CN116692397A - An automatic separation device and separation method for a cylinder head casting engineering pallet - Google Patents
An automatic separation device and separation method for a cylinder head casting engineering pallet Download PDFInfo
- Publication number
- CN116692397A CN116692397A CN202310712372.6A CN202310712372A CN116692397A CN 116692397 A CN116692397 A CN 116692397A CN 202310712372 A CN202310712372 A CN 202310712372A CN 116692397 A CN116692397 A CN 116692397A
- Authority
- CN
- China
- Prior art keywords
- tray
- workpiece
- data
- pallet
- workpiece tray
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G43/00—Control devices, e.g. for safety, warning or fault-correcting
- B65G43/08—Control devices operated by article or material being fed, conveyed or discharged
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G47/00—Article or material-handling devices associated with conveyors; Methods employing such devices
- B65G47/74—Feeding, transfer, or discharging devices of particular kinds or types
- B65G47/82—Rotary or reciprocating members for direct action on articles or materials, e.g. pushers, rakes, shovels
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G47/00—Article or material-handling devices associated with conveyors; Methods employing such devices
- B65G47/74—Feeding, transfer, or discharging devices of particular kinds or types
- B65G47/88—Separating or stopping elements, e.g. fingers
- B65G47/8807—Separating or stopping elements, e.g. fingers with one stop
- B65G47/8815—Reciprocating stop, moving up or down in the path of the article
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Numerical Control (AREA)
Abstract
本发明属于发动机缸盖铸造工程技术领域,公开了一种缸盖铸造工程托盘自动分离装置及分离方法。该方法包括:托盘定位器实时获取滑动或滚动硬接触在滑道上的工件托盘是否运动到设定的位置;当检测到工件托盘运动到设定的位置,通过气路调控器控制挡限位装置伸到工件托盘前侧,阻止工件托盘继续前行;气路调控器接收到托盘定位器反馈的工件托盘定位信息后,进一步调控循环作业的气路系统的气缸继续推送工件,输送到下道工序。本发明通过增加气缸提供推动力,工件托盘底部追加滑道,设置托盘定位、止挡限位装置,使工件滑动与托盘分离,从而消除分离中的重物搬起作业。其中利用了循环作业的气路系统,提升自动机构的安全性。
The invention belongs to the technical field of engine cylinder head casting engineering, and discloses an automatic separation device and a separation method for cylinder head casting engineering pallets. The method includes: the pallet positioner obtains in real time whether the workpiece pallet sliding or rolling hard-contacting on the slideway moves to a set position; Extend to the front of the workpiece pallet to prevent the workpiece pallet from moving forward; after the air circuit controller receives the positioning information of the workpiece pallet fed back by the pallet positioner, it further regulates the cylinder of the air circuit system of the cycle operation to continue to push the workpiece and transport it to the next process . In the present invention, the driving force is provided by adding an air cylinder, a slideway is added to the bottom of the workpiece pallet, and a pallet positioning, stop and limit device is provided, so that the workpiece slides and separates from the pallet, thereby eliminating the lifting operation of heavy objects during separation. Among them, the air circuit system of circulating operation is used to improve the safety of the automatic mechanism.
Description
技术领域technical field
本发明属于发动机缸盖铸造工程技术领域,尤其涉及一种缸盖铸造工程托盘自动分离装置及分离方法。The invention belongs to the technical field of engine cylinder head casting engineering, and in particular relates to an automatic separation device and method for cylinder head casting engineering pallets.
背景技术Background technique
发动机缸盖铸造工程中存在将铸件与托盘进行分离的工序,需要将工件搬起移走,返回托盘,重新进入浇注工程。现有技术的托盘分离过程一般包括:搬起、移动、放下、返回托盘。There is a process of separating the casting from the pallet in the casting process of the engine cylinder head. It is necessary to lift and remove the workpiece, return it to the pallet, and re-enter the pouring process. The tray separation process in the prior art generally includes: lifting, moving, putting down, and returning to the tray.
通过上述分析,现有技术存在的问题及缺陷为:现有方式需要将工件搬起,TNGA2.5L缸盖毛坯(含砂芯)重量约25公斤,存在超重作业,其他缸盖虽然较轻,频繁重物搬起,存在隐患。Through the above analysis, the problems and defects of the existing technology are: the existing method needs to lift the workpiece, the TNGA2.5L cylinder head blank (including sand core) weighs about 25 kg, and there is an overweight operation. Although other cylinder heads are lighter, Frequent lifting of heavy objects poses hidden dangers.
发明内容Contents of the invention
为克服相关技术中存在的问题,本发明公开实施例提供了一种缸盖铸造工程托盘自动分离装置及分离方法,具体涉及一种TNGA2.5L缸盖铸造工程托盘自动分离装置。In order to overcome the problems existing in the related technologies, the disclosed embodiments of the present invention provide an automatic separation device and separation method for cylinder head casting engineering pallets, in particular to a TNGA2.5L cylinder head casting engineering pallet automatic separation device.
