The Rapid Detection Method of Lubricant Oxidation State Based on Artificial Olfactory System

6 - Artificial olfactory sense and recognition system

Due to the complexity of real environments, it is hard to detect toxic and harmful gases by sensors. To address such an issue, an artificial olfactory system is promoted, emulating the function of the human nose by means of gas sensors and an inference system. In this work, an artificial olfactory inference system based on memristive devices is developed to classify four gases (ethanol, methane, ethylene, and carbon monoxide) with 10 different concentrations. First, the spike trains converted from signals of the sensor array are inputted to a reservoir computing (RC) system based on volatile memristive devices, which extracts spatiotemporal features; then the features are processed by a classifier based on nonvolatile memristive devices; the output of the classifier indicates the classification result. Moreover, to reduce the device number and the power consumption, three strategies are applied to reduce the extracted features from the RC system. Eventually, the olfactory inference system successfully identifies the gases with a high accuracy of 95%.image

Advances and opportunities of hydrogel-based artificial olfactory colorimetric systems for food safety detection: A review

An artificial olfactory system with sensing, memory and self-protection capabilities

The failure of electronic equipment causes serious consequences and even catastrophic fires. Abnormal thermal signals are one of the main characteristics of the failure of electronic equipment. Thus, a new method for recognizing and predicting the thermally induced failure states of electronic equipment was proposed, based on an artificial olfactory system (AOS). The AOS recognizes the state of the volatile components released during the early stages of thermally induced failure and uses it to predict the state of health of the electronic equipment. Some typical electronic devices, such as microcomputer units, electronic rectifiers, transformers, and battery modules, were tested with the AOS to recognize the failures indicated by abnormal thermal accumulation. Compared with infrared thermal imagers and gas analyzers, the PEN3 electronic nose was utilized to monitor the status of the devices under different thermal failure scenarios. It was found that infrared thermal imaging was only able to monitor the local surface temperature, and the air temperature in the device chamber changed slowly with the surface temperature of the electronic modules. However, the AOS was able to detect the abnormal change in the whole chamber. Linear discriminant analysis (LDA) and principal component analysis (PCA) were then adopted to investigate the features of thermally induced failure for different thermal states. The results showed that the models obtained both from LDA and PCA were able to distinguish the different states of the electronic devices. Furthermore, a support vector machine model was built, based on the AOS data, to recognize and predict the thermally induced failure processes. All the failure states of the electronic devices caused by thermal simulations were recognized successfully and the prediction accuracy was above 95%. Hence, the experimental results of this research proved that using the AOS, it is feasible to predict the thermally induced failure states of electronic equipment, and the failure of electronic devices can be forecast in advance, before the obvious temperature rise and smoke release. Moreover, the method proposed in this research can also be applied to the prediction of, and warning about, electrical fires, indoor fires, and other thermally induced accidents.

ABSTRACTIn this paper, strawberry freshness forecasting performed using artificial olfactory system (AOS) was investigated. Human sensory evaluation (HSE), firmness, total soluble sugar (TSS), and reducing sugar content (RSC) of the samples were examined to provide physical/chemical references for the AOS system. AOS responses to strawberry samples were measured and measurement data were analyzed by principal component analysis (PCA) and stochastic resonance (SR). Experimental results indicated that the PCA method qualitatively discriminated strawberry samples in different freshness levels. The strawberry freshness forecasting model was established based on AOS. The forecasting model successfully discriminated strawberry samples with regression coefficients of R2 = 0.98159. Validating experiment results indicated that the developed model using AOS presented a predictive accuracy of 92%.

Artificial olfactory systems are receiving increasing attention because of their potential applications in humanoid robots, artificial noses, and the next generation of human-computer interactions. However, simulating the human olfactory system, which recognizes, remembers, and automatically takes protective measures against gases, remains a challenge. In this paper, a WO3-TiO2@Ag NPs (silver nanoparticle) gas sensor was prepared by the sol-gel method, and an Al/pectin:AgNP/ITO memristor was prepared by spin coating and vacuum evaporation. The gas sensor has been combined with the memristor to simulate physical damage to humans in a dangerous gas environment for a long time, and an artificial olfactory system is constructed by field-programmable gate array external control. The WO3-TiO2@Ag NPs gas sensor can sense and identify ethanol vapor through changes in resistance, and the signal transmitted to the pectin-based memristor can switch the resistance state of the memristor to store gas information. Furthermore, the activation of the memristor can also trigger rotation of the fan to purify the gas and reduce damage caused by excessive exposure to dangerous gases. This artificial olfactory system provides a promising strategy for the development of artificial intelligence and human-computer interaction systems.

