Excavator track control method and system and excavator

Abstract

The invention discloses an excavator track control method and system and an excavator in the technical field of engineering machinery control, and aims to solve the problem of excavator track control deviation caused by the fact that bucket tooth abrasion cannot be efficiently and accurately recognized and detected in real time in the prior art. The method comprises the steps that posture signals of a big arm, a bucket rod and a bucket of the excavator are collected in real time; the predicted length of each bucket tooth is obtained, the image and the point cloud data of each bucket tooth are collected in real time, the actual coordinate of each bucket tooth in the image is calculated, and the actual length of each bucket tooth is obtained according to the actual coordinate of each bucket tooth in the image and the predicted length of each bucket tooth; even if the data of the camera and the laser radar are out of order, the bucket tooth abrasion prediction model still has the key recognition and judgment capability, comprehensive and accurate data are obtained through fusion of the multi-source sensor, the abrasion condition of the bucket tooth can be mastered accurately in real time in combination with an innovative algorithm, and high-precision control over the excavation track is achieved.

Description

Technical Field

[0001] The present invention relates to an excavator trajectory control method, system and excavator, and belongs to the technical field of engineering machinery control. Background Art

[0002] In the field of intelligent control technology for construction machinery, excavators, as crucial earthmoving machines, have a significant impact on the progress and quality of construction projects due to their operational efficiency and precision. Bucket teeth inevitably wear out over long periods of operation. In the context of intelligent excavator control, tooth wear can cause the actual excavation trajectory to deviate from the preset trajectory, impacting construction accuracy. Traditionally, the wear of excavator buckets and teeth has been primarily managed through regular manual inspections and maintenance. This approach is not only time-consuming and labor-intensive, but also fails to accurately reflect the actual wear status of the teeth. In recent years, with the advancement of intelligent technology, image recognition and sensor technologies have been increasingly applied to the monitoring and control of construction machinery. However, these existing solutions primarily focus on detecting wear levels and fail to effectively translate this wear information into precise adjustments to the excavator's trajectory control. As the deviation between the tooth lifecycle parameters and factory settings widens, the accuracy of intelligent operations decreases, limiting the advancement of intelligent and unmanned control.

[0003] In the existing technology, when obtaining the wear condition of bucket teeth, manual detection, sensor detection or image detection are usually used. Manual detection cannot obtain the wear condition of bucket teeth in real time and has low work efficiency; sensor detection needs to be precisely installed at a specific position on the bucket teeth, which is relatively complicated to install and can easily affect the normal digging work of the bucket teeth; image detection is easily affected by the environment, such as low light environment or clay adhering to the surface of the bucket teeth, resulting in the inability to obtain accurate bucket tooth wear conditions, affecting the control effect of the bucket tooth trajectory.

[0004] In summary, the existing technology cannot efficiently, real-timely and accurately complete the identification and detection of bucket tooth wear when obtaining the wear condition of bucket teeth. The bucket tooth wear detection results are prone to deviations, causing problems such as deviation in excavator trajectory control, affecting the actual working effect of the excavator. Summary of the Invention

[0005] The purpose of the present invention is to overcome the deficiencies in the prior art and provide an excavator trajectory control method, system and excavator, which realize real-time online detection of excavator bucket wear through image perception technology, emphasizing its real-time nature and degree of automation; the actual length of the bucket tooth is obtained through the image, point cloud and predicted length of the bucket tooth, and even if the camera and lidar data fail, the bucket tooth wear prediction model still plays a key role in identification and judgment; thereby completing the identification and detection of bucket tooth wear efficiently, in real time and accurately, avoiding the deviation of bucket tooth wear detection results and ensuring the actual working effect of the excavator.

[0006] In order to solve the above technical problems, the present invention is implemented by adopting the following technical solutions: In a first aspect, the present invention provides an excavator trajectory control method, comprising the following steps: Step a: Real-time collection of attitude signals of the excavator's boom, arm, and bucket; Step b: obtaining the predicted length of each bucket tooth, collecting images and point cloud data of each bucket tooth in real time, and calculating the actual coordinates of each bucket tooth in the image, and obtaining the actual length of each bucket tooth based on the actual coordinates of each bucket tooth in the image and the predicted length of each bucket tooth; Step c: Obtain the historical length of each bucket tooth, calculate the wear amount of each bucket tooth based on the historical length and actual length of each bucket tooth, and calculate the average wear amount and wear error rate based on the wear amount of each bucket tooth; Step d: Based on the wear error rate and the wear amount of each bucket tooth, determine whether the wear of each bucket tooth conforms to the wear law. If all bucket teeth conform to the wear law, execute step e; otherwise, the work ends. Step e: comparing the average wear amount with a preset range. If the average wear amount is greater than the preset range, the bucket tooth length parameter in the control system is corrected according to the wear amount of each bucket tooth; otherwise, the bucket tooth length parameter in the control system is not corrected. Step f: Calculate the three-dimensional posture coordinate information of the bucket tooth tip in the actual working space based on the control system and the posture signals of the excavator's boom, bucket arm, and bucket; Step g: The three-dimensional posture coordinate information of the bucket tooth tip in the actual working space is input into the excavator motion control system as a control parameter to realize the trajectory control of the excavator bucket tooth.

[0007] Furthermore, the calculation of the actual coordinates of each bucket tooth in the image specifically includes: Identify the characteristic points of each bucket tooth based on the image and point cloud data of each bucket tooth; Correct the size of each bucket tooth in the image through geometric transformation and projection relationship to obtain the appearance size of each bucket tooth; According to the characteristic points and appearance dimensions of each bucket tooth and combined with the calibration parameters, the actual coordinates of each bucket tooth in the image are obtained.

[0008] Furthermore, obtaining the actual length of each bucket tooth according to the actual coordinates of each bucket tooth in the image specifically includes: Get the actual coordinates of each bucket tooth fixing pin; According to the actual coordinates of each bucket tooth in the image, the actual coordinates of each bucket tooth tip in the image are obtained; The detection length of each bucket tooth is calculated based on the actual coordinates of the fixing pins of each bucket tooth and the actual coordinates of the tooth tips of each bucket tooth in the image. The specific expression is as follows: ; Where: is the detection length of the i-th bucket tooth in the bucket; i is the number of the bucket tooth; is the moment; the actual coordinate of the fixed pin of the i-th bucket tooth in the bucket is ( , , ); The actual coordinates of the tooth tip of the i-th bucket tooth in the bucket in the image are ( , , ); is the coordinate of the fixed pin of the i-th bucket tooth in the front-to-back direction; is the left-right coordinate of the fixing pin of the i-th bucket tooth in the bucket; is the vertical coordinate of the fixing pin of the i-th bucket tooth in the bucket; is the coordinate of the tooth tip of the i-th bucket tooth in the front-to-back direction of the image; is the left-right coordinate of the tooth tip of the i-th bucket tooth in the bucket; is the vertical coordinate of the tooth tip of the i-th bucket tooth in the bucket; The step of obtaining the predicted length of each bucket tooth specifically includes: Obtain the detection parameters of each bucket tooth, input the detection parameters of each bucket tooth into a pre-built and trained bucket tooth wear adaptive estimation model, and output the predicted length of each bucket tooth; According to the detected length of each bucket tooth and the corresponding predicted length of each bucket tooth, the actual length of each bucket tooth is calculated. The specific expression is as follows: ; ; Where: is the actual length of the i-th bucket tooth in the bucket; w1 and w2 are weights; is the predicted length of the i-th tooth in the bucket.

