張本華,錢長錢,焦晉康,丁兆赫,張 揚(yáng),崔紅光,劉翠紅,馮龍龍
·農(nóng)產(chǎn)品加工工程·
基于介電特性與SPA-SVR算法的水稻含水率檢測方法
張本華,錢長錢,焦晉康,丁兆赫,張 揚(yáng),崔紅光,劉翠紅,馮龍龍
(沈陽農(nóng)業(yè)大學(xué)工程學(xué)院,沈陽 110161)
為提高基于介電法水稻含水率的檢測精度,以北粳3號水稻為研究對象,利用阻抗分析儀及自制同軸圓柱型電容器測量了不同含水率水稻在1 kHz~1 MHz頻率下的相對介電常數(shù)及介質(zhì)損耗因數(shù)。采用共生距離法劃分了72個(gè)樣本校正集和48個(gè)樣本預(yù)測集。利用無信息變量消除法及連續(xù)投影法選取介電參數(shù)(、及和兩者結(jié)合)的特征變量,分別利用所提取的特征變量以及單頻、全頻下的介電參數(shù)來建立預(yù)測水稻含水率的多元線性回歸及支持向量機(jī)回歸模型,分析模型的預(yù)測性能,并對最佳模型的含水率預(yù)測結(jié)果進(jìn)行溫度補(bǔ)償。結(jié)果表明:基于與兩者結(jié)合并利用連續(xù)投影法提取特征變量建立的支持向量機(jī)回歸模型預(yù)測效果最佳,其預(yù)測集決定系數(shù)為0.980,預(yù)測均方根誤差為0.403%。最佳預(yù)測模型對不同品種水稻的含水率預(yù)測值與烘干法測得的含水率實(shí)測值的絕對誤差集中分布在±0.5%內(nèi),該研究可為糧食含水率的檢測提供參考。
含水率;水稻;介電特性;連續(xù)投影法;支持向量機(jī)回歸
水稻作為中國第一大糧食作物,其質(zhì)量的好壞直接影響著水稻的價(jià)格與消費(fèi)情況。而含水率作為影響水稻品質(zhì)的重要因素,對水稻的儲藏、運(yùn)輸、收購和加工有著極大的影響[1]。在中國,每年因水分檢測技術(shù)的不完善而導(dǎo)致糧食發(fā)霉變質(zhì)造成的產(chǎn)量損失高達(dá)107t,經(jīng)濟(jì)損失高達(dá)200億元[2]。因此,精準(zhǔn)檢測含水率,有利于提高水稻品質(zhì),減少損失。
目前,糧食含水率快速檢測方法主要包括電容法、電阻法、核磁共振法、微波法、紅外法、中子法等。其中核磁共振法[3]存在儀器昂貴,保養(yǎng)費(fèi)用高,需精確標(biāo)定等問題;微波法[4]、紅外法[5]、中子法[6]具有影響因素多等不足;電阻法[7]需將樣品粉碎,不適于無損檢測;電容法[8]具有分辨率高、價(jià)格便宜、動態(tài)響應(yīng)快等特點(diǎn)。從快速性和經(jīng)濟(jì)性考慮,電容法是檢測糧食含水率較為實(shí)用的方法。
電容法作為一種基于介電特性快速檢測糧食含水率的方法,因其影響因素較多,數(shù)據(jù)處理技術(shù)不完善,故測量精度不理想。如何提高電容式糧食水分檢測裝置精度成為目前創(chuàng)新和突破的難點(diǎn)。國內(nèi)外學(xué)者對電容式糧食水分傳感器結(jié)構(gòu)、影響因素、數(shù)據(jù)處理方法等方面進(jìn)行了相關(guān)研究。在電容器結(jié)構(gòu)方面,設(shè)計(jì)了電容傳感器的不同結(jié)構(gòu)并優(yōu)化了其結(jié)構(gòu)尺寸[9-16]。在影響因素方面,研究了電壓、頻率、溫度、容積密度等因素對介電參數(shù)的影響[17-22]。麥智煒等[23]設(shè)計(jì)了一種不受堆積密度影響的電容式糧食水分檢測裝置。在數(shù)據(jù)處理方法方面,考慮到溫度、容積密度等因素的影響,采用了多元回歸、神經(jīng)網(wǎng)絡(luò)、支持向量機(jī)等數(shù)學(xué)方法來建立糧食水分檢測模型[24-30]。
綜上所述,傳統(tǒng)的電容法多為用單一頻率下的單一電參數(shù)來預(yù)測糧食含水率,數(shù)學(xué)模型單一,影響因素較多,檢測精度不高。為此,本研究在優(yōu)化同軸圓柱型電容器極板結(jié)構(gòu)的基礎(chǔ)上,采用阻抗分析儀研究水稻含水率與介電參數(shù)間的關(guān)系,并分別在單頻、全頻及多個(gè)特征頻率下建立水稻含水率與介電參數(shù)間的多元回歸模型。分析模型的預(yù)測效果,確定檢測水稻含水率的最佳模型,并對預(yù)測結(jié)果進(jìn)行溫度補(bǔ)償。以期為基于介電特性糧食含水率的在線實(shí)時(shí)檢測提供參考。
試驗(yàn)水稻品種為北粳3號,選取完整無損且飽滿的水稻作為試驗(yàn)樣品。將試驗(yàn)樣品隨機(jī)分為120個(gè)樣本,每個(gè)樣本300 g水稻,裝于密封袋中保存在23 ℃的室溫環(huán)境下。
試驗(yàn)采用日置IM3570阻抗分析儀(日置電機(jī)株式會社)、101型電熱鼓風(fēng)干燥箱(北京市永光明醫(yī)療儀器有限公司)、JJ523BC型精密分析天平(上海銳析儀器)、RGX-400強(qiáng)光人工氣候箱(上海印溪儀器儀表有限公司)以及自制同軸圓柱型電容器。
