134 results about "Ship tracks" patented technology

The invention relates to an inland river bridge area ship safe navigation precontrol system which comprises a radar station, an information processing center and an AIS base station. The radar station and the AIS base station are respectively in communication connection with the information processing center. The information processing center comprises a data processing and recording unit, a track fusion unit, an electronic river map unit, a precontrol decision-making unit and a precontrol information sending unit, wherein the data processing and recording unit obtains data from the radar station or / and the AIS base station and processes and records the data, the track fusion unit carries out fusion on the obtained radar or / and AIS data to obtain ship tracks, the precontrol decision-making unit carries out prediction according to the data processed and recorded by the data processing and recording unit and judges whether alarm instructions are sent out or not, and the precontrol information sending unit controls the AIS base station to send out alarms according to the instructions sent out by the precontrol decision-making unit. According to real-time traffic situations, the inland river bridge area ship safe navigation precontrol system can automatically identify navigation risks of the ships, automatically carry out early warning on the ships, guide the ships to pass through a bridge area safely, and reduce accident risks.

The present invention provides an accurate track tracking control method based on a finite time expansion state observer. The method comprises the following steps of: establishing a mathematical modeland a kinematic equation representing current unmanned ship motion features, designing a combined nonsingular rapid terminal sliding-mode control law according to the unmanned surface ship motion tracking errors and a nonsingular rapid terminal sliding-mode surface, designing a finite time expansion state observer according to the unmanned ship motion features, and designing an accurate track tracking control law according to the combined nonsingular rapid terminal sliding-mode control law and the finite time expansion state observer. Through design of the finite time expansion state observer, the lump interference comprising external interference and a complex nonlinear term can be observed by the finite time to a small enough range to avoid the limitation of the approximation observation. Through the designed combined nonsingular rapid terminal sliding-mode control law and the nonsingular rapid terminal sliding-mode unmanned ship track tracking controller, the accurate track tracking control method achieves the accurate track tracking control performance in a complex external interference.

The invention provides a ship track active-disturbance-rejection control method based on the slip form of a multi-modal nonsingular terminal. The method includes the steps of constructing an expectedship heading equation according to navigational parameters of a ship, deducing a discretization nonlinear structural model of a two-order differentiator, processing expected ship heading signals in the expected ship heading equation to obtain expected ship heading differential signals required for controlling the rudder angle by the control law, obtaining the output rudder angle on the basis of the switchable error feedback control law, constructing an expanded state observer in combination with the error feedback control law, tracking the output deviation according to the expanded state observer, estimating the heading angle and inner and outer disturbance errors controlled by the control law, and feeding the heading angle and the inner and outer disturbance errors back into the control law. By improving the expanded state observer, a linear function and a nonlinear function can be switched in real time; the switchable segmented slip form face is designed; through the segmented slip form face, the switchable error feedback control law is designed, and the under-actuated ship track control is well realized.

The invention discloses an under-actuated ship path tracking planning method based on a dynamic virtual ship guidance algorithm. The method includes the following steps that 1, a guide virtual ship mathematic model is established, a ship tracking control reference path is planned out through the guidance algorithm according to the guide virtual ship mathematic model, and an instruction time series signal of the generated reference path of a guidance virtual ship is obtained; 2, the path tracking control state starts; 3, the ship position and movement posture of a dynamic virtual ship are configured dynamically according to the relative position of an actual ship and the guidance virtual ship; 4, control laws, namely the rotational speed nc of a main engine and the helm angle instruction signal delta c of the actual ship are designed according to a robust self-adaptation control strategy, a main engine and steering engine implementation device of the actual ship is controlled, the actual ship is driven and controlled to track the dynamic virtual ship, and the path tracking control task of the ship in navigation practice is finally fulfilled; 5, whether the ship reaches a destination or not is judged by measuring the position of the actual ship, if the ship reaches the destination, ship navigation is ended, and if the ship does not reach the destination, the time t is updated to be t plus one, and the step 2 is carried out.