所述技术方案如下:一种缸盖铸造工程托盘自动分离方法,包括以下步骤:The technical solution is as follows: a method for automatically separating cylinder head casting engineering pallets, comprising the following steps:
S1,托盘定位器实时获取滑动或滚动硬接触在滑道上的工件托盘是否运动到设定的位置;S1, the pallet positioner obtains in real time whether the workpiece pallet that slides or rolls in hard contact on the slideway moves to the set position;
S2,当托盘定位器检测到工件托盘运动到设定的位置,通过气路调控器控制挡限位装置伸到工件托盘前侧,阻止工件托盘继续前行;S2, when the pallet positioner detects that the workpiece pallet moves to the set position, the air path controller controls the stop limit device to extend to the front side of the workpiece pallet, preventing the workpiece pallet from continuing to move forward;
S3,气路调控器接收到托盘定位器反馈的工件托盘定位信息后,进一步调控循环作业的气路系统的气缸继续推送工件,输送到下道工序。S3. After receiving the workpiece pallet positioning information fed back by the pallet positioner, the air circuit controller further regulates the cylinders of the air circuit system for cyclic operation to continue to push the workpiece and transport it to the next process.
进一步,气路调控器接收到托盘定位器反馈的工件托盘定位信息进一步调控挡限位装置或气缸的方法包括:Further, the method for the air path regulator to receive the workpiece pallet positioning information fed back by the pallet positioner to further regulate the gear limit device or the cylinder includes:
步骤一,托盘定位器通过采集大量工件托盘的实时运行数据与下一步待运行数据并制作成神经网络的输入特征与标签,训练得到一个拟合工件托盘步态特征的网络模型;Step 1, the pallet positioner collects a large number of real-time running data of the workpiece pallet and the data to be run in the next step and makes it into the input features and labels of the neural network, and trains to obtain a network model that fits the gait characteristics of the workpiece pallet;
步骤二,利用所述拟合工件托盘步态特征的网络模型得到工件托盘的速度增量,再通过积分推导得到工件托盘的运动调整轨迹;Step 2, using the network model fitting the gait characteristics of the workpiece pallet to obtain the velocity increment of the workpiece pallet, and then deriving the motion adjustment trajectory of the workpiece pallet through integral derivation;
步骤三,将误差参数添加至神经网络框架并进行训练,预测运动变换及运动变换方差,并得到不同预测段的运动位置指标;Step 3, adding the error parameters to the neural network framework and performing training, predicting the motion transformation and the variance of the motion transformation, and obtaining the motion position indicators of different prediction segments;
步骤四,通过结合不确定性和气缸稳定运行调控方法,对神经网络进行运动位置校正,得到定位调整轨迹;Step 4: Correct the motion position of the neural network by combining the uncertainty and the stable operation control method of the cylinder to obtain the positioning adjustment trajectory;
步骤五,根据定位调整轨迹,气路调控器进一步调控挡限位装置或气缸的运动位置。Step 5, adjusting the trajectory according to the positioning, and the gas circuit controller further regulates the movement position of the gear limit device or the cylinder.
在步骤一中,构建并训练基于数据驱动的工件托盘运动状态检测模型,并利用训练好的基于数据驱动的工件托盘运动状态检测模型基于托盘定位器测量的数据确定相对位置和不确定性。In step one, a data-driven workpiece pallet motion state detection model is constructed and trained, and the trained data-driven workpiece pallet motion state detection model is used to determine the relative position and uncertainty based on the data measured by the pallet positioner.
进一步,所述构建并训练基于数据驱动的工件托盘运动状态检测模型包括:Further, the construction and training of a data-driven workpiece pallet motion state detection model includes:
(1)获取托盘定位器采集的相关数据,并基于获取的数据利用梯度方法计算得到姿态四元数,利用姿态四元数将加速度和角速度从托盘定位器坐标系转换到本地定位检测坐标系下;(1) Obtain the relevant data collected by the pallet locator, and use the gradient method to calculate the attitude quaternion based on the acquired data, and use the attitude quaternion to convert the acceleration and angular velocity from the pallet locator coordinate system to the local positioning detection coordinate system ;
(2)按照运动位置角、俯仰角和横滚角的顺序将四元数转变为欧拉角,取欧拉角与姿态角的运动位置角差值将运动调整轨迹从本地定位检测坐标系转换到全球坐标系;(2) Transform the quaternion into Euler angles in the order of motion position angle, pitch angle, and roll angle, and take the difference between the motion position angle of the Euler angle and the attitude angle to convert the motion adjustment trajectory from the local positioning detection coordinate system to the global coordinate system;
(3)构建基于数据驱动的工件托盘运动状态检测模型,利用标准数据集以及自采数据集作为训练集和测试集,对基于数据驱动的工件托盘运动状态检测模型进行训练,并于训练过程随机旋转基于数据驱动的工件托盘运动状态检测模型的每个窗口的特征与标签。(3) Build a data-driven workpiece pallet motion state detection model, use standard data sets and self-collected data sets as training sets and test sets, train the data-driven workpiece pallet motion state detection model, and randomly Rotate features and labels for each window based on the data-driven workpiece pallet motion detection model.
