基于知識(shí)引導(dǎo)的工業(yè)機(jī)器人泛化性視覺(jué)系統(tǒng)研究與實(shí)現(xiàn)
發(fā)布時(shí)間：2018-11-25 06:49
【摘要】：隨著現(xiàn)代科技的發(fā)展和自動(dòng)化生產(chǎn)程度的提高,工業(yè)機(jī)器人在工程領(lǐng)域已獲得了廣泛的應(yīng)用。在實(shí)際生產(chǎn)過(guò)程中,工業(yè)機(jī)器人所體現(xiàn)出來(lái)的高效性、高精度性和多功能性等特點(diǎn)是普通人力所不能比擬的。相信在不久的將來(lái),工業(yè)機(jī)器人必將替代普通人力成為工業(yè)發(fā)展的主要生產(chǎn)力。目前,工業(yè)機(jī)器人的發(fā)展在自主學(xué)習(xí)和記憶以及柔性加工等方面依然存在一定的缺陷。針對(duì)這些缺陷,本文通過(guò)在傳統(tǒng)算法的頂層引入知識(shí)工程,實(shí)現(xiàn)先驗(yàn)知識(shí)的共享、集成、推理和演繹,開(kāi)發(fā)了機(jī)器人視覺(jué)知識(shí)系統(tǒng)(子系統(tǒng)),以提高機(jī)器人的學(xué)習(xí)、思維記憶和環(huán)境感知功能:在此基礎(chǔ)上,進(jìn)一步研發(fā)了一套基于知識(shí)引導(dǎo)的工業(yè)機(jī)器人泛化性視覺(jué)系統(tǒng)(主系統(tǒng)),用于實(shí)現(xiàn)機(jī)器人對(duì)目標(biāo)對(duì)象的自動(dòng)識(shí)別和精準(zhǔn)定位。本文主要以缸體鑄件為實(shí)驗(yàn)對(duì)象,對(duì)兩套系統(tǒng)中涉及的相關(guān)理論和關(guān)鍵技術(shù)進(jìn)行了深入研究,并對(duì)該視覺(jué)系統(tǒng)的可靠性和泛化性進(jìn)行了驗(yàn)證。具體研究?jī)?nèi)容和研究結(jié)論總結(jié)如下:(1)基于人工神經(jīng)網(wǎng)絡(luò)具有非線(xiàn)性學(xué)習(xí)功能的特性,提出了一種可對(duì)機(jī)器人視覺(jué)知識(shí)系統(tǒng)中標(biāo)定知識(shí)自動(dòng)獲取的新標(biāo)定方法。通過(guò)定義手眼標(biāo)定模型中符號(hào)和邏輯表達(dá)(隱式知識(shí))的表示方法,可以實(shí)現(xiàn)手眼標(biāo)定模型中隱式知識(shí)向顯式知識(shí)的轉(zhuǎn)變。借助該標(biāo)定方法的使用,機(jī)器人視覺(jué)知識(shí)系統(tǒng)(子系統(tǒng))可通過(guò)學(xué)習(xí)機(jī)制獲取不同工作環(huán)境下的最佳標(biāo)定模型,用于指導(dǎo)工業(yè)機(jī)器人泛化性視覺(jué)系統(tǒng)(主系統(tǒng))的手眼標(biāo)定過(guò)程,實(shí)現(xiàn)機(jī)器人對(duì)目標(biāo)對(duì)象的精準(zhǔn)定位。(2)為了提高圖像分割算法在復(fù)雜工業(yè)圖像中分割的自適應(yīng)性和穩(wěn)定性,提出了基于圖像高層信息的改進(jìn)型變分水平集分割模型和基于先驗(yàn)知識(shí)的自適應(yīng)閾值分割模型。本文采用無(wú)參考圖像質(zhì)量評(píng)價(jià)分析方法,分析了不同工作環(huán)境下導(dǎo)致原始圖像質(zhì)量不穩(wěn)定的原因和影響圖像分割算法穩(wěn)定性的主要干擾因素。在此基礎(chǔ)上,提出了由圖像信息能量項(xiàng)、懲罰項(xiàng)和高斯金字塔項(xiàng)共同組成的改進(jìn)型變分水平集分割方法和基于峰值和灰度統(tǒng)計(jì)知識(shí)的自適應(yīng)閾值分割算法。兩種分割方法均能快速準(zhǔn)確地從復(fù)雜背景中分割出包含定位基準(zhǔn)的感興趣區(qū)域,且當(dāng)因環(huán)境光強(qiáng)改變?cè)斐晒ぜ上褓|(zhì)量發(fā)生變化時(shí),該分割方法仍然能夠準(zhǔn)確地分割出感興趣區(qū)域,兩種方法的分割耗時(shí)分別約為1.3s和0.8s。上述分割方法的應(yīng)用,可以進(jìn)一步提高工業(yè)機(jī)器人泛化性視覺(jué)系統(tǒng)(主系統(tǒng))的穩(wěn)定性和泛化性能。(3)本文提出了一種基于形狀知識(shí)的圖像語(yǔ)義識(shí)別方法。首先,針對(duì)工件形狀特征,構(gòu)建了具有平移、旋轉(zhuǎn)和縮放不變的內(nèi)、外部形狀特征圖像描述子的形狀描述數(shù)據(jù)庫(kù);其次,運(yùn)用數(shù)據(jù)挖掘技術(shù)中的粗糙集算法對(duì)數(shù)據(jù)庫(kù)中的數(shù)據(jù)進(jìn)行屬性約簡(jiǎn)和識(shí)別規(guī)則提取,以實(shí)現(xiàn)識(shí)別知識(shí)的自動(dòng)獲取,形成識(shí)別知識(shí)庫(kù);最后,將工件形狀的語(yǔ)義信息作為識(shí)別規(guī)則的前項(xiàng),將對(duì)應(yīng)的形狀描述子作為識(shí)別規(guī)則的結(jié)論,建立了工件形狀的語(yǔ)義信息和形狀特征圖像描述子之間的映射。通過(guò)使用該圖像語(yǔ)義識(shí)別方法,機(jī)器人視覺(jué)知識(shí)系統(tǒng)(子系統(tǒng))可根據(jù)工件形狀的語(yǔ)義信息,從識(shí)別知識(shí)庫(kù)中自動(dòng)獲取對(duì)應(yīng)的圖像描述,從而指導(dǎo)工業(yè)機(jī)器人泛化性視覺(jué)系統(tǒng)(主系統(tǒng))對(duì)目標(biāo)對(duì)象的自動(dòng)識(shí)別,運(yùn)用上述方法可對(duì)已建模形狀進(jìn)行識(shí)別,其識(shí)別率可達(dá)100%。