[0009] Furthermore, the detection parameters of each bucket tooth include bucket tooth material, bucket tooth rotation speed, bucket tooth rotation acceleration, bucket tooth excavation resistance, bucket tooth cumulative installation time and excavation target category attribute parameters, wherein: The output of the predicted length of each bucket tooth is expressed as follows: ; Where: is a prediction function based on multiple factors; Bucket tooth material; is the rotation speed of the i-th bucket tooth in the bucket; is the rotational acceleration of the i-th tooth in the bucket; is the digging resistance of the i-th tooth in the bucket; is the cumulative installation time of the i-th bucket tooth in the bucket; It is the mining target category attribute parameter.

[0010] Furthermore, the calculation of the wear amount of each bucket tooth according to the historical length and actual length of each bucket tooth specifically includes: Calculate the wear of the i-th bucket tooth in the bucket. The expression is as follows: ; Where, is the wear amount of the i-th bucket tooth in the bucket, Di is the historical length of the i-th bucket tooth in the bucket; is the actual length of the i-th bucket tooth in the bucket; n is the time; i is the number of the bucket tooth; The calculation of the average wear amount and the wear error rate based on the wear amount of each bucket tooth specifically includes: The expression of the average wear amount is as follows: ; Where: is the average wear amount; k is the number of bucket teeth in the bucket; , 2, …, k; The expression of the wear error rate is as follows: ; .

[0011] Furthermore, the determination of whether the wear of each bucket tooth conforms to the wear law specifically includes: Comparing the wear error rate with a first preset threshold value, if the wear error rate is less than the first preset threshold value, determining that the wear of each bucket tooth complies with the wear law; if the wear error rate is not less than the first preset threshold value, determining that the wear of each bucket tooth does not comply with the wear law; Among them, when the wear error rate is less than the first preset threshold, the difference between the wear amount of each bucket tooth and the average wear amount is calculated according to the wear amount of each bucket tooth and the average wear amount, and the difference between the wear amount of each bucket tooth and the average wear amount is compared with the second preset threshold. If the difference between the wear amount of each bucket tooth and the average wear amount is less than the second preset threshold, it is judged that the wear of each bucket tooth conforms to the wear law; if there is a difference between the wear amount of the bucket tooth and the average wear amount that is not less than the second preset threshold, it is judged that the wear of each bucket tooth does not conform to the wear law.

[0012] Furthermore, the trajectory control of the excavator bucket teeth specifically includes: The excavator motion control system continuously adjusts the control parameters based on the three-dimensional posture coordinate information of the bucket tooth tip in the actual working space through a closed-loop feedback mechanism. It adjusts the excavator's motion in real time based on the control parameters, thereby accurately controlling the motion trajectory of the bucket tooth tip. Among them, the excavator motion control system includes a model predictive control algorithm.

[0013] In a second aspect, the present invention provides an excavator trajectory control system, comprising: Posture signal detection module: used to collect the posture signals of the excavator's boom, arm and bucket in real time; Bucket tooth recognition and detection module: used to collect images and point cloud data of each bucket tooth in real time, calculate the actual coordinates of each bucket tooth in the image, and obtain the actual length of each bucket tooth based on the actual coordinates of each bucket tooth in the image; Error calculation and correction module: includes a calculation module and a correction module. The calculation module is used to obtain the historical length of each bucket tooth, calculate the wear amount of each bucket tooth based on the historical length and actual length of each bucket tooth, and calculate the average wear amount and wear error rate based on the wear amount of each bucket tooth; based on the wear error rate and the wear amount of each bucket tooth, judge whether the wear of each bucket tooth conforms to the wear law. If each bucket tooth conforms to the wear law, execute the correction module; otherwise, the work ends: the correction module is used to compare the average wear amount with the preset range. If the average wear amount is greater than the preset range, the bucket tooth length parameter in the control system is corrected according to the wear amount of each bucket tooth; otherwise, the bucket tooth length parameter in the control system is not corrected; Tooth tip attitude coordinate update module: Calculates the three-dimensional attitude coordinate information of the bucket tooth tip in the actual working space based on the control system and the attitude signals of the excavator's boom, arm, and bucket; Motion trajectory control module: used to input the three-dimensional posture coordinate information of the bucket tooth tip in the actual working space as control parameters into the excavator motion control system to realize the trajectory control of the excavator bucket tooth.

[0014] Furthermore, it also includes a parameter and model storage module: used to store and manage key parameters and data related to the error calculation and correction module and the excavator motion control system; The bucket tooth recognition and detection module is further used to identify each bucket tooth feature point based on the image and point cloud data of each bucket tooth; correct the size of each bucket tooth in the image through geometric transformation and projection relationship to obtain the appearance size of each bucket tooth; and obtain the actual coordinates of each bucket tooth in the image based on each bucket tooth feature point and each bucket tooth appearance size in combination with calibration parameters; The motion trajectory control module is used to receive the three-dimensional posture coordinate information of the bucket tooth tip in the actual working space in real time and send the three-dimensional posture coordinate information of the bucket tooth tip in the actual working space to the excavator motion control system. The excavator motion control system is used to adjust the posture of the excavator's boom, dipper arm and bucket according to the three-dimensional posture coordinate of the bucket tooth tip in the actual working space, so that the bucket tooth tip trajectory is consistent with the preset trajectory; Among them, the excavator motion control system calculates the preset trajectory based on the posture of the excavator's arm, dipper arm and bucket, the target position and the constraints of the working environment.

[0015] In a third aspect, the present invention provides an excavator, comprising the excavator trajectory control system described in the second aspect.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention realizes real-time online detection of excavator bucket wear through image perception technology, emphasizing its real-time nature and degree of automation; the actual length of the bucket tooth is obtained through the image, point cloud and predicted length of the bucket tooth. Even if the camera and lidar data fail, the bucket tooth wear prediction model still plays a key role in identification and judgment; thus, the identification and detection of bucket tooth wear is completed efficiently, in real time and accurately, avoiding the deviation of bucket tooth wear detection results and ensuring the actual working effect of the excavator. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flow chart of an excavator trajectory control method provided according to an embodiment of the present invention; Figure 2 is a logic diagram of an excavator trajectory control method provided according to an embodiment of the present invention; Figure 3 is a schematic diagram of a camera or a laser radar provided in an embodiment of the present invention in a complete coordinate system of an excavator; Figure 4 2 is a schematic diagram of a system of an excavator trajectory control system according to an embodiment of the present invention; Figure 5 2 is a system schematic diagram of an excavator provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0019] The term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. Additionally, the character " / " generally indicates an "or" relationship between the related objects. Example 1:

[0020] like Figure 1-Figure 2 As shown, the present invention provides an excavator trajectory control method, comprising the following steps: Step a: Real-time collection of attitude signals of the excavator's boom, arm, and bucket; Step b: obtaining the predicted length of each bucket tooth, collecting images and point cloud data of each bucket tooth in real time, and calculating the actual coordinates of each bucket tooth in the image, and obtaining the actual length of each bucket tooth based on the actual coordinates of each bucket tooth in the image and the predicted length of each bucket tooth; Step c: Obtain the historical length of each bucket tooth, calculate the wear amount of each bucket tooth based on the historical length and actual length of each bucket tooth, and calculate the average wear amount and wear error rate based on the wear amount of each bucket tooth; Step d: Based on the wear error rate and the wear amount of each bucket tooth, determine whether the wear of each bucket tooth conforms to the wear law. If all bucket teeth conform to the wear law, execute step e; otherwise, the work ends. Step e: comparing the average wear amount with a preset range. If the average wear amount is greater than the preset range, the bucket tooth length parameter in the control system is corrected according to the wear amount of each bucket tooth; otherwise, the bucket tooth length parameter in the control system is not corrected. Step f: Calculate the three-dimensional posture coordinate information of the bucket tooth tip in the actual working space based on the control system and the posture signals of the excavator's boom, bucket arm, and bucket; Step g: The three-dimensional posture coordinate information of the bucket tooth tip in the actual working space is input into the excavator motion control system as a control parameter to realize the trajectory control of the excavator bucket tooth.