进一步,利用姿态四元数将加速度和角速度从托盘定位器坐标系转换到本地定位检测坐标系下包括:Further, using the attitude quaternion to convert the acceleration and angular velocity from the pallet positioner coordinate system to the local positioning detection coordinate system includes:
利用下式将托盘定位器坐标系下的向量aIMU转换为本地定位检测坐标系下的aINS:Use the following formula to convert the vector a IMU in the pallet positioner coordinate system to a INS in the local positioning detection coordinate system:
其中,表示四元数的共复轭。in, Represents the conjugate conjugate of a quaternion.
在步骤二中,将误差参数添加至基于数据驱动的工件托盘运动状态检测模型并进行训练,预测运动变换及其方差,并计算预测结果的不确定性;同时得到预测的运动位置指标。In the second step, the error parameters are added to the data-driven workpiece pallet motion state detection model and trained to predict the motion transformation and its variance, and calculate the uncertainty of the prediction results; at the same time, the predicted motion position index is obtained.
在步骤四中,构建数模融合定位模型通过扩展卡尔曼滤波紧密耦合音频测距观测量与基于数据驱动的工件托盘运动状态检测模型输出的高频速度矢量,得到定位结果。In step 4, the digital-analog fusion positioning model is constructed to obtain the positioning result by expanding the Kalman filter to tightly couple the audio distance measurement and the high-frequency velocity vector output by the data-driven workpiece pallet motion state detection model.
在步骤四中,所述不确定性包括:In step four, the uncertainties include:
σdata=mean(vi)σ data = mean(v i )
σtotal=σdata+σmodel σ total = σ data + σ model
其中,σtotal表示预测的总不确定性;σdata表示数据不确定性;σmodel表示模型不确定性;Among them, σtotal represents the total uncertainty of prediction; σdata represents data uncertainty; σmodel represents model uncertainty;
对神经网络进行运动位置校正包括:Motion position correction for neural networks involves:
首先,利用下式计算直行序列的校正角 First, use the following formula to calculate the correction angle of the straight line sequence
其中,表示生产场景的平均稳定性,ci表示生产场景信息与设备方向的关联量,用各直行序列平均运动位置角和平均神经网络PDR方向的差值代表;ca表示锚点,所述锚点为稳定的生产场景环境和低不确定性的直行序列上的关联量;in, Represents the average stability of the production scene, c i represents the correlation between the production scene information and the direction of the equipment, represented by the difference between the average motion position angle of each straight line sequence and the average neural network PDR direction; c a represents the anchor point, the anchor point It is the correlation quantity on the stable production scene environment and low-uncertainty straight-line sequence;
其次,将基于数据驱动的工件托盘运动状态检测模型预测得到的调整轨迹旋转进行调整轨迹的自适应校正。Secondly, the adjustment trajectory predicted based on the data-driven workpiece pallet motion state detection model is rotated Adaptive correction of the adjustment trajectory is performed.
本发明的另一目的在于提供一种缸盖铸造工程托盘自动分离装置,实施所述的缸盖铸造工程托盘自动分离方法,该装置包括:Another object of the present invention is to provide an automatic separation device for cylinder head casting engineering pallets to implement the automatic separation method for cylinder head casting engineering pallets. The device includes:
循环作业的气路系统,用于通过气缸推送工件托盘;The air circuit system for circulating operation is used to push the workpiece pallet through the cylinder;
工件托盘,用于盛放工件;The workpiece tray is used to hold the workpiece;
工件托盘的下部滑动或滚动硬接触有滑道;The lower part of the workpiece pallet slides or rolls in hard contact with a slideway;
滑道的末端一侧安装有用于检测工件托盘运动位置的托盘定位器;A pallet positioner for detecting the moving position of the workpiece pallet is installed on the end side of the slideway;
滑道的末端一侧还安装有用于限制工件托盘继续向前运动的止挡限位装置;A stop limit device for limiting the forward movement of the workpiece pallet is also installed on the end side of the slideway;
在托盘定位器检测工件托盘运动到设定的位置后,通过气路调控器控制挡限位装置伸到工件托盘前侧,阻止工件托盘继续前行;当工件推送到适宜位置,循环作业的气路系统通过气路调控器调控气缸回收,回到原点,进行下一工件的推送。After the pallet positioner detects that the workpiece pallet moves to the set position, the air circuit regulator controls the stop limit device to extend to the front of the workpiece pallet to prevent the workpiece pallet from moving forward; The air circuit system regulates the recovery of the cylinder through the air circuit controller, returns to the origin, and pushes the next workpiece.
进一步,挡限位装置的高度低于工件托盘的高度,挡限位装置采用隐藏式结构,在托盘定位器检测工件托盘运动到设定的位置后,通过气路调控器控制挡限位装置伸到工件托盘前侧,阻止工件托盘继续前行。Further, the height of the stop and limit device is lower than the height of the workpiece pallet, and the stop and limit device adopts a hidden structure. After the pallet positioner detects that the workpiece pallet moves to the set position, the extension of the stop and limit device is controlled by the air circuit regulator. Go to the front of the workpiece pallet and stop the workpiece pallet from moving forward.