The invention relates to a ship track control method based on an improved LOS guidance algorithm. The method comprises the following steps: 1, obtaining the real-time navigation information of a ship by using the navigation module of the ship when the ship sails along a certain straight track segment in a path generated by set track points; 2, operating the improved LOS guidance algorithm to calculate a desired course when a track deviation between an actual track and a planned path exceeds an acceptable deviation d' or keeping an original planned track of the ship to sail if not; and 3, repeating the step 2 until the track deviation is within the acceptable deviation. The method applies the improved LOS guidance algorithm to the field of ship track tracking control, is clear in thinking and simple in algorithm, can control the ship to track the set ship course, is smooth in rudder angle change, and can avoid frequent steering of the ship.

The invention discloses a ship track logic initiation algorithm. The ship track logic initiation algorithm comprises steps that temporary track losing point classification discrimination, distance changing rule statistic discrimination, maneuverability analysis discrimination, namely suppression discrimination of continuous N-shaped false track having course deviation greater than or equal to 90 degrees and target speed, course, acceleration fluctuation discrimination are established by radar scanning. The ship track logic initiation algorithm is advantageous in that under a condition of severe clutter environment, by combining various track initiation rules, an initiation false alarm rate of a false target is reduced, and real target track initiation accuracy is improved, and therefore subsequent target stability tracking is facilitated, and probabilities of false track wrong following and real track losing are reduced.

The invention discloses a ship track recording and monitoring method, which relates to the monitoring of ship tracks. A ship track recording and monitoring method for fishery supervision and inspection needs to be provided. The method adopts a track recorder and a data reader; the track recorder is mounted on a fishing ship; the data reader comprises a wireless data transmission module antenna, a wireless data transmission module and a computer. The method is characterized in that the track recorder is provided with a wireless data transmission module and an antenna to become a track recorder with a transmission function, and the wireless data transmission module is connected with a low-power consumption singlechip and a large-capacity long-acting battery; normally, the wireless data transmission module is in a hibernation state, and can be periodically waken up by the low-power consumption singlechip to be in a monitoring state and receive data-reading instructions, the wireless data transmission module is utilized to transmit the recorded track data stored in a FLASH memory chip to the data reader, the wireless data transmission module of the data reader is connected with the computer, and the data reader is mounted in a supervision ship or a port. The method is used for recording and monitoring ship tracks.

The invention discloses a ship behavior track recognition method. The method comprises the following steps of: obtaining a track of a ship according to a track parameter; carrying out region divisionon the current sea area in which the ship travels according to the geographic condition of the current sea area; dividing a sea area track section by using a corner method according to the divided seaarea, so as to obtain a plurality of ship sub-track fragment sets; carrying out error back propagation multilayer feed-forward network set clustering on the plurality of ship sub-track fragment sets,so as to obtain a typical ship behavior track mode; calculating a Hausdoff distance between a track of a to-be-recognized ship and the typical ship behavior track mode; setting a Hausdoff distance threshold value; and judging a behavior track mode of the to-be-recognized ship according to a comparison result between the Hausdoff distance and the Hausdoff distance threshold value, and if the Hausdoff distance is smaller than or equal to the Hausdoff distance threshold value, judging the behavior track mode of the ship as the typical ship behavior track mode. The method is capable of correctlyand rapidly judging behavior modes of ship tracks, avoiding the waste of offshore management resources and ensuring the personal and property safety of seamen.

The invention relates to a ship location identification method based on multi-source data fusion. The method comprises the following steps: data calibration, wherein ship location data sent by a radarand ship location data sent by an AIS are received, and time shifting and coordinate transformation are carried out, so that unified time and space reference points can be formed by the ship locationdata sent by the radar and the ship location data sent by the AIS; data fusion, wherein the data fusion is carried out on the radar-measured data and the AIS-measured data, which are subjected to thedata calibration, through the normal membership function method; and coordinate prediction, wherein a ship track is predicted through the Kalman filtering algorithm, so that the coordinates of a shipare estimated. The method provided by the invention has the advantages that the data detected by the radar and the AIS are fused through the multi-source data fusion technology, and the ship track ispredicted through the Kalman filtering algorithm to estimate the coordinates of the ship, so that when the ship enters a prohibited area and tends to anchor, the corresponding ship can be automatically warned or expelled for sea area protection.

