Clamping force correction method, system and storage medium based on tea oil branch clamping manipulator

Abstract

The present invention provides a method, system and storage medium for correcting the clamping force of a clamping manipulator based on oil-tea camellia tree branches, which relates to the technical fields of mechanization and automation, and includes: monitoring and analyzing the oil-tea camellia tree branches, the operating environment and the motion state of the manipulator, collecting key parameters, generating a clamping adaptability index and a clamping stability index, combining the clamping adaptability index and the clamping stability index, and calculating a clamping control index; constructing a deep learning model, using the historical key parameters as the training set and the corresponding historical clamping force of the manipulator as the label, training the model to obtain a clamping force prediction model, inputting the real-time collected key parameters into the model, outputting the predicted clamping force, and combining it with the clamping control index to calculate the final clamping force. Based on the real-time acquisition of key parameters, the present invention generates a clamping adaptability index and a clamping stability index, and then calculates a clamping control index, so as to achieve the goal of dynamically adjusting the clamping force.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanization and automation, and particularly to a clamping force correction method, system and storage medium for a clamping manipulator based on oil tea tree branches. Background Art

[0002] In agricultural production, the management and picking of oil tea trees are key links affecting yield and quality. With the development of automation technology, manipulators are widely used in the clamping operation of oil tea trees. However, the existing manipulator clamping systems have many deficiencies in practical applications. Traditional clamping force control methods usually rely on fixed parameter settings and do not fully consider the physical properties of oil tea tree branches, such as average diameter, hardness and humidity. This results in that in different branch conditions, it is difficult for the clamping force of the manipulator to adapt, and it is easy to occur that the clamping force is insufficient and the branch slips, or the clamping force is too large and the branch is damaged. Such a fixed control strategy not only reduces the working efficiency of the manipulator, but also increases the risk of damage to the trees during the picking process, affecting the growth and yield of oil tea.

[0003] In addition, the current clamping force adjustment technologies often lack a real-time feedback mechanism. Most traditional systems cannot dynamically monitor and adjust the clamping force during operation and lack the ability to adapt to environmental changes. For example, changes in environmental temperature and humidity will directly affect the physical properties of the branches, yet traditional control systems cannot collect these key parameters in real time and make adjustments accordingly. Such a lack of flexibility in design makes the manipulator perform poorly in different operating environments and branch states, resulting in low production efficiency and resource waste. Therefore, there is an urgent need for a new clamping force correction method to achieve intelligent and refined control of the clamping process of oil tea tree branches and improve the adaptability and working performance of the manipulator.

[0004] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a clamping force correction method, system and storage medium for a clamping manipulator based on oil tea tree branches to solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] A clamping force correction method for a clamping manipulator based on oil tea tree branches, the specific steps include:

[0008] Step 1: Monitor and analyze the oil-tea camellia branches, operating environment, and the motion state of the manipulator, and collect key parameters, including the average diameter of the branches, branch hardness, branch humidity, target distance, the clamping speed of the manipulator, clamping angle, and environmental temperature;

[0009] Step 2: Generate a clamping adaptability index based on the dimensionless average diameter, branch hardness, branch humidity, and environmental temperature; generate a clamping stability index based on the dimensionless target distance, clamping angle, and clamping speed. Combine the clamping adaptability index and the clamping stability index, conduct a correlation analysis, and calculate the clamping control index;

[0010] Step 3: Build a deep learning model. Use the historical key parameters as the training set and input them into the model, and use the corresponding historical manipulator clamping force as the label to train the model to obtain a trained clamping force prediction model. Input the real-time collected key parameters into the clamping force prediction model to output the predicted clamping force;

[0011] Step 4: Combine the predicted clamping force with the clamping control index to obtain the corrected final clamping force.

