A parameterized shift-splitting preconditioner for saddle point problems

Li-Tao Zhang; Chao-Qian Li; Yao-Tang Li; Li-Tao Zhang; Chao-Qian Li; Yao-Tang Li

doi:10.3934/mbe.2019048

Mathematical Biosciences and Engineering

2019, Volume 16, Issue 2: 1021-1033. doi: 10.3934/mbe.2019048

Previous Article Next Article

Research article Special Issues

A parameterized shift-splitting preconditioner for saddle point problems

1.
College of Science, Zhengzhou University of Aeronautics, Zhengzhou, Henan, 450015, P. R. China
2.
College of Mathematics and Information Science, Henan Normal University, Xinxiang, Henan, 453007, P. R. China
3.
Henan province Synergy Innovation Center of Aviation economic development, Zhengzhou, Henan, 450015, P. R. China
4.
School of Mathematics and Statistics, Yunnan University, Kunming, Yunnan, 650091, P. R. China

Received: 06 November 2018 Accepted: 31 December 2018 Published: 30 January 2019

Recently, Chen and Ma [A generalized shift-splitting preconditioner for saddle point problems, Applied Mathematics Letters, 43 (2015) 49-55] introduced a generalized shift-splitting preconditioner for saddle point problems with symmetric positive definite (1, 1)-block. In this paper, I establish a parameterized shift-splitting preconditioner for solving the large sparse augmented systems of linear equations. Furthermore, the preconditioner is based on the parameterized shift-splitting of the saddle point matrix, resulting in an unconditional convergent fixed-point iteration, which has the intersection with the generalized shift-splitting preconditioner. In final, one example is provided to confirm the effectiveness.

Keywords:

Citation: Li-Tao Zhang, Chao-Qian Li, Yao-Tang Li. A parameterized shift-splitting preconditioner for saddle point problems[J]. Mathematical Biosciences and Engineering, 2019, 16(2): 1021-1033. doi: 10.3934/mbe.2019048

Related Papers:

[1]	Jagan Mohan Jonnalagadda . On a nabla fractional boundary value problem with general boundary conditions. AIMS Mathematics, 2020, 5(1): 204-215. doi: 10.3934/math.2020012
[2]	Lakhdar Ragoub, J. F. Gómez-Aguilar, Eduardo Pérez-Careta, Dumitru Baleanu . On a class of Lyapunov's inequality involving $\lambda$ -Hilfer Hadamard fractional derivative. AIMS Mathematics, 2024, 9(2): 4907-4924. doi: 10.3934/math.2024239
[3]	Wei Zhang, Jifeng Zhang, Jinbo Ni . New Lyapunov-type inequalities for fractional multi-point boundary value problems involving Hilfer-Katugampola fractional derivative. AIMS Mathematics, 2022, 7(1): 1074-1094. doi: 10.3934/math.2022064
[4]	Jaganmohan Jonnalagadda, Basua Debananda . Lyapunov-type inequalities for Hadamard type fractional boundary value problems. AIMS Mathematics, 2020, 5(2): 1127-1146. doi: 10.3934/math.2020078
[5]	Shuqin Zhang, Lei Hu . The existence of solutions and generalized Lyapunov-type inequalities to boundary value problems of differential equations of variable order. AIMS Mathematics, 2020, 5(4): 2923-2943. doi: 10.3934/math.2020189
[6]	Dumitru Baleanu, Muhammad Samraiz, Zahida Perveen, Sajid Iqbal, Kottakkaran Sooppy Nisar, Gauhar Rahman . Hermite-Hadamard-Fejer type inequalities via fractional integral of a function concerning another function. AIMS Mathematics, 2021, 6(5): 4280-4295. doi: 10.3934/math.2021253
[7]	Jonas Ogar Achuobi, Edet Peter Akpan, Reny George, Austine Efut Ofem . Stability analysis of Caputo fractional time-dependent systems with delay using vector lyapunov functions. AIMS Mathematics, 2024, 9(10): 28079-28099. doi: 10.3934/math.20241362
[8]	Chantapish Zamart, Thongchai Botmart, Wajaree Weera, Prem Junsawang . Finite-time decentralized event-triggered feedback control for generalized neural networks with mixed interval time-varying delays and cyber-attacks. AIMS Mathematics, 2023, 8(9): 22274-22300. doi: 10.3934/math.20231136
[9]	Yitao Yang, Dehong Ji . Properties of positive solutions for a fractional boundary value problem involving fractional derivative with respect to another function. AIMS Mathematics, 2020, 5(6): 7359-7371. doi: 10.3934/math.2020471
[10]	Tingting Guan, Guotao Wang, Haiyong Xu . Initial boundary value problems for space-time fractional conformable differential equation. AIMS Mathematics, 2021, 6(5): 5275-5291. doi: 10.3934/math.2021312

Abstract

1. Introduction

The well-known classical Lyapunov inequality ^[15] states that, if $u$ is a nontrivial solution of the Hill's equation

$\begin{equation} u^{\prime \prime }\left( t\right) +q\left( t\right) u\left( t\right) = 0, \text{ }a \lt t \lt b, \end{equation}$

(1.1)

subject to Dirichlet-type boundary conditions:

$\begin{equation} u\left( a\right) = u\left( b\right) = 0, \end{equation}$

(1.2)

then

$\begin{equation} \int_{a}^{b}\left\vert q\left( t\right) \right\vert dt \gt \frac{4}{b-a}, \end{equation}$

(1.3)

where $q:[a, b]\rightarrow \mathbb{R}$ is a real and continuous function.

