Temperature rise prediction method and device, equipment and storage medium
By collecting the current and speed of the robot joint motors and using inter-joint temperature compensation to correct the preliminary temperature rise prediction model, the problem of low temperature prediction accuracy caused by the mutual influence between robot joints is solved, and higher accuracy single-joint reducer temperature prediction is achieved.
Patent Information
- Application Number
- CN202311615461.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-11-28
- Publication Date
- 2026-03-03
- Estimated Expiration
- 2043-11-28
AI Technical Summary
In existing technologies, the joints of a robot affect each other during operation, and temperature prediction can only be performed on a single joint, which reduces the accuracy of predicting the temperature of a single joint reducer.
The current current of the motors at each joint of the robot and the current input speed of the joint reducer are collected to determine the target joint whose temperature needs to be predicted. The preliminary temperature rise prediction model corresponding to the target joint is then corrected through temperature compensation between joints to obtain a preset temperature rise prediction model, thereby improving the accuracy of temperature prediction.
By correcting the temperature between joints, the accuracy of temperature prediction for single-joint reducers is improved, and temperature errors caused by heat transfer are reduced.
Smart Images
Figure CN117574023B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of robotics technology, and in particular to a method, apparatus, device, and storage medium for predicting temperature rise. Background Technology
[0002] With the rapid development of robotics technology, industrial robots have been widely used in various fields. As some fields have increasingly higher requirements for the working cycle and load capacity of robots, the temperature of the robot joint reducer will rise, thus shortening the service life of the joint reducer.
[0003] To ensure the lifespan of a robot, it is necessary to monitor or predict the temperature of the robot's joint reducers in order to cool the robot joints in a timely manner and extend the robot's lifespan. Currently, the commonly used method for temperature monitoring or prediction is to use temperature rise models to predict the reducer temperature. However, the mechanism of robot joints is quite complex, and the joints affect each other during robot operation. This type of method can only predict the temperature of a single joint, which reduces the accuracy of predicting the temperature of a single joint reducer. Summary of the Invention
[0004] The main objective of this application is to provide a temperature rise prediction method, device, equipment, and storage medium, aiming to solve the technical problem in the prior art where the joints of a robot affect each other during operation, and temperature prediction can only be performed on a single joint, which reduces the accuracy of predicting the temperature of a single joint reducer.
[0005] To achieve the above objectives, this application provides a temperature rise prediction method, the temperature rise prediction method comprising:
[0006] Collect the current current of the motors at each joint of the robot and the current input speed of the joint reducer;
[0007] Identify the target joint whose temperature needs to be predicted, and the preset temperature rise prediction model corresponding to the target joint. The preset temperature rise prediction model is obtained by correcting the preliminary temperature rise prediction model corresponding to the target joint through temperature compensation between joints. The preliminary temperature rise prediction model uses the current of the joint motor and the input speed of the joint reducer in the robot as model parameters to predict the temperature of the joint reducer.
[0008] The preliminary temperature rise prediction model uses the current of the joint motors and the input speed of the joint reducer in the robot as model parameters to predict the temperature of the joint reducer.
[0009] Optionally, before the step of collecting the current current of each joint motor of the robot and the current input speed of the joint reducer, the method further includes:
[0010] Obtain the preliminary temperature rise prediction model corresponding to the joint to be corrected of the robot;
[0011] Collect the actual temperature of the joint to be corrected when other joints besides the joint to be corrected move individually under preset operating conditions;
[0012] Based on the actual temperature and the preliminary temperature rise prediction model, the temperature compensation of the joint to be corrected is obtained when the other joints move alone under the preset operating conditions.
[0013] By correcting the initial temperature rise prediction model through temperature compensation, a preset temperature rise prediction model corresponding to the joint to be corrected is obtained.
[0014] Return to the step of obtaining the preliminary temperature rise prediction model corresponding to the joint to be corrected in the robot, until the preliminary temperature rise prediction model corresponding to the joint to be corrected in the robot is corrected.
[0015] Optionally, the step of obtaining the temperature compensation of the joint to be corrected when the other joints move independently under the preset operating conditions based on the actual temperature and the preliminary temperature rise prediction model includes:
[0016] Based on the preliminary temperature rise prediction model, when the other joints move independently under the preset operating conditions, the transmitted temperature of the joint to be corrected and the predicted temperature rise of the other joints are predicted.
[0017] Based on the actual temperature, the transmission temperature, and the predicted temperature rise, determine the unit temperature rise compensation amount for the joint to be corrected when the other joints move independently under the preset operating conditions;
[0018] Based on the unit temperature rise compensation amount and the steady-state predicted temperature rise of the corresponding other joints, the temperature compensation of the other joints for the joint to be corrected is determined.
[0019] Optionally, the step of determining the temperature compensation of the other joints for the joint to be corrected based on the unit temperature rise compensation amount and the steady-state predicted temperature rise of the corresponding other joints includes:
[0020] The target compensation amount is determined from the unit temperature rise compensation amount, and the target compensation amount is the unit temperature rise compensation amount corresponding to the target operating condition with the highest actual temperature.
[0021] Based on the target compensation amount and the corresponding steady-state predicted temperature rise of the other joints, the temperature compensation of the other joints for the joint to be corrected is determined.