[0012] Furthermore, the specific logic for collecting key parameters is as follows:

[0013] Use a laser rangefinder to measure the maximum diameter and minimum diameter of the cross-section of the branch to be clamped, and calculate the average diameter according to the following formula:

[0014]

[0015] where D is the average diameter of the branch to be clamped, D max is the maximum diameter, and D min is the minimum diameter;

[0016] Use a Vickers hardness tester to obtain the branch hardness parameter: Select the cross-section of the branch to be tested, ensure that the surface is flat and dry, perpendicular to the cross-section of the branch with the indenter of the Vickers hardness tester, and apply a certain test force. After unloading, use a microscope to measure the diagonal length of the indentation, and calculate the Vickers hardness value of the branch according to the following formula, and use the Vickers hardness value as the branch hardness:

[0017]

[0018] where H is the branch hardness, F is the applied test force, and d is the diagonal length of the indentation;

[0019] The specific logic for obtaining the branch humidity is as follows: Adopt the weighing method. First, weigh the branch to be tested, then dry it in an oven until it reaches a constant weight, and weigh it again. Calculate the branch humidity according to the following formula:

[0020]

[0021] Among them, M is the humidity of the branch, W wet is the mass of the branch in the wet state, W dry is the mass of the branch in the dry state;

[0022] The target distance refers to the actual distance between the manipulator and the target object, which is calculated according to the following formula:

[0023]

[0024] Among them, P is the target distance, (x target , y target , z target ) is the coordinate of the target object in three-dimensional space, (x init , y init , z init ) is the initial position coordinate of the manipulator in three-dimensional space;

[0025] Use sensors to obtain the clamping speed V and the clamping angle θ in real time. The clamping angle refers to the angle between the manipulator and the horizontal plane during the clamping process;

[0026] Use a temperature sensor to collect the ambient temperature when the manipulator performs the clamping operation, denoted as T.

[0027] Furthermore, generate a clamping adaptability index, and the formula is as follows:

[0028]

[0029] Among them, ADAP is the clamping adaptability index, D is the average diameter of the branch, H is the branch hardness, M is the branch humidity, T is the ambient temperature, T ref is the ambient temperature in the ideal state, e is the natural constant, k1, k2, k3 and k4 are preset proportionality coefficients, and k3>k2 = k1>k4>0;

[0030] Generate a clamping stability index, and the formula is as follows:

[0031]

[0032] Among them, STA is the clamping stability index, V is the clamping speed, θ is the clamping angle, θ ref is the best clamping angle of the manipulator, P is the target distance, k5, k6 and k7 are preset proportionality coefficients, and k5>k6>k7>0;

[0033] Calculate the clamping control index, and the formula is as follows:

[0034]

[0035] Among them, CON is the clamping control index, ADAP is the clamping adaptability index, STA is the clamping stability index, D is the average diameter of the branch, e is the natural constant, μ is the adjustment coefficient used to adjust and balance the influence of other parameters, and μ > 0.

[0036] Further, the process of constructing the deep learning model specifically includes:

[0037] Collect the historical key parameters and corresponding clamping forces of the manipulator performing clamping operations in n groups. The key parameters include the average diameter of the branch, branch hardness, branch humidity, target distance, clamping speed of the manipulator, clamping angle, and environmental temperature, and preprocess the collected data to remove outliers and missing values; construct a deep learning model, use the historical key parameters as the training set, use the clamping force corresponding to each group of historical key parameters as the label, train the model to obtain a trained clamping force prediction model, and input the real-time collected key parameters into the clamping force prediction model to output the predicted clamping force for the current manipulator to perform clamping operations.

[0038] Further, combine the predicted clamping force with the clamping control index to obtain the corrected final clamping force, and the formula is as follows:

[0039] F corrected = F predicted *(1 + k f *CON)

[0040] Among them, F corrected is the final clamping force, F predicted is the predicted clamping force, CON is the clamping control index, and k f is the clamping force adjustment coefficient, which is determined according to actual test data.

[0041] The present invention also further provides a clamping force correction system for a clamping manipulator based on oil-tea camellia branches. The clamping force correction system for a clamping manipulator based on oil-tea camellia branches is used to execute the above-mentioned clamping force correction method for a clamping manipulator based on oil-tea camellia branches, and includes:

[0042] A data acquisition module for monitoring and analyzing the oil-tea camellia branches, operating environment, and manipulator motion state, and collecting key parameters, including the average diameter of the branch, branch hardness, branch humidity, target distance, clamping speed of the manipulator, clamping angle, and environmental temperature;

[0043] An index calculation module, which is used to generate a clamping adaptability index according to the dimensionless average diameter, branch hardness, branch humidity, and ambient temperature; generate a clamping stability index according to the dimensionless target distance, clamping angle, and clamping speed, combine the clamping adaptability index and the clamping stability index, conduct a correlation analysis, and calculate a clamping control index;

[0044] A model construction module, which is used to construct a deep learning model, input historical key parameters as a training set into the model, use the corresponding historical manipulator clamping force as a label, train the model, obtain a trained clamping force prediction model, input the real-time collected key parameters into the clamping force prediction model, and output a predicted clamping force;

[0045] A force correction module, which is used to combine the predicted clamping force with the clamping control index to obtain a corrected final clamping force.