(4)基于Java SSH軟件開(kāi)發(fā)平臺(tái),通過(guò)將建立的標(biāo)定知識(shí)庫(kù)、事實(shí)庫(kù)和形狀識(shí)別知識(shí)庫(kù)集成于MySQL數(shù)據(jù)庫(kù)管理系統(tǒng)中,開(kāi)發(fā)了基于Web的機(jī)器人視覺(jué)知識(shí)系統(tǒng)(子系統(tǒng)),以獲取不同工作環(huán)境下的最佳標(biāo)定模型和不同工件形狀語(yǔ)義信息對(duì)應(yīng)的識(shí)別知識(shí)信息,為工業(yè)機(jī)器人泛化性視覺(jué)系統(tǒng)(主系統(tǒng))服務(wù)。(5)設(shè)計(jì)了工業(yè)機(jī)器人泛化性視覺(jué)系統(tǒng)的總體框架結(jié)構(gòu)和各功能模塊�；赩S2012+QT5.3軟件開(kāi)發(fā)平臺(tái),研發(fā)了一套基于知識(shí)引導(dǎo)的工業(yè)機(jī)器人泛化性視覺(jué)系統(tǒng)(主系統(tǒng))。該主系統(tǒng)可以通過(guò)Socket通信方式與子系統(tǒng)進(jìn)行對(duì)接。當(dāng)用戶(hù)在瀏覽器上通過(guò)子系統(tǒng)向服務(wù)器發(fā)送檢測(cè)請(qǐng)求時(shí),主系統(tǒng)即可根據(jù)用戶(hù)權(quán)限獲取相關(guān)的標(biāo)定知識(shí)和識(shí)別知識(shí),從而引導(dǎo)機(jī)器人實(shí)現(xiàn)對(duì)目標(biāo)對(duì)象的自動(dòng)識(shí)別和精準(zhǔn)定位。本論文研究了基于知識(shí)引導(dǎo)的工業(yè)機(jī)器人泛化性視覺(jué)系統(tǒng)的關(guān)鍵技術(shù),對(duì)基于人工神經(jīng)網(wǎng)絡(luò)的機(jī)器學(xué)習(xí)標(biāo)定方法、復(fù)雜環(huán)境下的圖像自動(dòng)分割算法及基于形狀知識(shí)的圖像語(yǔ)義識(shí)別等方面進(jìn)行了研究,實(shí)現(xiàn)了工業(yè)機(jī)器人對(duì)目標(biāo)對(duì)象的自動(dòng)識(shí)別和精準(zhǔn)定位。該系統(tǒng)可有效提升工業(yè)生產(chǎn)線(xiàn)的柔性加工與連續(xù)作業(yè)的穩(wěn)定性,并可實(shí)現(xiàn)各類(lèi)知識(shí)的積累和共享,本文的研究成果可為今后工業(yè)機(jī)器人的智能化研究工作提供一定的理論依據(jù)。
[Abstract]:With the development of modern science and technology and the improvement of the degree of automatic production, the industrial robot has been widely used in the field of engineering. In the actual production process, the high efficiency, high precision and versatility embodied by the industrial robot are not comparable to the ordinary human resources. It is believed that in the near future, industrial robots will substitute for common human resources as the primary productivity of industrial development. At present, the development of industrial robot still has some defects in the aspects of autonomous learning and memory and flexible processing. In view of these defects, the paper introduces the knowledge engineering in the top layer of the traditional algorithm, realizes the sharing, integration, reasoning and deduction of the prior knowledge, and develops the robot vision knowledge system (sub-system) to improve the learning, thinking and environment-sensing functions of the robot: On this basis, a set of knowledge-guided industrial robot generalization vision system (main system) is further developed, which is used to realize the automatic recognition and accurate positioning of the target object by the robot. In this paper, the relevant theories and key technologies involved in the two systems are studied in detail, and the reliability and generalization of the visual system are verified. The specific research contents and conclusions are summarized as follows: (1) Based on the characteristic of the artificial neural network with the non-linear learning function, a new calibration method that can automatically acquire the calibration knowledge in the robot vision knowledge system is proposed. By defining