為減小電容器極板的邊緣效應(yīng)對介電參數(shù)的影響,本研究采用自制同軸圓柱型電容器。結(jié)構(gòu)如圖1所示。同軸圓柱型電容器主要由內(nèi)外極板、保護(hù)極板、內(nèi)外同心圓筒、屏蔽極板等組成。內(nèi)、外圓筒材料為亞克力,直徑分別為80 mm、30 mm、筒長120 mm、厚為3 mm。內(nèi)極板采用80 mm寬的長方形銅箔粘貼在內(nèi)筒外壁;為利用有機(jī)玻璃的絕緣特性來減小電導(dǎo)等因素對介電特性的影響,外極板采用銅箔粘貼在外圓筒的整個(gè)外壁;內(nèi)極板的上下兩端對稱粘貼18 mm的銅箔作為保護(hù)電極,以減小端部效應(yīng)的影響。屏蔽電極安裝在外極板的外側(cè)來減小外加寄生電容及外界磁場的干擾?;捎瞄L方形有機(jī)玻璃板。內(nèi)外極板分別通過銅箔與阻抗分析儀的低電位、高電位輸出端相連;保護(hù)電極和屏蔽電極與阻抗分析儀的接地端相連。
1.保護(hù)極板 2.外極板 3.內(nèi)極板 4.保護(hù)極板
1.4.1 不同含水率樣品的制備
將水稻樣品置于105 ℃的干燥箱內(nèi)烘干24 h至質(zhì)量恒定,根據(jù)烘干前后的質(zhì)量差計(jì)算水稻濕基含水率,每份樣品測3次取平均值,測得水稻的初始含水率為11.04%。為配制不同含水率的樣品,取120份(每份300 g)水稻樣品,每份樣品添加不同質(zhì)量的去離子水,得到120組不同含水率的樣品(當(dāng)配制樣本的含水率大于16%時(shí),需多次少量邊攪拌邊添加。將配制的樣品裝入雙層密封袋中放置于5℃氣候箱中2~3 d,期間每天攪動4~5次,使樣品吸水均勻)。采用烘干法對120組水稻樣品采樣抽檢,所制備的水稻濕基含水率為11.04%~23.70%,平均值為17.39%。
1.4.2 介電參數(shù)測量方法
介電參數(shù)的測量系統(tǒng)主要由阻抗分析儀、自制同軸圓柱型電容器以及計(jì)算機(jī)等組成。測量前,將阻抗分析儀預(yù)熱30 min,并對探頭進(jìn)行短路、斷路校正以及50 Ω負(fù)載校準(zhǔn)。測量時(shí),首先激勵電壓設(shè)置為1 V,利用阻抗分析儀測量在1 kHz~1 MHz內(nèi)201個(gè)對數(shù)頻率下的空筒電容0,然后將水稻樣品以自由落體的方式倒入電容器的介質(zhì)空腔內(nèi),并用刮板刮平,測量樣品的電容(C)及介質(zhì)損耗角正切(tan)。每個(gè)水稻樣品測3次取平均值作為測量結(jié)果。由式(1)和式(2)計(jì)算出相對介電常數(shù)及介質(zhì)損耗因數(shù)。
1.5.1 數(shù)據(jù)處理方法
因在所選頻率范圍內(nèi)的(或)存在一定的相關(guān)性,某個(gè)頻率對應(yīng)的(或)可由其他頻率下的(或)共同表示,該頻率下的介電參數(shù)稱為冗余信息,冗余信息會增加模型的復(fù)雜度[31]。因此對原頻譜的信息進(jìn)行篩選十分重要。本研究采用連續(xù)投影法(successive projection algorithm,SPA)及無信息變量消除法(uninformative variables elimination,UVE)來選取特征變量。SPA是一種使矢量空間共線性最小化的前向變量選擇算法,能夠提取全頻率的幾個(gè)特征頻率,消除原始頻譜矩陣中冗余信息,解決變量間的共線性問題[32]。UVE是基于偏最小二乘回歸系數(shù)的算法,以消除無用信息。在選取變量時(shí),UVE綜合考慮了噪聲和目標(biāo)含水率的信息,比較直觀實(shí)用[33]。
1.5.2 建模方法
常用的建模方法主要有多元線性回歸、偏最小二乘回歸、主成分回歸、人工神經(jīng)網(wǎng)絡(luò)、支持向量機(jī)回歸等。考慮到多元線性回歸模型簡單,支持向量機(jī)回歸模型泛化能力強(qiáng)。因此,本研究分別采用多元線性回歸(multiple linear regression,MLR)和支持向量機(jī)回歸法(support vector regression,SVR)來建立水稻含水率的線性和非線性預(yù)測模型。比較分析其預(yù)測效果。以校正集的決定系數(shù)(R2)和校正均方根誤差(root mean square error of calibration,RMSEC)及預(yù)測集的決定系數(shù)(R2)和預(yù)測均方根誤差(root mean square error of predication,RMSEP)作為評價(jià)模型性能的指標(biāo)。R2和R2越接近1,RMSEC和RMSEP越小,模型精度越高。
頻率對不同含水率水稻及的影響曲線如圖2、圖3所示。
