基于敲击振动检测苹果内部缺陷的研究

为了能快速检测并剔除有内部缺陷的苹果,利用敲击振动的方法研究了红富士和金冠苹果共振频率的变化规律,发现苹果的硬度系数和腐烂面积有很好的相关性,提出了一种无损检测苹果内部缺陷的方法。红富士和金冠苹果的硬度系数与腐烂面积的相关系数R2分别为0.998和0.878。以苹果的硬度系数为自变量,建立了Logistic回归方程,其中第5d红富士和金冠苹果的预测值与实际值一致对比例为76.0%和78.9%,OR(比数比)值分别为76.0和79.0,建立的方程基本能够检测出内部有缺陷的苹果。      

苹果糖度无损检测技术研究进展分析

无损检测技术作为一种新兴的检测技术,具有广阔的发展前景。基于此,本文调研了多种苹果糖度无损检测技术的原理及相关研究,旨在为未来相关技术的发展提供建议。     

基于高光谱成像技术的苹果表面缺陷无损检测

以\"红富士\"苹果为研究对象,提出基于高光谱成像技术结合图像分割技术的苹果表面缺陷的无损检测方法。采用高光谱图像采集系统(400 nm～1 000 nm)采集完好无损和表面有缺陷苹果的高光谱图像;对采集到的高光谱图像进行最小噪声分离变换,提取感兴趣区域的平均光谱反射率;采用图像分割技术提出苹果表面缺陷的无损检测方法。结果表明:采用最小噪声分离变换可有效地消除苹果高光谱图像中的噪声;在700 nm～800 nm以及900 nm～1 000 nm波段范围内完好无损和表面有缺陷的苹果的光谱反射率值具有明显的差异,同时选取特征波长717.98 nm处的光谱反射率值小于0.6以及982.59 nm处的光谱反射率值大于0.52作为区分苹果正常区域和表面缺陷区域的阈值条件,进一步利用阈值分割方法对80个完好无损苹果和40个表面有缺陷苹果的正确识别率分别为97.5%和95%。表明高光谱成像技术结合图像分割技术可实现苹果表面缺陷的无损检测。     

基于机器视觉的苹果缺陷快速检测方法研究

针对目前中国苹果分选大部分还是经由人工筛选的现状,提出一种基于机器视觉的苹果缺陷快速检测方法。采用亮度自动校正技术消除苹果表面亮度不均匀分布,根据缺陷候选区域的数量,完成对苹果的初步判断,并使用加权相关向量机进一步对有缺陷的苹果进行判断。通过试验对文中方法的有效性和准确性进行验证。试验结果表明,该检测方法对1 000个测试样本的识别准确率为99.1%,对各种缺陷的检测精度较高。     

关于开关柜内部绝缘缺陷的检测与研究

开关柜柜内有大量的元件,其对电路起到保护的作用,防止出现闪络等情况。然而一些开关柜因为技术上的不足,在功能和属性上并不符合使用的要求。绝缘缺陷是比较常见的一种,主要是由于技术原因导致,而且对电网造成极大的威胁。因此,对开关柜内部绝缘缺陷的检测十分有必要,必须通过此种方式发现并改良存在的绝缘缺陷问题。     

基于改进CNN的苹果缺陷检测方法研究

目的:解决现有苹果缺陷检测方法存在的精度低、效率差等问题。方法:基于水果图像采集系统,提出一种改进的卷积神经网络用于苹果表面缺陷检测;引入深度可分离卷积代换原网络标准卷积,提高特征提取速度;引入Leaky ReLU激活函数代替ReLU激活函数,提高计算效率和精度;引入全局平均池化替换全连接层,降低网络模型的计算量;并在每层卷积后加入批量归一化层,通过试验与常规方法进行对比分析,验证其优越性。结果:与常规方法相比,所提方法在苹果缺陷检测中具有较高的检测准确率和速度,且模型参数量少,准确率达99.60%,检测速度(每秒帧数)达526,模型参数量为389 072。结论:该苹果缺陷检测方法能有效降低模型参数和检测时间,具有较高的准确率和速度。     