结合上述的所有技术方案,本发明所具备的优点及积极效果为:通过增加气缸提供推动力,工件托盘底部追加滑道,设置托盘定位、止挡限位装置,使工件滑动与托盘分离,从而消除分离中的重物搬起作业。其中利用了循环作业的气路系统,提升自动机构的安全性。Combining all the above-mentioned technical solutions, the advantages and positive effects of the present invention are: by increasing the driving force provided by the cylinder, a slideway is added to the bottom of the workpiece pallet, and a pallet positioning, stop and limit device is set to separate the workpiece from the pallet, thereby Eliminate heavy lifting during separation. Among them, the air circuit system of circulating operation is used to improve the safety of the automatic mechanism.
附图说明Description of drawings
此处的附图被并入说明书中并构成本说明书的一部分,示出了符合本公开的实施例,并与说明书一起用于解释本公开的原理;The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description serve to explain the principles of the disclosure;
图1是本发明实施例提供的缸盖铸造工程托盘自动分离方法流程图;Fig. 1 is a flow chart of the automatic separation method for the cylinder head casting engineering pallet provided by the embodiment of the present invention;
图2是本发明实施例提供的气路调控器接收到托盘定位器反馈的工件托盘定位信息进一步调控挡限位装置或气缸的方法流程图;Fig. 2 is a flow chart of the method for further regulating the gear-limiting device or the cylinder by the gas path regulator receiving the workpiece pallet positioning information fed back by the pallet positioner provided by the embodiment of the present invention;
图3是本发明实施例提供的缸盖铸造工程托盘自动分离装置示意图;Fig. 3 is a schematic diagram of an automatic separation device for a cylinder head casting engineering pallet provided by an embodiment of the present invention;
图中:1、循环作业的气路系统;2、气缸;3、工件托盘;4、工件;5、滑道;6、托盘定位器;7、止挡限位装置;8、气路调控器。In the figure: 1. Pneumatic circuit system for cyclic operation; 2. Cylinder; 3. Workpiece pallet; 4. Workpiece; 5. Slideway; 6. Pallet positioner; .
具体实施方式Detailed ways
为使本发明的上述目的、特征和优点能够更加明显易懂,下面结合附图对本发明的具体实施方式做详细的说明。在下面的描述中阐述了很多具体细节以便于充分理解本发明。但是本发明能够以很多不同于在此描述的其他方式来实施,本领域技术人员可以在不违背本发明内涵的情况下做类似改进,因此本发明不受下面公开的具体实施的限制。In order to make the above objects, features and advantages of the present invention more comprehensible, specific implementations of the present invention will be described in detail below in conjunction with the accompanying drawings. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, the present invention can be implemented in many other ways different from those described here, and those skilled in the art can make similar improvements without departing from the connotation of the present invention, so the present invention is not limited by the specific implementation disclosed below.
实施例1,如图1所示,本发明实施例提供的缸盖铸造工程托盘自动分离方法包括:Embodiment 1, as shown in Figure 1, the method for automatically separating the cylinder head casting engineering pallet provided by the embodiment of the present invention includes:
S1,托盘定位器6实时获取滑动或滚动硬接触在滑道5上的工件托盘3是否运动到设定的位置;S1, the pallet positioner 6 obtains in real time whether the workpiece pallet 3 sliding or rolling hard-contacting on the slideway 5 moves to a set position;
S2,当检测到工件托盘3运动到设定的位置,通过气路调控器8控制挡限位装置7伸到工件托盘3前侧,阻止工件托盘3继续前行;S2, when it is detected that the workpiece pallet 3 moves to the set position, the stopper device 7 is controlled to extend to the front side of the workpiece pallet 3 through the air circuit regulator 8, preventing the workpiece pallet 3 from continuing to move forward;
S3,气路调控器8接收到托盘定位器6反馈的工件托盘3定位信息后,进一步调控循环作业的气路系统1的气缸2继续推送工件4,输送到下道工序。S3, after receiving the positioning information of the workpiece pallet 3 fed back by the pallet positioner 6, the gas circuit controller 8 further regulates the cylinder 2 of the gas circuit system 1 in the cycle operation to continue to push the workpiece 4 and transport it to the next process.
本发明利用气缸动作提供动力,通过推动滑移替代搬起作业实现托盘分离;利用双手作业回路,确保作业中的安全性。The invention utilizes the action of the cylinder to provide power, and realizes the pallet separation by pushing and sliding instead of lifting; and ensures the safety during the operation by using the two-hand operation circuit.
本发明通过设计新式样的托盘分离装置,达到了简化作业,减少了重物搬起作业,提高了工序作业性。The present invention simplifies the work by designing a new-style pallet separation device, reduces the work of lifting heavy objects, and improves the operability of the process.