由圖2可知,在1 kHz~1 MHz頻段內(nèi),隨著頻率的增大而減??;這主要因當(dāng)電介質(zhì)處于外加交流電場時(shí),其表面會發(fā)生離子、原子、空間電荷及偶極子極化,當(dāng)頻率較高時(shí),偶極子極化滯后于電場的變化,導(dǎo)致隨頻率的增大而減小。頻率相同時(shí),水稻含水率越大,越大。主要由于含水率的增大導(dǎo)致水稻整體代謝加速,內(nèi)部離子的活動性增強(qiáng),因此′ 表現(xiàn)出增大的趨勢[34]。通過方差分析,頻率與含水率對水稻′影響均極顯著(<0.01)。
圖2 頻率對不同含水率水稻ε′的影響曲線
圖3 頻率對不同含水率水稻ε"的影響曲線
由圖3可知,在1 kHz~1 MHz頻段內(nèi),不同含水率水稻隨頻率變化規(guī)律不一致,原因是頻率范圍過窄。當(dāng)含水率不同時(shí),水稻內(nèi)部水分運(yùn)移情況不同,導(dǎo)致內(nèi)部水分分布不均勻,松弛時(shí)間不同,從而導(dǎo)致在不同頻率下出現(xiàn)波峰。當(dāng)頻率大于300 kHz時(shí),隨著頻率的增大而減小,隨含水率的增大而增大。主要由離子傳導(dǎo)導(dǎo)致,隨著頻率的升高,離子導(dǎo)電性增強(qiáng),變小。通過方差分析,頻率和含水率對水稻影響均極顯著(<0.01)。
為使校正集樣本更具有代表性,本研究采用距離法(sample set partitioning based on joint-distances,SPXY)來對120個(gè)不同含水率樣本進(jìn)行劃分。劃分比例3:2。SPXY算法以經(jīng)典Kennard- Stone算法為基礎(chǔ),綜合考慮介電參數(shù)和含水率的歐氏距離,從而完成樣本集的劃分[35]。劃分結(jié)果見表1。
表1 校正集和預(yù)測集含水率統(tǒng)計(jì)結(jié)果
由表1可以看出,本研究共劃分72個(gè)樣本作為校正集,48個(gè)樣本作為預(yù)測集。校正集與預(yù)測集樣本中含水率變化范圍較大,說明樣本集具有一定的代表性,滿足了建立校正集含水率預(yù)測模型的基本條件。
2.3.1 無信息變量消除法選取結(jié)果
首先,采用五折交叉驗(yàn)證法確定,以及兩者結(jié)合變量的UVE因子數(shù)分別為7、9、6。的UVE選取結(jié)果見圖4。
圖4 ε′的穩(wěn)定性分布曲線
豎線左右兩側(cè)分別為輸入變量及隨機(jī)變量的穩(wěn)定性曲線,、及和結(jié)合變量的穩(wěn)定性分布曲線分別包括201(201個(gè)頻率點(diǎn)下的)、201(201個(gè)頻率點(diǎn)下的)、402個(gè)輸入變量(201個(gè)頻率點(diǎn)下的和)和201、201、402個(gè)隨機(jī)變量。虛線為變量選擇的閾值,2條閾值線間的變量為無信息變量,選擇2條閾值線外的輸入變量作為特征變量。最終確定,及兩者結(jié)合變量的特征變量數(shù)及所選頻率點(diǎn)見表2。
2.3.2 連續(xù)投影法選取結(jié)果
為保證模型的可靠性,設(shè)置SPA的特征變量數(shù)范圍為2~20。以RMSEC值作為選取特征變量數(shù)的指標(biāo)。RMSEC隨SPA選取特征變量數(shù)的變化曲線如圖5所示。
圖5 RMSEC隨SPA選取變量數(shù)的變化曲線
由圖5可知,隨著選取變量數(shù)的增加,RMSEC逐漸減小,以RMSEC不再顯著減小時(shí)的變量數(shù)作為特征變量數(shù)。考慮到變量選取過多會導(dǎo)致模型的復(fù)雜度上升,最終確定、及兩者結(jié)合變量經(jīng)SPA選取的特征變量數(shù)分別為5、9和6個(gè);所對應(yīng)的校正均方根誤差分別為0.555%、1.172%、0.536%。各特征變量所對應(yīng)的頻率見表2。
表2 UVE 與SPA選取的特征變量
,經(jīng)SPA選取的特征變量所對應(yīng)的頻率中都包括1 MHz,且在1 MHz頻率下,不同含水率水稻的,′′有明顯差異,故選擇1 MHz作為單頻的特征頻率。
為提高模型的穩(wěn)定性及準(zhǔn)確性,本研究采用徑向基核函數(shù)來建立SVR模型,并以校正集樣本為對象,采用六折交叉驗(yàn)證法優(yōu)化SVR模型的懲罰因子()和松弛變量(),,優(yōu)化結(jié)果如表3所示。分別以全頻、單頻下的介電參數(shù)(,,和結(jié)合)以及經(jīng)SPA和UVE選取的特征變量作為因變量建立MLR、SVR模型。建模結(jié)果如表3所示。
表3 多元回歸模型預(yù)測結(jié)果及參數(shù)優(yōu)化匯總表