[0021] Specifically, the present invention comprises the following steps: Step so1: gesture signal detection: Real-time collection of attitude signals of the excavator's boom, dipper arm and bucket: This step mainly uses attitude sensors to collect the movement angles of the excavator's boom, dipper arm and bucket in real time, and processes and analyzes the data signals of the attitude sensors to provide high-precision basic data for subsequent image modeling, algorithm execution and motion control; the attitude signal detection module in the system can efficiently and accurately capture and process the data signals from the attitude sensors on the boom, dipper arm and bucket devices; at the same time, the hydraulic oil pressure feedback signal from the boom, dipper arm and bucket devices is detected; the control program uses advanced filtering and smoothing algorithms to pre-process the original data to eliminate noise interference and improve the credibility of the data; the data from the attitude signal detection module will be used to construct a three-dimensional model and perceive the dynamic data of the excavation resistance to ensure the smooth progress of a series of complex operations such as path planning, collision detection, and motion control.

[0022] In one embodiment, calculating the actual coordinates of each bucket tooth in the image specifically includes: Identify the characteristic points of each bucket tooth based on the image and point cloud data of each bucket tooth; Correct the size of each bucket tooth in the image through geometric transformation and projection relationship to obtain the appearance size of each bucket tooth; According to the characteristic points and appearance dimensions of each bucket tooth and combined with the calibration parameters, the actual coordinates of each bucket tooth in the image are obtained.

[0023] In one embodiment, obtaining the actual length of each bucket tooth according to the actual coordinates of each bucket tooth in the image specifically includes: By analyzing the data from the attitude sensor, the actual coordinates of each bucket tooth fixing pin are obtained; According to the actual coordinates of each bucket tooth in the image, the actual coordinates of each bucket tooth tip in the image are obtained; The detection length of each bucket tooth is calculated based on the actual coordinates of the fixing pins of each bucket tooth and the actual coordinates of the tooth tips of each bucket tooth in the image. The specific expression is as follows: ; Where: is the detection length of the i-th bucket tooth in the bucket; i is the number of the bucket tooth; is the moment; the actual coordinate of the fixed pin of the i-th bucket tooth in the bucket is ( , , ); The actual coordinates of the tooth tip of the i-th bucket tooth in the bucket in the image are ( , , ); is the coordinate of the fixed pin of the i-th bucket tooth in the front-to-back direction; is the left-right coordinate of the fixing pin of the i-th bucket tooth in the bucket; is the vertical coordinate of the fixing pin of the i-th bucket tooth in the bucket; is the coordinate of the tooth tip of the i-th bucket tooth in the front-to-back direction of the image; is the left-right coordinate of the tooth tip of the i-th bucket tooth in the bucket; is the vertical coordinate of the tooth tip of the i-th bucket tooth in the bucket; Obtain the detection parameters of each bucket tooth, input the detection parameters of each bucket tooth into a pre-built and trained bucket tooth wear adaptive estimation model, and output the predicted length of each bucket tooth; According to the detected length of each bucket tooth and the corresponding predicted length of each bucket tooth, the actual length of each bucket tooth is calculated. The specific expression is as follows: ; ; Where: is the actual length of the i-th bucket tooth in the bucket; w1 and w2 are weights; is the predicted length of the i-th tooth in the bucket.

[0024] In one embodiment, the calculation of the detection length of each bucket tooth is performed using the following specific expression: ; Where: is the coordinate of the fixed pin of the i-th bucket tooth in the front-to-back direction; is the left-right coordinate of the fixing pin of the i-th bucket tooth in the bucket; is the vertical coordinate of the fixing pin of the i-th bucket tooth in the bucket; is the coordinate of the tooth tip of the i-th bucket tooth in the front-to-back direction of the image; is the left-right coordinate of the tooth tip of the i-th bucket tooth in the bucket; is the vertical coordinate of the tooth tip of the i-th bucket tooth in the bucket.

[0025] In one embodiment, the detection parameters of each bucket tooth include bucket tooth material, bucket tooth rotation speed, bucket tooth rotation acceleration, bucket tooth excavation resistance, bucket tooth cumulative installation time, and excavation target category attribute parameters; The output of the predicted length of each bucket tooth is expressed as follows: ; Where: is a prediction function based on multiple factors; Bucket tooth material; is the rotation speed of the i-th bucket tooth in the bucket; is the rotational acceleration of the i-th tooth in the bucket; is the digging resistance of the i-th tooth in the bucket; is the cumulative installation time of the i-th bucket tooth in the bucket; It is the mining target category attribute parameter.

[0026] Specifically, the following steps are included: Step so2: Bucket tooth identification and detection: Get the detection length of each bucket tooth: Based on the fusion detection of the camera and laser radar perception signal system, the bucket tooth image and point cloud data collected in real time are analyzed to accurately capture the characteristic points of the bucket tooth in the image, such as vertices and edges, to achieve dynamic evaluation of the bucket tooth wear condition; automatically identify the bucket tooth characteristic points, calculate the actual distance and shooting angle between the camera or laser radar and the bucket tooth, and use geometric transformation and projection relationship to correct the bucket tooth size to obtain accurate appearance data of the bucket tooth; in insufficient light or harsh environment (such as haze and dust), the laser radar can make up for the shortcomings of the camera, thereby ensuring the accuracy of the bucket tooth wear condition. Maintain high recognition accuracy and robustness; the real-time collected images and point cloud data are processed by the model to automatically identify the bucket tooth feature points, and the bucket tooth size in the image is corrected through geometric transformation and projection relationship to obtain accurate bucket tooth appearance data; through the distribution of key feature points such as the bucket tooth vertex in the image, combined with calibration parameters, the actual coordinate position of the bucket tooth in the X, Y, and Z directions is accurately calculated (the X direction is the front-to-back direction, the Y direction is the left-to-right direction, and the Z direction is the up-down direction). For example, the front-to-back, left-to-right, and up-to-down changes in the bucket tooth vertex in the image reflect the actual coordinates in the X, Y, and Z directions respectively.

[0027] like Figure 3 As shown, point M is the fixed coordinate point of the camera or laser radar in the complete coordinate system of the excavator, which is determined by the actual installation position and is an accurate fixed value, recorded as M(Xm, Ym, Zm); point A is the fixed coordinate point of the fixed pin shaft position of the i-th bucket tooth in the bucket in the complete coordinate system of the excavator, which is determined by the attitude signal detection system and is an accurate value that can be dynamically read out during step S01, recorded as A( , , ); Point B is the actual coordinate point of the tooth tip position of the i-th bucket tooth in the complete coordinate system of the excavator. It is determined by image detection and recognition by a camera or laser radar within the effective distance recognition and angle recognition range. It is a value that can be dynamically calculated and is recorded as B( , , ), i is the number of the bucket tooth.

[0028] The detection length parameter of the bucket tooth is based on the spatial distance between point A and point B , which can be calculated using the following formula: .

[0029] Obtaining the predicted length of each bucket tooth: The present invention adopts a deep learning algorithm to train an adaptive bucket tooth wear prediction model; this model takes data of multiple dimensions such as operation time, excavation material resistance, and excavation speed as input. By learning from a large amount of historical operation data, the model can automatically adjust its own parameters to adapt to the wear of bucket teeth under different working conditions; different excavation materials have different hardnesses, and the degree of wear on bucket teeth is also very different. The size of the excavation force will also affect the wear of bucket teeth. Traditional models are difficult to fully consider these complex factors. The bucket tooth wear adaptive prediction model invented in this scheme can more accurately predict the amount of bucket tooth wear through learning, providing a strong basis for the subsequent precise correction of the excavation trajectory.