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] Through the monitoring and analysis of multiple factors and in combination with a deep learning model, the present invention effectively solves the problem of inaccurate clamping force of traditional manipulators. Based on the real-time acquisition of key parameters, a clamping adaptability index and a clamping stability index are generated, and then a clamping control index is calculated, thereby achieving the goal of dynamically adjusting the clamping force. In this way, not only the reliability and stability of the clamping process are improved, unnecessary damage to branches is avoided, but also the operation efficiency of the manipulator is enhanced, the precise picking and efficient management of oil tea trees are promoted, and the development of agricultural automation technology is effectively facilitated. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0049] Figures 2 - 3 It is a three-dimensional schematic diagram of the manipulator; in the figure: base 1, connecting block 2, driving device 3, mechanical claw 4, connecting rod 5, contact head 6;

[0050] Figure 4 It is a schematic diagram of the system module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the following further elaborates on the present invention in detail with reference to specific embodiments.

[0052] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention shall have the ordinary meanings understood by those of ordinary skill in the field to which the present invention pertains. The "first", "second" and similar terms used in the present invention do not denote any order, quantity or importance, but are only used to distinguish different components. The terms such as "comprising" or "including" mean that the elements or objects appearing before this term cover the elements or objects listed after this term and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left" and "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0053] Embodiment:

[0054] Please refer to Figures 1 - 3 , the present invention provides a technical solution:

[0055] A method for correcting the clamping force of a clamping manipulator based on oil-tea camellia tree branches, the specific steps include:

[0056] Step 1: Monitor and analyze the oil-tea camellia tree branches, the operating environment and the motion state of the manipulator, and collect key parameters, including the average diameter of the branches, the hardness of the branches, the humidity of the branches, the target distance, the clamping speed of the manipulator, the clamping angle and the environmental temperature;

[0057] In this embodiment, the specific logic for collecting key parameters is as follows:

[0058] Use a laser rangefinder to measure the maximum diameter and minimum diameter of the cross-section of the branches to be clamped, and calculate the average diameter according to the following formula:

[0059]

[0060] where D is the average diameter of the branches to be clamped, D max is the maximum diameter, and D min is the minimum diameter;

[0061] Use a Vickers hardness tester to obtain the hardness parameter of the branches: Select the cross-section of the branches to be measured, ensure that the surface is flat and dry, perpendicular to the cross-section of the branches with the indenter of the Vickers hardness tester, and apply a certain test force. After unloading, use a microscope to measure the diagonal length of the indentation, calculate the Vickers hardness value of the branches according to the following formula, and use the Vickers hardness value as the hardness of the branches:

[0062]

[0063] Among them, H is the hardness of the branch, F is the applied test force, and d is the length of the indentation diagonal;

[0064] To obtain the humidity of the branch, the specific logic is as follows: The weighing method is adopted. First, weigh the branch to be measured, then dry it in an oven until it reaches a constant weight, and weigh it again. Calculate the humidity of the branch according to the following formula:

[0065]

[0066] Among them, M is the humidity of the branch, W wet is the mass of the branch in the wet state, W dry is the mass of the branch in the dry state;

[0067] The target distance refers to the actual distance between the manipulator and the target object, and is calculated according to the following formula:

[0068]

[0069] Among them, P is the target distance, (x target , y target , z target ) are the coordinates of the target object in three-dimensional space, (x init , y init , z init ) are the initial position coordinates of the manipulator in three-dimensional space;

[0070] Use a sensor to obtain the clamping speed V and the clamping angle θ in real time. The clamping angle refers to the angle between the manipulator and the horizontal plane during the clamping process;

[0071] Use a temperature sensor to collect the ambient temperature of the manipulator during the clamping operation, denoted as T.

