Mechanical arm control method and system based on monitoring of sensor made of barium titanate

Abstract

The invention discloses a mechanical arm control method and system based on monitoring of a sensor made of barium titanate, and relates to the technical field of intelligent control. The method comprises the steps that a barium titanate intelligent sensor is installed on a mechanical arm to collect operation data of the mechanical arm, and information of objects grabbed by the mechanical arm is obtained; an article is positioned and grabbed through acoustics guidance, local point cloud data are obtained, and the grabbing force of the mechanical arm is adjusted according to the local point cloud data and article information; mechanical arm faults are remotely monitored according to the mechanical arm operation data, and mechanical arm maintenance is conducted; and the operation state and the grabbing process of the mechanical arm are recorded in real time to be displayed and stored. According to the method, the target grabbing force of the mechanical arm to the object is calculated by obtaining the local point cloud data, the grabbing force of the mechanical arm is optimized in real time through an algorithm to grab the object, the grabbing stability and accuracy of the mechanical arm are effectively improved, mechanical arm operation fault monitoring and maintenance are conducted by synchronously constructing a support vector machine model, and the working efficiency is improved. And the operation safety of the mechanical arm is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a control method and system for a robotic arm monitored by a sensor made of barium titanate. Background Art

[0002] With the continuous development of industrial automation technology, robotic arms, as core equipment in automated production, play an indispensable role in many fields such as manufacturing, logistics, and medical care. Traditional robotic arm systems usually rely on standard sensors and control algorithms to complete precise operation tasks. However, with the continuous evolution of technology, higher requirements are placed on the control accuracy, stability, and real-time performance of robotic arms. For this reason, intelligent sensor technology has gradually been applied to the monitoring and control of robotic arms, especially intelligent sensors that can provide real-time feedback on environmental and operational information, such as pressure, position, speed, and strain sensors. However, the existing technology still has defects. Traditional robotic arm systems lack sufficient intelligence and adaptability, and it is difficult to achieve efficient control in real-time adjustment of grasping force. This limitation can easily lead to grasping failure or damage to items due to excessive grasping force. Summary of the invention

[0003] In view of the problems existing in the above-mentioned existing robot arm control method and system based on sensor monitoring made of barium titanate, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is that the traditional robotic arm system lacks sufficient intelligence and adaptability, and it is difficult to achieve efficient control in real-time adjustment of grasping force. This limitation can easily lead to grasping failure or excessive grasping force and damage to objects.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a robotic arm control method based on sensor monitoring made of barium titanate, which includes installing a barium titanate intelligent sensor on the robotic arm to collect robotic arm operation data and obtain information about objects grasped by the robotic arm; positioning and grasping objects through acoustic guidance, and obtaining local point cloud data, and adjusting the grasping force of the robotic arm according to the local point cloud data and object information; remotely monitoring robotic arm faults according to the robotic arm operation data, and performing robotic arm maintenance; and recording the robotic arm operation status and grasping process in real time for display and storage.

[0006] As a preferred solution of the robotic arm control method based on barium titanate sensor monitoring described in the present invention, wherein: the barium titanate intelligent sensor is installed on the robotic arm to collect the robotic arm operation data and obtain the information of the robotic arm grasping the object, which means deploying barium titanate intelligent sensors at the joints and end fingers of the robotic arm to collect the robotic arm operation data and the grasping force data of the end fingers, connecting all barium titanate intelligent sensors to form a Zigbee sensor network to the intelligent control end and transmitting the robotic arm operation data and grasping force data in real time, and the intelligent control end obtains the basic information of the grasped object through pre-input.

[0007] As a preferred solution of the robotic arm control method based on sensor monitoring made of barium titanate described in the present invention, the method of positioning and grasping objects through acoustic guidance and obtaining local point cloud data refers to installing an ultrasonic sensor on the robotic arm to determine the distance d between the robotic arm and the grasped object through ultrasound, setting the distance d as the local point cloud capture area range of the robotic arm, using laser radar to generate three-dimensional point cloud data of the grasped object, and screening the three-dimensional point cloud data according to the local point cloud capture area range to extract local point cloud data.