[0030] Optionally, the bucket tooth wear adaptive prediction model is a prediction model based on a neural network. By learning a large amount of historical operating data (including the material, speed, acceleration, excavation resistance, operating time, bucket tooth wear, and excavation target category of the operating device), a relationship model between the bucket tooth wear rate and various influencing factors is established; when the current operating device speed, acceleration, and excavation resistance data are obtained, the trained model is used to predict the bucket tooth wear in the future, aiming to accurately estimate the bucket tooth wear rate and expected state; these feature points include but are not limited to the vertices, edge contours, and other changes with significant geometric or morphological features of the bucket tooth. Through training with a large amount of labeled data, the model can accurately distinguish these features, and maintain high recognition accuracy and robustness even in the face of complex and changing background environments and lighting conditions. It can be calculated using the following formula: .

[0031] Among them, in daily equipment inspection and maintenance, the camera and lidar fusion detection results can be used as the main method to quickly determine whether there are obvious wear abnormalities on the bucket teeth and determine whether immediate maintenance or replacement is needed; under complex and changeable working conditions, such as working in harsh environments, the camera and lidar fusion detection may be affected to a certain extent. At this time, it is necessary to combine the prediction results of the deep learning model to comprehensively judge the wear condition of the bucket teeth to avoid misjudgment due to the limitations of a single detection method; in the context of the fusion detection results of the camera and lidar perception signal system and the bucket tooth wear prediction model trained by the deep learning algorithm, the adaptability of the two methods under different working conditions is analyzed. For example, when the fusion detection may have obvious distortion in the detection effect under certain specific working conditions, the deep learning model has a higher prediction accuracy under this working condition. In this case, the weight of the model prediction result can be appropriately increased under this working condition.

[0032] The confirmation of w1 weight and w2 weight specifically includes: assigning different weights to the camera and lidar fusion detection results and the deep learning wear prediction model results according to factors such as data reliability, time dimension and application scenario; the weight can be determined based on factors such as the accuracy of historical data, the performance of the model and the complexity of the current operating environment; generally, if the communication data of the camera and lidar are abnormal, and the bucket teeth will not be covered with attachments during normal application scenario operation, the data can be considered reliable, and the corresponding fusion detection weight w1 can be put into use normally; on the contrary, if any device of the camera and lidar fails, or the bucket teeth are easily covered with attachments, or the operating conditions are particularly harsh (including but not limited to extremely low visibility, heavy rain, heavy fog, high dust, etc.), the corresponding fusion detection weight can be directly defined as w1=0, thereby ensuring that when the camera and lidar data fail, the bucket tooth wear adaptive prediction model still plays a key role in identification and judgment.

[0033] Optionally, under daily working conditions, w1=0.6 and w2=0.4 can be defined; in complex working conditions or long-term prediction scenarios, the weight ratio can be adjusted appropriately.

[0034] On the basis of the above content, the weights of the real-time evaluation results and the model prediction results are comprehensively considered, and a weighted sum or weighted average is performed to obtain the final optimal calculation result; this result can more accurately reflect the actual wear condition and future trend of the bucket teeth; the two results are weighted and calculated according to the weights to obtain a comprehensive wear evaluation result, the formula is: ; ; Where: is the actual length of the i-th bucket tooth in the bucket; i is the number of the bucket tooth; is the moment; w1 and w2 are weights; is the detection length of the i-th bucket tooth in the bucket; is the predicted length of the i-th tooth in the bucket.

[0035] Compare the optimal calculation results with the actual situation, and collect feedback data to optimize the data processing algorithms of cameras and lidars, the training parameters of deep learning models, etc., to improve the accuracy and reliability of future calculations.

[0036] The present invention further comprises step so3: retrieving storage area data: Automatically retrieve various mechanical dimensional parameters of a single tooth tip of the excavator pre-stored in the storage area, including key historical parameters such as initial length, width, height, and shape characteristics; the storage area ensures the provision of the tooth tip mechanical dimensional parameters and correction rule models required by the control system, ensuring the smoothness and timeliness of data interaction between modules.

[0037] In one embodiment, the present invention includes step so4: bucket tooth error calculation: The calculation of the wear amount of each bucket tooth according to the historical length and actual length of each bucket tooth specifically includes: Calculate the wear of the i-th bucket tooth in the bucket. The expression is as follows: ; Where, is the wear amount of the i-th bucket tooth in the bucket, Di is the historical length of the i-th bucket tooth in the bucket; is the actual length of the i-th bucket tooth in the bucket; n is the time; The calculation of the average wear amount and the wear error rate based on the wear amount of each bucket tooth specifically includes: The expression of the average wear amount is as follows: ; Where: is the average wear amount; k is the number of bucket teeth in the bucket; , 2, …, k; optionally, the number of bucket teeth in the bucket is five; The expression of the wear error rate is as follows: ; This formula is used to measure the discrete degree of wear of each bucket tooth. The smaller the standard deviation, the more uniform the wear. ; The smaller the wear error rate calculated by this formula, the more normal the wear of the entire set of bucket teeth will be.

[0038] In one embodiment, the present invention includes step so5: wear pattern verification: The determination of whether the wear of each bucket tooth conforms to the wear law specifically includes: Comparing the wear error rate with a first preset threshold value, if the wear error rate is less than the first preset threshold value, determining that the wear of each bucket tooth complies with the wear law; if the wear error rate is not less than the first preset threshold value, determining that the wear of each bucket tooth does not comply with the wear law; Among them, when the wear error rate is less than the first preset threshold, the difference between the wear amount of each bucket tooth and the average wear amount is calculated according to the wear amount of each bucket tooth and the average wear amount, and the difference between the wear amount of each bucket tooth and the average wear amount is compared with the second preset threshold. If the difference between the wear amount of each bucket tooth and the average wear amount is less than the second preset threshold, it is judged that the wear of each bucket tooth conforms to the wear law; if there is a difference between the wear amount of the bucket tooth and the average wear amount that is not less than the second preset threshold, it is judged that the wear of each bucket tooth does not conform to the wear law.

[0039] Specifically, if the wear of one or more bucket teeth is significantly larger or smaller than the average wear, it may be caused by unreasonable installation position, special external force impact, quality problems of the bucket teeth themselves, etc., which indicates abnormal wear and requires further inspection and analysis. At the end of the work, an alarm will be issued to remind of the abnormal information.

[0040] In one embodiment, the present invention includes so6: bucket tooth error comparison: When the wear of the entire set of bucket teeth conforms to normal rules, the bucket tooth error comparison can be performed; by analyzing the factory or historically stored bucket tooth model data and the bucket tooth size changes in the actual physical coordinate system, the size of the excavation trajectory error can be determined.

[0041] For example, using cm as a unified unit of measurement, the average wear amount is compared with a preset range. If the average wear amount is greater than the preset range, the bucket tooth length parameter in the control system is corrected according to the wear amount of each bucket tooth; otherwise, the bucket tooth length parameter in the control system is not corrected.

[0042] In one embodiment, the present invention includes step so7: bucket tooth parameter correction: When the calculated wear error is confirmed, the stored bucket tooth mechanical size parameters are automatically corrected according to the error value caused by bucket tooth wear, and the stored inherent tooth tip mechanical size code is corrected.

[0043] For example: If the bucket tooth length is worn by 5cm, the stored bucket tooth length parameter will be automatically reduced by 5cm according to the preset correction rules to avoid the decrease in operating accuracy due to error accumulation.

[0044] In one embodiment, the present invention includes step so8: bucket tooth parameters and model storage; After the bucket tooth parameters are corrected, the update of necessary parameters including the effective length D of the bucket tooth is completed; the updated parameters and models are backed up in time to prevent damage to important data due to accidents such as hardware failure and data loss, thereby ensuring that the system always uses the most accurate and effective data and models for operation.