[0072] The advantage of step 1 is that by collecting a series of key parameters, such as the average diameter, hardness, humidity, target distance, clamping speed, clamping angle, and ambient temperature of the branch, it provides a scientific basis for the subsequent correction of the clamping force. This multi-dimensional data collection method can effectively reflect the changes under different environments and branch states, overcomes the deficiency of relying only on fixed parameters for clamping in the existing technology, and ensures higher accuracy and reliability for the dynamic adjustment of the clamping force.

[0073] Compared with the prior art, the beneficial effects of Step 1 are reflected in the improvement of the real-time performance and adaptability of the clamping process. Through the real-time monitoring of key parameters, it can respond to the changes of oil tea branches and the environment in a timely manner, so as to dynamically adjust the clamping force during the clamping process, reduce the risk of branch damage, and improve the working efficiency of the manipulator. In the solution of this application, adopting this step can provide a solid data basis for the overall solution, ensure that the subsequent generation of clamping adaptability and stability indexes is more scientific and reasonable, so as to achieve more effective clamping force correction, and promote the precise picking and efficient management of oil tea trees.

[0074] Step 2: Generate a clamping adaptability index based on the dimensionless average diameter, branch hardness, branch humidity, and environmental temperature; generate a clamping stability index based on the dimensionless target distance, clamping angle, and clamping speed, combine the clamping adaptability index and the clamping stability index, conduct a correlation analysis, and calculate the clamping control index;

[0075] In this embodiment, the formula for generating the clamping adaptability index is as follows:

[0076]

[0077] Among them, ADAP is the clamping adaptability index, D is the average diameter of the branch, H is the branch hardness, M is the branch humidity, T is the environmental temperature, T ref is the environmental temperature in the ideal state, e is the natural constant, k1, k2, k3, and k4 are preset proportionality coefficients, and k3>k2 = k1>k4>0. This is because the humidity of the branch directly affects its physical properties, such as toughness and elasticity. Too high or too low humidity will affect the clamping effect. Therefore, a higher weight is given to the humidity to ensure its dominant position in the adaptability evaluation; the diameter and hardness of the branch are both important parameters affecting clamping stability. The diameter size affects the contact area of the clamping point, and the hardness determines the anti-deformation ability of the branch during clamping. These two factors are equally important during the clamping process. Therefore, setting equal coefficients can reasonably reflect their relative importance to clamping adaptability; the influence of temperature on clamping adaptability is relatively small because although temperature can affect the physical properties of materials, its influence is usually not as direct and significant as humidity, diameter, and hardness. Therefore, the lowest weight is given to the temperature difference to reflect its secondary position in the adaptability evaluation.

[0078] ADAP is used to measure the suitability of the clamping force required for the branches of Camellia oleifera. The larger the ADAP, the more suitable it is to apply a larger clamping force to the branches of Camellia oleifera. Larger branch diameters usually require more clamping force to ensure stable clamping. Therefore, as the diameter D increases, it indicates that a higher clamping force correction is required, and the ADAP is also larger. The greater the branch hardness H, the greater the clamping force that the Camellia oleifera tree can withstand, and a larger clamping force can ensure stable clamping. Therefore, the greater the H, the more suitable it is to apply a larger clamping force to the Camellia oleifera tree, and the ADAP is also larger. When |T - T ref | increases, it means that the deviation between the ambient temperature and the ideal value increases, that is, it indicates that the ambient temperature is too cold or too hot. Under cold conditions, the surface of the Camellia oleifera tree will become brittle, and if the applied clamping force is too large, it will cause damage to the Camellia oleifera tree. Therefore, it is less suitable to apply a larger clamping force to the branches of Camellia oleifera, and the ADAP is also smaller. Similarly, under hot conditions, the surface of the Camellia oleifera tree will dry and dehydrate, and if the applied clamping force is too large, it will cause damage to the Camellia oleifera tree. Therefore, it is less suitable to apply a larger clamping force to the branches of Camellia oleifera, and the AD is also smaller; Branches with low hardness are easily compressed and deformed or damaged when subjected to clamping force, which will affect the health and subsequent growth of the tree. This may lead to branch breakage, peeling or other forms of physical damage. When the branch humidity is greater, it means that the moisture on the branch surface is greater, and it is more likely to have a sliding problem during clamping, resulting in unstable clamping. Therefore, to maintain stable clamping, it is more suitable to apply a larger clamping force to the Camellia oleifera tree, and the ADAP is also larger; That is to say, D, H, M are positively correlated with ADAP, and |T - T ref | is negatively correlated with ADAP.