Later, in 1951, Wintner ^[24], obtained the following inequality:

$\begin{equation} \int_{a}^{b}q^{+}\left( t\right) dt \gt \frac{4}{b-a}, \end{equation}$

(1.4)

where $q^{+}(t) = \max \left\{ q\left(t\right), 0\right\}.$

A more general inequality was given by Hartman and Wintner in ^[12], that is known as Hartman Wintner-type inequality:

$\begin{equation} \int_{a}^{b}\left( t-a\right) \left( b-t\right) q^{+}\left( t\right) dt \gt b-a, \end{equation}$

(1.5)

Since $\underset{t\in \lbrack a, b]}{\max }\left(t-a\right) \left(b-t\right) = \frac{\left(b-a\right) ^{2}}{4}$ , then, (1.5) implies (1.4).

The Lyapunov inequality and its generalizations have many applications in different fields such in oscillation theory, asymptotic theory, disconjugacy, eigenvalue problems.

Recently, many authors have extended the Lyapunov inequality (1.3) for fractional differential equations ^{[1,2,3,4,5,6,7,8,9,10,11,12,13,15,18,20,22,23,24]}. For this end, they substituted the ordinary second order derivative in (1.1) by a fractional derivative or a conformable derivative. The first result in which a fractional derivative is used instead of the ordinary derivative in equation (1.1), is the work of Ferreira ^[6]. He considered the following two-point Riemann-Liouville fractional boundary value problem

$\begin{equation*} D_{a^{+}}^{\alpha }u\left( t\right) +q(t)u\left( t\right) = 0, \text{ }a \lt t \lt b, \text{ }1 \lt \alpha \leq 2 \end{equation*}$

$\begin{equation*} u\left( a\right) = u\left( b\right) = 0. \end{equation*}$

And obtained the Lyapunov inequality:

$\begin{equation*} \int_{a}^{b}\left\vert q\left( t\right) \right\vert dt \gt \Gamma \left( \alpha \right) \left( \frac{4}{b-a}\right) ^{\alpha -1}. \end{equation*}$

Then, he studied in ^[7], the Caputo fractional differential equation

$\begin{equation*} ^{C}D_{a^{+}}^{\alpha }u\left( t\right) +q(t)u\left( t\right) = 0, \text{ } a \lt t \lt b, \text{ }1 \lt \alpha \leq 2 \end{equation*}$

under Dirichlet boundary conditions (1.2). In this case, the corresponding Lyapunov inequality has the form

$\begin{equation*} \int_{a}^{b}\left\vert q\left( t\right) \right\vert dt \gt \frac{\alpha ^{\alpha }\Gamma \left( \alpha \right) }{\left( \left( \alpha -1\right) \left( b-a\right) \right) ^{\alpha -1}}. \end{equation*}$

Later Agarwal and Özbekler in ^[1], complimented and improved the work of Ferreira ^[6]. More precisely, they proved that if $u$ is a nontrivial solution of the Riemann-Liouville fractional forced nonlinear differential equations of order $\alpha \in (0, 2]$ :

$\begin{equation*} D_{a^{+}}^{\alpha }u\left( t\right) +p\left( t\right) \left\vert u\left( t\right) \right\vert ^{\mu -1}u\left( t\right) +q\left( t\right) \left\vert u\left( t\right) \right\vert ^{\gamma -1}u\left( t\right) = f\left( t\right) , \text{ }a \lt t \lt b, \end{equation*}$

satisfying the Dirichlet boundary conditions (1.2), then the following Lyapunov type inequality

$\begin{equation*} \left( \int_{a}^{b}\left[ p^{+}\left( t\right) +q^{+}\left( t\right) \right] dt\right) \left( \int_{a}^{b}\left[ \mu _{0}p^{+}\left( t\right) +\gamma _{0}q^{+}\left( t\right) +\left\vert f\left( t\right) \right\vert \right] dt\right) \gt \frac{4^{2\alpha -3}\Gamma ^{2}\left( \alpha \right) }{\left( b-a\right) ^{2\alpha -2}}. \end{equation*}$

holds, where $p,$ $q,$ $f$ are real-valued functions, $0 < \gamma < 1 < \mu < 2$ , $\mu _{0} = \left(2-\mu \right) \mu ^{\mu /\left(2-\mu \right) }2^{2/\left(\mu -2\right) }$ and $\gamma _{0} = \left(2-\gamma \right) \gamma ^{\gamma /\left(2-\gamma \right) }2^{2/\left(\gamma -2\right) }$ .

In 2017, Guezane-Lakoud et al. ^[11], derived a new Lyapunov type inequality for a boundary value problem involving both left Riemann-Liouville and right Caputo fractional derivatives in presence of natural conditions

$\begin{equation*} -^{C}D_{b^{-}}^{\alpha }D_{a^{+}}^{\beta }u\left( t\right) +q(t)u\left( t\right) = 0, \text{ }a \lt t \lt b, \text{ }0 \lt \alpha , \beta \leq 1 \end{equation*}$

$\begin{equation*} u\left( a\right) = D_{a^{+}}^{\beta }u\left( b\right) = 0, \text{ } \end{equation*}$

then, they obtained the following Lyapunov inequality:

$\begin{equation*} \int_{a}^{b}\left\vert q\left( t\right) \right\vert dt \gt \frac{\left( \alpha +\beta -1\right) \Gamma \left( \alpha \right) \Gamma \left( \beta \right) }{ \left( b-a\right) ^{\alpha +\beta -1}}. \end{equation*}$

Recently, Ferreira in ^[9], derived a Lyapunov-type inequality for a sequential fractional right-focal boundary value problem