[0045] In one embodiment, the three-dimensional posture coordinate information of the bucket tooth tip in the actual working space is calculated based on the control system and the posture signals of the excavator's boom, dipper arm and bucket.

[0046] Specifically, the present invention includes step so0: tooth tip posture coordinate update: Using the corrected tooth tip mechanical dimension code stored in step S08 and the current posture information parsed in step S01, the three-dimensional posture coordinate calculation module will apply complex mathematical models and algorithms to perform calculations, including: automatically updating and generating the tooth tip space three-dimensional posture coordinate calculation model; combining the excavator kinematic model to replan the tooth tip motion trajectory; including constructing the corresponding rotation matrix and displacement vector based on the angles of the boom, dipper arm and bucket, and calculating the three-dimensional posture coordinate information of the tooth tip in the actual working space.

[0047] In one embodiment, the trajectory control of the excavator bucket teeth specifically includes: The excavator motion control system continuously adjusts the control parameters based on the three-dimensional coordinate information of the bucket tooth tip in the actual working space through a closed-loop feedback mechanism, adjusting the excavator's motion in real time, thereby accurately controlling the motion trajectory of the bucket tooth tip; Among them, the excavator motion control system includes a model predictive control algorithm.

[0048] Specifically, the present invention includes step so10: excavation trajectory control: The calculated three-dimensional coordinates of the actual spatial posture of the tooth tip are used as control parameters and input into the excavator's motion control system. Based on this precise coordinate information, the motion control system continuously adjusts the control parameters through a closed-loop feedback mechanism, and adjusts the movement of the excavator's working device in real time, thereby accurately controlling the motion trajectory of the tooth tip. This ensures that during operation, regardless of the degree of wear on the bucket teeth, the excavator can perform excavation operations according to the preset high-precision trajectory, ensuring the stability and efficiency of the operation accuracy.

[0049] Specific control methods include: Trajectory planning and control based on model prediction: A model predictive control algorithm is used to plan the motion trajectory of the excavator's working device. The model predictive control algorithm can predict the future output of the system based on the current system state and future constraints, and derive the optimal control input sequence through optimization calculation.

[0050] In an embodiment of the present invention, a model predictive control algorithm predicts the tooth tip position at multiple moments in the future based on real-time acquired position distribution information of the object to be excavated, tooth tip wear information, tooth tip position information, the current state of the excavator working device (such as the angle and speed of each component), and a preset excavation trajectory; then, the optimal control quantity of the working device at each moment, such as the extension and retraction length and speed of the cylinder, is calculated, thereby achieving precise control of the excavation trajectory and ensuring that the excavator operates efficiently according to the predetermined trajectory.

[0051] The core parameters of the model predictive control algorithm are realized through the following contents: real-time adjustment of fuzzy logic control parameters: real-time adjustment of motion control parameters in combination with fuzzy logic control algorithm; fuzzy logic control can process those imprecise and fuzzy information, especially in the excavation process, factors such as excavation resistance and excavation object conditions are often difficult to accurately measure and quantify; in an embodiment of the present invention, in the fuzzy logic control link, combined with the acquisition of camera or lidar image recognition data, the excavation object is identified, such as confirming that the excavation object is a specific type such as sand, clay, rock, etc.; according to these actual conditions, the speed, acceleration and other control parameters of the excavator working device are adjusted in real time; when the excavation object is a harder material such as rock, the excavation resistance will increase, and it will automatically reduce the excavation speed to avoid damage to the working device due to overload, while ensuring the stability and efficiency of the excavation process; when the excavation object is a loose material such as sand, the excavation speed is appropriately increased to improve the operation efficiency.

[0052] The present invention realizes real-time online detection of excavator bucket wear through image perception technology, emphasizing its real-time nature and degree of automation; the actual length of the bucket tooth is obtained through the image, point cloud and predicted length of the bucket tooth. Even if the camera and lidar data fail, the bucket tooth wear prediction model still plays a key role in identification and judgment; thus, the identification and detection of bucket tooth wear is completed efficiently, in real time and accurately, avoiding the deviation of bucket tooth wear detection results and ensuring the actual working effect of the excavator.

[0053] Compared with the prior art, the present invention not only provides qualitative analysis of wear, but also can perform quantitative analysis and automatically correct the motion model and control trajectory of the bucket according to the calculated error.

[0054] The present invention acquires comprehensive and accurate data through multi-source sensor fusion, and combined with innovative algorithms, can accurately grasp the status of the excavator's working device and the wear of the bucket teeth in real time, thereby achieving high-precision control of the excavation trajectory, ensuring the stability and efficiency of the operation accuracy, and improving the quality and efficiency of the excavation operation. The adaptive wear model and fuzzy logic control algorithm of the present invention can automatically and flexibly adjust the control strategy according to different working conditions and operating conditions, so that the excavator can operate stably and efficiently in various complex excavation environments, whether it is hard rock, loose soil, or severe weather conditions. Example 2:

[0055] like Figure 4 As shown, the present invention provides an excavator trajectory control system, comprising: Posture signal detection module: used to collect the posture signals of the excavator's boom, arm and bucket in real time; Bucket tooth recognition and detection module: used to collect images and point cloud data of each bucket tooth in real time, calculate the actual coordinates of each bucket tooth in the image, and obtain the actual length of each bucket tooth based on the actual coordinates of each bucket tooth in the image; Error calculation and correction module: includes a calculation module and a correction module. The calculation module is used to obtain the historical length of each bucket tooth, calculate the wear amount of each bucket tooth based on the historical length and actual length of each bucket tooth, and calculate the average wear amount and wear error rate based on the wear amount of each bucket tooth; based on the wear error rate and the wear amount of each bucket tooth, judge whether the wear of each bucket tooth conforms to the wear law. If each bucket tooth conforms to the wear law, execute the correction module; otherwise, the work ends: the correction module is used to compare the average wear amount with the preset range. If the average wear amount is greater than the preset range, the bucket tooth length parameter in the control system is corrected according to the wear amount of each bucket tooth; otherwise, the bucket tooth length parameter in the control system is not corrected; Tooth tip attitude coordinate update module: Calculates the three-dimensional attitude coordinate information of the bucket tooth tip in the actual working space based on the control system and the attitude signals of the excavator's boom, arm, and bucket; Motion trajectory control module: used to input the three-dimensional posture coordinate information of the bucket tooth tip in the actual working space as control parameters into the excavator motion control system to realize the trajectory control of the excavator bucket tooth.

[0056] Specifically, the attitude signal detection module is a key component of the excavator's intelligent control system. It is mainly responsible for real-time acquisition, processing and analysis of data signals from attitude sensors, providing high-precision basic data for subsequent image modeling, algorithm execution and motion control.

[0057] The attitude signal detection module efficiently and accurately captures and processes data signals from attitude sensors on the boom, arm, and bucket. At the software level, the module first decodes and verifies the angle change and angular velocity signals from these sensors to ensure data integrity and accuracy. The module then pre-processes the raw angle change and angular velocity signals using advanced filtering and smoothing algorithms to eliminate noise and enhance data reliability. The module then further analyzes the processed data to extract the precise angle values of the boom, arm, and bucket, as well as their relative positional relationships.

[0058] In addition, the excavation resistance signal detection is provided by the pressure sensor installed on the hydraulic oil pipeline of the boom, dipper arm and bucket device. At the software level, the pressure sensor data first decodes and verifies the hydraulic oil pressure signal from the boom, dipper arm and bucket device to ensure the integrity and accuracy of the data. Then, the module uses advanced filtering algorithms to eliminate noise interference and improve the credibility of the pressure data. On this basis, the module further analyzes the processed data to extract the comprehensive excavation resistance data of the boom, dipper arm and bucket.