the representation of the symbolic and logical expression (hidden knowledge) in the hand-eye calibration model, the transformation of the implicit knowledge to the explicit knowledge in the hand-eye calibration model can be realized. With the use of the calibration method, the robot vision knowledge system (subsystem) can acquire the optimal calibration model under different working environment through the learning mechanism, and is used for guiding the hand-eye calibration process of the industrial robot generalization vision system (main system), and the precise positioning of the target object is realized by the robot. (2) In order to improve the self-adaptability and stability of the segmentation of the image segmentation algorithm in the complex industrial image, an improved split-level set segmentation model based on high-level information of the image and a self-adaptive threshold segmentation model based on the prior knowledge are proposed. In this paper, a non-reference image quality evaluation and analysis method is used to analyze the causes of the instability of the original image quality under different working conditions and the main interference factors that affect the stability of the image segmentation algorithm. On this basis, an improved split-level set segmentation method, which is composed of image information energy terms, penalty terms and Gaussian pyramid terms, and an adaptive threshold segmentation algorithm based on peak and gray level statistical knowledge are proposed. in that method, the region of interest containing the positioning reference can be quickly and accurately segmented from the complex background, and when the image quality of the work piece is changed due to the change of the environment light intensity, the segmentation method can accurately segment the region of interest, The splitting time of the two methods is about 1. 3s and 0. 8s, respectively. The application of the segmentation method can further improve the stability and generalization performance of the industrial robot generalization vision system (main system). (3) An image semantic recognition method based on shape knowledge is presented in this paper. firstly, aiming at the shape characteristics of the workpiece, a shape description database of an inner and outer shape characteristic image description sub is constructed with a translation, rotation and scaling; secondly, the attribute reduction and the identification rule extraction are carried out on the data in the database by using the rough set algorithm in the data mining technology, so as to realize the automatic acquisition of the identification knowledge and form an identification knowledge base; and finally, the semantic information of the shape of the workpiece is taken as the preceding paragraph