$\begin{equation*} ^{C}D_{a^{+}}^{\alpha }D_{a^{+}}^{\beta }u\left( t\right) +q(t)u\left( t\right) = 0, \text{ }a \lt t \lt b \end{equation*}$

$\begin{equation*} u\left( a\right) = D_{a^{+}}^{\gamma }u\left( b\right) = 0, \text{ } \end{equation*}$

where $0 < \alpha, \beta, \gamma \leq 1,$ $1 < \alpha +\beta \leq 2,$ then, they obtained the following Lyapunov inequality:

$\begin{equation*} \int_{a}^{b}\left( b-s\right) ^{\alpha +\beta -\gamma -1}\left\vert q\left( t\right) \right\vert dt \gt \frac{1}{C}, \end{equation*}$

where

$\begin{eqnarray*} C & = &\left( b-a\right) ^{\gamma }\max \left\{ \frac{\Gamma \left( \beta -\gamma +1\right) }{\Gamma \left( \alpha +\beta -\gamma \right) \Gamma \left( \beta +1\right) }, \right. \\ &&\left. \frac{1-\alpha }{\beta \Gamma \left( \alpha +\beta \right) }\left( \frac{\Gamma \left( \beta -\gamma +1\right) \Gamma \left( \alpha +\beta -1\right) }{\Gamma \left( \alpha +\beta -\gamma \right) \Gamma \left( \beta \right) }\right) ^{\frac{\alpha +\beta -1}{\alpha -1}}, \text{ with }\alpha \lt 1\right\} \end{eqnarray*}$

Note that more generalized Lyapunov type inequalities have been obtained for conformable derivative differential equations in ^[13]. For more results on Lyapunov-type inequalities for fractional differential equations, we refer to the recent survey of Ntouyas et al. ^[18].

In this work, we obtain Lyapunov type inequality for the following mixed fractional differential equation involving both right Caputo and left Riemann-Liouville fractional derivatives

$\begin{equation} -^{C}D_{b^{-}}^{\alpha }D_{a^{+}}^{\beta }u\left( t\right) +q(t)u\left( t\right) = 0, \text{ }a \lt t \lt b, \end{equation}$

(1.6)

satisfying the Dirichlet boundary conditions (1.2), here $0 < \beta \leq \alpha \leq 1,$ $1 < \alpha +\beta \leq 2,$ $^{C}D_{b^{-}}^{\alpha }$ denotes right Caputo derivative, $D_{a^{+}}^{\beta }$ denotes the left Riemann-Liouville and $q$ is a continuous function on $\left[a, b\right].$

So far, few authors have considered sequential fractional derivatives, and some Lyapunov type inequalities have been obtained. In this study, we place ourselves in a very general context, in that in each fractional operator, the order of the derivative can be different. Such problems, with both left and right fractional derivatives arise in the study of Euler-Lagrange equations for fractional problems of the calculus of variations ^[2,16,17]. However, the presence of a mixed left and right Caputo or Riemann-Liouville derivatives of order $0 < \alpha < 1$ leads to great difficulties in the study of the properties of the Green function since in this case it's given as a fractional integral operator.

We recall the concept of fractional integral and derivative of order $p > 0$ . For details, we refer the reader to ^[14,19,21]

The left and right Riemann-Liouville fractional integral of a function $g$ are defined respectively by

$\begin{eqnarray*} I_{a^{+}}^{p}g(t) & = &\frac{1}{\Gamma \left( p\right) }\int_{a}^{t}\frac{g(s) }{(t-s)^{1-p}}ds, \\ I_{b^{-}}^{p}g(t) & = &\frac{1}{\Gamma \left( p\right) }\int_{t}^{b}\frac{g(s) }{(s-t)^{1-p}}ds. \end{eqnarray*}$

The left and right Caputo derivatives of order $p > 0,$ of a function $g$ are respectively defined as follows:

$\begin{eqnarray*} ^{C}D_{a^{+}}^{p}g(t) & = &I_{a^{+}}^{n-p}g^{\left( n\right) }(t), \\ ^{C}D_{b^{-}}^{p}g(t) & = &\left( -1\right) ^{n}I_{b^{-}}^{n-p}g^{\left( n\right) }(t), \end{eqnarray*}$

and the left and right Riemann-Liouville fractional derivatives of order $p > 0,$ of a function $g$ \ are respectively defined as follows:

$\begin{eqnarray*} D_{a^{+}}^{p}g(t) & = &\frac{d^{n}}{dt^{n}}\left( I_{a^{+}}^{n-p}g\right) (t), \\ D_{b^{-}}^{p}g(t) & = &\left( -1\right) ^{n}\frac{d^{n}}{dt^{n}} I_{b^{-}}^{n-p}g(t), \end{eqnarray*}$

where $n$ is the smallest integer greater or equal than $p$ .

We also recall the following properties of fractional operators. Let $0 < p < 1$ , then:

1- $I_{a^{+}}^{pC}D_{a^{+}}^{p}f\left(t\right) = f\left(t\right) -f(a).$

2- $I_{b^{-}}^{pC}D_{b^{-}}^{p}f\left(t\right) = f\left(t\right) -f\left(b\right).$

3- $\left(I_{a^{+}}^{p}c\right) \left(t\right) = \frac{c\left(t-a\right) ^{p}}{\Gamma \left(p+1\right) }, c\in \mathbb{R}$

4- $D_{a^{+}}^{p}u(t) = ^{C}D_{a^{+}}^{p}u(t)$ , when $u\left(a\right) = 0.$

5- $D_{b^{-}}^{p}u(t) = ^{C}D_{b^{-}}^{p}u(t)$ , when $u\left(b\right) = 0.$

2. Lyapunov inequality

Next we transform the problem (1.6) with (1.2) to an equivalent integral equation.