苹果腐心病的透射光谱在线检测系统设计及试验

针对苹果内部缺陷在线检测的产业技术需求,研究基于透射光谱技术的苹果内部缺陷在线检测系统。研究设计了光源套件、专用光纤和果托式输送单元等关键部件,提升在线透射光谱质量、降低热损伤和机械损伤;解决了光电信号干扰问题,开发了专用检测软件,实现苹果内部品质信息的无损在线获取。比较分析了正常苹果与腐心病果的光谱响应差异,优化参数后设置在线检测速度3个/秒,触发控制光谱采集时间80 ms。在选择特征波长的基础上利用线性判别分析建立了苹果腐心病的在线判别模型,预测的总体识别率达90%以上。研究结果表明该系统可以实现苹果内部缺陷的快速、无损在线检测。     

基于Halcon的苹果品质视觉检测试验研究

基于视觉检测平台和Halcon开发环境进行苹果典型品质检测试验,采集图像并处理。提取感兴趣区域,找出包含苹果的区域,用动态阈值分割的方法提取苹果的轮廓,并计算轮廓面积,以该面积来评定苹果的大小。对苹果的腐烂这一典型缺陷进行试验,用阈值分割的方法完成图像分割,不同灰度值显示为不同的颜色,据此将缺陷部分显示出来。颜色特征的检测是依据RGB颜色模型,采用模板匹配的方法,选取好的区域创建匹配模板,进行参数设置,并根据标准颜色的R分量设定合适的阈值作为合格苹果的颜色。该试验完成了水果轮廓的提取及面积的计算,实现了苹果部分区域的缺陷检测以及苹果颜色的检测。采用Halcon和机器视觉的方法对苹果品质的大小、缺陷、颜色检测能取得较好的效果。     

基于改进粒子群算法的苹果表面缺陷检测

通过适应值函数建立了粒子早熟判断机制,自适应调节粒子权重和反余弦策略调整粒子加速因子优化粒子寻优,给出苹果表面缺陷检测流程。试验仿真显示该算法检测苹果表面缺陷的轮廓较为清晰,漏检率测试指标最大为4.5%小于其他算法的,完成漏检率所消耗的时间最少,为苹果质量检测提供了一种新的思路。     

苹果近红外光谱无损检测技术的研究进展

介绍了NIR(近红外)无损检测技术的基本原理和数据处理方法,综述了国内外应用NIR无损检测技术在苹果糖度、酸度等内部品质以及褐变和病害等内部缺陷方面的研究现状,展望了苹果NIR光谱无损检测技术研究方向和应用前景。     

基于决策树支持向量机的苹果表面缺陷识别

在基于机器视觉苹果缺陷识别过程中,因果梗/花萼与缺陷表皮颜色相似,极大地降低苹果表面缺陷识别准确率,提出一种基于决策树支持向量机(DT-SVM)的苹果表面缺陷识别方法。该方法首先采用单阈值法去除背景,其次在R通道中利用Otsu法和连通域标记法提取目标区域(果梗、花萼和缺陷)的颜色、纹理和形状特征,最后利用决策树支持向量机进行识别。以600幅富士苹果图像为例,使用该方法进行缺陷识别,结果表明该方法的平均准确率为97.7%。与1-V-1多分类支持向量机(1-V-1SVM)和AdaBoost分类算法相比,DT-SVM方法正确率高、耗时短。说明决策树支持向量机对苹果表面缺陷识别十分有效。     

Detection of internal cracks in Manchego cheese using the acoustic impulse-response technique and ultrasounds

Nowadays, due to the more global nature of markets, the commercialization of cheese relies on the high quality of the product. Internal defects such as cracks or flaws may affect quality. Two different nondestructive inspection techniques (ultrasonic and acoustic experiments) were used to detect cracks in Manchego cheese. The existence of small eyes in this type of cheese limited the use of ultrasonic pulse-echo experiments due to high scattering, and only cracks close to the surface of the cheese could be detected. The acoustic impulse-response technique, however, allowed us to study wheel pieces with cracks located elsewhere in the cheese. Two different impact probes (A and B) were assayed. The energy content of the acoustic spectrum was higher for cracked wheel pieces (7,116 and 17,520 V Hz^1/2 for probes A and B, respectively) than for normal ones (6,841 and 16,821 V Hz^1/2). The differences were mainly found for frequencies higher than 150 Hz, which made the centroid for cracked pieces higher (162 and 170 Hz for probes A and B, respectively) than that for normal cheeses (132 and 148 Hz for probes A and B, respectively). Discriminant functions were developed to classify wheel pieces, and the input variables used were the acoustic parameters from the spectrum and the principal components extracted from the whole spectrum. The best classification procedure used the principal components from the principal components analysis of the spectrum for probe B. In this case, the 50 wheel pieces used in this study were correctly classified. These results showed that a simple and low-cost acoustic impulse-response technique could be used to detect cheese cracks, formed at different moments of Manchego cheese maturation.     