[0008] As a preferred solution of the robot arm control method based on barium titanate sensor monitoring of the present invention, wherein: the adjustment of the robot arm grasping force according to the local point cloud data and the object information includes:

[0009] Estimate the initial grasping force F based on the weight of the grasped object in ;

[0010] F in =m*g*α;

[0011] Where m is the weight of the grasped object, g is the acceleration of gravity, and α is the grasping safety factor;

[0012] For each point q in the local point cloud data i Perform K-nearest neighbor search to find the neighborhood point set, use the least squares method to fit the neighborhood plane of each point, and synthesize the normal vector N i ;

[0013] According to the initial gripping force F in and the normal vector N i Calculate point q i The normal force F n :

[0014] F n =F in *N i ;

[0015] Obtain the friction coefficient by grabbing the object information to calculate the friction force F of the normal force f , the friction force F fand the normal force F n Add together to get point q i Total gripping force F t (q i );

[0016] Extract the surface points of the grasped object in the point cloud data to form the XOY plane and XOZ plane, and extract the points of the XOY plane and XOZ plane in the local point cloud data to form point sets, and calculate the force balance of the XOY plane and XOZ plane respectively:

[0017]

[0018] where F XOY is the equilibrium force in the XOY plane, F XOZ is the equilibrium force on the XOZ plane, M is the set of points on the XOY plane, q j is the jth point in the point set M, m is the total number of points in the point set M, P is the point set on the XOZ plane, q k is the kth point in the point set P, and p is the total number of points in the point set P;

[0019] Compare the balance forces in the XOY plane and the XOZ plane, and select the minimum value as the target grasping force F to ;

[0020] The ultrasonic sensor guides the robot arm to locate and grasp the object, and obtains the grasping force F of the finger at the end of the robot arm in real time. i , define the residual r i The target grasping force F to and gripping force F i The difference between , defines the optimization objective f(x) as:

[0021]

[0022] Where n is the number of fingers at the end of the robotic arm;

[0023] Calculates the grip force adjustment value for the current iteration

[0024]

[0025] Among them J r is the Jacobian matrix, is the pseudo-inverse of the Jacobian matrix;

[0026] Adjustment value based on grip strength Update the gripping force of the robot's end-of-arm fingers:

[0027]

[0028] in is the grasping force of the hth iteration, β is the step size factor, To provide iterative updated grasping power;

[0029] The grasping force of the fingers at the end of the robot arm is iteratively updated through the Gauss-Newton method until the function value of the optimization target f(x) is less than the set iteration threshold, and then the iteration is stopped. The grasping force of the robot arm is adjusted in real time according to the grasping force of each finger at the end of the robot arm.

[0030] As a preferred solution of the robot arm control method based on the barium titanate sensor monitoring of the present invention, wherein: the remote monitoring of the robot arm fault according to the robot arm operation data refers to obtaining the robot arm operation data and then performing denoising processing through a Kalman filter, and extracting the operation data features through feature engineering;

[0031] Build a support vector machine model, use the training set to train the support vector machine model, and optimize the model parameters;

[0032] The extracted operation data features are input into the support vector machine model to obtain the robot arm fault monitoring results.

[0033] As a preferred solution of the robotic arm control method and system based on barium titanate sensor monitoring as described in the present invention, wherein: the robotic arm maintenance refers to performing robotic arm maintenance after obtaining the robotic arm fault monitoring result. If the fault monitoring result is that the operation is normal, the operation monitoring of the robotic arm is maintained, and regular robotic arm maintenance is arranged. If the fault monitoring result is that a fault exists, the robotic arm is stopped, and the real-time collected robotic arm operation data is sent to the staff to determine the cause and location of the fault, and fault repair content is formulated to perform robotic arm maintenance.

[0034] As a preferred solution of the robotic arm control method based on barium titanate sensor monitoring as described in the present invention, wherein: the real-time recording of the robotic arm operating status and grasping process for display and storage refers to real-time recording of the robotic arm operating status and grasping process to generate an operation log, and synchronously recording the robotic arm maintenance and repair content to generate a robotic arm maintenance log and store it in a database, the database regularly performs security checks on the operation log and maintenance log, and uploads them to the cloud for backup.