如图2所示,在步骤S2-步骤S3中,气路调控器8接收到托盘定位器6反馈的工件托盘3定位信息进一步调控挡限位装置7或气缸2的方法包括:As shown in Fig. 2, in step S2-step S3, the method for further regulating the gear limit device 7 or the cylinder 2 by the gas path controller 8 receiving the positioning information of the workpiece pallet 3 fed back by the pallet positioner 6 includes:
S201,托盘定位器6通过采集大量工件托盘3的实时运行数据与下一步待运行数据并制作成神经网络的输入特征与标签,训练得到一个拟合工件托盘3步态特征的网络模型;S201, the pallet locator 6 acquires a large number of real-time running data of the workpiece pallet 3 and data to be run in the next step and makes them into input features and labels of the neural network, and trains to obtain a network model that fits the gait characteristics of the workpiece pallet 3;
S202,利用所述拟合工件托盘3步态特征的网络模型得到工件托盘3的速度增量,再通过积分推导得到工件托盘3的运动调整轨迹;S202, using the network model fitting the gait characteristics of the workpiece pallet 3 to obtain the velocity increment of the workpiece pallet 3, and then deriving the movement adjustment trajectory of the workpiece pallet 3 through integral derivation;
S203,将误差参数添加至神经网络框架并进行训练,预测运动变换及运动变换方差,并得到不同预测段的运动位置指标;S203, adding error parameters to the neural network framework and performing training, predicting motion transformation and motion transformation variance, and obtaining motion position indicators of different prediction segments;
S204,通过结合不确定性和气缸稳定运行调控方法,对神经网络进行运动位置校正,得到定位调整轨迹;S204, by combining the uncertainty and the stable operation control method of the cylinder, correcting the motion position of the neural network to obtain a positioning adjustment trajectory;
S205,根据定位调整轨迹,气路调控器8进一步调控挡限位装置7或气缸2的运动位置。S205, adjusting the track according to the positioning, the gas circuit controller 8 further regulates the movement position of the gear limit device 7 or the cylinder 2 .
在本发明实施例中,在步骤S201中,构建并训练基于数据驱动的工件托盘3运动状态检测模型,并利用训练好的基于数据驱动的工件托盘3运动状态检测模型基于托盘定位器6测量的数据确定相对位置和不确定性。In the embodiment of the present invention, in step S201, a data-driven workpiece pallet 3 motion state detection model is constructed and trained, and the data-driven workpiece pallet 3 motion state detection model based on the training is based on the data measured by the pallet positioner 6. Data determine relative position and uncertainty.
所述构建并训练基于数据驱动的工件托盘3运动状态检测模型包括:The construction and training based on the data-driven workpiece pallet 3 motion state detection model includes:
(1)获取托盘定位器6采集的相关数据,并基于获取的数据利用梯度方法计算得到姿态四元数,利用姿态四元数将加速度和角速度从托盘定位器6坐标系转换到本地定位检测坐标系下;(1) Obtain the relevant data collected by the pallet positioner 6, and calculate the attitude quaternion based on the acquired data using the gradient method, and use the attitude quaternion to convert the acceleration and angular velocity from the pallet positioner 6 coordinate system to the local positioning detection coordinates Department;
(2)按照运动位置角、俯仰角和横滚角的顺序将四元数转变为欧拉角,取欧拉角与姿态角的运动位置角差值将运动调整轨迹从本地定位检测坐标系转换到全球坐标系;(2) Transform the quaternion into Euler angles in the order of motion position angle, pitch angle, and roll angle, and take the difference between the motion position angle of the Euler angle and the attitude angle to convert the motion adjustment trajectory from the local positioning detection coordinate system to the global coordinate system;
(3)构建基于数据驱动的工件托盘3运动状态检测模型,利用标准数据集以及自采数据集作为训练集和测试集,对基于数据驱动的工件托盘3运动状态检测模型进行训练,并于训练过程随机旋转基于数据驱动的工件托盘3运动状态检测模型的每个窗口的特征与标签。(3) Build a data-driven workpiece pallet 3 motion state detection model, use standard data sets and self-collected data sets as training sets and test sets, train the data-driven workpiece pallet 3 motion state detection model, and train The process randomly rotates the features and labels of each window based on the data-driven workpiece pallet 3 motion state detection model.
利用姿态四元数将加速度和角速度从托盘定位器6坐标系转换到本地定位检测坐标系下包括:Using the attitude quaternion to convert the acceleration and angular velocity from the pallet positioner 6 coordinate system to the local positioning detection coordinate system includes:
利用下式将托盘定位器6坐标系下的向量aIMU转换为本地定位检测坐标系下的aINS:Use the following formula to transform the vector a IMU in the 6-coordinate system of the pallet positioner into a INS in the local positioning detection coordinate system:
其中,表示四元数的共复轭。in, Represents the conjugate conjugate of a quaternion.
在步骤S202中,将误差参数添加至基于数据驱动的工件托盘3运动状态检测模型并进行训练,预测运动变换及其方差,并计算预测结果的不确定性;同时得到预测的运动位置指标。In step S202, the error parameters are added to the data-driven workpiece pallet 3 motion state detection model and trained to predict the motion transformation and its variance, and calculate the uncertainty of the prediction result; at the same time, obtain the predicted motion position index.