[0022] Optionally, the step of determining the unit temperature rise compensation amount for the joint to be corrected when the other joints move independently under the preset operating conditions, based on the actual temperature, the transmission temperature, and the predicted temperature rise, includes:
[0023] Based on the actual temperature and the transmitted temperature, determine the temperature error of the other joints that affects the joint to be corrected when they are running alone;
[0024] Based on the aforementioned temperature error and the corresponding predicted temperature rise, the unit temperature rise compensation amount for the joint to be corrected is determined when the other joints move independently under preset operating conditions.
[0025] Optionally, before the step of obtaining the preliminary temperature rise prediction model corresponding to the joint to be corrected of the robot, the method further includes:
[0026] The current of the joint motor and the input speed of the joint reducer are used as the input of the preset model, and the steady-state temperature rise of the joint reducer is used as the output of the preset model to establish a temperature rise prediction model to be trained.
[0027] The sample current of the joint motor, the sample rotational speed of the joint reducer, and the sample temperature rise of the joint reducer are obtained.
[0028] The preliminary temperature rise prediction model is obtained by training the temperature rise prediction model based on the sample current, the sample rotation speed, and the sample temperature rise.
[0029] Optionally, the step of obtaining the sample current of the joint motor, the sample rotational speed of the joint reducer, and the sample temperature rise of the joint reducer includes:
[0030] Obtain preset operating conditions for the robot joints, the preset operating conditions being set based on the joint stroke, operating speed, and end effector load of the robot joints;
[0031] When the robot joints are running independently according to the preset operating conditions, the sample current of the joint motor, the sample rotational speed of the joint reducer, and the sample temperature rise of the joint reducer are collected.
[0032] Furthermore, to achieve the above objectives, this application also provides a temperature rise prediction device, which includes:
[0033] The first acquisition module is used to acquire the current current of the motors of each joint of the robot and the current input speed of the joint reducer;
[0034] The determination module is used to determine the target joint whose temperature needs to be predicted, and the preset temperature rise prediction model corresponding to the target joint. The preset temperature rise prediction model is obtained by correcting the preliminary temperature rise prediction model corresponding to the target joint through temperature compensation between joints. The preliminary temperature rise prediction model uses the current of the joint motor and the input speed of the joint reducer in the robot as model parameters to predict the temperature of the joint reducer.
[0035] The preliminary temperature rise prediction model uses the current of the joint motors and the input speed of the joint reducer in the robot as model parameters to predict the temperature of the joint reducer.
[0036] In addition, to achieve the above objectives, this application also proposes a temperature rise prediction device, the device comprising: a memory, a processor, and a temperature rise prediction program stored in the memory and executable on the processor, the temperature rise prediction program being configured to implement the steps of the temperature rise prediction method as described above.
[0037] In addition, to achieve the above objectives, this application also proposes a storage medium storing a temperature rise prediction program, which, when executed by a processor, implements the steps of the temperature rise prediction method as described above.
[0038] This application provides a temperature rise prediction method, apparatus, device, and storage medium. Compared with the prior art where the joints of a robot interact during operation, allowing only single-joint temperature prediction and reducing the accuracy of predicting the temperature of a single joint reducer, this application collects the current current of the motors of each joint of the robot and the current input speed of the joint reducer; determines the target joint whose temperature needs to be predicted, and the preset temperature rise prediction model corresponding to the target joint. The preset temperature rise prediction model is obtained by correcting the preliminary temperature rise prediction model corresponding to the target joint through temperature compensation between joints. The preliminary temperature rise prediction model uses the current of the joint motors and the input speed of the joint reducer in the robot as model parameters to predict the temperature of the joint reducer. In this application, the current current of the motors of each joint of the robot and the current input speed of the joint reducer are collected, the target joint whose temperature needs to be predicted is determined, and the preset temperature rise prediction model corresponding to the target joint is determined. Since the preset temperature rise prediction model is obtained by correcting the preliminary temperature rise prediction model corresponding to the target joint through temperature compensation between joints, the predicted temperature of the target joint obtained by the preset temperature rise prediction model based on the current current and the current input speed includes the compensation temperature of the influence of each joint of the robot on the target joint. Therefore, the accuracy of predicting the temperature of a single joint reducer can be improved. Attached Figure Description
[0039] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0040] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0041] Figure 1 This is a schematic diagram of the temperature rise prediction device mechanism for the hardware operating environment involved in the embodiments of this application;
[0042] Figure 2 This is a flowchart illustrating the first embodiment of the temperature rise prediction method of this application;
[0043] Figure 3 This is a flowchart illustrating the second embodiment of the temperature rise prediction method of this application;
[0044] Figure 4 This is a flowchart illustrating the third embodiment of the temperature rise prediction method of this application;
[0045] Figure 5 This is a schematic diagram of the process for obtaining the preset temperature rise prediction model in the temperature rise prediction method of this application;
[0046] Figure 6 This is a schematic diagram of the sample data collection process in the temperature rise prediction method of this application;
[0047] Figure 7 This is a schematic diagram of the structural configuration of the temperature rise prediction device of this application.
[0048] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0049] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.
[0050] Reference Figure 1 , Figure 1 This is a schematic diagram of the temperature rise prediction device for the hardware operating environment involved in the embodiments of this application.
[0051] like Figure 1As shown, the temperature rise prediction device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.
[0052] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the temperature rise prediction device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.
[0053] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a temperature rise prediction program.