[0035] Another object of the present invention is to provide a robotic arm control system based on barium titanate sensor monitoring, which includes a data acquisition module for acquiring the operation data of the robotic arm and the information of the grasped object, and acquiring the grasping force data of the fingers at the end of the robotic arm during grasping;

[0036] The grasping control module is used to calculate the initial grasping force, obtain local point cloud data, and adjust the grasping force of the robot arm according to the local point cloud data and object information;

[0037] The operation monitoring module is used to analyze and monitor the operation status of the robot arm according to the collected operation data of the robot arm, and to perform maintenance on the robot arm;

[0038] The log recording module is used to generate operation logs and maintenance logs and store them in the database.

[0039] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned robot arm control method based on sensor monitoring made of barium titanate when executing the computer program.

[0040] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for controlling a robotic arm based on monitoring by a sensor made of barium titanate.

[0041] The beneficial effects of the present invention are as follows: the present invention locates and grasps objects, obtains local point cloud data to calculate the target grasping force of the robot arm for the object, and optimizes the grasping force of the robot arm in real time through an algorithm to grasp the object, thereby effectively improving the stability and accuracy of the robot arm's grasping, and simultaneously monitors and maintains the robot arm's operating faults by building a support vector machine model, thereby improving the safety of the robot arm's operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0043] Figure 1 The figure is a flow chart of a method for controlling a robotic arm based on monitoring by sensors made of barium titanate.

[0044] Figure 2 This is a schematic diagram of the structure of a robotic arm control system based on sensor monitoring made of barium titanate. DETAILED DESCRIPTION

[0045] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0046] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0047] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0048] Example 1

[0049] Reference Figure 1 , which is the first embodiment of the present invention, and provides a method for controlling a robotic arm based on monitoring by a sensor made of barium titanate. The method for controlling a robotic arm based on monitoring by a sensor made of barium titanate includes:

[0050] S1. Install the barium titanate smart sensor on the robotic arm to collect the operation data of the robotic arm and obtain the information of the objects grasped by the robotic arm;

[0051] Specifically, installing barium titanate smart sensors on the robotic arm to collect the robotic arm operation data and obtain the information of the robotic arm grasping objects means deploying barium titanate smart sensors on the joints and end fingers of the robotic arm to collect the robotic arm operation data and the grasping force data of the end fingers. The barium titanate smart sensors are made by 3D printing. The piezoelectric properties of barium titanate enable it to generate electrical signals under mechanical pressure, thereby monitoring the movement state of the robotic arm in real time. All barium titanate smart sensors form a Zigbee sensor network connected to the intelligent control end and transmit the robotic arm operation data and grasping force data in real time. The intelligent control end obtains basic information of the grasped object through pre-input, including size, weight, material, shape, etc.

[0052] By installing barium titanate smart sensors on the joints and end fingers of the robotic arm, the piezoelectric effect of the sensor enables it to sense and monitor mechanical pressure and strain in real time during the operation of the robotic arm. This real-time monitoring can not only capture the movement state of the robotic arm, but also accurately track the grasping force applied by the robotic arm fingers on the surface of the object. Through these high-precision data, the system can achieve precise control of the operation of the robotic arm to avoid damage to the object or grasping failure due to improper grasping force. The Zigbee network has the characteristics of low power consumption and high stability, and is particularly suitable for sensor systems that need to run continuously for a long time. Through the Zigbee protocol, all barium titanate smart sensors on the robotic arm are interconnected to form a complete wireless sensor network, ensuring that the data collected by each sensor can be The data is transmitted to the intelligent control terminal in real time. The low latency characteristic of the Zigbee network in data transmission ensures the real-time data of the robot's operation and grasping force. This provides a solid foundation for the efficient operation of the robot and ensures that it can make precise adjustments and operations in a short time. The intelligent control terminal is the "brain" of the entire system. By receiving data transmitted by the sensor network, the control terminal can monitor the operation status of the robot in real time and dynamically adjust the operation strategy of the robot based on the preset object information (such as size, weight, material and shape). The acquisition and input of object information enables the system to formulate adaptive grasping plans for different types of objects. For example, for fragile objects, the intelligent control terminal can reduce the grasping force; for heavier objects, the grasping stability can be improved.

