In this paper, we introduce a novel technique for mining fuzzy association rules in quantitative databases. Unlike other data mining techniques who can only discover association rules in discrete values, the algorithm reveals the relationships among different quantitative values by traversing through the partition grids and produces the corresponding Fuzzy Association Rules. Fuzzy Association Rules employs linguistic terms to represent the revealed regularities and exceptions in quantitative databases. After the fuzzy rule base is built, we utilize the definition of Support Degree in data mining to reduce the rule number and save the useful rules. Throughout this paper, we will use a set of real data from a wine database to demonstrate the ideas and test the models.

Danger model artificial immune algorithm that imitates biological immune system based on gene theory is an optimization search method suitable for complex problems.Principle of the algorithm is introduced.The strategy for ship collision avoidance is optimized by means of the algorithm in conjunction with the knowledge in the related subjects such as ship domain,collision risk and mathematical model of ship's movement.The effectiveness of the algorithm has been verified by simulation.The study offers new thinking and a practical method for decision making to avoid a collision.

The security of maritime traffic is a significant part of intelligent maritime traffic. It can reduce to ship maneuvering and collision avoidance by macroscopic. Eighty percents of marine accident induce by human factor from research data. So some researches about intelligent computer evaluation system to reduce the accident of human caused have emerged. Intelligent evaluation system of ship maneuvering can calculate the status of ship and getting the data of ship around, and then adopt fuzzy comprehensive evaluation method to calculate the collision risk and evaluate the operation of navigator. If it has danger of collision risk or the navigator adopts irrational operation scheme by calculating, the system will send message to the navigator. The navigator must affirm the messages, if there is not affirmance, the system will adopt collision avoidance measures or other rational operations automatically at the critical moment.

It is a matter of utmost importance to predict dangers accurately in advance and to prevent accidents from occurring for a ship, which is navigating on the sea. Based on analyzing the cases of a shipwreck which have occurred so far, we discovered that more than 80% of the accidents were caused by wrong instructions issued by the captain of a ship. Especially in severe weather or in an emergency, inaccurate instructions have caused fatal damages. Based on machine learning, a method for analyzing and assessing the operation instructions sent from the bridge is discussed in this paper. ID3 algorithm is applied to build up an assessing decision tree, which can be improved and modified in the course of practical application. Operation instructions can be analyzed and accessed using this decision tree. The objective is to prevent the accidents caused by false instructions, and hence the safety and security of a ship navigating on the sea will be improved.

The BP nerve network has been used widely in fault detection field, but the usage of solution seeking algorithm by along gradient descent often results in low convergence speed and frequently getting into the part minimum. On the contrary, the genetic algorithm has the advantage of fast seeking speed in full-scale. Therefore, to optimize the BP nerve network, this essay adopts the auto-fit genetic algorithm. Later, the example of shipping main shafting fault detection proves that the optimized BP nerve network combined with the genetic algorithm is more adapted to complicate equipments' fault detection.

For the sake of improving ship safety, evading tremendous loss of life and property and avoiding marine environment pollution that caused by ship fire hazard, this paper brings forward a new idea to cope with ship fire hazard based on ship fire zone division principle and emergency shutdown cause & effect chart design method. The new thought is to use intelligent emergency shutdown method to replace the conventional approach which excessively depends on the person. This paper also gives detail implement measures and points out the developing trend of the ship safety system.

Recently neural network is widely used in fault diagnosis. As the neural network method has the disadvantages of the slow convergence rate and the uncertain node number in neural network hidden layer, the results of fault diagnosis in complex devices are not satisfactory. This paper combines fuzzy logic and neural network, and presents a multilayer feed-forward fuzzy neural network with a serial structure for fault diagnosis. We take the fault diagnosis in ship diesel engine as an example to simulate. The results demonstrate that the method could improve the speed of diagnosis greatly and could diagnose and predict the device faults timely and rapidly. It can significantly improve the fault diagnosis to apply the method in large and complex devices.

The goal is to find web services,using SOAP protocol to communicate with the web service.The principle of SOAP message model and the application of the AXIS Server have been introduced in this papr.Make the HTTP as the default network transport protocol of SOAP.In communication with the Web Service interaction,SOAP message load from the WSDL description of web services.The system realized the communication between the java client and Web Service.

The factors which would cause shipping accidents are analyzed in detail and a model which can forecast shipping accidents is studied in this paper. During navigation, all the factors are integrated and calculated in this model which then estimate and speculate on the risk degree of collision for the own ship. Finally, the risk level and the possibility of shipping accidents can be forecasted in real-time. The proposed accident forecast model can estimate the possibility of collision with other ships or objects in a specific domain. Meanwhile, the external environment such as weather, stream, etc. is taken into account in the model. Besides, the validity of navigators' orders can also be evaluated in the model which consequently can forecast different kinds of shipping accidents effectively in that most of the factors which cause shipping accidents have been involved in the proposed model. With the accident forecast model, the shipping safety would be improved greatly. A practical example demonstrates the effectiveness and superiority of the proposed strategy.

