving technologies. Through the control method and system, the problem that online learning cannot be well completed self-adaptively in existing automatic driving is solved. The intelligent vehicle automatic driving control method comprises the steps that a global travel planning path of an intelligent vehicle is acquired, the global travel planning path is decomposed into different travel segments, and the different travel segments are dived into correspondingdriving subtasks according to a driving task; according to the current driving subtask, environment information corresponding to the driving subtask is collected, and the environment information is processed to obtain a state quantity corresponding to the driving subtask; the state quantity is input into a trained driver behavior learning model, and an action quantity is output in real time through processing by use of the driver behavior learning model; and a bottom control quantity of the intelligent vehicle is obtained according to the action quantity, and the intelligent vehicle is controlled to run based on the bottom control quantity. Through the control method and system, self-adaptive online learning of automatic driving of the intelligent vehicle is realized.

The invention discloses a warning method and a warning system for guaranteeing the safety of railway operation. The warning method for guaranteeing the safety of railway operation comprises the following steps: train driver operation equipment, non-train-driver worker handheld equipment, compartment positioning equipment and dispatching room equipment form a wireless network; the train driver operation equipment, the non-train-driver worker handheld equipment and the compartment positioning equipment acquire the own position through a satellite navigation and positioning system and broadcast the own position to other equipment continuously through the wireless network; the non-train-driver worker handheld equipment broadcasts the own operation state to other equipment continuously; and the train driver operation equipment collets other node positions and displays the positions of all the workers involved in the operation by combining a geographic information system. The warning system for guaranteeing the safety of railway operation comprises the train driver operation equipment, the non-train-driver worker handheld equipment, the compartment positioning equipment and the dispatching room equipment and realizes the method. The method and the system have the benefits of providing objective warning for guaranteeing the safety of railway operation and eliminating man-made hazards so as to guarantee the safety of railway operation.

The invention relates to a method for enhancing the clarity of speech signals, which comprises the steps of performing frame expansion and windowing processing on audio signals according to an audio coding and decoding format in a CRH train driver control information analysis system, estimating the location of the speech by using a dynamic speech detection algorithm based on the short time energydifference, performing noise estimation by using the non-speech audio signals, finally performing filtering processing by using a wiener filter, carrying out frame cutting on the filtered audio signals to recover back to the original frame length, and performing noise reduction processing in the real-time playing process of the audio, thereby providing a clear and fluent speech analysis environment for the related personnel, and providing convenient conditions for driver control analysis. The method is applied to the CRH train driver control information analysis system, can perform enhancementon the speech signals in the system, has a good suppression effect for noise signals, well restores the frequency spectrum, the tone and the pitch of the speech signals, and keeps the speech playingcontinuity and the timeliness and the correlation of dotting information.

A train driving safety monitoring device, mainly composed of a train monitoring signal system, a leading monitoring vehicle monitoring signal system, and a wireless communication system. The leading monitoring vehicle travels synchronously near the safe braking distance in front of the train, and a monitoring camera is installed on the leading monitoring vehicle An image monitor is set in front of the train driver's operating position, and images and data information are transmitted between the leading monitoring vehicle and the train through the vehicle-mounted wireless mobile communication system. Since the image monitoring of the leading monitoring vehicle extends the driver's field of vision forward, the road conditions beyond the safe braking distance ahead can be observed in real time. When an abnormality is found ahead, emergency braking or other emergency measures can be taken within the effective safe distance.

The invention provides an intelligent detection system for train driver gestures. The system comprises an image acquiring module, a wireless transmission module, a cloud server and a reporting module, which are connected in order. The cloud server comprises a DPM module, an LBP module, a CNN module, a REST APT module and a database; the image acquiring module is connected with the DPM module via the wireless transmission module; the DPM module is connected with the LBP module and the database and the LBP module is also connected with the database for acquiring data from the database; the LBP module is connected with the CNN module and the CNN module transmits identification results to the database; the database outputs reports to the reporting module via the REST APT module. The invention also provides an intelligent detection method for train driver gestures. The system and the method can reduce dependence of detection operation on humans, eliminate human error caused by dull work, be free from influence of human factors and improve the safety of train operation.