[0053] S2, locate and grasp the object through acoustic guidance, obtain local point cloud data, and adjust the grasping force of the robot arm according to the local point cloud data and object information;

[0054] Specifically, positioning and grasping objects through acoustic guidance and obtaining local point cloud data refers to installing an ultrasonic sensor on the robotic arm to determine the distance d between the robotic arm and the grasped object through ultrasound, setting the distance d as the local point cloud capture area range of the robotic arm, using lidar to generate three-dimensional point cloud data of the grasped object, and screening the three-dimensional point cloud data according to the local point cloud capture area range to extract local point cloud data.

[0055] Ultrasonic sensors can provide fast and accurate distance information and are not affected by changes in ambient light. They are suitable for grasping operations in complex industrial scenarios. By accurately determining the relative position of objects through ultrasound, more accurate grasping strategies can be set for the robot arm to ensure the correctness of the position and angle when grasping objects and reduce errors. Based on the distance obtained by the ultrasonic sensor, the system can dynamically set a local point cloud capture area, which represents the spatial range where the robot arm's fingers may contact the object, ensuring that only point cloud data related to the grasping operation is captured. By setting the local point cloud capture area, the processing volume of the large amount of point cloud data generated by the lidar can be effectively reduced, and only data related to the grasping operation is retained. The setting of the local point cloud capture area makes subsequent data processing more efficient, reduces unnecessary computing burden, and ensures that the data in the grasping process is highly relevant and accurate. Compared with traditional two-dimensional images, three-dimensional point cloud data provides spatial structural information of objects, allowing the robot arm to more accurately identify the size, shape and grasping points of objects. Combined with three-dimensional point cloud data, the robotic arm can identify the grasping method of objects with complex shapes and dynamically adjust the grasping action according to the geometric characteristics of the object. In addition, the high-precision measurement of the lidar enables the robotic arm to maintain a high grasping success rate in narrow spaces or environments with many obstructions. The screening of local point cloud data greatly reduces the amount of calculation, allowing the system to process grasping tasks faster and more accurately. The screened local point cloud data is highly concentrated in the operating area of ​​the robotic arm, which ensures the accuracy of subsequent grasping force calculation and path planning. By processing only local point cloud data, the response speed of the system is improved, thereby improving the operating efficiency and real-time performance of the robotic arm. The grasping strategy optimization based on point cloud data enables the system to cope with diverse object grasping needs. Whether it is a regular-shaped object or an irregular object, the system can formulate an accurate grasping strategy through detailed analysis of the point cloud data, which greatly improves the operational flexibility of the robotic arm. In addition, the dynamic adjustment of the grasping force avoids damage to the object due to excessive grasping force, or object falling due to insufficient grasping force.

[0056] Furthermore, adjusting the gripping force of the robot arm according to the local point cloud data and the object information includes:

[0057] Estimate the initial grasping force F based on the weight of the grasped object in ;

[0058] F in =m*g*α;

[0059] Where m is the weight of the grasped object, g is the acceleration of gravity, and α is the grasping safety factor, which is used to prevent grasping failure and is usually set to 1.2-1.5;

[0060] For each point q in the local point cloud data iPerform K-nearest neighbor search to find the neighborhood point set, use the least squares method to fit the neighborhood plane of each point, and synthesize the normal vector N i ;

[0061] ax+by+c+d=0;

[0062] Where (x, y, z) are the point coordinates, a, b and c are the normal vector components of the fitted neighborhood plane, and the normal vector N is obtained by combining the normal vector components. i ;

[0063] According to the initial gripping force F in and the normal vector N i Calculate point q i The normal force F n :

[0064] F n =F in *N i ;

