The unloaded SWCNTs-based nanomaterials were made by Timesnano of Chengdu Organic Chemicals Co. Ltd., Chinese Academy of Sciences. The outer Diameter (OD) of the unloaded SWCNTs-based gas sensing nanomaterials is 1–3 nm, and the purity is all higher than 90 wt%. The length of nanomaterials is about 50 microns. Concentrated hydrochloric acid, concentrated sulfuric acid, concentrated nitric acid, isopropanol, and ammonia used in the preparation process were purchased from Chongqing Chuandong Chemical Co., Ltd. (China), and all were of analytical grade. Palladium chloride (PdCl₂) provided a source of palladium. Deionized water was also used.

The processes of preparation of SWCNTs-based nanomaterials are classified into three steps:

(1) Purification of the unloaded SWCNTs

Six hundred milligram of unloaded SWCNTs were added to 300 ml of concentrated hydrochloric acid and ultrasonically cleaned for 30 min. Five hundred milligram of deionized water was used to ultrasonically clean the mixture for another 30 min. The cleaned mixture was placed in a drying box and dried at 150°C for 10 h. Purified unloaded SWCNTs were obtained.

(2) Acidification of the purified SWCNTs

Four hundred milligram of purified unloaded SWCNTs were added to 50 ml of concentrated sulfuric acid and 20 ml of concentrated nitric acid, and heated and stirred at 80°C for 4 h. After the mixture was cooled down, it was diluted with 60 ml deionized water. The mixture was filtered through a microporous membrane with a pore diameter of 0.45 microns, and washed repeatedly with deionized water until pH = 7. After drying at 80°C for 12 h, acidified SWCNTs were obtained.

(3) Functionalization of the acidified SWCNTs

Two hundred milligram of SWCNT was dissolved in 50 ml of isopropanol and sonicated for 20 min to improve the dispersibility of SWCNTs. 10.31 mg of PdCl₂ was dissolved in 3 ml of ammonia water. PdCl₂ solution was added to the SWCNTs/isopropanol mixed solution drop by drop, and stirred at a high speed for 2 h. The obtained suspension was put in a drying box and dried at 80°C for 2 h. The obtained powder was put in a calciner at 600°C for 2 h. 3.07 wt% Pd-doped SWCNTs-based nanomaterials were synthesized successfully.

The microstructure of the nanomaterials was characterized by Scanning Electron Microscopy (SEM) (SU8020, HITACHI, Japan) and Transmission Electron Microscopy (TEM) (JEM-2000EX, JEOL, Japan).

Planar gas sensors are applied in this paper. The structure of planar gas sensors is shown in Figure 1. The planar gas sensor is mainly composed of a Pt heating electrode, a Si base layer, an Au gas sensing electrode, and a SWCNTS-based sensing film layer. The size of the testing area is 300 μm ×300 μm. The hardware structure of the gas sensor is fabricated by Zhengzhou Winsen Electronics Technology CO., Ltd by processes mainly including oxidation, photolithography, sputtering, stripping, deposition, and etching, which are presented in Figure 2.

The planar sensor array is shown in Figure 3. The n-type (110) crystal face double polished silicon wafer (thickness is about 300 μm, and conductivity is 0.001–0.1 S/m) is used. In this paper, three SWCNTs-based sensing nanomaterials are coated by the droplet guiding method. After fully grinding the appropriate number of SWCNTs-based nanomaterials, it was dissolved in absolute ethanol for 1 h to obtain the corresponding dispersion, which was then dried at 400°C to get ultrafine powder. The deionized water droplets were applied to the sensor unit testing area using a micro syringe, and the SWCNTs-based nanomaterial powder was carefully applied to the droplets. After drying for 8 h, the powder was closely attached to the testing area, and three SWCNTs-based planar gas sensors were fabricated successfully.

The experimental platform consists of air source, RSC2000-A automatic gas mixing system (Beijing JS Co.), and CGS-8 intelligent gas sensitivity analysis system (Beijing Elite Tech Co., China), which is presented in Figure 4. The detection of the electrical signals of the gas sensor is mainly realized by the classical resistor divider principle, and the test circuit is shown in Figure 5, where R_L is the adjustable load resistance and R_S is the resistance at both ends of the test electrode. R_H is the resistance of the heating electrode of the sensing unit. V_H and V_S is the heating voltage and test voltage, respectively. During the test, R_S will vary with the change of condition and can be calculated by the principle of voltage division.

The sensor response values defined here are as follows (Wang et al., 2010):

R_s = (R_gas−R_air)/R_air

Specific steps are as follows:

Experiments were all carried out at a temperature of 28°C and at 60% humidity.

Figure 6 shows the SEM and TEM images of the unloaded, the carboxylated, and the Pd-doped SWCNTs. From the SEM images, the three kinds of SWCNTs are all intertwined and woven into a mesh, and the morphology of the SWCNTs after functioning has not changed much. However, in Figures 6b,c, the carboxylated and the Pd-doped SWCNTs are shorter in length and more distributed compared to the unloaded SWCNTs in Figure 6a. In the TEM images, all three SWCNTs are curved and tubular, and the basic structure has not been functionally damaged.