從選取變量角度來看,采用全頻變量建立的MLR模型R2達(dá)到1,RMSEC極小,而R2較R2顯著降低,主要原因是模型中存在過多的線性變量,導(dǎo)致MLR模型出現(xiàn)過擬合現(xiàn)象,從而導(dǎo)致模型泛化能力下降。對于SVR模型,建模時(shí)選取的變量數(shù)越多,模型的R2越高,RMSEP越小。采用全頻變量建立的SVR模型預(yù)測效果最佳,3種介電參數(shù)預(yù)測集R2分別達(dá)到0.982、0.974、0.983,說明SVR解決了全頻下MLR模型中出現(xiàn)的過擬合問題。雖采用全頻變量建立的SVR模型的R2最大,但考慮到全頻譜中包含大量冗余信息,增大模型運(yùn)算量,不宜采用。UVE和SPA均能有效提取原始變量中的有用信息,但SPA較UVE能更有效提取全頻譜中的特征變量,主要因SPA能剔除大量無用信息,解決變量間存在的共線性問題。3種介電參數(shù)(,,和結(jié)合)在單頻下建立的模型更簡單,較經(jīng)SPA提取特征變量建立的模型預(yù)測精度有所下降。從介電參數(shù)的角度來看,和均能預(yù)測水稻含水率,但采用和兩者結(jié)合建立的模型預(yù)測精度更高,預(yù)測效果優(yōu)于單一介電參數(shù),主要因兩者結(jié)合能夠進(jìn)行信息互補(bǔ),提高模型的預(yù)測性能。從建模方法來看,雖采用SVR建立的水稻含水率模型的預(yù)測準(zhǔn)確度優(yōu)于MLR,但MLR模型更簡單、具體且形象。從模型的預(yù)測效果及復(fù)雜度來看,采用和兩者結(jié)合并利用SPA選取變量建立的SVR模型預(yù)測效果最優(yōu),預(yù)測集R2達(dá)到0.980,RMSEP為0.403%。因此,最終選擇和相結(jié)合并基于SPA建立的SVR模型作為預(yù)測水稻含水率的最佳模型。預(yù)測集含水率的預(yù)測結(jié)果如圖6所示。
圖6 ε′和ε′′相結(jié)合的SPA-SVR模型含水率預(yù)測結(jié)果
考慮到溫度對介電參數(shù)有影響,需分析最佳模型下含水率預(yù)測值隨溫度的變化規(guī)律,并對模型的含水率預(yù)測結(jié)果進(jìn)行溫度補(bǔ)償。
試驗(yàn)溫度10 ℃~30 ℃,以5 ℃為梯度調(diào)節(jié)氣候箱溫度,測量5組水稻含水率樣品在5個(gè)不同溫度下的介電參數(shù),利用預(yù)測模型計(jì)算不同溫度下樣品的含水率,并與烘干法測得的含水率實(shí)測值進(jìn)行比較分析。不同溫度下水稻含水率預(yù)測值的變化規(guī)律如圖7所示。
圖7 不同溫度下含水率變化曲線
由圖7可知,溫度越高,模型的含水率預(yù)測值越大。在每個(gè)溫度梯度下,模型的含水率預(yù)測值與實(shí)測值呈線性關(guān)系,采用最小二乘法進(jìn)行線性回歸分析,并計(jì)算出線性回歸系數(shù)、。不同溫度下的回歸結(jié)果見表4。
表4 不同溫度下的回歸系數(shù)
表4中溫度每上升5℃,斜率的變化為0.057,0.049,0.050,0.044,平均值0.050;的變化為?0.522,?0.403,?0.369,?0.325,平均值?0.404。計(jì)算得回歸系數(shù)的平均變化率分別為Δ=0.050,Δ=?0.404。由Δ,Δ計(jì)算23 ℃下的、,得到水稻含水率預(yù)測值的溫度補(bǔ)償模型為
整理得
式中h為含水率預(yù)測值,%;h為溫度補(bǔ)償后的含水率值,%;為溫度,℃。
為探究最佳預(yù)測模型對不同品種水稻含水率的預(yù)測效果,分別以超產(chǎn)1號、臨稻、鐵粳15為對象,隨機(jī)配制158份不同含水率的樣品,含水率范圍9%~23%。在23 ℃下,測量介電參數(shù)并利用預(yù)測模型計(jì)算其含水率。圖8統(tǒng)計(jì)了樣本含水率的預(yù)測值與烘干法測得的實(shí)測值的絕對誤差水平,絕對誤差范圍為?1.14%~1.17%。最佳模型預(yù)測水稻含水率的絕對誤差集中分布在±0.5%內(nèi)。說明采用和相結(jié)合并利用SPA提取特征變量建立的SVR模型作為水分檢測模型時(shí),水稻含水率預(yù)測準(zhǔn)確度較高。
注:虛線為國家電容法水分測定儀二級準(zhǔn)確度標(biāo)準(zhǔn),取值為±0.5%。
1)通過探究含水率和頻率對水稻介電參數(shù)的影響發(fā)現(xiàn),在1 kHz~1 MHz頻率范圍內(nèi),相對介電常數(shù)隨頻率的增大而減小,隨含水率的增大而增大。當(dāng)頻率大于300 kHz時(shí),介質(zhì)損耗因數(shù)隨著頻率的增大而減小,隨含水率的增大而增大。頻率和含水率對相對介電常數(shù)和介質(zhì)損耗因數(shù)的影響均極顯著。
2)以120份不同含水率的水稻樣品為研究對象,通過對比不同介電參數(shù)在不同頻率下建立模型的預(yù)測效果發(fā)現(xiàn):相比于單一頻率下的單一介電參數(shù),利用多頻下相對介電常數(shù)和介質(zhì)損耗因數(shù)相結(jié)合的變量作為因變量建立的非線性模型的預(yù)測性能最優(yōu)。且當(dāng)采用不同處理方法來提取介電參數(shù)的特征變量時(shí),連續(xù)投影法較無信息變量消除法能更有效地篩選出特征變量,降低模型復(fù)雜度。通過對模型的預(yù)測性能進(jìn)行分析得出:采用相對介電常數(shù)和介質(zhì)損耗因數(shù)相結(jié)合并利用連續(xù)投影法提取特征變量建立的支持向量機(jī)回歸模型預(yù)測效果最佳,預(yù)測集的決定系數(shù)達(dá)到0.980,預(yù)測均方根誤差為0.403%。