[0065] Initial gripping force F in is a vector with direction and magnitude, normal vector N i In order to describe the geometric direction characteristics of a point on the surface of an object, in order to obtain the normal force applied to a point, the component of the force in the direction of the normal vector, i.e., the normal force, is obtained through vector motor calculation;

[0066] Obtain the friction coefficient by grabbing the object information to calculate the friction force F of the normal force f , the friction force F f and the normal force F n Add together to get point q i Total gripping force F t (q i );

[0067] Extract the surface points of the grasped object in the point cloud data to form the XOY plane and XOZ plane, and extract the points of the XOY plane and XOZ plane in the local point cloud data to form point sets, and calculate the force balance of the XOY plane and XOZ plane respectively:

[0068]

[0069]

[0070] where F XOY is the equilibrium force in the XOY plane, F XOZ is the equilibrium force on the XOZ plane, M is the set of points on the XOY plane, q j is the jth point in the point set M, m is the total number of points in the point set M, P is the point set on the XOZ plane, q k is the kth point in the point set P, and p is the total number of points in the point set P;

[0071] Compare the balance forces in the XOY plane and the XOZ plane, and select the minimum value as the target grasping force F to ;

[0072] The ultrasonic sensor guides the robot arm to locate and grasp the object, and obtains the grasping force F of the finger at the end of the robot arm in real time. i , define the residual r i The target grasping force F to and gripping force F i The difference between , defines the optimization objective f(x) as:

[0073]

[0074] Where n is the number of fingers at the end of the robotic arm;

[0075] Calculates the grip force adjustment value for the current iteration

[0076]

[0077] Among them J r is the Jacobian matrix, which represents the residual r i Grasping force F i The first-order derivative of represents the relationship between the adjustment of the grasping force and the change of the residual, is the pseudo-inverse of the Jacobian matrix;

[0078] Adjustment value based on grip strength Update the gripping force of the robot's end-of-arm fingers:

[0079]

[0080] in is the grasping force of the hth iteration, β is the step size factor, To provide iterative updated grasping power;

[0081] The grasping force of the fingers at the end of the robot arm is iteratively updated through the Gauss-Newton method until the function value of the optimization target f(x) is less than the set iteration threshold, and then the iteration is stopped. The grasping force of the robot arm is adjusted in real time according to the grasping force of each finger at the end of the robot arm.

[0082] By combining the object information, the system can dynamically adjust the initial grasping force to ensure that the robot arm can provide sufficient grasping force even when the object quality is uneven. At the same time, the setting of the safety factor increases the fault tolerance of the grasping process and effectively avoids grasping failure or object damage. By performing K-nearest neighbor search for each point, the system can more accurately describe the local geometric features of the object surface. The calculation of the normal vector provides a reference for the direction of the grasping force, so that the grasping force can be applied along the normal direction of the object surface, ensuring that the object surface will not be damaged due to excessive grasping force. Through the calculation of normal force and friction force, the system can accurately adjust the size and direction of the grasping force according to the geometric and physical characteristics of the object surface to ensure the grasping operation. It is stable without causing damage to objects. The precise control of the grasping force improves the success rate of the robot arm in grasping objects of various shapes and materials. Through force balance calculation, the system ensures that the grasping force of the robot arm remains stable on different planes to prevent grasping failures caused by uneven force distribution. Selecting the minimum value as the target grasping force can minimize the excessive force applied by the robot arm during the grasping process, further improving the safety and accuracy of grasping. Through iterative optimization of the Gauss-Newton method, the system can dynamically adjust the grasping force to ensure that the actual grasping force is closer to the target grasping force after each iteration. This process reduces the need for human intervention through automated force adjustment and improves the automation and accuracy of the robot arm operation.

[0083] S3. Remotely monitor robot arm failures based on robot arm operation data and perform robot arm maintenance;

[0084] Specifically, remotely monitoring the mechanical arm fault according to the mechanical arm operation data means obtaining the mechanical arm operation data, performing denoising processing through a Kalman filter, and extracting the operation data features through feature engineering;

[0085] Build a support vector machine model, use the training set to train the support vector machine model, and optimize the model parameters;

[0086] The extracted operation data features are input into the support vector machine model to obtain the robot arm fault monitoring results.