Lemma 1. Assume that $0 < \alpha, \beta \leq 1.$ The function $u$ is a solution to the boundary value problem (1.6) with (1.2) if and only if $u$ satisfies the integral equation

$\begin{equation} u\left( t\right) = \int_{a}^{b}G(t, r)q(r)u(r)dr, \end{equation}$

(2.1)

where

$\begin{equation} G(t, r) = \frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) } \left( \int_{a}^{\inf \left\{ r, t\right\} }\left( t-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right. \notag \end{equation}$

$\begin{equation} \left. -\frac{\left( t-a\right) ^{\beta }}{\left( b-a\right) ^{\beta }} \int_{a}^{r}\left( b-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right) \end{equation}$

(2.2)

is the Green's function of problem (1.6) with (1.2).

Proof. Firstly, we apply the right side fractional integral $I_{b^{-}}^{\alpha }$ to equation (1.6), then the left side fractional integral $I_{a^{+}}^{\beta }$ to the resulting equation and taking into account the properties of Caputo and\Riemann-Liouville fractional derivatives and the fact that $D_{a^{+}}^{\beta }u(t) = ^{C}D_{a^{+}}^{\beta }u(t)$ , we get

$\begin{equation} u\left( t\right) = I_{a^{+}}^{\beta }I_{b^{-}}^{\alpha }q(t)u(t)+\frac{ c\left( t-a\right) ^{\beta }}{\Gamma \left( \beta +1\right) }. \end{equation}$

(2.3)

In view of the boundary condition $u\left(b\right) = 0,$ we get

$\begin{equation*} c = \frac{-\Gamma \left( \beta +1\right) }{\left( b-a\right) ^{\beta }} I_{a^{+}}^{\beta }I_{b^{-}}^{\alpha }q(t)u(t)\mid _{t = b}. \end{equation*}$

Substituting $c$ in (2.3), it yields

$\begin{eqnarray*} u\left( t\right) & = &I_{a^{+}}^{\beta }I_{b^{-}}^{\alpha }q(t)u(t)-\frac{ \left( t-a\right) ^{\beta }}{\left( b-a\right) ^{\beta }}I_{a^{+}}^{\beta }I_{b^{-}}^{\alpha }q(t)u(t)\mid _{t = b} \\ & = &\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) } \int_{a}^{t}\left( t-s\right) ^{\beta -1}\left( \int_{s}^{b}\left( r-s\right) ^{\alpha -1}q(r)u(r)dr\right) ds \\ &&-\frac{\left( t-a\right) ^{\beta }}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) \left( b-a\right) ^{\beta }}\int_{a}^{b}\left( b-s\right) ^{\beta -1}\left( \int_{s}^{b}\left( r-s\right) ^{\alpha -1}q(r)u(r)dr\right) ds. \end{eqnarray*}$

Finally, by exchanging the order of integration, we get

$\begin{eqnarray*} u\left( t\right) & = &\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) }\int_{a}^{t}\left( \int_{a}^{r}\left( t-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right) q(r)u(r)dr \\ &&+\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) } \int_{t}^{b}\left( \int_{a}^{t}\left( t-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right) q(r)u(r)dr \\ &&-\frac{\left( t-a\right) ^{\beta }}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) \left( b-a\right) ^{\beta }}\int_{a}^{b}\left( \int_{a}^{r}\left( b-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right) q(r)u(r)dr, \end{eqnarray*}$

thus

$\begin{equation*} u\left( t\right) = \int_{a}^{b}G(t, r)q(r)u(r)dr, \end{equation*}$

with

$\begin{equation*} G(t, r) = \frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) } \left\{ \begin{array}{c} \int_{a}^{r}\left( t-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds \\ -\frac{\left( t-a\right) ^{\beta }}{\left( b-a\right) ^{\beta }} \int_{a}^{r}\left( b-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds, a\leq r\leq t\leq b, \\ \int_{a}^{t}\left( t-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds \\ -\frac{\left( t-a\right) ^{\beta }}{\left( b-a\right) ^{\beta }} \int_{a}^{r}\left( b-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds, a\leq t\leq r\leq b. \end{array} \right. \end{equation*}$

that can be written as

$\begin{eqnarray*} G(t, r) & = &\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) } \left( \int_{a}^{\inf \left\{ r, t\right\} }\left( t-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right. \\ &&\left. -\frac{\left( t-a\right) ^{\beta }}{\left( b-a\right) ^{\beta }} \int_{a}^{r}\left( b-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right) . \end{eqnarray*}$

Conversely, we can verify that if $u$ satisfies the integral equation (2.1), then $u$ is a solution to the boundary value problem (1.6) with (1.2). The proof is completed.

In the next Lemma we give the property of the Green function $G$ that will be needed in the sequel.

Lemma 2. Assume that $0 < \beta \leq \alpha \leq 1, 1 < \alpha +\beta \leq 2,$ then the Green function $G\left(t, r\right)$ given in (2.2) of problem (1.6) with (1.2) satisfies the following property:

$\begin{equation*} \left\vert G(t, r)\right\vert \leq \frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) \left( \alpha +\beta -1\right) \left( \alpha +\beta \right) }\left( \frac{\alpha \left( b-a\right) }{\left( \beta +\alpha \right) }\right) ^{\alpha +\beta -1}, \end{equation*}$

for all $a\leq r\leq t\leq b$ .