The invention discloses a ship track abnormity detection method based on a navigation channel model. The ship track abnormity detection method comprises the following steps: 1, obtaining historical AIS data in a selected time interval; 2, preprocessing the historical AIS data; 3, respectively extracting waypoints and air routes of the channel model from the preprocessed AIS data, and respectivelytaking the waypoints and the air routes as vertexes and edges of a graph in a graph theory to form the channel model: step 4, weighting the channel model according to time factors to obtain a final channel model; and 5, comparing the final channel model with the to-be-detected track, and judging whether the track is abnormal according to whether the to-be-detected track appears in the final channel model. According to the method, the advantages of a point-based algorithm and a track-based algorithm are fused, the historical law of navigation in a hot spot area is fully mined, and the behaviormode and space-time information left by a navigation track are obtained; short-term abnormity monitoring can be carried out, and long-term abnormity monitoring can also be carried out.

The invention discloses a method for improving the display speed of ship motion tracks on an electronic navigation chart client. The method comprises the steps of: dividing a display scale of an electronic navigation chart into different levels, wherein each level corresponds to one display scale range; presetting a data compression threshold for each display scale level; utilizing a vector data compression method to mark the display scale level for each position point in the ship motion track, wherein a scale is larger and corresponding ship motion track points are more; and only downloading data of the ship motion track points which are positioned in the geographical range displayed by the navigation chart of the client or the properly amplified range and correspond to the display scale of the navigation chart of the client from a server and displaying the data by the client. Through the method, when a user performs the display of the ship motion tracks on the electronic navigation chart client, only a less amount of ship track data is downloaded and displayed, which can effectively improve the download and display speed of the ship track data.

The invention provides a ship track data fusion method based on a LSTM model. The ship track data fusion method based on the LSTM model comprises the following steps: collecting ship navigation trackscollected by an AIS system, a shipborne radar and a high-precision GPS in one navigation as historical data, and collecting dynamic latitude and longitude coordinate information of the ship during anavigation process through the AIS system, and collecting dynamic image coordinate information of the ship during the navigation process through the shipborne radar, so as to be used as data to be trained; performing normalization on the radar latitude and longitude coordinate information, the AIS coordinate information and the high-precision GPS latitude and longitude coordinate information separately; grouping the normalized ship navigation track coordinate information collected by the shipborne radar, the AIS system and the high-precision GPS to obtain grouped coordinate information; and performing primary training on the LSTM model with the normalized and the grouped radar and AIS coordinate information as a training set, and then adjusting weighting parameters of the LSTM model usingthe grouped and normalized high-precision GPS coordinate information. The invention has the advantage of improving the accuracy of ship track fusion.

The invention provides a ship trajectory prediction method and system based on an LSTM automatic encoder and a bidirectional LSTM, and the method comprises the steps: carrying out the preprocessing ofship AIS trajectory data, and carrying out the feature extraction of the trajectory data through an automatic encoder; then, combining the extracted features with trajectory longitude and latitude data to represent the current navigation state of the ship; and taking the extracted features with trajectory longitude and latitude data as model input, learning a ship motion law implied in the trajectory data through a bidirectional LSTM neural network model containing an attention mechanism, and predicting the position of the ship at the next moment by using the ship motion law learned by the model. According to the method, the ship track prediction is carried out by adopting a scheme of the LSTM automatic encoder, the attention mechanism and the bidirectional LSTM neural network, and the bidirectional LSTM model can better mine the space-time association relationship of the track data on the premise of reserving enough effective information of the ship track data. According to the method, the trajectory prediction precision can be effectively improved, the real-time prediction is realized, and the requirement of a scene with relatively high trajectory prediction timeliness and accuracy is met.

The invention provides a port identification method based on ship track big data. The method is started from relatively neglected ship static state recognition in traditional research; the novel portberthing ship extraction method is provided, anchored ships are ingeniously filtered out, algorithm parameters are optimized through statistical analysis of a large number of historical ship navigation information, and finally automatic identification and extraction of the port position and range are achieved through a classical density clustering method. Potential and even secret berth wharf information which cannot be recognized based on remote sensing images traditionally can be recognized and serves as a beneficial supplement of an existing port recognition technology. Furthermore, important basic information is provided for evaluating the throughput of a port activity area and a port, analyzing ship behavior activities and identifying an abnormal ship target.