of the identification rule, and the corresponding shape description is taken as the conclusion of the identification rule, the mapping between the semantic information of the workpiece shape and the shape characteristic image description is established. by using the image semantic identification method, the robot vision knowledge system (sub-system) can automatically acquire the corresponding image description from the identification knowledge base according to the semantic information of the shape of the workpiece, so as to guide the automatic identification of the target object by an industrial robot generalization vision system (main system), and the method can identify the modeled shape, and the recognition rate can be up to 100 percent. (4) based on the Java SSH software development platform, a Web-based robot vision knowledge system (subsystem) is developed by integrating the established calibration knowledge base, fact base and shape identification knowledge base in the MySQL database management system, so as to obtain the identification knowledge information corresponding to the optimal calibration model and the different workpiece shape semantic information in different working environments, and serve the generalization visual system (main system) of the industrial robot. (5) The general frame structure and function modules of the generalized visual system of industrial robot are designed. Based on the software development platform of VSS2012 + QT5. 3, a set of knowledge-guided industrial robot generalization vision system (main system) is developed. The main system can interface with the sub-system in a socket communication mode. when a user sends a detection request to a server through a sub-system on a browser, the main system can acquire relevant calibration knowledge and identification knowledge according to the user authority so as to guide the robot to realize the automatic identification and accurate positioning of the target object. This paper studies the key technology of the generalization visual system of the industrial robot based on the knowledge guidance, and studies the machine learning and calibration method based on the artificial neural network, the image automatic segmentation algorithm in the complex environment and the image semantic recognition based on the shape knowledge. and realizes the automatic identification and precise positioning of the target object by the industrial robot. The system can effectively improve the stability of the flexible processing and continuous operation of the industrial production line, and can realize the accumulation and sharing of all kinds of knowledge. The research results in this paper can provide some theoretical basis for the intelligent research work of the industrial robot in the future.