Proof. Firstly, for $a\leq r\leq t\leq b$ , we have $G(t, r)\geq 0$ . In fact, we have

$\begin{eqnarray*} G(t, r) & = &\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) } \left( \int_{a}^{r}\left( t-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right. \\ &&-\frac{\left( t-a\right) ^{\beta }}{\left( b-a\right) ^{\beta }}\left. \int_{a}^{r}\left( b-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right) \\ &\geq &\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) } \left( \int_{a}^{r}\left( b-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right. \\ &&-\frac{\left( t-a\right) ^{\beta }}{\left( b-a\right) ^{\beta }}\left. \int_{a}^{r}\left( b-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right) \end{eqnarray*}$

$\begin{equation} = \frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) }\left( 1- \frac{\left( t-a\right) ^{\beta }}{\left( b-a\right) ^{\beta }}\right) \int_{a}^{r}\left( b-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\geq 0 \end{equation}$

(2.4)

in addition,

$\begin{eqnarray*} G(t, r) &\leq &\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) }\left( \int_{a}^{r}\left( r-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right. \\ &&-\frac{\left( r-a\right) ^{\beta }}{\left( b-a\right) ^{\beta }}\left. \int_{a}^{r}\left( b-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right) \\ &\leq &\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) } \left( \frac{(r-a)^{\alpha +\beta -1}}{\left( \alpha +\beta -1\right) } \right. \\ &&\left. -\frac{\left( r-a\right) ^{\beta }}{\left( b-a\right) ^{\beta }} \int_{a}^{r}\left( b-a\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right) \end{eqnarray*}$

$\begin{equation} = \frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) }\left( \frac{(r-a)^{\alpha +\beta -1}}{\left( \alpha +\beta -1\right) }-\frac{ \left( r-a\right) ^{\beta +\alpha }}{\alpha \left( b-a\right) }\right) . \end{equation}$

(2.5)

Thus, from (2.4) and (2.5), we get

$\begin{equation} 0\leq G(t, r)\leq h\left( r\right) , \text{ }a\leq r\leq t\leq b, \end{equation}$

(2.6)

where

$\begin{equation*} h\left( s\right) : = \frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) }\left( \frac{(s-a)^{\alpha +\beta -1}}{\left( \alpha +\beta -1\right) }-\frac{\left( s-a\right) ^{\beta +\alpha }}{\alpha \left( b-a\right) }\right) , \end{equation*}$

it is clear that $h\left(s\right) \geq 0,$ for all $s\in \left[a, b\right]$ .

Now, for $a\leq t\leq r\leq b$ , we have

$\begin{eqnarray*} G(t, r) & = &\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) } \left( \int_{a}^{t}\left( t-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right. \\ &&\left. -\frac{\left( t-a\right) ^{\beta }}{\left( b-a\right) ^{\beta }} \int_{a}^{r}\left( b-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right) \\ &\leq &\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) } \left( \int_{a}^{t}\left( t-s\right) ^{\beta -1}\left( t-s\right) ^{\alpha -1}ds\right. \\ &&\left. -\frac{\left( t-a\right) ^{\beta }}{\left( b-a\right) } \int_{a}^{r}\left( r-s\right) ^{\alpha -1}ds\right) \\ & = &\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) }\left( \frac{(t-a)^{\alpha +\beta -1}}{\left( \alpha +\beta -1\right) }-\frac{ \left( t-a\right) ^{\beta }\left( r-a\right) ^{\alpha }}{\alpha \left( b-a\right) }\right) \end{eqnarray*}$

$\begin{equation} \leq \frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) } \left( \frac{(t-a)^{\alpha +\beta -1}}{\left( \alpha +\beta -1\right) }- \frac{\left( t-a\right) ^{\beta +\alpha }}{\alpha \left( b-a\right) }\right) = h(t). \end{equation}$

(2.7)

On the other hand,

$\begin{eqnarray*} G(t, r) &\geq &\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) }\left( r-a\right) ^{\alpha -1}\int_{a}^{t}\left( t-s\right) ^{\beta -1}ds \\ &&\left. -\frac{\left( t-a\right) ^{\beta }}{\left( b-a\right) ^{\beta }} \int_{a}^{r}\left( r-s\right) ^{\beta -1}\left( r-s\right) ^{\alpha -1}ds\right) \\ &\geq &\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) } \left( \frac{\left( t-a\right) ^{\alpha }\left( t-a\right) ^{\beta }}{\beta \left( b-a\right) }-\frac{\left( t-a\right) ^{\beta }}{\left( b-a\right) ^{\beta }}\frac{(r-a)^{\alpha +\beta -1}}{\left( \alpha +\beta -1\right) } \right) \\ &\geq &\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) } \left( \frac{\left( t-a\right) ^{\alpha +\beta }}{\beta \left( b-a\right) }- \frac{\left( t-a\right) ^{\beta }(r-a)^{\alpha -1}}{\left( \alpha +\beta -1\right) }\right) \\ &\geq &\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) } \left( \frac{\left( t-a\right) ^{\alpha +\beta }}{\beta \left( b-a\right) }- \frac{(t-a)^{\alpha +\beta -1}}{\left( \alpha +\beta -1\right) }\right) , \end{eqnarray*}$

since $\beta \leq \alpha$ , we get

$\begin{equation} G(t, r)\geq -h\left( t\right) , \text{ }a\leq t\leq r\leq b. \end{equation}$

(2.8)

From (2.7) and (2.8) we obtain

$\begin{equation} \left\vert G(t, r)\right\vert \leq h\left( t\right) , \text{ }a\leq t\leq r\leq b. \end{equation}$

(2.9)