[0054] exist Figure 1 In the temperature rise prediction device shown, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the temperature rise prediction device of this application can be set in the temperature rise prediction device, and the temperature rise prediction device calls the temperature rise prediction program stored in the memory 1005 through the processor 1001 and executes the temperature rise prediction method provided in the embodiment of this application.
[0055] This application provides a method for predicting temperature rise, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of a temperature rise prediction method according to this application.
[0056] It should be noted that the execution subject of this embodiment can be the temperature rise prediction device, which can be a personal computer, smartphone, tablet computer or other electronic device, or other devices that can achieve the same or similar functions. This embodiment does not limit this. In this embodiment and the following embodiments, the temperature rise prediction device is used as an example to illustrate the temperature rise prediction method of this application.
[0057] In this embodiment, the temperature rise prediction method includes:
[0058] Step S10: Collect the current current of the motors of each joint of the robot and the current input speed of the joint reducer.
[0059] The robot can be an industrial robot, a robotic arm, a service robot, or any other robot used in various fields; there are no specific limitations.
[0060] It should be noted that when a robot is working, multiple joints often move together. Since heat can be transferred between the robot's joints, when predicting the temperature at the joint reducer, it is necessary not only to predict the temperature of the heat generated by the joint itself, but also to predict the heat conducted to the joint by other joints. That is, the influence value of the other joints on the joint temperature is used as a compensation value for the predicted temperature of the joint, so as to reduce the prediction error of the joint temperature and improve the prediction accuracy.
[0061] In practical implementation, to predict the compensation value of the other joints for the impact on the temperature of the target joint, it is necessary to collect the current current of the robot's joint motors and the current input speed of the joint reducers. A preset temperature rise prediction model is then used to predict the temperature of the target joint based on the current current and current input speed. Here, the joint motors are the drive devices for each joint of the robot, and the joint reducers are the transmission mechanisms that decelerate the joints.
[0062] Step S20: Determine the target joint whose temperature needs to be predicted, and the preset temperature rise prediction model corresponding to the target joint. The preset temperature rise prediction model is obtained by correcting the preliminary temperature rise prediction model corresponding to the target joint through temperature compensation between joints. The preliminary temperature rise prediction model uses the current of the joint motor and the input speed of the joint reducer in the robot as model parameters to predict the temperature of the joint reducer.
[0063] It should be noted that because the degree of temperature influence varies among the joints, the preset temperature rise prediction model used for temperature prediction also differs for each joint. That is, each joint corresponds to a preset temperature rise prediction model. After determining the target joint whose temperature needs to be predicted, it is also necessary to determine the corresponding preset temperature rise prediction model for that target joint to ensure the accuracy of the preset temperature rise prediction model's compensation temperature prediction for the target joint. In other words, selecting the appropriate preset temperature rise prediction model based on different target joints can effectively reduce the influence of other joints on the target joint, thereby improving the prediction accuracy of the target joint's temperature.
[0064] The target joint for determining the predicted temperature can be determined based on user-input instructions, or it can be determined based on the sequence of joint reducers in the monitoring robot, etc., without any specific limitation.
[0065] The preliminary temperature rise prediction model uses the current of the joint motors and the input speed of the joint reducer in the robot as model parameters to predict the temperature of the joint reducer.
[0066] It should be noted that the current current and the current input speed are input into the preset temperature rise prediction model. The preset temperature rise model is used to predict the temperature of the heat generated by the target joint itself, and to predict the compensation temperature of the heat transferred from the other joints to the target joint. The compensation temperature is added to the target joint to obtain the predicted temperature. Therefore, the temperature error caused by heat transfer between joints is reduced and the accuracy of predicting the temperature of the joint reducer is improved.
[0067] It should be noted that the preset temperature rise prediction model is obtained by correcting the initial temperature rise prediction model corresponding to the target joint through temperature compensation correction between joints. This allows the preset temperature rise prediction model to use the temperature error compensation of the other joints on the target joint to predict the temperature of the target joint separately when predicting the temperature of the target joint, thereby improving the prediction accuracy of the joint reducer temperature.
[0068] Optionally, the preliminary temperature rise prediction model can be established based on the current of the joint motor and the input speed of the joint reducer in the robot as the parameter variables of the model, and is used to predict the temperature of the joint reducer. Compared with the existing prediction model, it reduces the detailed thermal parameters of each component inside the joint, thereby reducing the complexity of the preliminary temperature rise model, reducing the network resources required to use the preliminary temperature rise prediction model, and thus improving the real-time performance of the predicted temperature.
[0069] In the specific implementation, the current current and the current input speed are input into a preset temperature rise prediction model. The preset temperature rise prediction model predicts the temperature of the heat generated at the target joint and the temperature of the heat transferred from other joints to the target joint. This temperature is used as a compensation temperature to correct the temperature of the target joint, so as to accurately obtain the predicted temperature of the target joint. The predicted temperature of the target joint is obtained by using the current current of the joint motor that drives the target joint and the current input speed of the joint reducer that drives the target joint. This can reduce the calculation load of the preset temperature rise prediction model, speed up the prediction rate of the preset temperature rise prediction model, and improve the real-time performance of temperature prediction using the preset temperature rise prediction model.
