基于神经网络的软测量技术及应用

软测量是一门新兴的工业技术，它借助现代估计理论构造模型推断出工程上难以检测的变量。本文提出了基于径向基函数神经网络（RBFNN）的软测量技术，并且结合工艺机理分析和过程数据关联，对其在轻柴油凝固点软测量的应用进行了研究。结果表明，RBFNN的良好的非线性动态建模能力使其在软测量中具有很大的应用潜力。     

Modelling and solving English Peg Solitaire

Peg Solitaire is a well known puzzle, which can prove difficult despite its simple rules. Pegs are arranged on a board such that at least one ‘hole’ remains. By making draughts/checkers-like moves, pegs are gradually removed until no further moves are possible or some goal configuration is achieved. This paper considers the English variant, consisting of a board in a cross shape with 33 holes. Modelling Peg Solitaire via constraint or integer programming techniques presents a considerable challenge and is examined in detail. The merits of the resulting models are discussed and they are compared empirically. The sequential nature of the puzzle naturally conforms to a planning problem, hence we also present an experimental comparison with several leading AI planning systems. Other variants of the puzzle, such as ‘Fool's Solitaire’ and ‘Long-hop’ Solitaire are also considered.     

Mass recovery adsorption refrigeration cycle—improving cooling capacity

The study investigates the performance of two-bed, silica gel-water adsorption refrigeration cycle with mass recovery process. The cycle with mass recovery can be driven by the relatively low temperature heat source. In an adsorption refrigeration cycle, the pressures in adsorber and desorber are different. The chiller with mass recovery process utilizes the pressure difference to enhance the refrigerant mass circulation. Cooling capacity and coefficient of performance (COP) were calculated by cycle simulation computer program to analyze the influences of operating conditions. The mass recovery cycle was compared with conventional cycle such as the single stage adsorption cycle in terms of cooling capacity and COP. The results show that the cooling capacity of mass recovery cycle is superior to that of conventional cycle and the mass recovery process is more effective for low regenerating temperature.     

Applying grey forecasting to predicting the operating energy performance of air cooled water chillers

Grey forecasting has found applications in finance, social science, economics, etc. However, its applications in air conditioning and refrigeration have not been reported. This paper reports on a study where grey forecasting method is applied to predicting the operating energy performance for an air cooled water chiller (ACWC) units, so as to demonstrate this forecasting approach can be applied to building Heating Ventilation and Air Conditioning (HVAC) installations. In this paper, a brief introduction of the background and fundamentals of grey forecasting is firstly presented. This is followed by reporting the application of grey forecasting to an ACWC unit installed in Northern China for predicting its operating energy performance using the variation ratio of coefficient of performance (ΔCOP). The predicted values of ΔCOP agreed well with the measured ΔCOP, demonstrating that grey forecasting may be used for predicting the operating energy performance of an ACWC unit with a high accuracy. Finally, the potential use of grey forecasting in fault detection and diagnostics (FDD) or energy management systems (EMSs) for air conditioning and refrigeration systems is assessed, and the comparison with the prediction method based on artificial neural network (ANN) discussed.     

Numerical simulation of double-pipe condensers and evaporators

A detailed one-dimensional steady and transient numerical simulation of the thermal and fluid-dynamic behaviour of double-pipe heat exchangers (evaporators and condensers) has been carried out. The governing equations (continuity, momentum and energy) inside the internal tube and the annulus, together with the energy equation in the internal tube wall, external tube wall and insulation, are solved iteratively in a segregated manner. The discretized governing equations in the zones with fluid flow are efficiently coupled using an implicit step by step method. This formulation requires the use of empirical correlations for the evaluation of convective heat transfer, shear stress and void fraction. An implicit central difference numerical scheme and a line-by-line solver was used in the internal and external tube walls and insulation. A special treatment has been implemented in order to consider transitions (single-phase/two-phase, dry-out,…). All the flow variables (enthalpies, temperatures, pressures, mass fractions, velocities, heat fluxes,…) together with the thermophysical properties are evaluated at each point of the grid in which the domain is discretized. Different numerical aspects and comparisons with analytical and experimental results are presented in order to verify and validate the model.     

微合金钢中板热轧时晶粒尺寸的模拟计算

通过Φ180mm× 2 0 0mm二辊实验轧机对成分 (% )为 0 0 5 3C 1 5 6Mn 0 0 4 6Nb 0 2 5Mo 0 0 14Ti 0 0 0 12B微合金化钢的轧制实验 ,验证了新建立的热轧板带晶粒尺寸的仿真模拟系统 ,得出晶粒尺寸的仿真计算值与实测值的相对误差≤ 8 3% ,并对该微合金钢 9道次 2 2 0 0mm× 14mm中板轧制时各道次钢板晶粒尺寸进行了计算。结果表明 ,精轧各道次均没有发生动态再结晶 ,在板厚 5 1 6mm轧至 2 2 0mm的 1～ 5道次 ,晶粒尺寸显著减小 ,由 4 5 μm降至 10 μm ,在板厚 2 2 0mm轧至 14 0mm的 6～ 9道次 ,晶粒尺寸减小不显著 ,由10 μm降至 7 5 μm     

Thermomechanical modelling the fire properties of fibre–polymer composites

Simple-to-use models are presented in this paper for determining the residual tension, compression and flexural properties of burnt fibre reinforced polymer composite materials following a fire. The post-fire mechanical properties are calculated using analytical equations that combine the properties of the fire-damaged (i.e. char) and undamaged regions of a composite. Fire tests were performed on composites containing carbon, glass or Kevlar fibres with an epoxy, polyester, vinyl ester or phenolic resin matrix to assess the accuracy of the models. The composites were tested to a wide range of fire conditions with temperatures from 525 to 850 °C for times up to 30 min. It is found that the post-fire properties drop rapidly with increasing heat flux and duration of a fire due to the thermal degradation of the polymer matrix. It is shown that the reduction to the post-fire properties of the burnt composites can be accurately determined using the models. In almost all test cases, the agreement between the calculated and measured residual mechanical properties is within 10%.     

A numerical study of the effects of cutter runout on milling process geometry based on true tooth trajectory

Cutter runout is a common phenomenon affecting the cutting performances in milling operations. To date, most of the milling process models considering cutter runout were established based on the circular tooth path approximation, which brought errors into the runout estimation. In this paper, a new approach is presented for modelling the milling process geometry with cutter runout based on the true tooth trajectory of cutter in milling. The mathematical relationship between the trajectories generated by successive cutter teeth with runout is analysed. The milling process geometrical parameters, including the instantaneous undeformed chip thickness, the entry and exit angles of a cutting tooth, and the ideal peripheral machined workpiece surface roughness, are modelled according to the true tooth trajectories. Numerical method is used to solve the derived transcendental equations. A simulation study of the effects of cutter runout on milling process geometry is conducted using the models. It was found that the change of cutter radius for a tooth relative to its preceding one is the most important factor in evaluating the effects of cutter runout.