Finally, by differentiating the function $h,$ it yields

$\begin{equation*} h^{\prime }(s) = \frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) }(s-a)^{\alpha +\beta -2}\left( 1-\frac{\left( \beta +\alpha \right) \left( s-a\right) }{\alpha \left( b-a\right) }\right) . \end{equation*}$

We can see that $h^{\prime }(s) = 0$ for $s_{0} = a+\frac{\alpha \left(b-a\right) }{\left(\beta +\alpha \right) }\in \left(a, b\right),$ $h^{\prime }(s) < 0$ for $s > s_{0}$ and $h^{\prime }(s) > 0$ for $s < s_{0}.$ Hence, the function $h(s)$ has a unique maximum given by

$\begin{eqnarray*} \underset{s\in \left[ a, b\right] }{\max }h\left( s\right) & = &h\left( s_{0}\right) \\ & = &\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) }\left( \frac{\left( \frac{\alpha \left( b-a\right) }{\left( \beta +\alpha \right) } \right) ^{\alpha +\beta -1}}{\left( \alpha +\beta -1\right) }-\frac{\left( \frac{\alpha \left( b-a\right) }{\left( \beta +\alpha \right) }\right) ^{\beta +\alpha }}{\alpha \left( b-a\right) }\right) \\ & = &\frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) \left( \alpha +\beta -1\right) \left( \alpha +\beta \right) }\left( \frac{\alpha \left( b-a\right) }{\left( \beta +\alpha \right) }\right) ^{\alpha +\beta -1}. \end{eqnarray*}$

From (2.6) and (2.9), we get $\left\vert G(t, r)\right\vert \leq h(s_{0})$ , from which the intended result follows.

Next, we state and prove the Lyapunov type inequality for problem (1.6) with (1.2).

Theorem 3. Assume that $0 < \beta \leq \alpha \leq 1$ and $1 < \alpha +\beta \leq 2.$ If the fractional boundary value problem (1.6) with (1.2) has a nontrivial continuous solution, then

$\begin{equation} \int_{a}^{b}\left\vert q\left( r\right) \right\vert dr\geq \frac{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) \left( \alpha +\beta -1\right) \left( \alpha +\beta \right) ^{\alpha +\beta }}{\left( \alpha \left( b-a\right) \right) ^{\alpha +\beta -1}}. \end{equation}$

(2.10)

Proof. Let $X = C[a, b]$ be the Banach space endowed with norm $\left\vert \left\vert u\right\vert \right\vert = \underset{t\in \left[a, b\right] }{\max } \left\vert u\left(t\right) \right\vert$ . It follows from Lemma 1 that a solution $u\in X$ to the boundary value problem (1.6) with (1.2) satisfies

$\begin{eqnarray*} \left\vert u\left( t\right) \right\vert &\leq &\int_{a}^{b}\left\vert G(t, r)\right\vert \left\vert q\left( r\right) \right\vert \left\vert u\left( r\right) \right\vert dr \\ &\leq &\left\Vert u\right\Vert \int_{a}^{b}\left\vert G(t, r)\right\vert q\left( r\right) dr, \end{eqnarray*}$

Now, applying Lemma 2 to equation (2.1), it yields

$\begin{equation*} \left\vert u\left( t\right) \right\vert \leq \frac{1}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) \left( \alpha +\beta -1\right) \left( \alpha +\beta \right) }\left( \frac{\alpha \left( b-a\right) }{\left( \beta +\alpha \right) }\right) ^{\alpha +\beta -1}\left\Vert u\right\Vert \int_{a}^{b}\left\vert q\left( r\right) \right\vert dr \end{equation*}$

Hence,

$\begin{equation*} \left\Vert u\right\Vert \leq \frac{\left( \alpha \left( b-a\right) \right) ^{\alpha +\beta -1}}{\Gamma \left( \alpha \right) \Gamma \left( \beta \right) \left( \alpha +\beta -1\right) \left( \alpha +\beta \right) ^{\alpha +\beta }}\left\Vert u\right\Vert \int_{a}^{b}\left\vert q\left( r\right) \right\vert dr, \end{equation*}$

from which the inequality (2.10) follows. Note that the constant in (2.10) is not sharp. The proof is completed.

Remark 4. Note that, according to boundary conditions (1.2), the Caputo derivatives $^{C}D_{b^{-}}^{\alpha }$ and $\ ^{C}D_{a^{+}}^{\beta }$ coincide respectively with the Riemann-Liouville derivatives $D_{b^{-}}^{\alpha }$ and $D_{a^{+}}^{\beta }$ . So, equation (1.6) is reduced to the one containing only Caputo derivatives or only Riemann-Liouville derivatives, i.e.,

$\begin{equation*} -^{C}D_{b^{-}}^{\alpha C}D_{a^{+}}^{\beta }u\left( t\right) +q(t)u\left( t\right) = 0, \text{ }a \lt t \lt b \end{equation*}$

$\begin{equation*} -D_{b^{-}}^{\alpha }D_{a^{+}}^{\beta }u\left( t\right) +q(t)u\left( t\right) = 0, \text{ }a \lt t \lt b \end{equation*}$

Furthermore, by applying the reflection operator $(Qf)(t) = f(a+b-t)$ and taking into account that $Q^{C}D_{a+}^{\alpha } = ^{C}D_{b^{-}}^{\alpha }Q$ and $Q^{C}D_{b^{-}}^{\beta } = ^{C}D_{a^{+}}^{\beta }Q$ (see ^[21]), we can see that, the boundary value problem (1.6) with (1.2) is equivalent to the following problem

$\begin{equation*} -^{C}D_{a^{+}}^{\alpha }D_{b^{-}}^{\beta }u\left( t\right) +q(t)u\left( t\right) = 0, \text{ }a \lt t \lt b, \end{equation*}$

$\begin{equation*} u\left( a\right) = u\left( b\right) = 0. \end{equation*}$

Remark 5. If we take $\alpha = \beta = 1,$ then the Lyapunov type inequality (2.3) is reduced to

$\begin{equation*} \int_{a}^{b}\left\vert q\left( t\right) \right\vert dt\geq \frac{4}{b-a}. \end{equation*}$

Acknowledgements

The authors thank the anonymous referees for their valuable comments and suggestions that improved this paper.

