基于TDLAS技术的CH4气体检测与温度补偿方法

CH₄气体的精准检测对防止矿井瓦斯爆炸,确保安全生产至关重要。目前基于可调谐半导体激光吸收光谱技术（TDLAS）存在因温度变化导致气体浓度测量误差较大。探究了基于TDLAS的CH₄气体检测系统与温度补偿方法,分析温度对CH₄气体吸收谱线的影响,通过算法补偿模型消除环境温度对CH₄气体检测的影响。依据TDLAS技术原理及相关理论,对系统发射单元、吸收池、信号接收单元、数据处理单元进行设计,搭建了基于TDLAS技术的CH₄气体浓度检测系统,实验检测了不同环境温度（10~50 ℃）时0.04%CH₄气体浓度,分析温度变化对CH₄气体在波长为1.653 μm处吸收谱线强度和半宽度的影响。为消除温度对CH₄气体检测的影响并提高补偿效果,采用粒子群优化算法（PSO）优化BP神经网络（BPNN）的最佳权值和阈值,建立CH₄气体的PSO-BP温度补偿模型,克服了BP神经网络收敛速度慢、易陷入局部最优的缺点。结果表明：（1）基于TDLAS的CH₄气体检测浓度随环境温度升高而下降,整个实验温度内相对误差范围为4.25%~12.13%,不同环境温度下CH₄气体检测浓度与温度之间的关系可用一元三次多项式表示;（2）CH₄气体的吸收强度和半宽度随着温度的升高而下降,与温度变化之间的关系为单调递减函数,温度对CH₄气体吸收谱线强度的相对变化率大于吸收谱线半宽度的相对变化率,CH₄气体吸收谱线的强度更容易受温度变化的影响;（3）BP神经网络和PSO-BP模型测试样本的绝对平均误差（MAE）分别为12.88%和1.81%,平均绝对百分比误差（MAPE）分别为2.3%和0.3%,均方根误差（RMSE）分别为15.96%和2.69%,相关系数R2分别为0.980 6和0.999 6。通过建立PSO-BP温度补偿模型,补偿效果大部分分布在±1.0%的误差范围内,MAE,MAPE,RMSE和R2等评价指标均大幅度提升,对提高TDLAS技术在矿井CH₄的精准检测具有一定的参考意义。     

概率神经网络及FAAS在植物药分类研究中的应用

用火焰原子吸收法（FAAS）测定了植物药中Fe、Mg、Mn、Cu、Zn和Ca元素的含量,采用主成分分析法对所测数据进行预处理,结合概率神经网络模型对中药功效类别进行识别预测研究,取得了较满意的结果。     

Crankshaft-bearing evolution indexes investigation and asperity contact identification based on neural network

The dynamic and lubrication characteristic analyses of the crankshaft–bearing system is quite a complex problem, and it is important to avoid asperity contact which may lead to bearing wear and increase of friction loss significantly in dynamic lubrication condition. In this paper, the dynamic characteristic that has an essential impact on lubrication was investigated over an inline six-cylinder engine. Multi-body dynamics method, tribology, finite element method (FEM), finite difference method (FDM) and component mode synthesis method (CMS) were combined to analyze the dynamic characteristic of crankshaft, oil leakage, oil film pressure, asperity contact pressure and friction loss. Then the orthogonal experiment that included 5 levels and 6 factors was conducted to obtain the training sample sets for neural network, and the probabilistic neural network (PNN) was employed to identify weather the asperity contact happened or not according to its nonlinear characteristic. The analyses which can provide the guidance for the design of main bearing, and avoid the asperity contact in the lubrication are significant to the design of the bearing at the development stage of the engine.     

Interpolation by neural network operators activated by ramp functions

In this paper, a family of interpolation neural network operators are introduced. Here, ramp functions as well as sigmoidal functions generated by central B-splines are considered as activation functions. The interpolation properties of these operators are proved, together with a uniform approximation theorem with order, for continuous functions defined on bounded intervals. The relations with the theory of neural networks and with the theory of the generalized sampling operators are discussed.     

Simulation of the effect of learning on the topology of the functional connectivity of neural networks

We introduce a procedure for simulating adaptive learning in neural networks and the effect this learning has on the way in which the functional connections between the nodes of the network are established. The procedure combines two mechanisms: firstly, the gradual dilution of the network through the elimination of synaptic weights in increasing order of magnitude, thus reducing the costs of the network structure. Secondly, to train the network as it is diluted so as not to compromise its performance pursuant to the proposed task. Considering different levels of learning difficulty, we compare the topology of the functional connectivities that result from the application of this procedure with those obtained using fMRI in healthy volunteers. According to our results, the topology of functional connectivities in healthy subjects can be interpreted as the product of a learning process with a specific degree of difficulty.     

Bankruptcy prediction in banks and firms via statistical and intelligent techniques – A review

This paper presents a comprehensive review of the work done, during the 1968–2005, in the application of statistical and intelligent techniques to solve the bankruptcy prediction problem faced by banks and firms. The review is categorized by taking the type of technique applied to solve this problem as an important dimension. Accordingly, the papers are grouped in the following families of techniques: (i) statistical techniques, (ii) neural networks, (iii) case-based reasoning, (iv) decision trees, (iv) operational research, (v) evolutionary approaches, (vi) rough set based techniques, (vii) other techniques subsuming fuzzy logic, support vector machine and isotonic separation and (viii) soft computing subsuming seamless hybridization of all the above-mentioned techniques. Of particular significance is that in each paper, the review highlights the source of data sets, financial ratios used, country of origin, time line of study and the comparative performance of techniques in terms of prediction accuracy wherever available. The review also lists some important directions for future research.     

Asymptotic stability analysis in uncertain multi-delayed state neural networks via Lyapunov–Krasovskii theory

This paper presents a new approach to the analysis of asymptotic stability of artificial neural networks (ANN) with multiple time-varying delays subject to polytope-bounded uncertainties. This approach is based on the Lyapunov–Krasovskii stability theory for functional differential equations and the linear matrix inequality (LMI) technique with the use of a recent Leibniz–Newton model based transformation without including any additional dynamics.Three examples with numerical simulations are used to illustrate the effectiveness of the proposed method. The first example considers the neural network with multiple time-varying delays, which may be seen as a particular case of the second example where it is subject to uncertainties and multiple time-varying delays. Finally, the third example analyzes the stability of the neural network with higher numbers of neurons subject to a single time-delay. The Hopf bifurcation theory is used to verify the stability of the system when the origin falls into instability in the bifurcation point.     

Conditions for the emergence of spatially asymmetric retrieval states in an attractor neural network

In this paper we show that during the retrieval process in a binary symmetric Hebb neural network, spatially localized states can be observed when the connectivity of the network is distance-dependent and a constraint on the activity of the network is imposed, which forces different levels of activity in the retrieval and learning states. This asymmetry in the activity during retrieval and learning is found to be a sufficient condition to observe spatially localized retrieval states. The result is confirmed analytically and by simulation.