The invention provides a ship track tracking prediction control method inhibiting parametric rolling actively. The method includes steps of constructing a multivariate multi-index RBF-ARX model describing dynamic relationship among yew angle deviation, location tracking errors, a rudder angle, navigational speed and a rolling angle of a ship during a track tracking process comprehensively; analyzing the parametric rolling process of the ship and constructing a predication model for the parametric rolling process under a uniform frame of a RBF-ARX model constructing theory; performing comprehensive evaluation of model construction performance by taking long-term predication performance, short term predication performance within a certain time domain and turning experimental performance of a model as indicators for performance check. The ship track tracking prediction control method can be used as an inner model of a ship track tracking predication controller, so that the control precision of the track tracking process is improved. Ship travelling safety can be enhanced in a large degree and accidents can be reduced. The method only needs to be used with an existing autopilot system of the ship together, so that the upgrading cost of ship equipment can be reduced substantially.

The invention belongs to the technical field of unmanned ship navigation control, and specifically relates to anunmanned ship track planning method based on deep optimization. The unmanned ship trackplanning method based on deep optimization comprises the following steps that rasterized map information is read, starting and ending points are set, the obtained starting point and reachable neighbornodes in the eight directions of the starting pointare added to theopenlist; the point with the smallest F value in the openlistis searched for and set as the current node; whether the current node is the ending point or not is determined; if yes, then path searching is over; if not, then the current node is utilized to search for a next jump-point based on a jump-point search strategy; whether the jump-point is in the openlistor not is determined, and the point with the smallest F value is continuously searched for; and an optimal path is outputted. According to the unmanned ship track planning method based on deep optimization,the execution efficiency of grid method track planning algorithm is greatly improved based on the jump-point search optimization preprocessing algorithm,an path turning point is optimized, and finally a smooth navigation track is outputted.

The invention discloses a water traffic supervision and early warning system and method based on a machine learning technology. According to the system, big data and machine learning technologies aremainly utilized, historical ship track data are trained according to ship types and regions to obtain a ship navigation rule model which is more consistent with the actual navigation condition of theship, abnormal behaviors of the ships in the whole sea area in the administrative region are monitored in real time by utilizing the model, and finally, the abnormal behaviors are displayed to water traffic supervisors through an electronic nautical chart. Compared with a system for water traffic safety supervision and early warning based on rule setting, the system has the advantages of being higher in intelligent degree, complete in supervision water region coverage rate and low in early warning false alarm rate.

The invention puts forward a ship target detection method based on an infrared remote sensing image. The method comprises the following steps that: S1: carrying out water-coast separation on an infrared remote sensing image, and segmenting a sea area image which contains a ship target; S2: carrying out contrast enhancement processing on the sea area image obtained after the water-coast separation is carried out, highlighting the ship target in the image, and selecting the candidate area of the ship target according to the highlighted ship target; and S3: determining a ship suspected target in the candidate area, and extracting the ship target according to the personalized features of the ship. Under a situation of complex background interference including wind waves, cloud backgrounds, ship tracks, solar flares, islands and the like, the ship target can be accurately detected in real time.

The invention discloses an online compression method and device for mass ship AIS track data. The online compression method is a threshold combination algorithm for limiting double factors (synchronous Euclidean distance and steering angle). The method comprises the following steps: taking a water area as a research object, firstly finding historical characteristics of a ship track in a certain water area according to historical AIS data, then carrying out online compression based on a mode of combining change of a motion state with historical characteristic data, and finally constructing shipAIS track data based on kernel density estimation. According to the method, the AIS data can be efficiently compressed, the track feature points of the AIS data can be completely and accurately reserved, efficient management of the AIS data is facilitated, and the information communication efficiency and supervision efficiency between ships are improved.

The invention discloses a ship great circle sailing track deviation determination method, which comprises the following five steps: the shortest distance between two points of an expected track is calculated; the shortest track distance between a starting point and the current position is calculated; auxiliary reference points on the expected track are found out; an auxiliary correction deviation angle is calculated; and the track deviation is calculated. A method of acquiring reference points on a planned track is adopted to obtain the track deviation, the ship can correct the sailing direction quickly, and the sailing time is really shortened; according to the determination method applied to the track deviation, the track deviation in the case of great circle sailing can be calculated in a more real-time and accurate mode, the ship track control precision is improved, sailing of the entire segment can be instructed and completed in a more economic and more reliable sailing route, and the purposes of energy conservation and emission reduction can be achieved.