An Artificial Olfactory System (AOS) for Detection of Highly Toxic Gases in Air Based on YCoO3

The olfactory system can generate unique sensory memories of various odorous molecules, guiding emotional and cognitive decisions. However, most existing electronic noses remain constrained to momentary concentration, failing to trigger specific memories for different smells. Here, we report an artificial olfactory memory system utilizing conductive metal-organic frameworks (Ce-HHTP) that integrates sensing and memory and exhibits short- and long-term memory responses to alcohols and aldehydes. Experiments and theoretical calculations show that distinct memories are derived from the specific combinations of Ce-HHTP with O atoms in different guest. An unmanned aircraft equipped with this system realized the sensory memories in established areas. Moreover, the fusion of portable detection boxes and wearable flexible electrodes demonstrated the immense potential in off-site pollution monitoring and health management. This work represents an artificial olfactory memory system with two specific sensory memories under simultaneous conditions, laying the foundation for bionic design with qualities of human olfactory memory.

The importance of engaging students in authentic inquiry tasks has been emphasized in recent discussions of science educational standards. Authentic inquiry tasks can provide students with legitimate views of the nature of scientific investigation and contemporary scientific practice. Computer-based laboratory environments are widely used in inquiry-based activities to enable students to experience the complexity of authentic experimentation. An artificial olfactory system was developed and used as an interactive computerized laboratory tool to support students’ inquiry into odor classification. Sixteen 12th grade students in Thailand participated in the study. The results showed that participating in experiments with the artificial olfactory system had a positive impact on the students’ scientific inquiry abilities and their perceptions of inquiry-based science.

To improve the accuracy of detecting soil total nitrogen (STN) content by an artificial olfactory system, this paper proposes a multi-feature optimization method for soil total nitrogen content based on an artificial olfactory system. Ten different metal–oxide semiconductor gas sensors were selected to form a sensor array to collect soil gas and generate response curves. Additionally, six features such as the response area, maximum value, average differential coefficient, standard deviation value, average value, and 15th-second transient value of each sensor response curve were extracted to construct an artificial olfactory feature space (10 × 6). Moreover, the relationship between feature space and soil total nitrogen content was used to establish backpropagation neural network (BPNN), extreme learning machine (ELM), and partial least squares regression (PLSR) models were used, and the coefficient of determination (R2), root mean square error (RMSE), and the ratio of performance to deviation (RPD) were selected as prediction performance indicators. The Monte Carlo cross-validation (MCCV) and K-means improved leave-one-out cross-validation (K-means LOOCV) were adopted to identify and remove abnormal samples in the feature space and establish the BPNN model, respectively. There were significant improvements before and after comparing the two rejection methods, among which the MCCV rejection method was superior, where values for R2, RMSE, and RPD were 0.75671, 0.33517, and 1.7938, respectively. After removing the abnormal samples, the soil samples were then subjected to feature-optimized dimensionality reduction using principal component analysis (PCA) and genetic algorithm-based optimization backpropagation neural network (GA-BP). The test results showed that after feature optimization the model indicators performed better than those of the unoptimized model, and the PLSR model with GA-BP for feature optimization had the best prediction effect, with an R2 value of 0.93848, RPD value of 3.5666, and RMSE value of 0.16857 in the test set. R2 and RPD values improved by 14.01% and 50.60%, respectively, compared with those before optimization, and RMSE value decreased by 45.16%, which effectively improved the accuracy of the artificial olfactory system in detecting soil total nitrogen content and could achieve more accurate quantitative prediction of soil total nitrogen content.