3)采用最小二乘回歸法對模型在不同溫度下水稻含水率預(yù)測值進(jìn)行溫度修正,當(dāng)采用最佳模型來預(yù)測158份不同品種的水稻含水率時(shí),預(yù)測結(jié)果較準(zhǔn)確,同烘干法測得的實(shí)測含水率相比較,預(yù)測誤差集中分布在±0.5%內(nèi)。
[1] 趙博,毛文華,胡小安,等. 糧食收購品質(zhì)自動評定裝置設(shè)計(jì)與試驗(yàn)[J]. 農(nóng)業(yè)機(jī)械學(xué)報(bào),2010,41(S1):268-271,276.
Zhao Bo, Mao Wenhua, Hu Xiaoan, et al. Design and experiment of automatic quality grading equipment in grain purchase[J]. Transactions of the Chinese Society for Agricultural Machinery, 2010, 41(S1): 268-271, 276. (in Chinese with English abstract)
[2] 高利偉,許世衛(wèi),李哲敏,等. 中國主要糧食作物產(chǎn)后損失特征及減損潛力研究[J]. 農(nóng)業(yè)工程學(xué)報(bào),2016,32(23):1-11.
Gao Liwei, Xu Shiwei, Li Zhemin, et al. Main grain crop postharvest losses and its reducing potential in China[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2016, 32(23): 1-11. (in Chinese with English abstract)
[3] 宋平,彭宇飛,王桂紅,等. 玉米種子萌發(fā)過程內(nèi)部水分流動規(guī)律的低場核磁共振檢測[J]. 農(nóng)業(yè)工程學(xué)報(bào),2018,34(10):282-289.
Song Ping, Peng Yufei, Wang Guihong, et al. Detection of internal water flow in germinating corn seeds based on low field nuclear magnetic resonance[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2018, 34(10): 282-289. (in Chinese with English abstract)
[4] Kovaleva A A, Saitov R I, Zaporozhets A S, et al. Microwave moisture meter for cereal grains[J]. Measurement Techniques, 2017, 59(10): 1056-1060.
[5] 黃華,吳習(xí)宇,祝詩平. 近紅外光譜預(yù)測稻谷水分含量特征譜區(qū)選擇及其效率分析[J]. 光譜學(xué)與光譜分析,2018,38(4):1070-1075.
Huang Hua, Wu Xiyu, Zhu Shiping. Feature wavelength selection and efficiency analysis for paddy moisture content prediction by near infrared spectroscopy [J]. Spectroscopy and Spectral Analysis, 2018, 38(4):1070-1075.
[6] 楊悅乾,王劍平,王成芝. 谷物含水率中子法在線測量的可行性研究[J]. 農(nóng)業(yè)工程學(xué)報(bào),2000,16(5):99-101.
Yang Yueqian, Wang Jianping, Wang Chengzhi. Study on on-line measurement of grain moisture content by neutron gauge[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2000, 16(5): 99-101. (in Chinese with English abstract)
[7] 宋琦,盧澤民,孫衛(wèi)紅,等. 水稻電阻抗譜分析及檢測頻率范圍的確定[J]. 農(nóng)機(jī)化研究,2018,40(4):172-176.