[0070] This embodiment provides a temperature rise prediction method. Compared with the prior art, where the joints of a robot influence each other during operation, only single-joint temperature prediction is possible, reducing the accuracy of predicting the temperature of a single joint reducer, this application collects the current current of the motors of each joint of the robot and the current input speed of the joint reducer; determines the target joint whose temperature needs to be predicted, and the preset temperature rise prediction model corresponding to the target joint. The preset temperature rise prediction model is obtained by correcting the preliminary temperature rise prediction model corresponding to the target joint through temperature compensation between joints. The preliminary temperature rise prediction model uses the current of the joint motors and the input speed of the joint reducer in the robot as model parameters to predict the temperature of the joint reducer. In this application, the current current of the motors of each joint of the robot and the current input speed of the joint reducer are collected, the target joint whose temperature needs to be predicted is determined, and the preset temperature rise prediction model corresponding to the target joint is determined. Since the preset temperature rise prediction model is obtained by correcting the preliminary temperature rise prediction model corresponding to the target joint through temperature compensation between joints, the predicted temperature of the target joint obtained by the preset temperature rise prediction model based on the current current and the current input speed includes the compensation temperature of the influence of each joint of the robot on the target joint. Therefore, the accuracy of predicting the temperature of a single joint reducer can be improved.
[0071] refer to Figure 3 , Figure 3 This is a flowchart illustrating the second embodiment of the temperature rise prediction method of this application.
[0072] Based on the above embodiments, in this embodiment, in order to obtain a preset temperature rise prediction model for each joint of the robot in advance, so as to ensure that after determining the target joint, the preset temperature rise prediction model corresponding to the target joint can be directly obtained, the following is included before step S10:
[0073] Step S01: Obtain the preliminary temperature rise prediction model corresponding to the joint to be corrected of the robot;
[0074] Step S02: Collect the actual temperature of the joint to be corrected when other joints besides the joint to be corrected move individually under preset operating conditions;
[0075] Step S03: Based on the actual temperature and the preliminary temperature rise prediction model, obtain the temperature compensation of the joint to be corrected when the other joints move alone under the preset operating conditions;
[0076] Step S04: Correct the preliminary temperature rise prediction model through temperature compensation to obtain the preset temperature rise prediction model corresponding to the joint to be corrected;
[0077] Step S05: Return to the step of obtaining the preliminary temperature rise prediction model corresponding to the joint to be corrected in the robot, until the preliminary temperature rise prediction model corresponding to the joint to be corrected in the robot is corrected.
[0078] It should be noted that since the robot's joints generate heat during movement, and there is thermal coupling between the joints, that is, heat transfer between the joints causes the actual temperature of the joint that needs correction to be higher than the temperature at which it generates heat. Moreover, the effects on each joint are different. In order to make the temperature compensation of each joint more accurate and avoid compensation misalignment, it is necessary to compensate and correct the preliminary temperature rise prediction model corresponding to each joint in the robot one by one. Therefore, the joints corresponding to the preliminary temperature rise prediction models that need to be compensated and corrected can be marked as joints to be corrected, and the joints in the robot other than those to be corrected can be marked as other joints, so as to facilitate the correction of the preliminary temperature rise preset models of each joint.
[0079] It should be noted that since the operating conditions of the robot are different, the temperature of the joints is also affected differently. Therefore, it is necessary to collect the actual temperature of the joint to be corrected under the preset operating conditions of other joints. This can minimize the influence between joints and obtain the influence of other joints when they run alone, so as to reduce the error of temperature compensation.
[0080] In the specific implementation, the first joint to be corrected is identified from the robot's joints, and the other joints are marked as other joints. The preliminary temperature rise prediction model corresponding to the joint to be corrected is obtained, and the actual temperature of the joint to be corrected is collected when the other joints run alone under preset working conditions. The preliminary temperature rise prediction model is used to predict the remaining temperature data for determining the temperature compensation of the joint to be corrected. Using this temperature data and the actual temperature, the temperature compensation of the joint to be corrected when the other joints move alone under preset working conditions is determined. The preliminary temperature rise prediction model is corrected by the temperature compensation of the joint to be corrected, and the preset temperature rise prediction model corresponding to the joint to be corrected is obtained. Then, a joint other than the joint to be corrected is identified from the robot's joints as the second joint to be corrected, and the preliminary temperature rise prediction model of the second joint to be corrected is corrected, until the preliminary temperature rise prediction models corresponding to all joints in the robot are corrected.
[0081] For example, if a robot has N joints, the nth joint is marked as the joint to be corrected. The temperature compensation of the nth joint is determined based on the actual temperature of the nth joint when the kth joint is moved alone and the corresponding preliminary temperature rise prediction model. The temperature compensation of the nth joint for all other joints is obtained in sequence. The steady-state predicted temperature rise algorithm in the preliminary temperature rise prediction model is corrected with this temperature compensation to obtain the algorithm of the preset temperature rise prediction model.
[0082] The algorithm for the preset temperature rise prediction model can be described as follows:
[0083]
[0084] in, The steady-state predicted temperature rise for the nth joint is the temperature at which the temperature rises to its maximum and stabilizes. The steady-state predicted temperature rise for the k-th joint is given, where p has no specific meaning. For the k-th joint of a single-action motor, the unit temperature rise compensation of the reducer for the n-th joint is given, where c has no specific meaning, i.e., This can be understood as temperature compensation for the nth joint when the kth joint is moved alone.