After acidification treatment, SWCNTs were oxidized under the action of concentrated sulfuric acid and concentrated nitric acid. Oxygen atoms released by concentrated nitric acid attacked carbon nanotubes, especially the defects at the ends and on the tube walls. Because carbon atoms are not stable six-membered rings in SWCNTs and are in a metastable state, SWCNTs will break in places where the nanotube curvature is large. Thus, the length of nanotubes becomes shorter, and nanotubes gradually disperse.

The temperature characteristics, concentration characteristics (including linearity and detecting limitation), response and recovery time characteristics of the unloaded, the carboxylated, and the Pd-doped SWCNTs- based gas sensors were studied in the hydrogen atmosphere.

In Figure 7, the temperature characteristics of three SWCNTs-based gas sensors are illustrated among 150–400°C to 100 μL/L hdrogen. On the one hand, three different SWCNTs-based gas sensors present the same trend of temperature characteristics: curves climb at first with the increase of the temperature and decrease after reaching the optimal operating temperature. This might be because when heated to a certain temperature, the surface of SWCNTs nanomaterials is occupied by oxygen atoms released from the air, which increases the surface conductance of the materials and, thus, shows a decrease in resistance. On the other hand, after modifying SWCNTs-based nanomaterials with Pd nanoparticles, the optimal operating temperature dropped sharply by 125°C, and the peak response of Pd-doped SWCNTs-based gas sensor is 10.1 and 3.2 times higher than that of the unloaded and carboxylated SWCNTs-based gas sensors under the respective optimal operating temperature, respectively.

Concentration characteristics were tested in 0–500 μL/L hydrogen at 275°C, as shown in Figure 8. As the gas concentration rises, the growth rate of the response value of all three gas sensors slows down and gradually becomes saturated. However, 3.07 wt% Pd-doped SWCNT-based gas sensor has better gas sensing performance in an extreme high gas concentration atmosphere. When the concentration of hydrogen is 500 μL/L, the gas sensing response of Pd-doped SWCNTs-based gas sensor is about 33.79, which is almost 14 and 3.7 times higher than the gas sensing response of the unloaded and the carboxylated SWCNTs-based gas sensors, respectively.

In Figure 8, R_s is linearly related to the concentration in the respective low concentration ranges (1–30 μL/L), and the fitting function and corresponding R²(linearity) is shown in Table 1. Assuming that when hydrogen is 1 μL/L, the gas sensing response is not lower than 1, the corresponding gas sensor is able to reach the detecting limitation (International Standard IEC 60599: 2015, 2015; Tang et al., 2017). Results are shown in Table 1. SWCNTs-based gas sensors with or without functionalization all show perfect linearity, while only the Pd-doped SWCNTs-based gas sensor can meet the requirement of detecting limitation.

Figure 9 presents the response and recovery time characteristics of three gas sensors which were tested at 275°C to 50 μL/L hydrogen. The experiment was repeated three times: 50 μL/L hydrogen was injected at 50, 800, and 1,550 s, and was exhausted at 450, 1,200, and 1,950 s. It is obvious that both response and recovery time of Pd-doped SWCNTs-based gas sensor are shorter than the other two. The response time and recovery time of Pd-doped SWCNTs-based gas sensor are about 100 and 150 s. What's more, the gas sensing response value of the three gas sensors is slightly increased after the third time test, which might be because of the incomplete exhaust each time, resulting in the presence of more hydrogen than expected in the final gas chamber. The recovery process of gas sensing materials is a dynamic process of adsorption and desorption between the molecules of the test gas, hydrogen, and nanotubes. If the hydrogen molecules in the gas chamber are not exhausted cleanly, a small amount of hydrogen molecules will still be adsorbed with the active sites on the surface of the nanotube at high temperatures, shown as the hydrogen atoms, so that there will still be less electron exchange in the gas sensing material nanotubes.

Obviously, after decorating SWCNTs with Pd nanoparticles, the gas sensing performance to hydrogen was remarkably enhanced. This is attributed to the enhanced electrical property toward molecular hydrogen compared with the undecorated SWCNTs. The gas sensing reaction is the interactions between H₂, Pd, and the nanotubes. After heating, hydrogen molecules dissociate faster into atomic hydrogen on Pd surface, resulting in the dissolution of atomic hydrogen in Pd with high solubility, consequently decreasing the work function of Pd, that is shown in the formula (1). The lowering of the work function of Pd leads to faster and easier electron transfer from Pd to SWCNTs, reducing the number of hole-carries in the p-type nanotubes and the value of conductance.

When the Pd-doped SWCNTs-based gas sensor was in a low hydrogen atmosphere, the reason why it can reverse and auto recover is because of the oxygen in the air and on the surfaces, which is represented as the formulas (2) and (3) (Mandelis et al., 1993; Collins, 2000; Kong, 2000).

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.