[0079] Using the logarithmic form to process the non-linear relationship, slowing down the sharp change brought about by the increase in diameter D, making the response of the clamping adaptability index to the diameter smoother, and avoiding excessive exponential growth; The square form emphasizes the significant influence of branch hardness H on clamping stability. The square form makes the increase in adaptability index more obvious when the hardness increases, reflecting the weighted effect of hardness on clamping effect; The exponential form reflects the significance of branch humidity M on clamping adaptability. The increase in humidity will significantly improve the clamping ability, and the exponential form effectively amplifies this influence; The square root form smooths the influence of temperature difference on the adaptability index, avoiding excessive increase in the adaptability index when the temperature approaches the ideal value, and reasonably reflecting the role of ambient temperature on clamping effect.

[0080] The formula for generating the clamping stability index is as follows:

[0081]

[0082] Among them, STA is the clamping stability index, V is the clamping speed, θ is the clamping angle, θ refis the optimal clamping angle of the manipulator, P is the target distance, k5, k6, and k7 are preset proportionality coefficients, and k5 > k6 > k7 > 0. This is because a higher clamping speed may lead to unstable clamping. Especially during the process of contacting and clamping an object, a rapid clamping action may increase the risk of the object slipping or displacing. Therefore, the clamping speed has the most significant impact on clamping stability; the change in the clamping angle affects the distribution of the clamping force, thereby affecting clamping stability. Although the influence of the clamping angle is important, generally its influence on clamping stability is slightly weaker than that of the clamping speed, so it is given a medium weight; the greater the target distance, the greater the difficulty and uncertainty of clamping the object, but compared with the clamping speed and the clamping angle, its influence on stability is usually smaller. STA is used to measure the stability of the clamping process. The smaller STA is, the lower the clamping stability, and it is necessary to increase the clamping force to ensure clamping stability. When the clamping speed V increases, it may lead to an unsmooth clamping action, increasing the risk of the object slipping, thereby affecting the clamping stability and causing STA to decrease; a larger deviation angle may lead to uneven distribution of the clamping force, increasing the risk of clamping failure and reducing the clamping stability. Therefore, when |θ - θ ref | increases, STA will decrease; a farther target distance may lead to an increase in the uncertainty of clamping, increasing the clamping difficulty, thereby affecting the clamping stability. Therefore, when the target distance P increases, STA will decrease accordingly; that is to say, V, |θ - θ ref |, and P are negatively correlated with STA.

[0083] The influence of the clamping speed V on stability is an inverse proportional relationship. Therefore, using the square root form can smooth the influence of speed changes and avoid a sharp drop in stability caused by high speed; using the cube root form can effectively slow down the influence of the angle difference on stability, reflecting that small deviations can significantly improve stability while large deviations have less impact; the influence of the target distance P is non-linear, and using the logarithmic form can slow down the influence of distance on stability, ensuring that as the distance increases, the stability gradually decreases but at a slower rate.

[0084] The formula for calculating the clamping control index is as follows:

[0085]

[0086] Among them, CON is the clamping control index, ADAP is the clamping adaptability index, STA is the clamping stability index, D is the average diameter of the branch, e is the natural constant, μ is the adjustment coefficient used to adjust and balance the influence of other parameters, and μ ∈ [0.1, 2]. CON is used to correct the predicted clamping force output by the model. The larger CON is, the greater the clamping force needs to be increased based on the predicted clamping force to ensure clamping stability. A high clamping adaptability index indicates that the manipulator can better adjust its own clamping strategy under different clamping conditions, thus more effectively completing the clamping task. That is, when ADAP increases, CON will increase accordingly; higher stability means that it is not easy to slide or become unstable during the clamping process, enhancing the reliability of clamping, thereby improving the control ability. Therefore, the smaller STA is, the lower the clamping stability is, and the more the clamping force needs to be increased, and the greater CON will be; a larger branch diameter usually requires more clamping force to ensure firm clamping. Therefore, when D increases, CON will increase; that is, it shows that ADAP, D and CON are in a positive correlation, and STA and CON are in a negative correlation.