[0085] The formula for calculating the unit temperature rise compensation is as follows:
[0086]
[0087] Among them, record When the joint is a single-moving joint n, the predicted temperature of the reducer of joint k is; When n is a single-moving joint, the actual temperature of the reducer of joint k is given, where r has no specific meaning. The steady-state temperature rise of joint k is predicted.
[0088] Optionally, the step of obtaining the temperature compensation of the joint to be corrected when the other joints move independently under the preset operating conditions based on the actual temperature and the preliminary temperature rise prediction model includes:
[0089] Step S031: Based on the preliminary temperature rise prediction model, predict the transmission temperature of the joint to be corrected and the predicted temperature rise of the other joints when they move alone under the preset operating conditions;
[0090] Step S032: Based on the actual temperature, the transmission temperature and the predicted temperature rise, determine the unit temperature rise compensation amount for the joint to be corrected when the other joints move alone under the preset operating conditions;
[0091] Step S033: Based on the unit temperature rise compensation amount and the steady-state predicted temperature rise of the corresponding other joints, determine the temperature compensation of the other joints for the joint to be corrected.
[0092] It should be noted that, based on the preliminary temperature rise prediction model, the transfer temperature of the joint to be corrected and the predicted temperature rise of other joints are predicted when the other joints move alone under the preset operating conditions. By using the transfer temperature and the actual temperature, the temperature rise at the joint to be corrected due to heat transfer between the other joints and the joint to be corrected is determined. Then, by using the predicted temperature and the temperature rise, the unit temperature rise compensation amount of the joint to be corrected is determined when the other joints move alone under the preset operating conditions.
[0093] In the specific implementation, the preliminary temperature rise prediction model is used to predict the transmission temperature of the joint to be corrected when each other joint operates alone under the preset operating conditions, and the predicted temperature of the other joints is obtained. Based on the transmission temperature, predicted temperature and actual temperature, the unit temperature rise compensation amount of each other joint moving alone under the preset operating conditions is determined. The unit temperature rise compensation amount is multiplied by the steady-state predicted temperature rise of the corresponding other joints to determine the temperature compensation of the other joints for the joint to be corrected.
[0094] Optionally, the step of determining the temperature compensation of the other joints for the joint to be corrected based on the unit temperature rise compensation amount and the steady-state predicted temperature rise of the corresponding other joints includes:
[0095] Step S0331: Determine the target compensation amount from the unit temperature rise compensation amount, wherein the target compensation amount is the unit temperature rise compensation amount corresponding to the target operating condition with the highest actual temperature.
[0096] Step S0332: Based on the target compensation amount and the steady-state predicted temperature rise of the other joints, determine the temperature compensation of the other joints for the joint to be corrected.
[0097] It should be noted that, since the obtained unit temperature rise compensation corresponds to each preset operating condition, in order to reduce the amount of calculation, the unit temperature rise compensation under all preset operating conditions can be generalized to obtain a target temperature rise compensation that can characterize all operating conditions. Based on the target compensation and the steady-state predicted temperature rise of the corresponding other joints, the temperature compensation of the other joints for the correction joint can be determined, thereby reducing the amount of calculation of the preset temperature rise prediction model and improving the real-time performance of the prediction.
[0098] In practice, the target compensation amount can be determined from the unit temperature rise compensation amount based on the actual temperature level, corresponding to the highest actual temperature.
[0099] Further, the step of determining the unit temperature rise compensation amount for the joint to be corrected when the other joints move independently under the preset operating conditions, based on the actual temperature, the transmission temperature, and the predicted temperature rise, includes:
[0100] Step S0321: Based on the actual temperature and the transmitted temperature, determine the influence temperature error transmitted to the joint to be corrected when the other joints are running alone;
[0101] Step S0322: Based on the temperature error and the corresponding predicted temperature rise, determine the unit temperature rise compensation amount for the joint to be corrected when the other joints move alone under the preset operating conditions.
[0102] It should be noted that, since the heat at the joint to be corrected is transferred from the other joints when they move individually, the difference between the actual temperature and the transferred temperature at the joint to be corrected can be used to determine the error in the predicted influence of other joints on the joint to be corrected. This yields the temperature error of the influence transmitted to the joint to be corrected when other joints operate alone. This temperature error is then divided by the predicted temperature rise to determine the unit temperature rise compensation amount for the joint to be corrected when other joints move alone under the preset operating conditions. By calculating the error in the temperature influence, the temperature error of the influence transmitted to the joint to be corrected when other joints operate alone can be obtained, thereby improving the correction accuracy of the initial temperature rise prediction model and ultimately improving the prediction accuracy of the preset temperature rise prediction model.
[0103] refer to Figure 4 , Figure 4 This is a flowchart illustrating the third embodiment of the temperature rise prediction method of this application.
[0104] Based on the above embodiments, in this embodiment, a trained preliminary temperature rise prediction model needs to be obtained before modifying the preliminary temperature rise prediction model. Therefore, before step S01, the following steps are also included:
[0105] Step S1: Use the current of the joint motor and the input speed of the joint reducer as the input of the preset model, and the steady-state temperature rise of the joint reducer as the output of the preset model to establish a temperature rise prediction model to be trained.
[0106] Step S2: Obtain the sample current of the joint motor, the sample rotation speed of the joint reducer, and the sample temperature rise of the joint reducer;
[0107] Step S3: Based on the sample current, the sample rotation speed, and the sample temperature rise, train the temperature rise prediction model to be trained to obtain the preliminary temperature rise prediction model.