Detection of coating waxes on apples by differential scanning calorimetry

In the European Union, beeswax, candelilla wax, carnauba wax and shellac are approved as coating agents for apple surfaces, provided that the coating is clearly stated. For detecting such coatings on apples, differential scanning calorimetry (DSC) was successfully applied. From the thermograms, the temperature at the peak maximum and the phase transition enthalpy were obtained as the main criteria. For the genuine surface wax of ten apple cultivars, the means were 64.4°C [standard deviation (SD), 1.5°C] for the maximum temperature and 82 J/g (SD, 9 J/g) for the enthalpy. The four coating agents resulted in divergent peak maxima and in enthalpies above 100 J/g in all cases. For beeswax, means of 68°C and 136-165 J/g were found, for candelilla wax 77°C and 116-161 J/g, for carnauba wax 89°C and 127-162 J/g and for shellac (two samples only) 76-89°C and 141-208 J/g. Studies with mixtures of the coating agents and apple wax and analyses of commercial apple samples marked as waxed confirm that DSC suits very well as a screening method for detecting an unstated treatment. In some cases it is even possible to characterize the coating agent used. First results indicate that paraffins, montanic acid esters and polyethylene wax oxides which are not approved for coating apples can be detected in the same way.     

New contact acoustic emission detector for texture evaluation of apples

A new contact acoustic emission detector (CAED) was developed for the instrumental texture evaluation of apples. The goal of this work was to determine the relations between instrumental parameters and sensory texture attributes, and to develop calibration models for prediction of the sensory texture of apples with CAED. Seven apple cultivars were used for the construction and validation of the models. CAED is particularly useful for evaluation of sensory crispness, crunchiness and hardness. There is also a significant correlation of acoustic emission counts with juiciness, mealiness and overall texture. Validation of the models indicates better prediction of these sensory attributes by total acoustic emission counts than prediction by puncture firmness in terms of variance explained, root-mean-square of a model prediction, and bias.     

Ultrasonic internal defect detection in cheese

Different ultrasonic signals and detection techniques were used and compared to detect internal foreign bodies present in semi-soft cheeses. The signals were a pulse or a chirp and the detection was carried out by using either correlation with a reference signal or a wavelet decomposition. The principle of the detection consisted in measuring the time of flight of the transmitted signals and of the echoes, the latter in the absence of foreign body should be the double of the former. The presence of a foreign object affected this pattern in several ways. In order to assess the method, a small plastic cylindrical object of 3 mm in diameter was introduced in one half of the cheese and was tested for detection, the second half being used as reference for the control cheese. The results showed that the two signals and the two detection methods were able to localise the transmitted signals and the echo from the opposite face of the cheese under all circumstances. For the foreign body detection, the correlation method gave superior results, in term of signal to noise ratio as well as in term of error rate, while the two signals gave similar results. The analysis of the mean and standard deviation of the signal to noise ratio of the object echo showed that some samples presented peak values close to those due to the noise. Nevertheless, the object was detected in 90% of the tests. There was no significant effect of temperature on the detection technique.     

Sensory quality and internal atmosphere of fresh-cut Golden Delicious apples

The sensory shelf‐life of Golden Delicious fresh‐cut apples, dipped in 10 g L^?1 ascorbic acid and 5 g L^?1 calcium chloride and packaged under different modified atmosphere conditions, was assessed throughout refrigerated storage. An initial atmosphere of 0 kPa O₂ and plastic packages of an O₂ permeability of 15 cm³ m^?2 bar^?1 day^?1 were very effective in preserving the initial colour and firmness of apple cubes during at least 3 weeks of storage. These conditions resulted in increased respiration coefficients, which curbed the product consumer acceptance beyond the second week of storage. However, reduced ethylene and CO₂ production limited the appearance of fermentative metabolites during this period.     