[0059] These processed data not only provide precise posture parameters for subsequent image modeling, but also become an indispensable foundation for algorithm execution. In image modeling, data from the posture signal detection module is used to construct three-dimensional models, enabling real-time rendering and visualization of working scenes. At the algorithm execution level, these data serve as input parameters, supporting the smooth progress of a series of complex operations such as path planning, collision detection, and motion control. The software functions of the posture signal detection module not only ensure the accurate capture and processing of data, but also lay a solid foundation for the stable operation and efficient operation of the entire system.

[0060] Bucket tooth recognition and detection module: Based on the fusion data of the camera and lidar perception signal system, it can dynamically identify the characteristic points of the bucket teeth in the image, such as the vertices and edges of the bucket teeth, and detect and analyze the wear data of each bucket tooth; The system compares the real-time bucket tooth images and point cloud data with the standard model to calculate the wear of the bucket teeth in various directions and dimensions, and then analyzes the errors caused by bucket tooth wear. For example, by comparing the position change data of the bucket tooth vertices in the image and combining it with image calibration parameters, the wear errors of the bucket teeth in the X, Y, and Z directions are calculated.

[0061] The system collects images and point cloud data of bucket teeth in real time and automatically identifies each tooth's characteristic points by processing the input image. It calculates the actual distance and shooting angle between the camera or lidar and the tooth, and uses geometric transformations and projection relationships to calibrate and confirm the tooth's dimensions in the image, resulting in accurate tooth appearance data. Image calibration is performed by analyzing the stored tooth model at factory dimensions and establishing a mapping relationship between the image coordinate system and the actual physical coordinate system. Based on pixel changes in the image, the system infers the actual tooth's dimensional changes and positional offsets. Furthermore, by comparing the positional changes of key feature points, such as the tooth vertex, in the image, and combining them with parameters derived from image calibration, the system can accurately calculate the tooth's wear error in the three orthogonal directions of X, Y, and Z. For example, if the tooth vertex in the image is offset to the left by a certain number of pixels relative to the standard image, and taking into account the actual distance represented by each pixel in the image calibration, the system can calculate the tooth's wear in the Y direction. Similarly, changes in the vertex's front-to-back or up-down positions in the image reflect wear in the Y and Z directions, respectively.

[0062] Error calculation and correction module: In the intelligent control system of the excavator, the wear of the tooth tip directly affects the accuracy and efficiency of the excavation operation. To ensure that the excavator maintains high-precision control during long-term operation, the system needs to monitor the wear of the tooth tip in real time and correct the mechanical dimension code of the tooth tip based on the wear error.

[0063] In the excavator's control system, the memory is used to store the mechanical dimensional parameters of the tooth tip; these parameters include the initial length, width, height, and shape characteristics of the tooth tip; the data in the memory is the basis for the system to correct wear errors; the control system will compare the stored tooth tip mechanical dimensional data, and based on the calculated wear error, correct the tooth tip mechanical dimensional code according to the preset correction rules.

[0064] After receiving the wear error data, the module first calls and reads the corresponding parameters in the memory; then, based on the real-time monitoring of bucket tooth wear, it accurately adjusts the tooth tip mechanical dimension code in the system according to the modification rules, and outputs the calculated results to the actual posture coordinate update module accordingly.

[0065] When the error calculation and coordinate correction module receives wear error data from the image recognition and error calculation module, it first calls and reads the corresponding parameters from the memory. The correction rules can be customized according to actual needs. For example, if the bucket tooth wears 5 cm in the X direction, the module will automatically reduce the size code of the tooth tip in the X direction by 5 cm according to the preset correction rules, avoiding the loss of operating accuracy due to error accumulation.

[0066] Tooth tip attitude coordinate update module: After the error data is corrected, the control system will call the tooth tip spatial three-dimensional attitude coordinate calculation module within the system; this module uses the corrected tooth tip mechanical dimension code, combined with the current posture information of the excavator (such as the angles of the boom, dipper arm and bucket, etc.), through complex mathematical models and algorithms to calculate the three-dimensional attitude coordinate information of the tooth tip in the actual working space; this coordinate information is crucial for the precise control and operation of the excavator. It can not only analyze the real-time position and posture of the bucket tooth, but also provide data support for advanced functions such as automatic excavation and obstacle avoidance.

[0067] The three-dimensional attitude coordinate calculation module first obtains the current posture information of the excavator, which includes key parameters such as the angles of the boom, arm and bucket. Then, using the corrected tooth tip mechanical size code and the current posture information, the three-dimensional attitude coordinate calculation module will apply complex mathematical models and algorithms for calculation: including constructing the corresponding rotation matrix and displacement vector based on the angles of the boom, arm and bucket. The system will calculate the three-dimensional attitude coordinate information of the tooth tip in the actual working space. These coordinate information are usually expressed in the form of (X, Y, Z), which can reflect the position and direction of the tooth tip in three-dimensional space.

[0068] The system will analyze the current position and posture of the bucket teeth in real time, ensuring the stability and accuracy of the excavator during operation, and providing data support for subsequent advanced functions such as automatic excavation and obstacle avoidance. It can not only improve the operating accuracy and efficiency of the excavator, but also reduce operating errors and failure rates caused by wear, providing a strong guarantee for the efficient and safe operation of the excavator in complex environments.

[0069] The motion control module sends the calculated three-dimensional coordinates of the tooth tip's actual spatial posture to the excavator's motion control module. Based on these coordinates, the motion control module controls the hydraulic system's solenoid valves to adjust the extension and retraction of the boom, arm, and bucket cylinders, thereby altering the excavator's working mechanism's posture and aligning the tooth tip's trajectory with the preset trajectory. For example, if the tooth tip deviates by 10 cm in the Y direction, the motion controller activates the corresponding cylinders to move the tooth tip 10 cm in the Y direction, returning it to the preset trajectory.

[0070] The motion trajectory control module is the core module in the automated and intelligent operation of the excavator. It is responsible for accurately transmitting the actual three-dimensional posture coordinates of the tooth tip output by the error calculation and coordinate correction module to the excavator's motion controller. This transmission process not only requires the accuracy and timeliness of the data, but also ensures that the motion controller can respond to these coordinate information quickly and accurately to achieve precise operation of the excavator.

[0071] After receiving the actual spatial three-dimensional posture coordinates of the tooth tip, the motion controller immediately begins to parse and process this information. It first calculates the motion path and action sequence required to reach the target position based on the excavator's current posture, the configuration of the working device, and the constraints of the working environment. This process involves complex kinematic and dynamic calculations to ensure that the excavator can complete the task with the optimal posture and path.

[0072] After calculating the required motion path, the motion controller will further adjust the extension and retraction of the boom, dipper arm and bucket cylinders by controlling the solenoid valves of the hydraulic system. The extension and retraction changes of these cylinders directly determine the posture and position of the excavator's working device and are the key to the excavator's precise operation. The motion controller will accurately control the opening and closing time, current size and other parameters of the solenoid valve according to the preset control strategy and algorithm, thereby achieving precise control of the extension and retraction of the cylinders.

[0073] For example, when the motion trajectory control module detects that the tooth tip deviates from the preset trajectory by 10 cm in the Y direction, it will immediately calculate the amount and direction of movement that needs to be adjusted, and control the corresponding cylinder action through the motion controller; if the tooth tip needs to be moved 10 cm in the Y direction to return to the preset trajectory, the motion controller will increase or decrease the extension and contraction of the cylinder in the Y direction accordingly until the tooth tip is re-aligned with the preset trajectory.