[0108] It should be noted that, in order to reduce the computational load of the entire model, and because the regression model has predictive capabilities, the regression model can be used as the base model, and the algorithm in the regression model can be modified. That is, the current of the joint motor and the input speed of the joint reducer are used as the input of the preset model, and the steady-state temperature rise of the joint reducer is used as the output of the preset model to establish a temperature rise prediction model to be trained, so as to reduce the computational load of the model.
[0109] The algorithm for the temperature rise prediction model to be trained can be:
[0110]
[0111] Where, θ p For the steady-state temperature rise prediction of the joint reducer, I q is the q-axis current of the permanent magnet synchronous motor, w is the input speed of the reducer, and a1, a2, b2, b1, and c are the parameters of the temperature rise prediction model to be trained.
[0112] It should be noted that, in order to improve the accuracy of the preliminary temperature rise prediction model, it is necessary to obtain the sample current of the joint motor, the sample speed of the joint reducer, and the sample temperature rise of the joint reducer. The sample current, sample speed, and sample temperature rise are used to train the temperature rise prediction model to be trained. After multiple training sessions, the prediction results are made to reach the preset accuracy. Then, the parameters a1, a2, b2, b1, and c of the temperature rise prediction model to be trained are determined to ensure the accuracy of the preliminary temperature rise prediction model.
[0113] In the specific implementation, if for each joint n, there are M sets of operating condition data, each set of data includes sample current, sample rotation speed, and sample temperature rise. Using the sample current and sample rotation speed of each set of data as input and the sample temperature rise as output, the temperature rise prediction regression model is trained until the error between the predicted steady-state temperature rise and the sample temperature rise is within the preset acceptable error, and the parameters a1, a2, b2, b1, and c are obtained.
[0114] In the specific implementation, refer to Figure 5First, the current of the joint motor and the input speed of the joint reducer are used as inputs to a preset model, and the steady-state temperature rise of the joint reducer is used as the output of the preset model to establish a temperature rise prediction model to be trained (joint reducer temperature rise prediction model). Then, sample currents of the joint motor, sample speeds of the joint reducer, and sample temperature rises of the joint reducer are collected under each preset operating condition. The temperature rise prediction model to be trained is trained using these sample currents, sample speeds, and sample temperature rises (data processing and model identification) to obtain a preliminary temperature rise prediction model with current and input speed as inputs and steady-state temperature rise as output. Then, the thermal coupling between joints is used as a correction condition to determine the temperature compensation between each joint, so as to use the temperature compensation to correct the preliminary temperature rise prediction model to obtain the final temperature rise model of the joint reducer (preset temperature rise prediction model).
[0115] Further, the step of obtaining the sample current of the joint motor, the sample rotational speed of the joint reducer, and the sample temperature rise of the joint reducer includes:
[0116] Step S201: Obtain the preset operating conditions of the robot joint, wherein the preset operating conditions are set based on the joint stroke, running speed and end effector load of the robot joint;
[0117] Step S202: Collect sample current of the joint motor, sample rotational speed of the joint reducer, and sample temperature rise of the joint reducer when the robot joint is running alone according to the preset operating conditions.
[0118] It should be noted that, in order to make the preliminary temperature rise prediction samples applicable to various working conditions, preset operating conditions of the robot joints can be obtained. These preset operating conditions are set by the joint stroke, running speed, and end-effector load of the robot joints. Sample current, sample rotation speed, and sample temperature rise are collected when the robot joints run individually according to the preset operating conditions. The sample current, sample rotation speed, and sample temperature rise obtained from each preset operating condition are used to train the temperature rise prediction model, so that the preliminary temperature rise prediction model can adapt to various working conditions.
[0119] In the specific implementation, refer to Figure 6For an N-joint robot, each of the N joints is individually moved, and each joint runs through M sets of operating conditions. Simultaneously, sample temperature rise, sample current, and sample rotational speed of the N joint reducers are collected. For example, joint J1 runs alone, performing M sets of operating conditions, and then sample temperature rise, sample current, and sample rotational speed of the N joints under each set of conditions are collected. Then, joint J2 runs alone, performing M sets of operating conditions, and sample temperature rise, sample current, and sample rotational speed of the N joints under each set of conditions are collected, and so on, until joint JN runs alone, performing M sets of operating conditions, and sample temperature rise, sample current, and sample rotational speed of the N joints under each set of conditions. Individual joint movement (joint running independently) can be achieved by adjusting the robot's posture while moving joint n, minimizing the current of other joints.
[0120] This application also provides a temperature rise prediction device, referencing... Figure 7 The temperature rise prediction device includes:
[0121] The first acquisition module 701 is used to acquire the current current of the motors of each joint of the robot and the current input speed of the joint reducer;
[0122] The determination module 702 is used to determine the target joint whose temperature needs to be predicted, and the preset temperature rise prediction model corresponding to the target joint. The preset temperature rise prediction model is obtained by correcting the preliminary temperature rise prediction model corresponding to the target joint through temperature compensation between joints. The preliminary temperature rise prediction model uses the current of the joint motor and the input speed of the joint reducer in the robot as model parameters to predict the temperature of the joint reducer.
[0123] The preliminary temperature rise prediction model uses the current of the joint motors and the input speed of the joint reducer in the robot as model parameters to predict the temperature of the joint reducer.