【學(xué)位授予單位】：江蘇大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.41;TP242.2
[Abstract]:With the development of modern science and technology and the improvement of the degree of automatic production, the industrial robot has been widely used in the field of engineering. In the actual production process, the high efficiency, high precision and versatility embodied by the industrial robot are not comparable to the ordinary human resources. It is believed that in the near future, industrial robots will substitute for common human resources as the primary productivity of industrial development. At present, the development of industrial robot still has some defects in the aspects of autonomous learning and memory and flexible processing. In view of these defects, the paper introduces the knowledge engineering in the top layer of the traditional algorithm, realizes the sharing, integration, reasoning and deduction of the prior knowledge, and develops the robot vision knowledge system (sub-system) to improve the learning, thinking and environment-sensing functions of the robot: On this basis, a set of knowledge-guided industrial robot generalization vision system (main system) is further developed, which is used to realize the automatic recognition and accurate positioning of the target object by the robot. In this paper, the relevant theories and key technologies involved in the two systems are studied in detail, and the reliability and generalization of the visual system are verified. The specific research contents and conclusions are summarized as follows: (1) Based on the characteristic of the artificial neural network with the non-linear learning function, a new calibration method that can automatically acquire the calibration knowledge in the robot vision knowledge system is proposed. By defining the representation of the symbolic and logical expression (hidden knowledge) in the hand-eye calibration model, the transformation of the implicit knowledge to the explicit knowledge in the hand-eye calibration model can be realized. With the use of the calibration method, the robot vision knowledge system (subsystem) can acquire the optimal calibration model under different working environment through the learning mechanism, and is used for guiding the hand-eye calibration process of the industrial robot generalization vision system (main system), and the precise positioning of the target object is realized by the robot. (2) In order to improve the self-adaptability and stability of the segmentation of the image segmentation algorithm in the complex industrial image, an improved split-level set segmentation model based on high-level information of the image and a self-adaptive threshold segmentation model based on the prior knowledge are proposed. In this paper, a non-reference image quality evaluation and analysis method is used to analyze the causes of the instability of the original image quality under different working conditions and the main interference factors that affect the stability of the image segmentation algorithm. On this basis, an improved split-level set segmentation method, which is composed of image information energy terms, penalty terms and Gaussian pyramid terms, and an adaptive threshold segmentation algorithm based on peak and gray level statistical knowledge are proposed. in that method, the region of interest containing the positioning reference can be quickly and accurately segmented from the complex background, and when the image quality of the work piece is changed due to the change of the environment light intensity, the segmentation method can accurately segment the region of interest, The splitting time of the two methods is about 1. 3s and 0. 8s, respectively. The application of the segmentation method can further improve the stability and generalization performance of the industrial robot generalization vision system (main system). (3) An image semantic recognition method based on shape knowledge is presented in this paper. firstly, aiming at the shape characteristics of the workpiece, a shape description database of an inner and outer shape characteristic image description sub is constructed with a translation, rotation and scaling; secondly, the attribute reduction and the identification rule extraction are carried out on the data in the database by using the rough set algorithm in the data mining technology, so as to realize the automatic acquisition of the identification knowledge and form an identification knowledge base; and finally, the semantic information of the shape of the workpiece is taken as the preceding paragraph of the identification rule, and the corresponding shape description is taken as the conclusion of the identification rule, the mapping between the semantic information of the workpiece shape and the shape characteristic image description is established. by using the image semantic identification method, the robot vision knowledge system (sub-system) can automatically acquire the corresponding image description from the identification knowledge base according to the semantic information of the shape of the workpiece, so as to guide the automatic identification of the target object by an industrial robot generalization vision system (main system), and the method can identify the modeled shape, and the recognition rate can be up to 100 percent. (4) based on the Java SSH software development platform, a Web-based robot vision knowledge system (subsystem) is developed by integrating the established calibration knowledge base, fact base and shape identification knowledge base in the MySQL database management system, so as to obtain the identification knowledge information corresponding to the optimal calibration model and the different workpiece shape semantic information in different working environments, and serve the generalization visual system (main system) of the industrial robot. (5) The general frame structure and function modules of the generalized visual system of industrial robot are designed. Based on the software development platform of VSS2012 + QT5. 3, a set of knowledge-guided industrial robot generalization vision system (main system) is developed. The main system can interface with the sub-system in a socket communication mode. when a user sends a detection request to a server through a sub-system on a browser, the main system can acquire relevant calibration knowledge and identification knowledge according to the user authority so as to guide the robot to realize the automatic identification and accurate positioning of the target object. This paper studies the key technology of the generalization visual system of the industrial robot based on the knowledge guidance, and studies the machine learning and calibration method based on the artificial neural network, the image automatic segmentation algorithm in the complex environment and the image semantic recognition based on the shape knowledge. and realizes the automatic identification and precise positioning of the target object by the industrial robot. The system can effectively improve the stability of the flexible processing and continuous operation of the industrial production line, and can realize the accumulation and sharing of all kinds of knowledge. The research results in this paper can provide some theoretical basis for the intelligent research work of the industrial robot in the future.