The detection of ultralow or nonvolatile target analytes remains a significant challenge for artificial olfactory systems even after decades of development, which severely limits their widespread application. To overcome this challenge, an artificial olfactory system based on a colorimetric hydrogel array is constructed for the first time as a universal representative. As an effective extension of conventional artificial olfactory systems that integrates the merits of its predecessors, the proposed system accurately mimics olfactory mucosa and specific odorant binding proteins using hydrogels endowed with specific colorimetric reagents for the detection of hypochlorite, chlorate, perchlorate, urea, and nitrate. Therefore, the proposed system is capable of detecting and discriminating between these five airborne improvised explosive microparticulates with a detection limit as low as 39.4 pg. Additionally, the system demonstrates good reusability over ten cycles, rapid response time of ≈0.2 s, and excellent discrimination properties, despite significant variation. This proof-of-concept study on colorimetric artificial olfactory systems yields a novel strategy for the direct and discriminative detection of nonvolatile airborne microparticulates.

Artificial olfactory systems (AOSs) that mimic biological olfactory systems are of great interest. However, most existing AOSs suffer from high energy consumption levels and latency issues due to data conversion and transmission. In this work, an energy‐ and area‐efficient AOS based on near‐sensor computing is proposed. The AOS efficiently integrates an array of sensing units (merged field effect transistor (FET)‐type gas sensors and amplifier circuits) and an AND‐type nonvolatile memory (NVM) array. The signals of the sensing units are directly connected to the NVM array and are computed in memory, and the meaningful linear combinations of signals are output as bit line currents. The AOS is designed to detect food spoilage by employing thin zinc oxide films as gas‐sensing materials, and it exhibits low detection limits for H2S and NH3 gases (0.01 ppm), which are high‐protein food spoilage markers. As a proof of concept, monitoring the entire spoilage process of chicken tenderloin is demonstrated. The system can continuously track freshness scores and food conditions throughout the spoilage process. The proposed AOS platform is applicable to various applications due to its ability to change the sensing temperature and programmable NVM cells.

Metal oxide semiconductor gas sensors have attracted particular attention due to their merits of high sensitivity and easy integration. However, their insufficient selectivity severely limited their applications, especially in identifying low-concentration gases in a complex environment. Herein, inspired by the human olfaction, an in situ colloidal assembly strategy is developed to directly synthesize ordered macroporous metal oxide monolayers on micro-electromechanical system (MEMS) chips. It enables wafer-scale fabrication of gas sensors with excellent device-to-device consistency, which is beneficial for the construction of a highly reliable artificial olfactory system. In order to exploit efficient sensor arrays, five different monolayer macroporous gas sensitive materials with high specific surface areas, diverse nanostructures, rich catalytically active sites, and diverse compositions are synthesized in situ on MEMS chips, which displayed tailored selectivity and sensing behaviors. The crucial cross-selectivity contributes to the complex gas identification. Based on principal component analysis and back propagation neural network algorithm, an advanced artificial olfactory system is constructed, which candistinguish four different common hazardous gases with accurate concentrations, including hydrogen sulfide, carbon monoxide, acetone, and toluene. The proposed MEMS-based artificial olfactory system holds great promise to develop an electronic nose for detection of toxic gases in a complex environment.

Bitumen is a very complex material with chemical composition and properties highly dependent on the crude oil source and refinery processes. Several analytical procedures were developed to understand the relationship between bitumen composition, microstructure and physical properties. Nevertheless, these techniques are expensive, time-consuming and involve significant drawbacks. Moreover, advanced research and industrial research have often different purposes and timing perspectives. Several bitumen operators require simpler and more suitable techniques for research and technology development, production and acceptance control and above all polymer modification. This necessity has led the authors to propose a new approach based on the artificial olfactory system (AOS), also known as electronic nose or e-nose. AOS is an instrument consisting of an array of partially selective sensors coupled to a suitable pattern-recognition system capable of recognising complex odours. The warm-up study highlighted the possibility of AOS to discriminate, already at room temperature without the need of sample pre-treatments, between bitumen produced with different origin crude oils and to verify the production stability in the same plant. Thus, these results indicate that the e-nose method may be used for quality assurance and quality control applications and for the fingerprinting of bitumen, showing a number of advantages over classical analytical instruments.