Song Qi, Lu Zemin, Sun Weihong, et al. Electrical impedance spectroscopy analysis of rice and determination of detection frequency range[J]. Journal of Agricultural Mechanization Research, 2018, 40(4): 172-176. (in Chinese with English abstract)
[8] 趙麗清,尚書旗,高連興,等. 基于同心軸圓筒式電容傳感器的花生仁水分無損檢測技術(shù)[J]. 農(nóng)業(yè)工程學(xué)報(bào),2016,32(9):212-218.
Zhao Liqing, Shang Shuqi, Gao Lianxing, et al. Nondestructive measurement of moisture content of peanut kernels based on concentric cylindrical capacitance[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2016, 32(9): 212-218. (in Chinese with English abstract)
[9] 陳進(jìn),王月紅,練毅,等. 高頻電容式聯(lián)合收獲機(jī)谷物含水量在線監(jiān)測裝置研制[J]. 農(nóng)業(yè)工程學(xué)報(bào),2018,34(10):36-45.
Chen Jin, Wang Yuehong, Lian Yi, et al. Development of on-line monitoring device of grain moisture content in combine harvester with high frequency capacitance[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2018, 34(10): 36-45. (in Chinese with English abstract)
[10] 黃滔,趙春宇,朱成剛,等. 同面弧面電容式種子水分傳感器的研究[J]. 農(nóng)機(jī)化研究,2016,38(11):252-256.
Huang Tao, Zhao Chunyu, Zhu Chenggang, et al. Study on uniplanar cambered capacitive sensor of seed moisture content[J]. Journal of Agricultural Mechanization Research, 2016, 38(11): 252-256. (in Chinese with English abstract)
[11] 劉志壯,朱湘萍,張文昭,等. 介電法小麥含水率檢測試驗(yàn)研究[J]. 傳感技術(shù)學(xué)報(bào),2017,30(12):1857-1861.
Liu Zhizhuang, Zhu Xiangping, Zhang Wenzhao, et al. Wheat moisture content detection based on dielectric constant[J]. Chinese Journal of Sensors and Actuators, 2017, 30(12): 1857-1861. (in Chinese with English abstract)
[12] 劉志壯,呂貴勇. 基于電容法的稻谷含水率檢測[J]. 農(nóng)業(yè)機(jī)械學(xué)報(bào),2013,44(7):179-182.
Liu Zhizhuang, Lui Guiyong. Mositure content detection of paddy rice based on capacitande approach[J]. Transactions of the Chinese Society for Agricultural Machinery, 2013, 44(7): 179-182. (in Chinese with English abstract)
[13] 陳建國,李彥明,覃程錦,等. 小麥播種量電容法檢測系統(tǒng)設(shè)計(jì)與試驗(yàn)[J]. 農(nóng)業(yè)工程學(xué)報(bào),2018,34(18):51-58.
Chen Jianguo, Li Yanming, Qin Chengjin, et al. Design and test of capacitive detection system for wheat seeding quantity[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2018, 34(18): 51-58. (in Chinese with English abstract)
[14] 閆華,邢振,薛緒掌,等. 土壤剖面水分傳感器探頭仿真與試驗(yàn)[J]. 農(nóng)業(yè)機(jī)械學(xué)報(bào),2017,48(10):244-251.
Yan Hua, Xing Zhen, Xue Xuzhang, et al. Simulation and experiment on soil moisture profile sensor probe[J]. Transactions of the Chinese Society for Agricultural Machinery, 2017, 48(10): 244-251. (in Chinese with English abstract)
[15] 徐冬平,張鵬鵬,孫詩裕. 基于FDC1004的電容式谷物水分檢測儀的設(shè)計(jì)[J]. 農(nóng)機(jī)化研究,2016,38(8):173-178.
Xue Dongping, Zhang Pengpeng, Sun Shiyu. Design of a grain moisture detector based on dielectric character[J]. Journal of Agricultural Mechanization Research, 2016, 38(8): 173-178. (in Chinese with English abstract)
[16] 楊柳,毛志懷,董蘭蘭. 電容式谷物水分傳感器平面探頭的研制[J]. 農(nóng)業(yè)工程學(xué)報(bào),2010,26(2):185-189.
Yang Liu, Mao Zhihuai, Dong Lanlan. Development of plane polar probe of capacitive grain moisture sensor[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2010, 26(2): 185-189. (in Chinese with English abstract)
[17] 郭交,段凱文,郭文川. 基于微波自由空間測量的小麥含水率檢測方法[J]. 農(nóng)業(yè)機(jī)械學(xué)報(bào),2019,50(6):338-343,378.
Guo Jiao, Duan Kaiwen, Guo Wenchuan. Detection method of moisture content of wheat with microwave free-space measurement[J].Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(6):338-343, 378.
[18] Ling Bo, Guo Wenchuan, Hou Lixia, et al. Dielectric properties of pistachio kernels as influenced by frequency, temperature, moisture and salt content[J]. Food and Bioprocess Technology, 2015, 8(2): 420-430.