On-line estimation of eggshell strength based on acoustic impulse response analysis

This paper proposes a nondestructive method for on-line estimation of eggshell strength based on acoustic resonance analysis. The system employed digital signal processing (DSP, TMS320F2812) as core processor to collect and analyze the response signal of eggshell. Fast Fourier Transform (FFT) and Discrete Cosine Transform (DCT) were used to transform the time domain signal into frequency domain signal for next analysis. Synergy interval partial least square (si-PLS) combined with multiple stepwise regression was used to establish a linear calibration model for eggshell strength measurement. The performance of the optimal model using 11 frequency variables was achieved, with R (correlation coefficient) of 0.776 and RMSEP (root mean square error of prediction) of 3.010 in prediction set. Good consistence confirmed that the acoustic resonance system has significant potential in on-line estimation of the eggshell strength.Industrial relevanceWith processing and handling procedure continues increasing in egg production, the possibility of the presence of eggshell crack sharply increases. In such case, it is essential to measure the strength of eggshell, so as to maintain the balance between eggshell strength and the handling load in the processing of egg collection, sorting and transportation. This work proposes a nondestructive method for on-line estimation of eggshell strength based on acoustic resonance analysis, and builds a robust calibration model to improve the prediction ability. The research data presents a potential way for on-line and non-destructive measurement of eggshell strength in egg industry.     

Detection of early bruises in apples using hyperspectral data and thermal imaging

The early detection of bruises in apples was studied using a system that included hyperspectral cameras equipped with sensors working in the visible and near-infrared (400–1000 nm), short wavelength infrared (1000–2500 nm) and thermal imaging camera in mid-wavelength infrared (3500–5000 nm) ranges. The principal components analysis (PCA) and minimum noise fraction (MNF) analyses of the images that were captured in particular ranges made it possible to distinguish between areas with defects in the tissue and the sound ones. The fast Fourier analysis of the image sequences after pulse heating of the fruit surface provided additional information not only about the position of the area of damaged tissue but also about its depth. The comparison of the results obtained with supervised classification methods, including soft independent modelling of class analogy (SIMCA), linear discriminant analysis (LDA) and support vector machines (SVM) confirmed that broad spectrum range (400–5000 nm) of fruit surface imaging can improve the detection of early bruises with varying depths.     

光电技术在纱线疵点检测中的应用

介绍了纱线疵点的检测方法,讨论了测量系统的构成,给出了该系统硬件原理图,分析了系统工作原理.基于CCD的塑料薄膜缺陷检测系统在平行光的照射下,通过线阵CCD控制电路获得塑料薄膜缺陷信号,使用虚拟示波器DSO-2902对缺陷信号进行采集、传输,借助计算机进行分析处理,从而精准地检测出缺陷.该系统硬件线路简单可靠、性价比高,并配有与上位机通信的USB接口,能高速实时地将纱线疵点图像信息传送至上位PC计算机.     

气质联用和电子鼻对1-MCP不同处理时期苹果检测分析

运用顶空固相微萃取-气质联用和电子鼻2种技术,对贮后货架期间1-MCP低温不同处理时期苹果的挥发性物质进行检测分析。结果表明:苹果的挥发性物质主要是由酯类、醛类和醇类物质组成,对照组果实醇类和酯类物质相对含量要高于1-MCP处理组,而醛类物质相对含量小于1-MCP处理组;在1-MCP低温不同处理期间,1-MCP-1d处理酯类物质低于其他1-MCP处理组。电子鼻分析结果显示,在贮后货架20 d,LDA方法有效区分对照果实和1-MCP低温不同处理时期果实,而贮后货架0 d时除1-MCP-1d外,其他1-MCP低温不同处理时期组区分效果不理想,与气质联用分析结果相一致。结果还表明:随着贮后货架时间的延长,处理组间的差异越加明显,电子鼻区分效果也越好。因此,电子鼻对1-MCP低温不同处理时期苹果整体气味特征进行判别具有可行性。