[0074] During the entire motion control process, the motion trajectory control module will continuously receive real-time coordinate information from the error calculation and coordinate correction module and perform closed-loop control; the system will continuously adjust the control strategy based on the deviation between the actual position and posture of the tooth tip and the preset trajectory to ensure the excavator's operating accuracy and stability; this closed-loop control mechanism greatly improves the excavator's operating efficiency and quality, enabling the excavator to maintain high precision and stability in complex and changing operating environments.

[0075] In summary, the motion trajectory control module achieves precise control of the excavator working device by accurately receiving and processing the actual three-dimensional posture coordinate information of the tooth tip, combining complex kinematic and dynamic calculations, and a precise hydraulic control system.

[0076] The present invention also includes a parameter and model storage module, a core component of the excavator's intelligent control system. It is primarily responsible for storing and managing key parameters and model data related to tooth tip mechanical dimensions, wear error correction rules, and system operation. This module provides basic data support for functions such as error calculation and correction, and attitude coordinate updates, ensuring the system can accurately adjust the tooth tip mechanical dimension code in real time, thereby maintaining high precision and efficiency in excavation operations.

[0077] First, it stores the mechanical dimensional parameters of the excavator's tooth tip, including key parameters such as initial length, width, height, and shape. These initial parameters form the basis for the system's subsequent wear error calculation and correction. Ensuring the accuracy and integrity of this data is crucial to the precision control of the entire system.

[0078] In addition to parameters, related models for error calculation and correction can also be stored; for example, preset wear error correction rule models. These models are built based on actual operational requirements and experience, guiding the system on how to accurately adjust the mechanical dimension code according to the wear condition of the tooth tip, providing strong support for the intelligent operation of the system.

[0079] It also has efficient data management functions, which can classify, index and update stored parameters and models; when the tooth tip is worn, the corresponding parameters are updated according to the real-time monitoring data to ensure the timeliness of the data; at the same time, when the model is optimized or the correction rules are adjusted, the stored model is updated in time to ensure that the system always uses the most accurate and effective data and models for operation, and can provide data reading and calling services for other modules conveniently and quickly. When the error calculation and correction module receives the wear error data, it can respond quickly and accurately provide the required tooth tip mechanical size parameters and correction rule models, ensuring the smoothness and timeliness of data interaction between modules, which is a key link in achieving system collaboration.

[0080] Stored parameters and models can also be backed up regularly to prevent damage to important data due to unexpected situations such as hardware failure and data loss. In the event of a system anomaly, data can be quickly restored, allowing the excavator's intelligent control system to quickly return to normal operation, reducing downtime and ensuring the continuity and stability of excavation operations. Example 3:

[0081] like Figure 5 As shown, the present invention provides an excavator, characterized in that it includes the excavator trajectory control system described in Example 2.

[0082] Specifically, to ensure the real-time and accuracy of image acquisition, processing, storage and control, the excavator of the present invention is provided with a controller, a sensor, a camera or a laser radar and a memory.

[0083] Sensor: The attitude sensor is fixedly installed on the boom, arm and bucket device, connected to the controller through a data cable, and transmits the received angle change data signal to the controller; when any angle change occurs in the boom, arm or bucket, the sensor will immediately capture these changes and convert them into corresponding data signals; in addition, the excavation resistance signal detection is provided by the pressure sensor installed on the hydraulic oil pipeline of the boom, arm and bucket device to provide data signals; these data signals are transmitted to the controller through the data cable; the controller, as the core of data processing, can receive and process these data signals from the attitude sensor in real time, thereby providing basic data for subsequent image modeling, algorithm execution, etc.

[0084] Camera or LiDAR: Install cameras and / or LiDAR on the top of the excavator's cab, boom, or dipper arm to enable them to clearly capture the position and movement of the bucket teeth from different angles. The installation position of the camera or LiDAR must be precisely debugged to ensure that the image of the bucket teeth accurately reflects their actual status. Set an appropriate image acquisition frequency, such as capturing an image every N seconds, to meet the needs of real-time detection. By collecting camera or LiDAR image recognition data, it is also possible to identify the excavation object, such as distinguishing between different types of sand, clay, rock, etc.

[0085] The controller, installed within the excavator system, is responsible for processing image data and point cloud modeling, performing deep learning algorithm and model training, completing bucket tooth wear analysis and calculation, solving tooth tip spatial posture coordinates, and executing core module programs such as tooth tip motion trajectory planning and high-precision trajectory control. The controller uses received posture sensor data, combined with image and point cloud modeling technology, to accurately digitally represent the excavator's current operating status. The controller also uses deep learning algorithms to train a bucket tooth wear prediction model. By combining visual fusion detection data with bucket tooth wear analysis and calculation, it can identify the degree of wear on the excavator's bucket teeth. Simultaneously, the controller uses advanced algorithms to accurately solve the spatial posture coordinates of the tooth tip, thereby determining its specific position in three-dimensional space. Based on this information, the controller can plan the tooth tip's motion trajectory and, through precise control algorithms, achieve coordinated control of the excavator's boom, arm, and bucket. The excavator can then operate according to the preset motion trajectory and execution force, ensuring the accuracy and efficiency of construction operations.

[0086] Memory: As an important component of the controller, it is integrated inside the controller; it is mainly responsible for completing key tasks such as storing the mechanical dimensions of the excavator at the factory and storing the modeling data of the entire machine; when the excavator leaves the factory, its various mechanical dimensions and parameters will be accurately measured and confirmed and stored in the memory; this stored information is crucial for image modeling and algorithm execution, and provides basic data for the digital representation of the excavator; the memory will also store the modeling data of the entire machine, including the three-dimensional model of the excavator, the structural parameters of each part and the relative position relationship between them, etc.; when the controller performs image modeling and algorithm execution, it will frequently access and call this data to ensure that the intelligent target precision control task of the excavator can proceed smoothly.

[0087] In summary, cameras or lidar, attitude sensors, controllers, and memory together form the core system for intelligent excavator operation. Their coordinated and collaborative work enables high-precision and efficient excavator operation.

[0088] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0089] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0090] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0091] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0092] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for controlling an excavator trajectory, characterized in that: The following steps are involved: Step a: Real-time collection of attitude signals of the excavator's boom, arm, and bucket; Step b: obtaining the predicted length of each bucket tooth, collecting images and point cloud data of each bucket tooth in real time, and calculating the actual coordinates of each bucket tooth in the image, and obtaining the actual length of each bucket tooth based on the actual coordinates of each bucket tooth in the image and the predicted length of each bucket tooth; Step c: Obtain the historical length of each bucket tooth, calculate the wear amount of each bucket tooth based on the historical length and actual length of each bucket tooth, and calculate the average wear amount and wear error rate based on the wear amount of each bucket tooth; Step d: Based on the wear error rate and the wear amount of each bucket tooth, determine whether the wear of each bucket tooth conforms to the wear law. If all bucket teeth conform to the wear law, execute step e; otherwise, the work ends. Step e: comparing the average wear amount with a preset range. If the average wear amount is greater than the preset range, the bucket tooth length parameter in the control system is corrected according to the wear amount of each bucket tooth; otherwise, the bucket tooth length parameter in the control system is not corrected. Step f: Calculate the three-dimensional posture coordinate information of the bucket tooth tip in the actual working space based on the control system and the posture signals of the excavator's boom, bucket arm, and bucket; Step g: The three-dimensional posture coordinate information of the bucket tooth tip in the actual working space is input into the excavator motion control system as a control parameter to realize the trajectory control of the excavator bucket tooth.

2. The excavator trajectory control method according to claim 1, characterized in that: The calculation of the actual coordinates of each bucket tooth in the image specifically includes: Identify the characteristic points of each bucket tooth based on the image and point cloud data of each bucket tooth; Correct the size of each bucket tooth in the image through geometric transformation and projection relationship to obtain the appearance size of each bucket tooth; According to the characteristic points and appearance dimensions of each bucket tooth and combined with the calibration parameters, the actual coordinates of each bucket tooth in the image are obtained.