[0087] The advantage of step 2 is that by dimensionless processing the collected key parameters, the clamping adaptability index and the clamping stability index are generated, thus quantifying the multi-dimensional information required for clamping force correction. This method can comprehensively consider the mutual relationship between key parameters, ensure that the adjustment of the clamping force is more scientific and accurate. Especially in complex environments and diverse branch states, it can effectively avoid clamping force errors caused by fluctuations in a single parameter.

[0088] Compared with the prior art, the beneficial effect of step 2 is that it introduces two indexes of clamping adaptability and stability, making the control of the clamping force not only depend on simple fixed standards, but dynamically adjust based on real-time data. This innovation significantly improves the flexibility and adaptability of the manipulator in practical applications, reduces the risk of damage to the branches, and enhances the picking efficiency. In the solution of this application, adopting this step can provide a more refined control mechanism for the overall solution, thereby promoting the intelligence of the clamping force correction process and improving the accuracy and safety of oil tea tree picking.

[0089] Step 3: Build a deep learning model. Input the historical key parameters as the training set into the model, use the corresponding historical manipulator clamping force as the label, train the model to obtain a trained clamping force prediction model, input the key parameters collected in real time into the clamping force prediction model, and output the predicted clamping force;

[0090] In this embodiment, the process of building the deep learning model specifically includes:

[0091] Collect the historical key parameters of the clamping operations of n groups of manipulators and the corresponding clamping forces. The key parameters include the average diameter of the branches, branch hardness, branch humidity, target distance, clamping speed of the manipulator, clamping angle, and ambient temperature, and preprocess the collected data to remove outliers and missing values; construct a deep learning model, use the historical key parameters as the training set, and use the clamping force corresponding to each group of historical key parameters as the label to train the model to obtain a trained clamping force prediction model, and input the key parameters collected in real time into the clamping force prediction model to output the predicted clamping force for the current clamping operation of the manipulator.

[0092] When obtaining the historical key parameters and the corresponding clamping forces, obtain the key parameters and clamping forces under the conditions of stable clamping and no damage to the oil tea trees.

[0093] The advantage of step 3 is that by constructing a deep learning model, the historical key parameters are associated and learned with the corresponding clamping forces, so as to realize the intelligent prediction of the clamping force. This process enables the manipulator to quickly and accurately adjust the clamping force according to the data collected in real time to adapt to different branch characteristics and environmental conditions. This intelligent processing method significantly improves the accuracy and efficiency of clamping force correction and reduces the need for manual intervention.

[0094] Compared with the prior art, the beneficial effect of step 3 is that traditional methods often rely on experience or fixed parameters to adjust the clamping force, which is prone to errors or inadaptability. Through the training of the deep learning model, the best clamping force adjustment strategy can be automatically learned according to a large amount of historical data, thus improving the autonomous adaptation ability of the manipulator. This data-driven method makes the adjustment of the clamping force more flexible and accurate, and significantly reduces the risk of damage to the branches. In the solution of this application, adopting this step can provide higher-level intelligent support for the overall solution and realize the automation and optimization of the clamping force correction process. This not only improves the efficiency and safety of oil tea tree picking, but also lays a solid foundation for the future development of intelligent agriculture and promotes the process of agricultural mechanization and intelligentization.

[0095] Step 4: Combine the predicted clamping force with the clamping control index to obtain the corrected final clamping force;

[0096] In this embodiment, the predicted clamping force is combined with the clamping control index to obtain the corrected final clamping force, and the formula is as follows:

[0097] F corrected =F pred ted *(1 + k f *CON)

[0098] Where, F cprrected is the final clamping force, F ptedictedTo predict the clamping force, CON is the clamping control index, k f is the clamping force adjustment coefficient, k f The specific value is dynamically updated according to the clamping situation. Specifically, k is updated according to the actual situation of each clamping operation. f Update the value:

[0099] If the clamping is not stable, increase k f value, adjust it to the range of 0.3 to 0.5 to increase the final clamping force and ensure the stability of clamping;

[0100] If the tea tree has clamping damage, reduce k f value, adjust it to a value between 0.1 and 0.2 to reduce the final clamping force and reduce damage to the plants.

[0101] The advantage of step 4 is that the predicted clamping force is combined with the clamping control index to form the corrected final clamping force. This process makes effective use of real-time data, so that the clamping force can be flexibly adjusted according to specific operating conditions and environmental changes. This dynamic adjustment mechanism significantly improves the clamping accuracy of the manipulator, ensures that the optimal clamping force can be provided under different conditions, and reduces the risk of damage to the tea tree branches.