在步骤S204中,构建数模融合定位模型通过扩展卡尔曼滤波紧密耦合音频测距观测量与基于数据驱动的工件托盘3运动状态检测模型输出的高频速度矢量,得到定位结果。In step S204, a digital-analog fusion positioning model is constructed to obtain a positioning result by tightly coupling the audio ranging observations with the extended Kalman filter and the high-frequency velocity vector output by the data-driven workpiece pallet 3 motion state detection model.
在步骤S204中,所述不确定性包括:In step S204, the uncertainty includes:
σdata=mean(vi)σ data = mean(v i )
σtotal=σdata+σmodel σ total = σ data + σ model
其中,σtotal表示预测的总不确定性;σdata表示数据不确定性;σmodel表示模型不确定性;Among them, σtotal represents the total uncertainty of prediction; σdata represents data uncertainty; σmodel represents model uncertainty;
对神经网络进行运动位置校正包括:Motion position correction for neural networks involves:
首先,利用下式计算直行序列的校正角 First, use the following formula to calculate the correction angle of the straight line sequence
其中,表示生产场景的平均稳定性,ci表示生产场景信息与设备方向的关联量,用各直行序列平均运动位置角和平均神经网络PDR方向的差值代表;ca表示锚点,所述锚点为稳定的生产场景环境和低不确定性的直行序列上的关联量;in, Represents the average stability of the production scene, c i represents the correlation between the production scene information and the direction of the equipment, represented by the difference between the average motion position angle of each straight line sequence and the average neural network PDR direction; c a represents the anchor point, the anchor point It is the correlation quantity on the stable production scene environment and low-uncertainty straight-line sequence;
其次,将基于数据驱动的工件托盘3运动状态检测模型预测得到的调整轨迹旋转进行调整轨迹的自适应校正。Secondly, the adjustment trajectory predicted based on the data-driven workpiece pallet 3 motion state detection model is rotated Adaptive correction of the adjustment trajectory is performed.
实施例2,图3是本发明实施例提供的缸盖铸造工程托盘自动分离装置包括:Embodiment 2, Fig. 3 is the cylinder head casting engineering tray automatic separation device provided by the embodiment of the present invention, including:
循环作业的气路系统1,用于通过气缸2推送工件托盘3;The air circuit system 1 for circulating operation is used to push the workpiece pallet 3 through the cylinder 2;
工件托盘3,用于盛放工件4;The workpiece tray 3 is used to hold the workpiece 4;
工件托盘3的下部滑动或滚动硬接触有滑道5;The lower part of the workpiece pallet 3 slides or rolls in hard contact with a slideway 5;
滑道5的末端一侧安装有用于检测工件托盘3运动位置的托盘定位器6;A pallet positioner 6 for detecting the movement position of the workpiece pallet 3 is installed on one side of the end of the slideway 5;
滑道5的末端一侧还安装有用于限制工件托盘3继续向前运动的止挡限位装置7;A stop limit device 7 for limiting the workpiece pallet 3 to move forward is also installed on the end side of the slideway 5;
当托盘定位器6检测工件托盘3运动到设定的位置后,通过止挡限位装置7阻挡工件托盘3继续前行,利用气缸2将工件4从工件托盘3上推出,送入滑道5进入下道工序;挡限位装置7的高度低于工件托盘3的高度,避免阻碍工件4从工件托盘3上分离;挡限位装置7采用隐藏式结构,在托盘定位器6检测工件托盘3运动到设定的位置后,通过气路调控器8控制挡限位装置7伸到工件托盘3前侧,阻止工件托盘3继续前行;当工件4推送到适宜位置,循环作业的气路系统1通过气路调控器8调控气缸2回收,回到原点,进行下一工件4的推送。如此往复运行,解决现有技术人工托盘分离过程存在的问题,节约了劳动力以及实现了安全生产。When the pallet positioner 6 detects that the workpiece pallet 3 moves to the set position, the stopper device 7 stops the workpiece pallet 3 from moving forward, and the workpiece 4 is pushed out from the workpiece pallet 3 by the cylinder 2 and sent into the slideway 5 Enter the next process; the height of the stop limit device 7 is lower than the height of the workpiece pallet 3, so as to avoid hindering the separation of the workpiece 4 from the workpiece pallet 3; the stop limit device 7 adopts a hidden structure, and the workpiece pallet 3 is detected by the pallet positioner 6 After moving to the set position, the stop limit device 7 is controlled by the air circuit regulator 8 to extend to the front side of the workpiece pallet 3 to prevent the workpiece pallet 3 from moving forward; 1. Regulate the recovery of the cylinder 2 through the air circuit regulator 8, return to the original point, and push the next workpiece 4. Such reciprocating operation solves the problems existing in the manual tray separation process in the prior art, saves labor and realizes safe production.
在上述实施例中,对各个实施例的描述都各有侧重,某个实施例中没有详述或记载的部分,可以参见其它实施例的相关描述。In the above-mentioned embodiments, the descriptions of each embodiment have their own emphases, and for parts that are not detailed or recorded in a certain embodiment, refer to the relevant descriptions of other embodiments.