[0087] Through Kalman filtering, the system can remove random noise in the robot arm operation data, making the sensor data more reliable and stable, which provides high-quality data input for subsequent feature extraction and fault monitoring, ensuring the accuracy of fault monitoring results. Through feature engineering, the system can accurately extract important information during the operation of the robot arm and provide high-quality input features for the fault monitoring model. Feature engineering can not only improve the prediction accuracy of the model, but also reduce the redundancy of the original data, reduce computing costs, and enhance the real-time monitoring capabilities of the system. The support vector machine can construct the optimal classification hyperplane in high-dimensional space to ensure the accuracy and robustness of the robot arm fault monitoring results. Through parameter optimization, the system can achieve higher classification accuracy between fault and non-fault states and reduce the risk of misclassification, which makes the system more efficient in detecting potential faults of the robot arm at an early stage and avoids economic losses caused by equipment damage or downtime.

[0088] Furthermore, performing robot arm maintenance refers to performing robot arm maintenance after obtaining the robot arm fault monitoring result. If the fault monitoring result is that the operation is normal, the operation monitoring of the robot arm is maintained and regular robot arm maintenance is arranged. If the fault monitoring result is that a fault exists, the robot arm is stopped and the real-time collected robot arm operation data is sent to the staff to determine the cause and location of the fault, and fault repair content is formulated to perform robot arm maintenance.

[0089] By incorporating regular maintenance under normal operating conditions into systematic management, it is possible to effectively prevent unexpected failures of the robot arm due to excessive wear or fatigue. Regular maintenance can promptly detect and resolve potential problems, prevent small problems from gradually accumulating into major failures, and at the same time improve the service life and stability of the robot arm. The combination of automated monitoring and regular maintenance reduces reliance on manual inspections and improves the operating efficiency and reliability of the equipment. When a fault is detected, timely shutdown can not only protect the robot arm from further damage, but also avoid other chain failures or accidents on the automated production line. This protection mechanism greatly improves the safety of the system and reduces downtime and repair time caused by equipment failures. The shutdown protection function also ensures that maintenance personnel can safely access the equipment to perform fault analysis and repairs, and collect real-time data. It enables technicians to quickly grasp the details of the failure when it occurs, so as to more accurately determine the cause and location of the failure. With the support of real-time data, the diagnosis time is greatly shortened, and technicians can quickly develop repair plans to reduce equipment downtime. In addition, detailed operating data can help technicians better prevent similar failures in the future and provide data support for the continuous optimization of maintenance strategies. Through systematic maintenance plans, maintenance work can be more efficient and targeted. The formulation of maintenance plans is based on real-time collected data and fault diagnosis results to ensure that each maintenance can accurately solve the problem and avoid repeated failures. The re-monitoring function after the repair is completed provides a guarantee for the stability of the system after the repair, so that the robotic arm can be put back into operation safely and stably, improving the reliability and sustainability of the system.

[0090] S4, real-time recording of the robot arm's operating status and grasping process for display and storage;

[0091] Specifically, real-time recording of the robot arm's operating status and grasping process for display and storage refers to real-time recording of the robot arm's operating status and grasping process to generate an operation log, and synchronously recording the robot arm's maintenance and repair content to generate a robot arm maintenance log and store it in a database. The database regularly performs security checks on the operation log and maintenance log, and uploads them to the cloud for backup.