[19] Boreddy S R, Subbiah J. Temperature and moisture dependent dielectric properties of egg white powder[J]. Journal of Food Engineering, 2016, 168: 60-67.
[20] Ling Bo, Liu Xiaoli, Zhang Lihui, et al. Effects of temperature, moisture, and metal salt content on dielectric properties of rice bran associated with radio frequency heating[J]. Scientific Reports, 2018, 8(1): 1-12.
[21] Chinma C E, RamakrishnanY. Properties of cereal brans: A review[J]. Cereal Chem, 2015, 92(1): 1-7.
[22] Bo L, Lyng J G, Shaojin W. Radio-frequency treatment for stabilization of wheat germ: Dielectric properties and heating uniformity[J]. Innovative Food Science & Emerging Technologies, 2018, 48: 66-74.
[23] 麥智煒,李長友,徐鳳英,等. 浮地式糧食水分在線檢測裝置設(shè)計(jì)與試驗(yàn)[J]. 農(nóng)業(yè)機(jī)械學(xué)報(bào),2014,45(10):207-213.
Mai Zhiwei, Li Changyou, Xue Fengying, et al. Design and test of grain moisture online measuring system based on floating ground capacitance[J]. Transactions of the Chinese Society for Agricultural Machinery, 2014, 45(10): 207-213. (in Chinese with English abstract)
[24] 郭文川,劉馳,楊軍. 小麥秸稈含水率測量儀的設(shè)計(jì)與試驗(yàn)[J]. 農(nóng)業(yè)工程學(xué)報(bào),2013,29(1):33-40.
Guo Wenchuan, Liu Chi, Yang Jun. Design and experiment on wheat straw moisture content meter[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2013, 29(1): 33-40. (in Chinese with English abstract)
[25] 郭文川,趙志翔,楊沉陳. 基于介電特性的小雜糧含水率檢測儀設(shè)計(jì)與試驗(yàn)[J]. 農(nóng)業(yè)機(jī)械學(xué)報(bào),2013,44(5):188-193.
Guo Wenchuan, Zhao Zhixiang, Yang Chenchen. Moisture meter for coarse cereals based on dielectric property[J]. Transactions of the Chinese Society for Agricultural Machinery, 2013, 44(5): 188-193. (in Chinese with English abstract)
[26] 李靖軒,冷文秀. 基于圓筒形電容器的糧食含水率測定研究[J]. 物理與工程,2019,29(1):73-78.
Li Jingxuan, Leng Wenxiu. Study on determination of grain moisture content based on cylindrical capaitor[J]. Physics and Engineering, 2019, 29(1): 73-89. (in Chinese with English abstract)
[27] 鄂旭,翟寶峰,徐進(jìn),等. 一種新型食品安全存儲中的水分檢測方法[J]. 計(jì)算機(jī)技術(shù)與發(fā)展,2014,24(2):220-223.
E Xu, Zhai Baofeng, Xu Jin, et al. A new method of water-containing detection for food safety storage[J]. Computer Technology and Development, 2014, 24(2): 220-223. (in Chinese with English abstract)
[28] 張妤,謝永華,穆麗新,等. 基于支持向量機(jī)的電容式傳感器溫度補(bǔ)償研究[J]. 傳感器與微系統(tǒng),2009,28(6):40-42.
Zhang Yu, Xie Yonghua, Mu Lixin, et al. Study on temperature compensation for capacitance sensor based on support vector machine[J]. Transducer and Microsystem Technologies, 2009, 28(6): 40-42. (in Chinese with English abstract)
[29] Solar M, Solar A. Non-destructive determination of moisture content in hazelnut[J]. Computers and Electronics in Agriculture, 2016, 121(2): 320-330.
[30] 史晏澤. 糧食水分測量儀的設(shè)計(jì)與實(shí)現(xiàn)[D]. 長春:吉林大學(xué),2018.
Shi Yanze. Design and Implementation of Food Moisture Meter[D]. Changchun: Jilin University, 2018.
[31] 孫俊,莫云南,戴春霞,等. 基于介電特性與IRIV-GWO-SVR算法的番茄葉片含水率檢測[J]. 農(nóng)業(yè)工程學(xué)報(bào),2018,34(14):188-195.
Sun Jun, Mo Yunnan, Dai Chunxia, et al. Detection of moisture content of tomato leaves based on dielectric properties and IRIV-GWO-SVR algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2018, 34(14): 188-195. (in Chinese with English abstract)
[32] 王轉(zhuǎn)衛(wèi),趙春江,商亮,等. 基于介電頻譜技術(shù)的甜瓜品種無損檢測[J]. 農(nóng)業(yè)工程學(xué)報(bào),2017,33(9):290-295.
Wang Chuanwei, Zhao Chunjiang, Shang Liang, et al. Nondestructive testing of muskmelons varieties based on dielectric spectrum technology[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2017, 33(9): 290-295. (in Chinese with English abstract)
[33] 商亮,谷靜思,郭文川. 基于介電特性及ANN的油桃糖度無損檢測方法[J]. 農(nóng)業(yè)工程學(xué)報(bào),2013,29(17):257-264.