The invention provides a rail vehicle ultrahigh voltage overcurrent fault detection device and method. The device comprises two pantographs , each pantograph is correspondingly connected with a current sensor and a main transformer, and a third current sensor is connected between two current sensors in parallel; a main circuit breaker is connected between the current sensor correspondingly connected with each pantograph and the main transformer; two ends of the third current sensor are connected between the main circuit breakers and transformers between two pantographs in parallel; one end ofthe third current sensor is serially connected with a high-voltage isolation switch; the detection device further comprises a control module for identifying the pantograph in a photograph-lifting state, and positioning a fault region through a logic relation according to a collected overcurrent signal at a ultrahigh voltage loop. Through the device and method provided by the invention, the ultrahigh voltage overcurrent fault region can be accurately and quickly positioned, and the train driver is prompted to perform corresponding operation according to the logic relation, and the running security and reliability of the train are improved.

The invention discloses a rail vehicle driving simulator operation evaluation system. The rail vehicle driving simulator operation evaluation system mainly comprises a data service module, an evaluation service module, a data management module and a debugging platform module, wherein the data service module is connected with a simulator database; and the evaluation service module, the data management module and the debugging platform module are respectively connected with the data service module. The invention also discloses an evaluation method based on the rail vehicle driving simulator operation evaluation system. The rail vehicle driving simulator operation evaluation system and the rail vehicle driving simulator operation evaluation method disclosed by the invention can objectively evaluate the traffic regulation obeying and executing capacity, the vehicle driving capacity, the trouble shooting capacity and the emergency event responding capacity of a train driver trained on a simulator, provide a uniform evaluation platform, and are convenient to establish different levels of evaluation systems.

A vehicle-mounted high-speed bullet train operation security indicating device comprises a train computer and is characterized by further comprising a micro controller, a displayer and a wireless distance measuring device. The wireless distance measuring device comprises a satellite positioning device, an infrared device, a laser device and a radar, wherein the infrared device comprises an infrared imaging device body, an infrared detecting device body and an infrared sensing device body, the laser device comprises a laser detecting device body, a laser imaging device body and a laser distance measuring device body, and the radar comprises a radar detecting device, a radar distance measuring device, a radar imaging device and a radar sensing device. The displayer is in electric signal connection with the micro controller, and the wireless distance measuring device is in electric signal connection with the micro controller. According to the vehicle-mounted high-speed bullet train operation security indicating device, data and images required by high-speed bullet train operation security are displayed on the displayer, so that a train driver can observe railway signals and also see a screen of the displayer, and train drivers can communicate information with each other in the driving process. The data and the images can be transmitted to a scheduling room so that people in the scheduling room can know about situations of a train, visual train scheduling is achieved, and the fact that accidents do not happen is guaranteed.

The invention relates to the railway gale early warning field, in particular to a train-mounted gale early warning system which comprises a wireless transverse wind velocity sensor and an alarm, wherein the wireless transverse wind velocity sensor and the alarm are powered by a high-energy Li/SOCl2 battery, the wireless transverse wind velocity sensor is mounted at the top of a train, the alarm is mounted in the cab of the train, the wireless transverse wind velocity sensor sends transverse wind velocity information monitored in the running process of the train in real time to the alarm by an wireless communication module embedded in the sensor, and the alarm sends out early warning information to the train driver and simultaneously sends the early warning information to a train scheduling center by a GPRS module embedded in the alarm. The invention solves the problem that the sparse wind velocity monitoring and control networks of the existing ground gale early warning system are difficult to monitor micro-scale gale. The early warning system is directly mounted on the train and has the capability of monitoring the near-field wind velocity of the train, thereby being capable of monitoring the transverse wind velocity of the train in real time and sending out the gale early warning to the train driver at the first time.