[0092] The real-time recorded robot arm operation data can provide an accurate basis for subsequent fault analysis, performance optimization, and grasping strategy improvement. Through the long-term accumulated operation logs, the system can identify the operation mode and potential problems of the robot arm, thereby optimizing the workflow and reducing the mistakes and failures of the robot arm. At the same time, the detailed records of the grasping process provide accurate feedback for automated operations in industrial scenarios, helping to improve the grasping success rate and overall operation efficiency. By generating and storing maintenance logs, the system can better manage the maintenance cycle of the robot arm and ensure that every maintenance is accurately recorded and archived. The long-term preservation of maintenance logs helps to identify which parts are prone to problems and optimize the maintenance cycle, thereby reducing maintenance costs and increasing the service life of the robot arm. Furthermore, these logs can also provide data support for predictive maintenance. Support helps the system take preventive measures before a failure occurs and improves the reliability of the equipment. Through regular database security testing, the system can effectively prevent data loss and external intrusion, and ensure the security and integrity of key operation and maintenance data, which is crucial to ensure the long-term reliable operation of the robot arm. Especially in high-precision applications such as industry and medical care, the security of data directly affects the use and decision-making of the equipment. Cloud backup provides double protection for the operation data and maintenance data of the robot arm, avoiding data loss caused by uncontrollable factors such as hardware failure and unexpected disasters. By backing up data to the cloud, enterprises can access these logs anytime and anywhere for remote management and analysis. This provides a convenient solution for cross-regional equipment management and large-scale equipment monitoring, and also improves the flexibility and security of data management.

[0093] Example 2

[0094] Reference Figure 2 , which is the second embodiment of the present invention, is different from the previous embodiment and provides a robot arm control system based on barium titanate sensor monitoring, which includes:

[0095] The data acquisition module is used to obtain the operation data of the robot arm and the information of the grasped object, and to obtain the grasping force data of the fingers at the end of the robot arm during grasping;

[0096] The grasping control module is used to calculate the initial grasping force, obtain local point cloud data, and adjust the grasping force of the robot arm according to the local point cloud data and object information;

[0097] The operation monitoring module is used to analyze and monitor the operation status of the robot arm according to the collected operation data of the robot arm, and to perform maintenance on the robot arm;

[0098] The log recording module is used to generate operation logs and maintenance logs and store them in the database.

[0099] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0100] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0101] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0102] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0103] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the technical solutions of the present invention.

Claims

1. A robotic arm control method based on barium titanate sensor monitoring, characterized in that: include, Install the barium titanate smart sensor on the robotic arm to collect the robotic arm operation data and obtain the information of the objects grasped by the robotic arm; The robot can locate and grasp objects through acoustic guidance, obtain local point cloud data, and adjust the grasping force of the robot arm according to the local point cloud data and object information; Remotely monitor robot arm failures based on robot arm operation data and perform robot arm maintenance; The robot arm’s operating status and grasping process are recorded in real time for display and storage.

2. The method for controlling a robotic arm based on monitoring by a sensor made of barium titanate according to claim 1, characterized in that: The installation of the barium titanate smart sensor on the robotic arm to collect the robotic arm operation data and obtain the information of the robotic arm grasping the object refers to deploying the barium titanate smart sensor on the robotic arm joints and end fingers to collect the robotic arm operation data and the grasping force data of the end fingers, connecting all the barium titanate smart sensors to form a Zigbee sensor network to the intelligent control end and transmitting the robotic arm operation data and grasping force data in real time, and the intelligent control end obtains the basic information of the grasped object through pre-input.

3. The method for controlling a robotic arm based on monitoring by a sensor made of barium titanate according to claim 2, characterized in that: The method of positioning and grasping an object through acoustic guidance and obtaining local point cloud data refers to installing an ultrasonic sensor on the robotic arm to determine the distance d between the robotic arm and the grasped object through ultrasound, setting the distance d as the local point cloud capture area range of the robotic arm, using a laser radar to generate three-dimensional point cloud data of the grasped object, and screening the three-dimensional point cloud data according to the local point cloud capture area range to extract local point cloud data.