Shang Liang, Gu Jingsi, Guo Wenchuan. Non-destructively detecting sugar content of nectarines based on dielectric properties and ANN[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2013, 29(17): 257-264. (in Chinese with English abstract)
[34] 郭文川,王東陽,孔繁榮,等. 基于介電特性的豆?jié){固形物含量檢測[J]. 農(nóng)業(yè)機(jī)械學(xué)報(bào),2016,47(7):239-245.
Guo Wenchuan, Wang Dongyang, Kong Fanrong, et al. Solids content detection of soybean milk based on permittivities[J]. Transactions of the Chinese Society for Agricultural Machinery, 2016, 47(7): 239-245. (in Chinese with English abstract)
[35] Galvao R K H, Araujo M C U, Jose G E, et al. A method for calibration and validation subset partitioning[J]. Talanta, 2005, 67(4): 736-740.
Rice moisture content detection method based on dielectric properties and SPA-SVR algorithm
Zhang Benhua,Qian Changqian, Jiao Jinkang, Ding Zhaohe, Zhang Yang, Cui Hongguang, Liu Cuihong, Feng Longlong
(,,110161,)
Water content affects rice quality, which also has an important impact on rice storage, transportation, acquisition and processing. The annual loss of production caused by grain deterioration was up to 10 million tons, and the economic loss was up to 20 billion. Therefore, detecting rice moisture content accurately is beneficial to improve rice quality and reduce yield loss. A new method based on dielectric properties was proposed to detect the moisture content of rice in this study. Firstly, the dielectric properties (relative dielectric constant and dielectric loss factor) of 120 copies of rice of Japonica No.3 with different moisture contents were measured with impedance analyzer and self-made coaxial cylindrical capacitor at 201 discrete frequencies over the frequency range of 1 kHz-1 MHz, and the moisture contents of rice were measured by dry weight method. Secondly, sample set partitioning based on joint-distances (SPXY) was used to subset partitioning. Uninformative variables elimination (UVE) and successive projection algorithm (SPA) were applied to extract the characteristic variables of dielectric parameters ((the relative dielectric constant, dielectric loss factor and relative dielectric constant combined with dielectric loss factor). And the effect of SPA was compared with that of UVE to determine the optimal method for characteristic variable selection simultaneously. Finally, the support vector regression (SVR) machine and multiple linear regression (MLR) were adopted to establish the relationship models with two kinds of characteristic variables, single variables and full variables for predicting rice moisture content. And the performances of all the models were evaluated by the determination coefficient and root mean square error for calibration set and prediction set. The least square method was used for linear regression of predicted moisture content and measured moisture content at different temperatures, and the temperature compensation was carried out for the prediction results. The performances of the best model to predict different varieties of rice moisture content were explored to determine the applicability of the model. The research results showed that the relative dielectric constant decreased with the increase of the measurement frequency between 1kHz and 1MHz. When the frequency was greater than 300 kHz, the dielectric loss factor decreased with the increase of frequency and increased with the increase of water content. The measurement frequency and moisture content had an obvious effect on the dielectric properties of rice. Based on SPXY, 72 samples were partitioned to a calibration set and 48 samples to a prediction set. SPA was more effective than UVE in selecting useful information from the whole spectra of dielectric constant and dielectric loss factor. The model established by using the combination of relative dielectric constant and dielectric loss factor at multiple frequencies had better performance in predicting moisture content, which compared with the single dielectric parameter at a single frequency. Compared with MLR, SVR had better performance in predicting moisture content. The results showed that the support vector machine regression model based on the combination of relative dielectric constant and dielectric loss factorand SPA gave the highest correlation coefficient of predication set (0.980) and the lowest root mean square error of predication set (0.403%). When the best model was used to predict the water content of different varieties of rice, the prediction results were more accurate. Compared with the measured water content by the drying method, the prediction error was concentrated within ±0.5%. The study provided a reference for improving the accuracy of the grain moisture detection device.
water content; rice; dielectric properties; successive projection algorithm; support vector regression
張本華,錢長錢,焦晉康,丁兆赫,張 揚(yáng),崔紅光,劉翠紅,馮龍龍. 基于介電特性與SPA-SVR算法的水稻含水率檢測方法[J]. 農(nóng)業(yè)工程學(xué)報(bào),2019,35(18):237-244.doi:10.11975/j.issn.1002-6819.2019.18.029 http://www.tcsae.org
Zhang Benhua, Qian Changqian, Jiao Jinkang, Ding Zhaohe, Zhang Yang, Cui Hongguang, Liu Cuihong, Feng Longlong. Rice moisture content detection method based on dielectric properties and SPA-SVR algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2019, 35(18): 237-244. (in Chinese with English abstract) doi:10.11975/j.issn.1002-6819.2019.18.029 http://www.tcsae.org
2019-05-19
2019-08-25
國家重點(diǎn)研發(fā)計(jì)劃(2018YFD0300309-01)
張本華,教授,博士,主要從事農(nóng)業(yè)機(jī)械化方面研究。Email:zbh@syau.edu.cn
10.11975/j.issn.1002-6819.2019.18.029
S233.71
A
1002-6819(2019)-19-0237-08