Nuclear fuelNuclear fuel is material used in nuclear power stations to produce heat to power turbines. Heat is created when nuclear fuel undergoes nuclear fission. Most nuclear fuels contain heavy fissile actinide elements that are capable of undergoing and sustaining nuclear fission. The three most relevant fissile isotopes are uranium-233, uranium-235 and plutonium-239. When the unstable nuclei of these atoms are hit by a slow-moving neutron, they frequently split, creating two daughter nuclei and two or three more neutrons.
Artificial neural networkArtificial neural networks (ANNs, also shortened to neural networks (NNs) or neural nets) are a branch of machine learning models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.
Types of artificial neural networksThere are many types of artificial neural networks (ANN). Artificial neural networks are computational models inspired by biological neural networks, and are used to approximate functions that are generally unknown. Particularly, they are inspired by the behaviour of neurons and the electrical signals they convey between input (such as from the eyes or nerve endings in the hand), processing, and output from the brain (such as reacting to light, touch, or heat). The way neurons semantically communicate is an area of ongoing research.
Neural networkA neural network can refer to a neural circuit of biological neurons (sometimes also called a biological neural network), a network of artificial neurons or nodes in the case of an artificial neural network. Artificial neural networks are used for solving artificial intelligence (AI) problems; they model connections of biological neurons as weights between nodes. A positive weight reflects an excitatory connection, while negative values mean inhibitory connections. All inputs are modified by a weight and summed.
Nuclear fissionNuclear fission is a reaction in which the nucleus of an atom splits into two or more smaller nuclei. The fission process often produces gamma photons, and releases a very large amount of energy even by the energetic standards of radioactive decay. Nuclear fission was discovered on 19 December 1938 in Berlin by German chemists Otto Hahn and Fritz Strassmann. Physicists Lise Meitner and her nephew Otto Robert Frisch explained it theoretically in January 1939. Frisch named the process "fission" by analogy with biological fission of living cells.
Nuclear fuel cycleThe nuclear fuel cycle, also called nuclear fuel chain, is the progression of nuclear fuel through a series of differing stages. It consists of steps in the front end, which are the preparation of the fuel, steps in the service period in which the fuel is used during reactor operation, and steps in the back end, which are necessary to safely manage, contain, and either reprocess or dispose of spent nuclear fuel.
Spent nuclear fuelSpent nuclear fuel, occasionally called used nuclear fuel, is nuclear fuel that has been irradiated in a nuclear reactor (usually at a nuclear power plant). It is no longer useful in sustaining a nuclear reaction in an ordinary thermal reactor and, depending on its point along the nuclear fuel cycle, it will have different isotopic constituents than when it started. Nuclear fuel rods become progressively more radioactive (and less thermally useful) due to neutron activation as they are fissioned, or "burnt" in the reactor.
Recurrent neural networkA recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.
Nuclear fission productNuclear fission products are the atomic fragments left after a large atomic nucleus undergoes nuclear fission. Typically, a large nucleus like that of uranium fissions by splitting into two smaller nuclei, along with a few neutrons, the release of heat energy (kinetic energy of the nuclei), and gamma rays. The two smaller nuclei are the fission products. (See also Fission products (by element)). About 0.2% to 0.4% of fissions are ternary fissions, producing a third light nucleus such as helium-4 (90%) or tritium (7%).
Long-lived fission productLong-lived fission products (LLFPs) are radioactive materials with a long half-life (more than 200,000 years) produced by nuclear fission of uranium and plutonium. Because of their persistent radiotoxicity, it is necessary to isolate them from humans and the biosphere and to confine them in nuclear waste repositories for geological periods of time. Nuclear fission produces fission products, as well as actinides from nuclear fuel nuclei that capture neutrons but fail to fission, and activation products from neutron activation of reactor or environmental materials.