[0102] Compared with the prior art, the beneficial effects of step 4 are reflected in its comprehensiveness and adaptability. Traditional methods usually rely on fixed clamping force standards, which are often unable to cope with complex environments or changes in branch characteristics. By introducing the concept of clamping control index, the correction of the clamping force can take into account a variety of influencing factors, ensuring that the adjustment of the clamping force is more scientific and reasonable, and improving the performance and reliability of the manipulator in practical applications. In the present application scheme, the use of this step can provide a higher level of flexibility and intelligent support for the overall scheme, and promote the automation and refinement of the clamping force correction process. This not only improves the picking efficiency and safety of tea oil trees, but also provides a solid technical foundation for the promotion of manipulators in other agricultural applications, which helps to achieve a wider range of smart agricultural development.

[0103] The manipulator includes a base 1 for fixing, a driving device 3 connected to the base 1 via a connecting block 2, and a mechanical claw 4 for clamping an object to be clamped. The driving device 3 drives the mechanical claw 4 to clamp via a connecting rod 5, and the mechanical claw 4 has a plurality of contacts 6 on one side for clamping the object to be clamped.

[0104] See also Figure 4 , a clamping force correction system based on a tea tree branch clamping manipulator, comprising:

[0105] A data acquisition module is used to monitor and analyze the branches of camellia oleifera, the operating environment, and the motion state of the manipulator, and collect key parameters, including the average diameter of the branches, branch hardness, branch humidity, target distance, clamping speed of the manipulator, clamping angle, and environmental temperature;

[0106] An index calculation module is used to generate a clamping adaptability index based on the dimensionless average diameter, branch hardness, branch humidity, and environmental temperature; generate a clamping stability index based on the dimensionless target distance, clamping angle, and clamping speed, combine the clamping adaptability index and the clamping stability index, conduct a correlation analysis, and calculate a clamping control index;

[0107] A model construction module is used to construct a deep learning model, input historical key parameters as a training set into the model, use the corresponding historical manipulator clamping force as a label, train the model, obtain a trained clamping force prediction model, input the real-time collected key parameters into the clamping force prediction model, and output the predicted clamping force;

[0108] A force correction module is used to combine the predicted clamping force with the clamping control index to obtain the corrected final clamping force.

[0109] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0110] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0111] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0112] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered within the protection scope of this application.

Claims

1. A method for correcting the clamping force of a tea tree branch clamping manipulator, characterized in that: The specific steps include: Step 1: Monitor and analyze the tea tree branches, operating environment, and robot motion status, and collect key parameters, including the average diameter of the branches, branch hardness, branch humidity, target distance, robot gripping speed, gripping angle, and ambient temperature; Step 2: Generate a clamping adaptability index based on the dimensionless average diameter, branch hardness, branch humidity and ambient temperature; generate a clamping stability index based on the dimensionless target distance, clamping angle and clamping speed; combine the clamping adaptability index and the clamping stability index, perform correlation analysis and calculate the clamping control index; Step 3: Build a deep learning model, input the historical key parameters into the model as a training set, use the corresponding historical manipulator gripping force as a label, train the model, obtain a trained gripping force prediction model, input the key parameters collected in real time into the gripping force prediction model, and output the predicted gripping force; Step 4: Combine the predicted clamping force with the clamping control index to obtain the corrected final clamping force; The clamping adaptability index is generated based on the following formula: Among them, ADAP is the clamping adaptability index, D is the average diameter of the branch, H is the branch hardness, M is the branch humidity, T is the ambient temperature, and T ref is the ambient temperature under ideal conditions, e is a natural constant, k1, k2, k3 and k4 are preset proportional coefficients, and k3>k2=k1>k4>0; The clamping stability index is generated based on the following formula: Where STA is the clamping stability index, V is the clamping speed, θ is the clamping angle, and θ ref is the optimal gripping angle of the manipulator, P is the target distance, k5, k6 and k7 are preset proportional coefficients, and k5>k6>k7>0; The clamping control index is calculated based on the following formula: Among them, CON is the clamping control index, ADAP is the clamping adaptability index, STA is the clamping stability index, D is the average diameter of the branch, e is the natural constant, and μ is the adjustment coefficient, which is used to adjust and weigh the influence of other parameters, μ>0; The predicted clamping force is combined with the clamping control index to obtain the corrected final clamping force based on the following formula: F corrected =F predicted *(1+k f *CON) Among them, F corrected is the final clamping force, F predicted To predict the clamping force, CON is the clamping control index, k f is the clamping force adjustment coefficient, which is determined based on actual test data.