[0124] Optionally, the temperature rise prediction device further includes:
[0125] The acquisition module 703 is used to acquire the preliminary temperature rise prediction model corresponding to the joint to be corrected of the robot;
[0126] The second acquisition module 704 is used to acquire the actual temperature of the joint to be corrected when other joints besides the joint to be corrected move individually under preset operating conditions.
[0127] Data processing module 705 is used to obtain the temperature compensation of the joint to be corrected when the other joints move alone under the preset operating conditions, based on the actual temperature and the preliminary temperature rise prediction model.
[0128] Correction module 706 is used to correct the preliminary temperature rise prediction model through the temperature compensation to obtain the preset temperature rise prediction model corresponding to the joint to be corrected;
[0129] The loop module 707 is used to return to the step of obtaining the preliminary temperature rise prediction model corresponding to the joint to be corrected in the robot, until the preliminary temperature rise prediction model corresponding to the joint to be corrected in the robot is corrected.
[0130] Optionally, the data processing module 705 is further configured to predict, based on the preliminary temperature rise prediction model, the transmission temperature of the joint to be corrected and the predicted temperature rise of the other joints when they move alone under the preset operating conditions; determine, based on the actual temperature, the transmission temperature and the predicted temperature rise, the unit temperature rise compensation amount of the other joints to the joint to be corrected when they move alone under the preset operating conditions; and determine, based on the unit temperature rise compensation amount and the corresponding steady-state predicted temperature rise of the other joints, the temperature compensation of the other joints to the joint to be corrected.
[0131] Optionally, the data processing module 705 is further configured to determine a target compensation amount from the unit temperature rise compensation amount, wherein the target compensation amount is the unit temperature rise compensation amount corresponding to the target operating condition with the highest actual temperature; and based on the target compensation amount and the steady-state predicted temperature rise of the corresponding other joints, determine the temperature compensation of the other joints for the joint to be corrected.
[0132] Optionally, the data processing module 705 is further configured to determine the influence temperature error transmitted to the joint to be corrected when the other joints operate alone, based on the actual temperature and the transmitted temperature; and to determine the unit temperature rise compensation amount for the joint to be corrected when the other joints move alone under preset operating conditions, based on the influence temperature error and the corresponding predicted temperature rise.
[0133] Optionally, the acquisition module 703 is further configured to use the current of the joint motor and the input speed of the joint reducer as inputs to a preset model, and the steady-state temperature rise of the joint reducer as outputs of the preset model, to establish a temperature rise prediction model to be trained; acquire sample current of the joint motor, sample speed of the joint reducer, and sample temperature rise of the joint reducer; train the temperature rise prediction model to be trained based on the sample current, sample speed, and sample temperature rise to obtain the preliminary temperature rise prediction model.
[0134] Optionally, the acquisition module 703 is further configured to acquire preset operating conditions of the robot joint, the preset operating conditions being set based on the joint stroke, running speed, and end-effector load of the robot joint; and to collect sample current of the joint motor, sample rotational speed of the joint reducer, and sample temperature rise of the joint reducer when the robot joint is running alone according to the preset operating conditions.
[0135] The specific implementation of the temperature rise prediction device in this application is basically the same as the embodiments of the temperature rise prediction method described above, and will not be repeated here.
[0136] This application provides a storage medium that stores one or more programs, which can be executed by one or more processors to implement the steps of the temperature rise prediction method described above.
[0137] The specific implementation of the storage medium in this application is basically the same as the embodiments of the temperature rise prediction method described above, and will not be repeated here.
[0138] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one, etc." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0139] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0140] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods of the various embodiments of this application.
[0141] The above are merely preferred embodiments of this application and do not limit the scope of this patent application. Any equivalent structural or procedural changes made based on the description and drawings of this application, or any direct or indirect application in other related technical fields, are similarly included within the scope of patent protection of this application.
Claims
1. A method for predicting temperature rise, characterized in that, The temperature rise prediction method includes: Collect the current current of the motors at each joint of the robot and the current input speed of the joint reducer; A target joint whose temperature needs to be predicted is identified, along with a preset temperature rise prediction model corresponding to the target joint. The preset temperature rise prediction model is obtained by correcting the initial temperature rise prediction model corresponding to the target joint through temperature compensation between the target joint and other joints. The temperature compensation is determined based on the unit temperature rise compensation amount for the target joint when the other joints move independently under preset operating conditions, and the steady-state predicted temperature rise of the corresponding other joints. The unit temperature rise compensation amount is determined based on the actual temperature and transmission temperature of the target joint when it operates independently under preset operating conditions, and the predicted temperature rise of the other joints obtained through the initial temperature rise prediction model. The initial temperature rise prediction model is obtained by training the temperature rise prediction model to be trained using the sample current of the joint motor and the sample speed of the joint reducer as model inputs, and the sample temperature rise of the joint reducer as model output. The current current and the current input speed are input into the preset temperature rise prediction model to obtain the predicted temperature of the target joint.