【學(xué)位授予單位】：江蘇大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.41;TP242.2
【相似文獻(xiàn)】
相關(guān)期刊論文 前10條
1 Mary Aichlmayr;羅雁;;視覺(jué)系統(tǒng)提升產(chǎn)品質(zhì)量[J];飲料工業(yè);2008年05期
2 劉輝;王瑜輝;尹周平;熊有倫;;一種新型的飛行視覺(jué)系統(tǒng)設(shè)計(jì)[J];光學(xué)技術(shù);2007年02期
3 ;康耐視推出在線(xiàn)視覺(jué)系統(tǒng)評(píng)估工具[J];汽車(chē)工藝與材料;2009年03期
4 李俊嶺;李嵐;孫曉波;楊靜;;視覺(jué)系統(tǒng)在超聲打孔機(jī)中的應(yīng)用[J];電子工藝技術(shù);2009年02期
5 Sarah Sookman;陳廷炯;;智能視覺(jué)系統(tǒng):質(zhì)量控制盲點(diǎn)的終結(jié)者[J];軟件;2009年09期
6 壽天德;;視覺(jué)系統(tǒng)中反饋投射的功能作用(英文)[J];Neuroscience Bulletin;2010年05期
7 田娜;龐師軍;衛(wèi)曉沖;;視覺(jué)系統(tǒng)在硅片檢測(cè)上的應(yīng)用[J];電子工藝技術(shù);2010年05期
8 肖明怡;;激光視覺(jué)系統(tǒng)使汽車(chē)制造自動(dòng)化[J];激光與光電子學(xué)進(jìn)展;1985年04期
9 童永承;視覺(jué)系統(tǒng)電子技術(shù)的模擬探討[J];湖北師范學(xué)院學(xué)報(bào)(自然科學(xué)版);1987年01期
10 童永承;視覺(jué)系統(tǒng)的自控阻斷特性及模擬[J];湖北師范學(xué)院學(xué)報(bào)(自然科學(xué)版);1988年01期
相關(guān)會(huì)議論文 前10條
1 李文元;;昆蟲(chóng)復(fù)眼視覺(jué)系統(tǒng)的仿真研究[A];加入WTO和中國(guó)科技與可持續(xù)發(fā)展——挑戰(zhàn)與機(jī)遇、責(zé)任和對(duì)策（下冊(cè)）[C];2002年
2 陳勇軍;;動(dòng)態(tài)標(biāo)志在現(xiàn)代視覺(jué)系統(tǒng)中的運(yùn)用[A];節(jié)能環(huán)保 和諧發(fā)展——2007中國(guó)科協(xié)年會(huì)論文集（二）[C];2007年
3 王國(guó)建;陶霖密;葉喜勇;邸慧軍;;視覺(jué)系統(tǒng)分布式計(jì)算結(jié)構(gòu)模型的構(gòu)建與實(shí)現(xiàn)[A];第六屆和諧人機(jī)環(huán)境聯(lián)合學(xué)術(shù)會(huì)議（HHME2010)、第19屆全國(guó)多媒體學(xué)術(shù)會(huì)議（NCMT2010）、第6屆全國(guó)人機(jī)交互學(xué)術(shù)會(huì)議（CHCI2010）、第5屆全國(guó)普適計(jì)算學(xué)術(shù)會(huì)議（PCC2010）論文集[C];2010年
4 吳繁;潘煉;;工業(yè)機(jī)器人單目雙視的應(yīng)用研究[A];中國(guó)計(jì)量協(xié)會(huì)冶金分會(huì)2009年年會(huì)論文集[C];2009年
5 ;工業(yè)機(jī)器人[A];日本機(jī)械學(xué)會(huì)技術(shù)路線(xiàn)圖[C];2008年
6 羅t，
本文編號(hào)：2355161
本文鏈接：http://www.sikaile.net/kejilunwen/zidonghuakongzhilunwen/2355161.html
最近更新
教材專(zhuān)著