The invention discloses a ship behavior identification method based on deep learning, and belongs to the field of mode identification. The ship behavior identification method can be applied to the fields of intelligent marine monitoring, ship intelligent supervision and the like. The ship behavior identification method specifically comprises the steps: S1, acquiring original ship track data, and building a ship behavior identification data set through a data preprocessing and track segmentation method; and S2, designing a ship behavior identification network in which the multi-scale convolution module and the long-short-term memory network are cascaded, and realizing behavior identification of the ship track data by using the ship behavior identification network trained by the self-built ship behavior identification data set. By the adoption of the technical scheme, the ship behavior identification technology is applied to the field of ship supervision, and ship behaviors are automatically analyzed from mass ship track data, and effective evidence obtaining and supervision can be conducted on ship behavior activities of offshore oceans, and a low-efficiency manual inspection mode is replaced. The whole scheme has the characteristics of low dependence on equipment, high identification accuracy, high identification speed and the like.

The invention relates to a ship track real-time prediction method which comprises the steps that firstly, a sea radar is used for acquiring real-time and historic position information of a ship and processes the information primarily; then ship track data are preprocessed at each sampling moment, the ship track data are clustered at each sampling moment, parameter training is performed on the ship track data at each sampling moment with a hidden Markov model, a hidden state q corresponding to a current moment observation value is obtained with a Viterbi algorithm at each sampling moment according to parameters of the hidden Markov model, and finally, a ship position predication value in a further time period is obtained on the basis of the hidden state q of the ship at the current moment by setting a set predication time domain W at each sampling moment, and accordingly, the track of the ship in a future time period is speculated in a rolling manner at each sampling moment. The ship track real-time prediction method can predicate the ship track in real time in a rolling manner, the accurate is better, and powerful guarantee is provided for follow-up ship conflict release.

The invention provides a compression resistance static loading test system for a foundation. The static loading test system comprises a platform, a cab, an engine unit, a motor hydraulic pump, two rotating platforms, two long ships and two inner ships. The platform is used for bearing ballasting, and the middle of the upper end of the platform is provided with a main side oil cylinder; the cab is arranged on one side of the platform, and the engine unit and the motor hydraulic pump are arranged on the other side of the platform; the two rotating platforms are connected with the platform through connecting shafts; the two long ships are connected with the side faces at the two ends of the platform through connecting pieces respectively and respectively comprise a long ship safe buttress, and the long ships are connected with the connecting pieces through long ship supporting legs; the two inner ships are connected with the two ends of the rotating platforms respectively, each inner ship comprises an inner safe buttress, two inner ship track side plates arranged on the inner safe buttress, an inner ship track groove, a sideway oil cylinder arranged in the inner ship track groove and inner ship support legs arranged in the inner ship track groove in a sliding mode. The static loading test system is high in security coefficient, labor efficiency and automation degree and can ensure normalized construction.

The invention discloses an optimized ship track analytical method, belonging to the field of common ship sailing measurement and analysis. According to the actual sailing track of a ship, which is detected by a stem DGPS receiver, a stern DGPS receiver and an electric gyrocompass as well as wind-current and wind-force disturbing variable parameters measured by an anemoscope, a series of vector composition and dynamic regulation are carried out on the actual track data so as to modify the sailing track of the ship by optimized calculation, thus obtaining the corresponding sailing track when the ship sails on calm sea and determining more accurate parameters of movement performance during the trial voyage of the ship. With accurate measurement, the method is suitable for real-time detection.

The invention provides an active anti-ship collision monitoring and early warning system for a bridge for tracing ship tracks of all ships in a target channel for early warning ship collision of the bridge in the target channel actively. The system is characterized by comprising a plurality of monitoring video acquiring devices and a track tracing device, wherein each monitoring video acquiring device is provided with a video collecting part and a collecting side communication part. The track tracing device is provided with a nerve network storage part storing a nerve network model, a target ship acquiring part for acquiring the ship position of the target ship, a coordinate acquiring part for acquiring coordinate values of the ship according to the ship position, a ship track acquiring part for acquiring the ship track and a route speed of the ship according to the coordinate values of the ship, a ship track predicting part for acquiring a predicted track, a predicted speed, a bridgearriving time and probability distribution of passing positions according to the ship track and the route speed, and a ship collision early warning part for acquiring the ship collision probability according to the bridge arriving time and the passing positions and sending alarm.