2. The temperature rise prediction method as described in claim 1, characterized in that, Before the step of collecting the current current of each joint motor of the robot and the current input speed of the joint reducer, the method further includes: Obtain the preliminary temperature rise prediction model corresponding to the joint to be corrected of the robot; Collect the actual temperature of the joint to be corrected when other joints besides the joint to be corrected move individually under preset operating conditions; Based on the actual temperature and the preliminary temperature rise prediction model, the temperature compensation of the joint to be corrected is obtained when the other joints move alone under the preset operating conditions. By correcting the initial temperature rise prediction model through temperature compensation, a preset temperature rise prediction model corresponding to the joint to be corrected is obtained. Return to the step of obtaining the preliminary temperature rise prediction model corresponding to the joint to be corrected in the robot, until the preliminary temperature rise prediction model corresponding to the joint to be corrected in the robot is corrected.
3. The temperature rise prediction method as described in claim 2, characterized in that, The step of obtaining the temperature compensation of the joint to be corrected when the other joints move independently under the preset operating conditions based on the actual temperature and the preliminary temperature rise prediction model includes: Based on the preliminary temperature rise prediction model, when the other joints move independently under the preset operating conditions, the transmitted temperature of the joint to be corrected and the predicted temperature rise of the other joints are predicted. Based on the actual temperature, the transmission temperature, and the predicted temperature rise, determine the unit temperature rise compensation amount for the joint to be corrected when the other joints move independently under the preset operating conditions; Based on the unit temperature rise compensation amount and the steady-state predicted temperature rise of the corresponding other joints, the temperature compensation of the other joints for the joint to be corrected is determined.
4. The temperature rise prediction method as described in claim 3, characterized in that, The step of determining the temperature compensation of the other joints for the joint to be corrected based on the unit temperature rise compensation amount and the steady-state predicted temperature rise of the corresponding other joints includes: The target compensation amount is determined from the unit temperature rise compensation amount, and the target compensation amount is the unit temperature rise compensation amount corresponding to the target operating condition with the highest actual temperature. Based on the target compensation amount and the corresponding steady-state predicted temperature rise of the other joints, the temperature compensation of the other joints for the joint to be corrected is determined.
5. The temperature rise prediction method as described in claim 3, characterized in that, The step of determining the unit temperature rise compensation amount for the joint to be corrected when the other joints move independently under the preset operating conditions, based on the actual temperature, the transmission temperature, and the predicted temperature rise, includes: Based on the actual temperature and the transmitted temperature, determine the influence temperature error transmitted to the joint to be corrected when the other joints are running alone; Based on the aforementioned temperature error and the corresponding predicted temperature rise, the unit temperature rise compensation amount for the joint to be corrected is determined when the other joints move independently under preset operating conditions.
6. The temperature rise prediction method according to any one of claims 2-5, characterized in that, Before the step of obtaining the preliminary temperature rise prediction model corresponding to the joint to be corrected of the robot, the method further includes: The current of the joint motor and the input speed of the joint reducer are used as the input of the preset model, and the steady-state temperature rise of the joint reducer is used as the output of the preset model to establish a temperature rise prediction model to be trained. The sample current of the joint motor, the sample rotational speed of the joint reducer, and the sample temperature rise of the joint reducer are obtained. The preliminary temperature rise prediction model is obtained by training the temperature rise prediction model based on the sample current, the sample rotation speed, and the sample temperature rise.
7. The temperature rise prediction method as described in claim 6, characterized in that, The steps of obtaining the sample current of the joint motor, the sample rotational speed of the joint reducer, and the sample temperature rise of the joint reducer include: Obtain preset operating conditions for the robot joints, the preset operating conditions being set based on the joint stroke, operating speed, and end effector load of the robot joints; When the robot joints are running independently according to the preset operating conditions, the sample current of the joint motor, the sample rotational speed of the joint reducer, and the sample temperature rise of the joint reducer are collected.
8. A temperature rise prediction device, characterized in that, The temperature rise prediction device includes: The first acquisition module is used to acquire the current current of the motors of each joint of the robot and the current input speed of the joint reducer; A determination module is used to determine the target joint whose temperature needs to be predicted, and the preset temperature rise prediction model corresponding to the target joint. The preset temperature rise prediction model is obtained by correcting the preliminary temperature rise prediction model corresponding to the target joint through temperature compensation between the target joint and other joints other than the target joint. The temperature compensation is determined based on the unit temperature rise compensation amount of the target joint when the other joints move alone under preset operating conditions and the steady-state predicted temperature rise of the corresponding other joints. The unit temperature rise compensation amount is determined based on the actual temperature and transmission temperature of the target joint when the other joints other than the target joint run alone under preset operating conditions, and the predicted temperature rise of the other joints predicted by the preliminary temperature rise prediction model. The preliminary temperature rise prediction model is obtained by training the temperature rise prediction model to be trained with the sample current of the joint motor and the sample speed of the joint reducer as the model input and the sample temperature rise of the joint reducer as the model output. The preliminary temperature rise prediction model uses the current of the joint motors and the input speed of the joint reducer in the robot as model parameters to predict the temperature of the joint reducer.
9. A temperature rise prediction device, characterized in that, The temperature rise prediction device includes: a memory, a processor, and a temperature rise prediction program stored in the memory and executable on the processor, the temperature rise prediction program being configured to implement the steps of the temperature rise prediction method as described in any one of claims 1 to 7.
10. A storage medium, characterized in that, The storage medium stores a program for implementing the temperature rise prediction method, which is executed by a processor to implement the steps of the temperature rise prediction method as described in any one of claims 1 to 7.
Citation Information
Patent Citations
Temperature prediction method of rotary cement kiln
CN115392125A