Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Memetic algorithms (MAs) are population-based meta-heuristic search algorithms that combine the composite benefits of natural and cultural evolutions. An adaptive MA (AMA) incorporates an adaptive selection of memes (units of cultural transmission) from a meme pool to improve the cultural characteristics of the individual member of a population-based search algorithm. This paper presents a novel approach to design an AMA by utilizing the composite benefits of differential evolution (DE) for global search and Q-learning for local refinement. Four variants of DE, including the currently best self-adaptive DE algorithm, have been used here to study the relative performance of the proposed AMA with respect to runtime, cost function evaluation, and accuracy (offset in cost function from the theoretical optimum after termination of the algorithm). Computer simulations performed on a well-known set of 25 benchmark functions reveal that incorporation of Q-learning in one popular and one outstanding variants of DE makes the corresponding algorithm more efficient in both runtime and accuracy. The performance of the proposed AMA has been studied on a real-time multirobot path-planning problem. Experimental results obtained for both simulation and real frameworks indicate that the proposed algorithm-based path-planning scheme outperforms the real-coded genetic algorithm, particle swarm optimization, and DE, particularly its currently best version with respect two standard metrics defined in the literature.

Realization of an Adaptive Memetic Algorithm Using Differential Evolution and Q-Learning: A Case Study in Multirobot Path Planning

Mobile robot path planning algorithm based on single-chain sequential backtracking Q-learning

The invention discloses an efficient powered deicing device for aerial power transmission and distribution cables. The efficient powered deicing device comprises a base, a power unit, a control unit, a running unit and a deicing unit, the power unit, the running unit and the deicing unit are matched in a driving manner and are respectively disposed on the base, the control unit is matched with the power unit in an electrical connection manner, and the deicing unit forms a structure in wrap-around matching with a cable. The efficient powered deicing device is of a wrap-around rotary scraper structure with the running unit which is hung on the cable, and a rotary scraper rotationally scrapes coated ice from the periphery of the cable, is suitable for scraping the coated ice from thin to thick, and is integrally light, lightweight, convenient to operate and high in working efficiency. The efficient powered deicing device is particularly suitable for removing the coated ice of glaze, mixed rime and the like strong in binding force and thick in ice layer, is convenient for mounting, demounting and adjustment on a construction site by the aid of design of multiple scrapper heads and the self-running unit, has the advantages of compact structure, light weight, convenience in remote operate and long continuous working time, and is particularly suitable for deicing operation of aerial power transmission and distribution lines in mountain areas.

Efficient powered deicing device for aerial power transmission and distribution cables

Four-bundle conductor traveling apparatus of 500kV transmission line

The invention provides an intelligent robot for removing ice in a high-voltage transmission line, which is characterized by comprising a machine body, and a thread drawing mechanism, a walking drive mechanism, a brake mechanism and an ice removing mechanism which are mounted on the machine body, wherein the thread drawing mechanism comprises a wheel frame, three coplanar walking wheels capable of drawing threads mounted on the wheel frame, an L-shaped thread feeding groove, a thread holding mechanism, four coplanar thread holding wheels mounted on the top of the thread holding mechanism, and a lever mechanism used for regulating upper-lower position of the thread holding mechanism; the brake mechanism comprises a braking claw, a return spring used for resetting the claw and an electric push rod used for driving the claw to open and close; and the ice removing mechanism comprises an ice removing motor, a cam, an ice breaking steel knife, a sliding block, a tension spring and a support disk for fixing the ice breaking steel knife. The intelligent robot for removing ice in a high-voltage transmission line has simple and reliable structure, portability, high level of automation and low energy consumption and can automatically effectively remove ice in a transmission line.

Intelligent robot for removing ice in high-voltage transmission line

The invention discloses a traveling mechanism of a robot on a high voltage transmission line, which is characterized in that 3 traveling arms including a fore arm, a middle arm and a rear arm are arranged on a robot main body When the robot travels on the transmission line, the fore arm and the rear arm are on the same side of the transmission line, and the middle arm is on the other side of thetransmission line Each traveling arm comprises a traveling wheel, a lifting arm, a braking mechanism and a swing arm, wherein one end of the swing arm is connected with the robot main body through aswing joint, and the other end is connected with the lower end of the lifting arm; the traveling wheel is installed at the side part on the upper end of the lifting arm; and the braking mechanism is installed on the lifting arm and below the traveling wheel The traveling mechanism can drive the robot to conveniently cross various obstacles on the transmission line, and the stability is good

Traveling mechanism of robot on high voltage transmission line

The invention discloses a combined type running deicing mechanism of an online deicing robot of a high-voltage transmission line, comprising a bracket and a milling wheel mechanism, a tapping mechanism and a running laminating wheel mechanism assembled on the bracket. The milling wheel mechanism and the running laminating wheel mechanism are arranged in a same running direction. The tapping mechanism is arranged below the milling wheel mechanism and the running laminating wheel mechanism. The combined type running deicing mechanism of the online deicing robot of the high voltage transmission line can deice by three mechanical ways of milling, laminating and tapping simultaneously and has the advantages of compact structure and high deicing efficiency.

Combined type running deicing mechanism of online deicing robot of high-voltage transmission line

The invention discloses an automatic line-grasping control method of a deicing robot in a high-voltage transmission line. An enhanced learning system is established by setting a state set, an action set, a Q table and a reward function. The method comprises the following steps of: selecting an action a to act on the environment by the system; after the action is accepted, transferring the environment to next state s'; meanwhile, giving out an evaluation signal r; if r meets certain conditions, stopping controlling, and otherwise deciding next action a' by the enhanced learning system according to the evaluation signal and the state s' through a behavior selection strategy; and entering next iteration after updating the Q table. The method overcomes the influence brought by the model errorof the robot, inaccurate posture at the tail end of robot arms, complicated environment and the like, and can be used for adjusting the posture at the tail end of the arm on line in real time for realizing the quick and accurate line grasping of the arm without human remote control, thereby achieving the aim of the automatic line-grasping control.

Automatic line-grasping control method of deicing robot in high-voltage transmission line

Ice coating in power networks could result in power-tower collapse and power interruption. This paper introduces a preliminary design of deicing robot, which travels on transmission lines and automatically remove ices. Inevitably, the deicing robot will encounter some obstacles. To cross an obstacle, the deicing robot needs to control its arms to grasp transmission line over the obstacle. In this paper, Q-learning, one of reinforcement learning algorithms is applied to study the line-grasping control strategies for deicing robot. We implement a graphical simulation environment and use it to evaluate the Q-learning based line-grasping control policy study algorithm. Simulation results show that the proposed algorithm is promising for the line-grasping control of deicing robot.

Yaonan Wang

Papers

Intelligent robot for removing ice in high-voltage transmission line

Traveling mechanism of robot on high voltage transmission line

Combined type running deicing mechanism of online deicing robot of high-voltage transmission line

Automatic line-grasping control method of deicing robot in high-voltage transmission line

Applying Q-Learning Algorithm to Study Line-Grasping Control Policy for Transmission Line Deicing Robot