The invention provides an overall planning method for a track and a speed of a ship. The method is characterized by comprising the following steps, 1), a ship fuel consumption monitoring system is used for collecting ship instantaneous fuel consumption data which comprises data such as ship position reports in all previous voyages, the original data are cleaned, wrong data or inaccurate data are removed, and a ship instantaneous fuel consumption navigation big database is established; 2), an attribute reduction theory and a dependency degree algorithm in a rough set or a clustering and decision tree analysis method are used for finding relevant variables with the most important influence on fuel consumption from influence parameters such as wind, wave and flow; and 3), an instantaneous fuel consumption model of the ship is extracted, and a relation between the ship fuel consumption and navigation environment parameters such as the wind, the wave, the flow and the ship speed is found. According the ship track optimization method, the ship safe obstacle avoidance is considered, and the energy conservation and the like of the ship are considered by comprehensively considering the running working conditions of equipment such as a ship main engine and a ship auxiliary machine and the environment of a sea voyage, so that it is guaranteed that the ship can adapt to complex sea conditions and navigation environments to the largest extent.

A ship optimal route automatic generation method based on AIS big data belongs to the technical field of big data mining, can solve the problem that an existing method cannot be applied to actual ship route planning and the like, and comprises the following steps: firstly, preprocessing massive historical AIS data, then introducing ship static data; adding ship draft in distance measurement to perform similarity measurement on AIS data; then using an improved adaptive clustering algorithm to perform clustering on ship track clusters until subclass clusters are single; and finally, using a main navigation route extraction method to extract a main navigation route from the clustered subclass clusters to realize automatic generation of an optimal ship route. The ship motion track is analyzed and processed based on historical AIS big data, the thought of referring to the specific navigation experience of other ships during ship route design is met, the new route planning method is provided, the main navigation route can be accurately extracted, and ship route planning can be provided for ships with different characteristics.

The invention discloses a cross-land ship track line correction method based on obstacle-avoiding path planning, belongs to the technical field of track analysis, and aims to solve the problems that a conventional method is low in correction efficiency on a large-area land and a great number of track lines. The cross-land ship track line correction method comprises the following steps: I, acquiring a wrong ship track line; II, analyzing a buffer range of a cross land so as to obtain a land buffer area; III, dividing the land buffer area into two parts by a wrong line section of the wrong ship track line, and forming a polygon as an obstacle-avoiding polygon by a relatively small part; IV, according to the start point and the final point of the wrong line section, acquiring a shortest obstacle-avoiding path as a modified path by using the obstacle-avoiding polygon, and replacing the wrong line section of the wrong ship track line by the modified path.

The invention relates to a fishing boat track abnormity detection method based on Beidou satellite transmission data. A traditional ship track anomaly detection algorithm is mainly used for carrying out anomaly detection on position information of a ship track. Inherent motion attributes such as the speed and direction of the ship are ignored. On the basis of a TRAOD algorithm, motion characteristics such as fishing boat course, navigational speed and the like are added into track abnormity detection. Fishing boat track abnormity is detected from multiple aspects of fishing boat position information and behavior characteristics, modeling is carried out on multiple track abnormity influence factors, fishing boat track abnormity trend scores under all track characteristics are calculated, and the reliability and effectiveness of fishing boat track abnormity detection are improved. The combination of the component abnormal trend scores is realized by using a weighted cumulative sum mode,the component weight can be changed according to the effectiveness of different component abnormal detection, and the problem that the final abnormal trend score depends too much on a certain component is avoided.

The invention discloses an unmanned ship track tracking control method based on a disturbance observer and an RBFNN. The method is based on a traditional sliding mode control method. According to theinvention, the method comprises: establishing the nonlinear kinetic model of the unmanned ship; designing the disturbance observer to observe and compensate strong external disturbance such as wind wave flow, and designing the RBFNN to estimate and compensate the model uncertainty part (including parameter uncertainty and modeling error) of the unmanned ship, so that the stability of the system isensured, the flight path tracking error of the unmanned ship is reduced, and the flight path tracking control effect is greatly improved. According to the invention, the stability of the control system is ensured, the track tracking error of the unmanned ship is reduced, and the track tracking control performance is improved.