4. The method for controlling a robotic arm based on monitoring by a sensor made of barium titanate as claimed in claim 3, characterized in that: The adjusting the grasping force of the robot arm according to the local point cloud data and the object information includes: Estimate the initial grasping force F based on the weight of the grasped object in ; F in = m*g*a; Where m is the weight of the grasped object, g is the acceleration of gravity, and α is the grasping safety factor; For each point q in the local point cloud data i Perform K-nearest neighbor search to find the neighborhood point set, use the least squares method to fit the neighborhood plane of each point, and synthesize the normal vector N i ; According to the initial gripping force F in and the normal vector N i Calculate point q i The normal force F n : F n =F in *N i ; Obtain the friction coefficient by grabbing the object information to calculate the friction force F of the normal force f , the friction force F f and the normal force F n Add together to get point q i Total gripping force F t (q i ); Extract the surface points of the grasped object in the point cloud data to form the XOY plane and XOZ plane, and extract the points of the XOY plane and XOZ plane in the local point cloud data to form point sets, and calculate the force balance of the XOY plane and XOZ plane respectively: where F XOY is the equilibrium force in the XOY plane, F XOZ is the equilibrium force on the XOZ plane, M is the set of points on the XOY plane, q j is the jth point in the point set M, m is the total number of points in the point set M, P is the point set on the XOZ plane, q k is the kth point in the point set P, and p is the total number of points in the point set P; Compare the balance forces in the XOY plane and the XOZ plane, and select the minimum value as the target grasping force F to ; The ultrasonic sensor guides the robot arm to locate and grasp the object, and obtains the grasping force F of the finger at the end of the robot arm in real time. i , define the residual r i The target grasping force F to and gripping force F i The difference between , defines the optimization objective f(x) as: Where n is the number of fingers at the end of the robotic arm; Calculates the grip force adjustment value for the current iteration Among them J r is the Jacobian matrix, is the pseudo-inverse of the Jacobian matrix; Adjustment value based on grip strength Update the gripping force of the robot's end-of-arm fingers: in is the grasping force of the hth iteration, β is the step size factor, To provide iterative updated grasping power; The grasping force of the fingers at the end of the robot arm is iteratively updated through the Gauss-Newton method until the function value of the optimization target f(x) is less than the set iteration threshold, and then the iteration is stopped. The grasping force of the robot arm is adjusted in real time according to the grasping force of each finger at the end of the robot arm.

5. The method for controlling a robotic arm based on monitoring by a sensor made of barium titanate as claimed in claim 4, characterized in that: Remotely monitoring the mechanical arm fault according to the mechanical arm operation data refers to obtaining the mechanical arm operation data, performing denoising processing through a Kalman filter, and extracting operation data features through feature engineering; Build a support vector machine model, use the training set to train the support vector machine model, and optimize the model parameters; The extracted operation data features are input into the support vector machine model to obtain the robot arm fault monitoring results.

6. The method for controlling a robotic arm based on monitoring by a sensor made of barium titanate according to claim 5, characterized in that: The robotic arm maintenance refers to performing robotic arm maintenance after obtaining the robotic arm fault monitoring result. If the fault monitoring result is that the operation is normal, the operation monitoring of the robotic arm is maintained and regular robotic arm maintenance is arranged. If the fault monitoring result is that a fault exists, the robotic arm is stopped and the real-time collected robotic arm operation data is sent to the staff to determine the cause and location of the fault, and fault repair content is formulated to perform robotic arm maintenance.

7. The method for controlling a robotic arm based on monitoring by a sensor made of barium titanate according to claim 6, characterized in that: The real-time recording of the robot arm's operating status and grasping process for display and storage refers to real-time recording of the robot arm's operating status and grasping process to generate an operation log, and simultaneously recording the robot arm's maintenance and repair content to generate a robot arm maintenance log and store it in a database. The database regularly performs security checks on the operation log and maintenance log, and uploads them to the cloud for backup.

8. A robotic arm control system according to any one of claims 1 to 7, wherein: include, The data acquisition module is used to obtain the operation data of the robot arm and the information of the grasped object, and to obtain the grasping force data of the fingers at the end of the robot arm during grasping; The grasping control module is used to calculate the initial grasping force, obtain local point cloud data, and adjust the grasping force of the robot arm according to the local point cloud data and object information; The operation monitoring module is used to analyze and monitor the operation status of the robot arm according to the collected operation data of the robot arm, and to perform maintenance on the robot arm; The log recording module is used to generate operation logs and maintenance logs and store them in the database.

9. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the robot arm control method based on barium titanate sensor monitoring according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for controlling a robotic arm based on monitoring by a sensor made of barium titanate according to any one of claims 1 to 7 are implemented.

Images