3. The excavator trajectory control method according to claim 1, characterized in that: The step of obtaining the actual length of each bucket tooth according to the actual coordinates of each bucket tooth in the image specifically includes: Get the actual coordinates of each bucket tooth fixing pin; According to the actual coordinates of each bucket tooth in the image, the actual coordinates of each bucket tooth tip in the image are obtained; The detection length of each bucket tooth is calculated based on the actual coordinates of the fixing pins of each bucket tooth and the actual coordinates of the tooth tips of each bucket tooth in the image. The specific expression is as follows: ； Where: is the detection length of the i-th bucket tooth in the bucket; i is the number of the bucket tooth; is the moment; the actual coordinate of the fixed pin of the i-th bucket tooth in the bucket is ( , , ); The actual coordinates of the tooth tip of the i-th bucket tooth in the bucket in the image are ( , , ); is the coordinate of the fixed pin of the i-th bucket tooth in the front-to-back direction; is the left-right coordinate of the fixing pin of the i-th bucket tooth in the bucket; is the vertical coordinate of the fixing pin of the i-th bucket tooth in the bucket; is the coordinate of the tooth tip of the i-th bucket tooth in the front-to-back direction of the image; is the left-right coordinate of the tooth tip of the i-th bucket tooth in the bucket; is the vertical coordinate of the tooth tip of the i-th bucket tooth in the bucket; The step of obtaining the predicted length of each bucket tooth specifically includes: Obtain the detection parameters of each bucket tooth, input the detection parameters of each bucket tooth into a pre-built and trained bucket tooth wear adaptive estimation model, and output the predicted length of each bucket tooth; According to the detected length of each bucket tooth and the corresponding predicted length of each bucket tooth, the actual length of each bucket tooth is calculated. The specific expression is as follows: ； ； Where: is the actual length of the i-th bucket tooth in the bucket; w1 and w2 are weights; is the predicted length of the i-th tooth in the bucket.

4. The excavator trajectory control method according to claim 3, characterized in that: The detection parameters of each bucket tooth include bucket tooth material, bucket tooth rotation speed, bucket tooth rotation acceleration, bucket tooth excavation resistance, bucket tooth cumulative installation time and excavation target category attribute parameters, among which: The output of the predicted length of each bucket tooth is expressed as follows: ； Where: is a prediction function based on multiple factors; Bucket tooth material; is the rotation speed of the i-th bucket tooth in the bucket; is the rotational acceleration of the i-th tooth in the bucket; is the digging resistance of the i-th tooth in the bucket; is the cumulative installation time of the i-th bucket tooth in the bucket; It is the mining target category attribute parameter.

5. The excavator trajectory control method according to claim 1, characterized in that: The calculation of the wear amount of each bucket tooth according to the historical length and actual length of each bucket tooth specifically includes: Calculate the wear of the i-th bucket tooth in the bucket. The expression is as follows: ； Where, is the wear amount of the i-th bucket tooth in the bucket, Di is the historical length of the i-th bucket tooth in the bucket; is the actual length of the i-th bucket tooth in the bucket; n is the time; i is the number of the bucket tooth; The calculation of the average wear amount and the wear error rate based on the wear amount of each bucket tooth specifically includes: The expression of the average wear amount is as follows: ； Where: is the average wear amount; k is the number of bucket teeth in the bucket; , 2, …, k; The expression of the wear error rate is as follows: ； 。 6. The excavator trajectory control method according to claim 1, characterized in that: The determination of whether the wear of each bucket tooth conforms to the wear law specifically includes: The wear error rate is compared with a first preset threshold value. If the wear error rate is less than the first preset threshold value, it is determined that the wear of each bucket tooth conforms to the wear law; if the wear error rate is not less than the first preset threshold value, it is determined that the wear of each bucket tooth does not conform to the wear law. Among them, when the wear error rate is less than the first preset threshold, the difference between the wear amount of each bucket tooth and the average wear amount is calculated according to the wear amount of each bucket tooth and the average wear amount, and the difference between the wear amount of each bucket tooth and the average wear amount is compared with the second preset threshold. If the difference between the wear amount of each bucket tooth and the average wear amount is less than the second preset threshold, it is judged that the wear of each bucket tooth conforms to the wear law; if there is a difference between the wear amount of the bucket tooth and the average wear amount that is not less than the second preset threshold, it is judged that the wear of each bucket tooth does not conform to the wear law.

7. The excavator trajectory control method according to claim 1, characterized in that: The trajectory control of the excavator bucket teeth specifically includes: The excavator motion control system continuously adjusts the control parameters based on the three-dimensional posture coordinate information of the bucket tooth tip in the actual working space through a closed-loop feedback mechanism. It adjusts the excavator's motion in real time based on the control parameters, thereby accurately controlling the motion trajectory of the bucket tooth tip. Among them, the excavator motion control system includes a model predictive control algorithm.

8. An excavator trajectory control system, characterized in that: include: Posture signal detection module: used to collect the posture signals of the excavator's boom, arm and bucket in real time; Bucket tooth recognition and detection module: used to collect images and point cloud data of each bucket tooth in real time, calculate the actual coordinates of each bucket tooth in the image, and obtain the actual length of each bucket tooth based on the actual coordinates of each bucket tooth in the image; Error calculation and correction module: includes a calculation module and a correction module. The calculation module is used to obtain the historical length of each bucket tooth, calculate the wear of each bucket tooth based on the historical length and actual length of each bucket tooth, and calculate the average wear and wear error rate based on the wear of each bucket tooth. Based on the wear error rate and the wear of each bucket tooth, it is judged whether the wear of each bucket tooth conforms to the wear law. If all bucket teeth conform to the wear law, the correction module is executed. Otherwise, the work ends: the correction module is used to compare the average wear amount with the preset range. If the average wear amount is greater than the preset range, the bucket tooth length parameter in the control system is corrected according to the wear amount of each bucket tooth; otherwise, the bucket tooth length parameter in the control system is not corrected; Tooth tip attitude coordinate update module: Calculates the three-dimensional attitude coordinate information of the bucket tooth tip in the actual working space based on the control system and the attitude signals of the excavator's boom, arm, and bucket; Motion trajectory control module: used to input the three-dimensional posture coordinate information of the bucket tooth tip in the actual working space as control parameters into the excavator motion control system to realize the trajectory control of the excavator bucket tooth.

9. The excavator trajectory control system according to claim 8, characterized in that: It also includes a parameter and model storage module: used to store and manage key parameters and data related to the error calculation and correction module and the excavator motion control system; The bucket tooth recognition and detection module is further used to identify each bucket tooth feature point based on the image and point cloud data of each bucket tooth; correct the size of each bucket tooth in the image through geometric transformation and projection relationship to obtain the appearance size of each bucket tooth; and obtain the actual coordinates of each bucket tooth in the image based on each bucket tooth feature point and each bucket tooth appearance size in combination with calibration parameters; The motion trajectory control module is used to receive the three-dimensional posture coordinate information of the bucket tooth tip in the actual working space in real time and send the three-dimensional posture coordinate information of the bucket tooth tip in the actual working space to the excavator motion control system. The excavator motion control system is used to adjust the posture of the excavator's boom, dipper arm and bucket according to the three-dimensional posture coordinate of the bucket tooth tip in the actual working space, so that the bucket tooth tip trajectory is consistent with the preset trajectory; Among them, the excavator motion control system calculates the preset trajectory based on the posture of the excavator's arm, dipper arm and bucket, the target position and the constraints of the working environment.

10. An excavator, characterized in that: The excavator trajectory control system includes any one of claims 8 to 9.

Images