Conflict of interest

All authors declare no conflicts of interest in this paper.

References

[1]	M. Arioli, I. S. Du and P. P. M. de Rijk, On the augmented system approach to sparse leastsquares problems, Numer. Math., 55 (1989), 667–684.
[2]	Z. Z. Bai, B. N. Parlett and Z. Q. Wang, On generalized successive overrelaxation methods for augmented linear systems, Numer. Math., 102 (2005), 1–38.
[3]	Z. Z. Bai and Z. Q. Wang, On parameterized inexact Uzawa methods for generalized saddle point problems, Linear Algebra Appl., 428 (2008), 2900–2932.
[4]	Z. Z. Bai and X. Yang, On HSS-based iteration methods for weakly nonlinear systems, Appl. Numer. Math., 59 (2009), 2923–2936.
[5]	Z. Z. Bai, G. H. Golub and K. N. Michael, On inexact hermitian and skew-Hermitian splitting methods for non-Hermitian positive definite linear systems, Linear Algebra Appl., 284 (2008), 413–440.
[6]	Z. Z. Bai, Several splittings for non-Hermitian linear systems, Science in China, Series A: Math., 51 (2008), 1339–1348.
[7]	Z. Z. Bai, G. H. Golub, L. Z. Lu and J. F. Yin, Block-Triangular and skew-Hermitian splitting methods for positive definite linear systems, SIAM J. Sci. Comput., 26 (2005), 844–863.
[8]	Z. Z. Bai, G. H. Golub and M. K.Ng, Hermitian and skew-Hermitian splitting methods for non- Hermitian positive definite linear systems, SIAM J. Matrix Anal. A., 24 (2003), 603–626.
[9]	Z. Z. Bai, G. H. Golub and M. K. Ng, On successive-overrelaxation acceleration of the Hermitian and skew-Hermitian splitting iteration. Available from: http://www.sccm.stanford.edu/wrap/pubtech. html.
[10]	Z. Z. Bai, G. H. Golub and C. K. Li, Optimal parameter in Hermitian and skew-Hermitian splitting method for certain twoby- two block matrices, SIAM J. Sci. Comput., 28 (2006), 28:583–603.
[11]	Z. Z. Bai, G. H. Golub and M. K. Ng, On successive-overrelaxation acceleration of the Hermitian and skew-Hermitian splitting iterations, Numer. Linear Algebra Appl., 14 (2007), 319–335.
[12]	Z. Z. Bai, G. H. Golub and J. Y. Pan, Preconditioned Hermitian and skew-Hermitian splitting methods for non-Hermitian positive semidefinite linear systems, Numer. Math., 98 (2004), 1–32.
[13]	Z. Z. Bai and M. K. Ng, On inexact preconditioners for nonsymmetric matrices, SIAM J. Sci. Comput., 26 (2005), 1710–1724.
[14]	Z. Z. Bai, M. K. Ng and Z. Q.Wang, Constraint preconditioners for symmetric indefinite matrices, SIAM J. Matrix Anal. Appl., 31 (2009), 410–433.
[15]	Z. Z. Bai, Optimal parameters in the HSS-like methods for saddle-point problems, Numer. Linear Algebra Appl., 16 (2009), 447–479.
[16]	Z. Z. Bai, J. F. Yin and Y. F. Su, A shift-splitting preconditioner for non-Hermitian positive definite matrices, J. Comput. Math., 24 (2006), 539–552.
[17]	Z. Z. Bai, G. H. Golub and J. Y. Pan, Preconditioned Hermitian and skew-Hermitian splitting methods for non-Hermitian positive semidefinite linear systems. Technical Report SCCM-02-12, Scientific Computing and Computational Mathematics Program, Department of Computer Science, Stanford University, Stanford, CA, 2002.
[18]	Z. Z. Bai, M. Benzi and F. Chen, Modified HSS iteration methods for a class of complex symmetric linear systems, Comput., 87 (2010), 93–111.
[19]	Y. Cao, J. Du and Q. Niu, Shift-splitting preconditioners for saddle point problems, J. Comput. Appl. Math., 272 (2014), 239–250.
[20]	Y. Cao, L. Q. Yao and M. Q. Jiang, A modified dimensional split preconditioner for generalized saddle point problems, J. Comput. Appl. Math., 250 (2013), 70–82.
[21]	Y. Cao, L. Q. Yao, M. Q. Jiang and Q. Niu, A relaxed HSS preconditioner for saddle point problems from meshfree discretization, J. Comput. Math., 31 (2013), 398–421.
[22]	C. R. Chen and C. F. Ma, A generalized shift-splitting preconditioner for saddle point problems, Appl. Math. Lett., 43 (2015), 49–55.
[23]	F. Chen and Y. L. Jiang, A generalization of the inexact parameterized Uzawa methods for saddle point problems, Appl. Math. Comput., 206 (2008), 765–771.
[24]	L. B. Cui, C. Chen, W. Li and M.K. Ng, An eigenvalue problem for even order tensors with its applications, Linear Multilinear Algebra, 64 (2016), 602–621.
[25]	L. B. Cui, W. Li and M. K. Ng, Primitive tensors and directed hypergraphs, Linear Algebra Appl., 471 (2015), 96–108.