上述装置/单元之间的信息交互、执行过程等内容,由于与本发明方法实施例基于同一构思,其具体功能及带来的技术效果,具体可参见方法实施例部分,此处不再赘述。The information interaction and execution process between the above-mentioned devices/units are based on the same idea as the method embodiment of the present invention, and its specific functions and technical effects can be found in the method embodiment section, and will not be repeated here.
所属领域的技术人员可以清楚地了解到,为了描述的方便和简洁,仅以上述各功能单元、模块的划分进行举例说明,实际应用中,可以根据需要而将上述功能分配由不同的功能单元、模块完成,即将所述装置的内部结构划分成不同的功能单元或模块,以完成以上描述的全部或者部分功能。实施例中的各功能单元、模块可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中,上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。另外,各功能单元、模块的具体名称也只是为了便于相互区分,并不用于限制本发明的保护范围。上述系统中单元、模块的具体工作过程,可以参考前述方法实施例中的对应过程。Those skilled in the art can clearly understand that for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used for illustration. In practical applications, the above-mentioned functions can be assigned to different functional units, Completion of modules means that the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated into one processing unit, or each unit may exist separately physically, or two or more units may be integrated into one unit, and the above-mentioned integrated units may adopt hardware It can also be implemented in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the present invention. For the specific working process of the units and modules in the above system, reference may be made to the corresponding process in the foregoing method embodiments.
基于上述本发明实施例记载的技术方案,进一步的可提出以下应用例。Based on the technical solutions described in the above-mentioned embodiments of the present invention, the following application examples can be further proposed.
根据本申请的实施例,本发明还提供了一种计算机设备,该计算机设备包括:至少一个处理器、存储器以及存储在所述存储器中并可在所述至少一个处理器上运行的计算机程序,所述处理器执行所述计算机程序时实现上述任意各个方法实施例中的步骤。According to an embodiment of the present application, the present invention also provides a computer device, which includes: at least one processor, a memory, and a computer program stored in the memory and operable on the at least one processor, When the processor executes the computer program, the steps in any of the foregoing method embodiments are implemented.
本发明实施例还提供了一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,所述计算机程序被处理器执行时可实现上述各个方法实施例中的步骤。An embodiment of the present invention also provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps in the foregoing method embodiments can be implemented.
本发明实施例还提供了一种信息数据处理终端,所述信息数据处理终端用于实现于电子装置上执行时,提供设备输入接口以实施如上述各方法实施例中的步骤,所述信息数据处理终端不限于手机、电脑、交换机。The embodiment of the present invention also provides an information data processing terminal. When the information data processing terminal is implemented on an electronic device, it provides a device input interface to implement the steps in the above-mentioned method embodiments. The information data Processing terminals are not limited to mobile phones, computers, and switches.
本发明实施例还提供了一种调控器,所述调控器用于实现于电子装置上执行时,提供设备输入接口以实施如上述各方法实施例中的步骤。The embodiment of the present invention also provides a regulator, which is used to provide a device input interface to implement the steps in the above method embodiments when implemented on an electronic device.
本发明实施例还提供了一种计算机程序产品,当计算机程序产品在电子设备上运行时,使得电子设备执行时可实现上述各个方法实施例中的步骤。The embodiment of the present invention also provides a computer program product, which, when the computer program product is run on the electronic device, enables the electronic device to implement the steps in the foregoing method embodiments.
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请实现上述实施例方法中的全部或部分流程,可以通过计算机程序来指令相关的硬件来完成,所述的计算机程序可存储于一计算机可读存储介质中,该计算机程序在被处理器执行时,可实现上述各个方法实施例的步骤。其中,所述计算机程序包括计算机程序代码,所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述计算机可读介质至少可以包括:能够将计算机程序代码携带到拍照装置/终端设备的任何实体或装置、记录介质、计算机存储器、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random AccessMemory,RAM)、电载波信号、电信信号以及软件分发介质。例如U盘、移动硬盘、磁碟或者光盘等。If the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the procedures in the method of the above-mentioned embodiments in the present application can be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium. The computer program When executed by a processor, the steps in the above-mentioned various method embodiments can be realized. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program codes to a photographing device/terminal device, a recording medium, a computer memory, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), electrical carrier signals, telecommunication signals, and software distribution media. Such as U disk, mobile hard disk, magnetic disk or optical disk, etc.