In this paper, an online self-organizing scheme for Parsimonious and Accurate Fuzzy Neural Networks (PAFNN), and a novel structure learning algorithm incorporating a pruning strategy into novel growth criteria are presented. The proposed growing procedure without pruning not only simplifies the online learning process but also facilitates the formation of a more parsimonious fuzzy neural network. By virtue of optimal parameter identification, high performance and accuracy can be obtained. The learning phase of the PAFNN involves two stages, namely structure learning and parameter learning. In structure learning, the PAFNN starts with no hidden neurons and parsimoniously generates new hidden units according to the proposed growth criteria as learning proceeds. In parameter learning, parameters in premises and consequents of fuzzy rules, regardless of whether they are newly created or already in existence, are updated by the extended Kalman filter (EKF) method and the linear least squares (LLS) algorithm, respectively. This parameter adjustment paradigm enables optimization of parameters in each learning epoch so that high performance can be achieved. The effectiveness and superiority of the PAFNN paradigm are demonstrated by comparing the proposed method with state-of-the-art methods. Simulation results on various benchmark problems in the areas of function approximation, nonlinear dynamic system identification and chaotic time-series prediction demonstrate that the proposed PAFNN algorithm can achieve more parsimonious network structure, higher approximation accuracy and better generalization simultaneously.

The security of maritime traffic is a significant part of maritime transportation. Human plays an important role in it. However, many marine accidents induced by human. Some researches have applied automatic operation system in ship manoeuvre and collision avoidance to reduce accident caused by human. Researchers found that some accidents related to automatic equipment. Automation operation changes the style of working, and forms a new way to make mistake. The paper proposes a man-machine interactive ship manoeuvre system. Man is the main part of system. Computer is an auxiliary facility. Adopt Arena and ship domain method to calculate collision risk and evaluate operation of navigator. If it has high risk of collision or navigator adopts irrational strategy, the system will send warning signal to navigator. Navigator must affirm the messages, if there is not reply, system will adopt collision avoidance and other rational operations at the point of last helm.

A novel online self-constructing fuzzy neural network is proposed for time-series prediction. The proposed approach not only speeds up the learning process but also builds a more parsimonious fuzzy neural network while comparable performance and accuracy can be achieved since the new growing criteria feature characteristics of growing and pruning. The learning scheme starts with no hidden neurons and parsimoniously generates new hidden units according to the proposed growing criteria as learning proceeds. In the parameter learning phase, all free parameters of hidden units are updated by the extended Kalman filter (EKF) method. Simulation results demonstrate that the proposed approach can provide faster learning speed and more compact network structure with comparable generalization performance and accuracy.

To enhance the reliability of fault diagnosis in marine diesel engine, a fault diagnosis method based on fuzzy information multilevel fusion is applied to the fault diagnosis of marine diesel engine. This method processes fault diagnosis of marine diesel engine after fusing diagnostic data in each level once more, application results indicate that the method is accurate and available, which not only can make correct diagnoses in the general case, but also can avoid the false judgment of fault diagnosis of marine diesel engine in the case of failures of the local detection sensor, and give a beneficial reference to enhance the reliability of fault diagnosis in marine diesel engine.

The proportion of main reasons of ships accidents to the whole reasons is discussed in the paper. Among these reasons, human factors are in the majority. So a method to prevent wrong orders sent by a navigator is laid emphasis on. On the basis of this, a ships safety control system is studied. The construction and control principle of the ships safety control system, as well as control strategy, implementation method and key technology are elaborated in the paper.

Inspired from the experience of genetic and clone algorithm, propose an algorithm of danger model immune algorithm (DMIA) according to the danger model theory. It has a good performance in function optimization. From the simulation result, we can see that DMIA is valid, and also with higher efficiency than genetic algorithm.

The security of maritime traffic is a significant part of intelligent maritime traffic. It can reduce to ship manipulation and collision avoidance by macroscopic. Eighty percents of marine accident induce by human factor from research data. So some researches about computer evaluation system inducted to ship manipulation and collision avoidance to reduce the accident of human caused. Evaluation system of ship manipulation will calculate the statement of ship and getting the data of ship around, then adopt fuzzy comprehensive evaluation method to calculate the collision risk, and evaluate the operation of mariner. If it has collision risk or the navigator adopts irrational operation scheme by calculating, the system will send message to the navigator. The navigator must affirm the messages, if there is not affirmance, the system will adopt collision avoidance measures and other rational operations automatically at the critical moment.

Danger Model Immune Algorithm(DMIA) is an algorithm based on the danger theory of biological immune system. In the basic algorithm, the danger area is fixed through the initial setting. It is an important parameter which will affect the capability of algorithm. In this paper, propose an adaptive danger area DMIA. The radius of danger area is decrease gradually according to the iteration steps. The simulation results indicate that the adaptive danger area DMIA is valid and has better optimization capability.

Wind power energy is a renewable resource which is clean without pollution. The early research on wind power energy mainly focused on the on land utilization. The application on the sea is infrequent. Much less to find the application on the ships and offshore structures. Based on the fact that the energy crisis becomes more and more severe, this paper puts forward the idea to install wind power generation sets on the ships and offshore structures widely, and also gives the problems to be resolved and the solutions.

A novel paradigm termed fast and compact fuzzy neural network (FCFNN), which incorporates a pruning strategy into some growing criteria, is proposed for online extraction of fuzzy rules. The proposed growing criteria not only speed up the online learning process but also result in a parsimonious fuzzy neural network while achieving comparable performance and accuracy by virtue of the growing and pruning mechanism. The FCFNN starts with no hidden neurons and parsimoniously generates new hidden units according to the proposed growing criteria as learning proceeds. In the second learning phase, all free parameters of the hidden units are updated by the extended Kalman filter (EKF) method. The performance of the FCFNN algorithm is compared with other popular algorithms like ANFIS, GDFNN and SOFNN, etc., for nonlinear function approximation. Simulation results demonstrate that the learning speed of the proposed FCFNN algorithm is faster and the network structure is more compact while comparable generalization performance and accuracy are achieved, moreover, it is capable of extracting fuzzy rules online.

This paper introduces a two-axis tracking system of the solar panel based on FPGA.The FPGA is used to control the speed and direction of the stepping motor.The fine division driver stage of the stepping motor is also introduced.