[26]	L. B. Cui, C. X. Li and S. L. Wu, The relaxation convergence of multisplitting AOR method for linear complementarity problem, Linear Multilinear Algebra, DOI: 10.1080/03081087.2018.1511680.
[27]	L. B. Cui and Y. S. Song, On the uniqueness of the positive Z-eigenvector for nonnegative tensors, J. Comput. Appl. Math., 352 (2019), 72C78.
[28]	M. T. Darvishi and P. Hessari, Symmetric SOR method for augmented systems, Appl. Math. Comput., 183 (2006), 409–415.
[29]	H. Elman and D. Silvester, Fast nonsymmetric iterations and preconditioning for Navier-Stokes equations, SIAM J. Sci. Comput., 17 (1996), 33–46.
[30]	H. Elman and G. H. Golub, Inexact and preconditioned Uzawa algorithms for saddle point problems, SIAM J. Numer. Anal., 31 (1994), 1645–1661.
[31]	B. Fischer, A. Ramage, D. J. Silvester and A. J.Wathen, Minimum residual methods for augmented systems, BIT, 38 (1998), 527–543.
[32]	G. H. Golub, X. Wu and J. Y. Yuan, SOR-like methods for augmented systems, BIT, 55 (2001), 71–85.
[33]	M. Q. Jiang and Y. Cao, On local Hermitian skew-Hermitian splitting iteration methods for generalized saddle point problems, J. Comput. Appl. Math., 231 (2009), 973–982.
[34]	X.Y. Li, L. Gao, Q. K. Pan, L. Wan and K. M. Chao, An e ective hybrid genetic algorithm and variable neighborhood search for integrated process planning and scheduling in a packaging machine workshop, IEEE Transactions on Systems, Man and Cybernetics: Systems, 2018, DOI 10.1109/TSMC.2018.2881686.
[35]	X. Y. Li, C. Lu, L. Gao, S. Q. Xiao and L.Wen, An E ective Multi-Objective Algorithm for Energy Efficient Scheduling in a Real-Life Welding Shop, IEEE T. Ind. Inform., 14 (2018), 5400–5409.
[36]	X. Y. Li and L. Gao, An E ective Hybrid Genetic Algorithm and Tabu Search for Flexible Job Shop Scheduling Problem, Int. J. Prod. Econ., 174 (2016), 93–110.
[37]	X. F. Peng and W. Li, On unsymmetric block overrelaxation-type methods for saddle point, Appl. Math. Comput., 203 (2008), 660–671.
[38]	C. H. Santos, B. P. B. Silva and J. Y. Yuan, Block SOR methods for rank deficient least squares problems, J. Comput. Appl. Math., 100 (1998), 1–9.
[39]	H. A. Van der Vorst, Iterative Krylov Methods for Large Linear Systems, Cambridge Monographs on Applied and Computational Mathematics, Cambridge University Press, Cambridge, UK, 2003.
[40]	L. Wang and Z. Z. Bai, Convergence conditions for splitting iteration methods for non-Hermitian linear systems, Linear Algebra Appl., 428 (2008), 453–468.
[41]	S. Wright, Stability of augmented system factorizations in interior-point methods, SIAM J. Matrix Anal. Appl., 18 (1997), 191–222.
[42]	S. L.Wu, T. Z. Huang and X. L. Zhao, A modified SSOR iterative method for augmented systems, J. Comput. Appl. Math., 228 (2009), 424–433.
[43]	D. M. Young, Iteratin Solution for Large Systems, Academic Press, New York, 1971.
[44]	J. Y. Yuan, Numerical methods for generalized least squares problems, J. Comput. Appl. Math., 66 (1996), 571–584.
[45]	J. Y. Yuan and A. N. Iusem, Preconditioned conjugate gradient method for generalized least squares problems, J. Comput. Appl. Math., 71 (1996), 287–297.
[46]	G. F. Zhang and Q. H. Lu, On generalized symmetric SOR method for augmented systems, J. Comput. Appl. Math., 1 (2008), 51–58.
[47]	L. T. Zhang, A new preconditioner for generalized saddle matrices with highly singular(1,1) blocks, Int. J. Comput. Math., 91 (2014), 2091–2101.
[48]	L. T. Zhang, T. Z. Huang, S. H. Cheng and Y. P. Wang, Convergence of a generalized MSSOR method for augmented systems, J. Comput. Appl. Math., 236 (2012), 1841–1850.
[49]	B. Zheng, Z. Z. Bai and X. Yang, On semi-convergence of parameterized Uzawa methods for singular saddle point problems, Linear Algebra Appl., 431 (2009), 808–817.
[50]	Y. Z. Zhou, W. C. Yi, L. Gao and X. Y. Li, Adaptive di erential evolution with sorting crossover rate for continuous optimization problems, IEEE T. Cybernetics, 47 (2017), 2742–2753.

This article has been cited by:

1.	Aidyn Kassymov, Berikbol T. Torebek, Lyapunov-type inequalities for a nonlinear fractional boundary value problem, 2021, 115, 1578-7303, 10.1007/s13398-020-00954-9
2.	Jie Wang, Shuqin Zhang, A Lyapunov-Type Inequality for Partial Differential Equation Involving the Mixed Caputo Derivative, 2020, 8, 2227-7390, 47, 10.3390/math8010047

Reader Comments

Your name:*

Email:*
© 2019 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)