2. According to claim 1, a method for correcting the clamping force of a tea tree branch clamping manipulator is characterized in that: The specific logic for collecting key parameters is as follows: Use a laser rangefinder to measure the maximum and minimum diameters of the cross section of the branch to be clamped, and calculate the average diameter according to the following formula: Where D is the average diameter of the branches to be clamped, D max is the maximum diameter, D min is the minimum diameter; Use a Vickers hardness tester to obtain the hardness parameters of the branch: select the cross section of the branch to be tested, ensure that the surface is flat and dry, place the indenter of the Vickers hardness tester perpendicular to the cross section of the branch, and apply a certain test force. After unloading, use a microscope to measure the diagonal length of the indentation, calculate the Vickers hardness value of the branch according to the following formula, and use the Vickers hardness value as the branch hardness: Where H is the hardness of the branch, F is the applied test force, and d is the diagonal length of the indentation; The specific logic for obtaining the humidity of the branches is as follows: the branch to be tested is weighed by weighing method, then dried in an oven to constant weight, and weighed again. The humidity of the branch is calculated according to the following formula: Where M is the branch humidity, W wet is the mass of the branch in a wet state, W dry is the mass of the branch in dry state; The target distance refers to the actual distance between the manipulator and the target object, which is calculated according to the following formula: Where P is the target distance, (x target ,y target ,z target ) is the coordinate of the target object in three-dimensional space, (x init ,y init ,z init ) is the initial position coordinate of the manipulator in three-dimensional space; Using sensors, the clamping speed V and the clamping angle θ are acquired in real time, wherein the clamping angle refers to the angle between the manipulator and the horizontal plane during the clamping process; A temperature sensor is used to collect the ambient temperature of the manipulator when it is performing a clamping operation, denoted as T.

3. According to claim 1, a method for correcting the clamping force of a tea tree branch clamping manipulator is characterized in that: The process of building a deep learning model specifically includes: Collect n groups of historical key parameters and corresponding clamping forces of the manipulator's clamping operation, wherein the key parameters include the average diameter of the branch, the hardness of the branch, the humidity of the branch, the target distance, the clamping speed of the manipulator, the clamping angle and the ambient temperature, and preprocess the collected data to remove outliers and missing values. Build a deep learning model, use the historical key parameters as a training set, and use the clamping force corresponding to each group of historical key parameters as a label to train the model to obtain a trained clamping force prediction model, input the key parameters collected in real time into the clamping force prediction model, and output the predicted clamping force of the current manipulator performing the clamping operation.

4. A clamping force correction system based on a tea tree branch clamping manipulator, characterized in that: The clamping force correction system based on the oil-tea branch clamping manipulator is used to execute the clamping force correction method based on the oil-tea branch clamping manipulator according to any one of claims 1 to 3, comprising: The data acquisition module is used to monitor and analyze the tea tree branches, operating environment and robot motion status, and collect key parameters, including the average diameter of the branches, branch hardness, branch humidity, target distance, robot gripping speed, gripping angle and ambient temperature; The index calculation module is used to generate a clamping adaptability index according to the dimensionless average diameter, branch hardness, branch humidity and ambient temperature; generate a clamping stability index according to the dimensionless target distance, clamping angle and clamping speed, combine the clamping adaptability index and the clamping stability index, perform correlation analysis and calculate the clamping control index; The model building module is used to build a deep learning model, input the historical key parameters into the model as a training set, use the corresponding historical manipulator clamping force as a label, train the model, obtain a trained clamping force prediction model, input the key parameters collected in real time into the clamping force prediction model, and output the predicted clamping force; The force correction module is used to combine the predicted clamping force with the clamping control index to obtain a corrected final clamping force.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, it implements the clamping force correction method based on the oil-tea tree branch clamping robot as described in any one of claims 1 to 3.

Images