以上所述,仅为本发明较优的具体的实施方式,但本发明的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本发明揭露的技术范围内,凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等,都应涵盖在本发明的保护范围之内。The above is only a preferred specific implementation of the present invention, but the protection scope of the present invention is not limited thereto. Any person familiar with the technical field is within the technical scope disclosed in the present invention. Any modifications, equivalent replacements and improvements made within the spirit and principles shall fall within the protection scope of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310712372.6A CN116692397A (en) | 2023-06-15 | 2023-06-15 | An automatic separation device and separation method for a cylinder head casting engineering pallet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310712372.6A CN116692397A (en) | 2023-06-15 | 2023-06-15 | An automatic separation device and separation method for a cylinder head casting engineering pallet |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116692397A true CN116692397A (en) | 2023-09-05 |
Family
ID=87833661
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310712372.6A Pending CN116692397A (en) | 2023-06-15 | 2023-06-15 | An automatic separation device and separation method for a cylinder head casting engineering pallet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116692397A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5518105A (en) * | 1992-10-23 | 1996-05-21 | Jean Gallay S.A. | Process and device for conveying objects along a circuit and use thereof |
| CN108058972A (en) * | 2018-01-17 | 2018-05-22 | 龙利得包装印刷股份有限公司 | A kind of intelligence production material separator |
| CN213084680U (en) * | 2020-07-13 | 2021-04-30 | 上海牧森自动化设备有限公司 | Conveying blocking mechanism |
| CN213504867U (en) * | 2020-09-06 | 2021-06-22 | 襄阳市苏海机械设备有限公司 | Fragment of brick hacking machine layer board dismounting device |
| CN113537096A (en) * | 2021-07-21 | 2021-10-22 | 常熟理工学院 | ROS-based AGV fork parking pallet identification and auxiliary positioning method and system |
| CN114972968A (en) * | 2022-05-19 | 2022-08-30 | 长春市大众物流装配有限责任公司 | Tray identification and pose estimation method based on multiple neural networks |
| CN217397510U (en) * | 2022-05-30 | 2022-09-09 | 中山市文联智能包装机械有限公司 | Novel differential roller conveying line |
| CN115112121A (en) * | 2022-03-28 | 2022-09-27 | 浙江德清知路导航科技有限公司 | Multi-source fusion positioning method, system and terminal based on combination of data and model |
-
2023
- 2023-06-15 CN CN202310712372.6A patent/CN116692397A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5518105A (en) * | 1992-10-23 | 1996-05-21 | Jean Gallay S.A. | Process and device for conveying objects along a circuit and use thereof |
| CN108058972A (en) * | 2018-01-17 | 2018-05-22 | 龙利得包装印刷股份有限公司 | A kind of intelligence production material separator |
| CN213084680U (en) * | 2020-07-13 | 2021-04-30 | 上海牧森自动化设备有限公司 | Conveying blocking mechanism |
| CN213504867U (en) * | 2020-09-06 | 2021-06-22 | 襄阳市苏海机械设备有限公司 | Fragment of brick hacking machine layer board dismounting device |
| CN113537096A (en) * | 2021-07-21 | 2021-10-22 | 常熟理工学院 | ROS-based AGV fork parking pallet identification and auxiliary positioning method and system |
| CN115112121A (en) * | 2022-03-28 | 2022-09-27 | 浙江德清知路导航科技有限公司 | Multi-source fusion positioning method, system and terminal based on combination of data and model |
| CN114972968A (en) * | 2022-05-19 | 2022-08-30 | 长春市大众物流装配有限责任公司 | Tray identification and pose estimation method based on multiple neural networks |
| CN217397510U (en) * | 2022-05-30 | 2022-09-09 | 中山市文联智能包装机械有限公司 | Novel differential roller conveying line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220366576A1 (en) | Method for target tracking, electronic device, and storage medium | |
| CN110895809B (en) | Method for accurately extracting key points in hip joint image | |
| CN112650298B (en) | A UAV tracking and landing method and system | |
| CN113313703B (en) | UAV transmission line inspection method based on deep learning image recognition | |
| CN114898355B (en) | Method and system for self-supervised learning of body motion for autonomous driving | |
| CN110610166A (en) | Text region detection model training method and device, electronic equipment and storage medium | |
| CN109421050B (en) | Robot control method and device | |
| CN113838058B (en) | An automatic annotation method and system for medical images based on small sample segmentation | |
| CN103208008A (en) | Fast adaptation method for traffic video monitoring target detection based on machine vision | |
| CN107610235B (en) | Mobile platform navigation method and device based on deep learning | |
| CN118262145A (en) | Improved YOLOv5 bridge crack detection method based on coordinate attention mechanism | |
| CN114708300B (en) | An adaptive target tracking method and system capable of resisting occlusion | |
| Mohammadi et al. | Toward predicting SO2 solubility in ionic liquids utilizing soft computing approaches and equations of state | |
| CN115311617A (en) | Method and system for acquiring passenger flow information of urban rail station area | |
| CN114494436A (en) | Indoor scene positioning method and device | |
| CN116483108A (en) | State correction method, device, electronic device and storage medium of quadruped robot | |
| CN110517285B (en) | Large-scene minimum target tracking based on motion estimation ME-CNN network | |
| CN111127510B (en) | A method and device for predicting the position of a target object | |
| CN111624875A (en) | Visual servo control method and device and unmanned equipment | |
| CN112329645A (en) | Image detection method, image detection device, electronic equipment and storage medium | |
| CN110610140B (en) | Training method, device and equipment of face recognition model and readable storage medium | |
| CN112364854B (en) | Airborne target approach guidance system and method based on detection and tracking fusion | |
| CN113639757A (en) | Map matching method and system based on bidirectional scoring model and retrospective correction mechanism | |
| CN116692397A (en) | An automatic separation device and separation method for a cylinder head casting engineering pallet | |
| CN115079700B (en) | A control method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |