Submerged excavation control method for multi-transmission system of power plant wharf grab ship unloader

Abstract

The invention relates to the technical field of transmission system control, and provides an excavation control method for a multi-transmission system of a power plant wharf grab ship unloader, which solves the problems that the data transmission stability is easy to interfere in a complex industrial environment, a control instruction is delayed and a motion error is caused by a complex coupling relationship among mechanisms of the multi-transmission system. According to the method, system basic data is acquired and preprocessed, a random forest model is utilized to train an underground excavation control model, an underground excavation control task is received, simulation data is generated, data features are extracted and compared with actual data for verification, inconsistent data are replaced, and then a real-time control task is output to an equipment end to be executed. According to the invention, the precision and stability of sinking excavation control are effectively improved, the failure rate and the maintenance cost are reduced, the system reliability is improved, the operation process is optimized, and the method is suitable for different material characteristics and operation environments.

Description

Technical Field

[0001] The invention relates to the technical field of transmission system control, and in particular to a sinking and digging control method of a multi-transmission system of a grab ship unloader at a power plant wharf. Background Art

[0002] The multi-drive system of the grab ship unloader at the power plant wharf is the core of its efficient operation. The multi-drive system of the grab ship unloader at the power plant wharf is usually composed of a DC speed regulation system or an AC frequency conversion speed regulation system. Among them, the AC frequency conversion speed regulation system has gradually become the mainstream choice due to its advantages such as high rated power and diverse control methods. The multi-drive system of the grab ship unloader at the power plant wharf controls the lifting, opening and closing of the grab, and the trolley running mechanism (the three are collectively referred to as the four-drum mechanism), as well as the amplitude change mechanism, the trolley running mechanism, etc., to realize the whole process of the grab digging materials from the cabin, lifting to the safe height of the hatch, moving horizontally to the top of the hopper to unload materials, and then returning to the top of the cabin for the second grab. The multi-drive system also involves complex electrical transmission control, including the coordinated actions of the lifting, opening and closing, trolley running mechanisms, and the application of differential reducers, so that the grab can flexibly and accurately complete the task under various working conditions.

[0003] During the data processing process of the multi-drive system of the grab ship unloader at the power plant wharf, since the multi-drive system of the grab ship unloader at the power plant wharf needs to process a large amount of data from multiple sensors and controllers in real time, in a complex industrial environment, the stability of data transmission is easily disturbed, resulting in delays in control commands. There are complex coupling relationships between the various transmission mechanisms in the multi-drive system. If there are delays and errors in the data, errors will occur in the movement of each mechanism, causing errors in the sinking and digging control of the multi-drive system of the grab ship unloader at the power plant wharf. In order to solve this technical pain point, the present invention provides a sinking and digging control method for the multi-drive system of the grab ship unloader at the power plant wharf. Summary of the invention

[0004] In view of the above technical problems, the present invention provides a sinking and digging control method for a multi-drive system of a grab ship unloader at a power plant wharf, which is used to solve the problem that the stability of data transmission is easily disturbed in a complex industrial environment, resulting in delays in control instructions, and there are complex coupling relationships between the various transmission mechanisms in the multi-drive system. If the data is delayed and erroneous, it will cause errors in the movement of each mechanism, resulting in errors in the sinking and digging control of the multi-drive system of the grab ship unloader at the power plant wharf.

[0005] The present invention provides a sinking and digging control method for a multi-drive system of a grab ship unloader at a power plant wharf, comprising:

[0006] Step S101, obtaining basic data of the multi-drive system of the grab ship unloader at the power plant wharf, the basic data of the multi-drive system of the grab ship unloader at the power plant wharf including sensor data, position data, load data, system status data, material characteristic data, control instruction data, and historical data of the multi-drive system of the grab ship unloader at the power plant wharf;

[0007] Step S102, preprocessing the basic data of the multi-drive system of the grab ship unloader of the power plant wharf, dividing the preprocessed basic data of the multi-drive system of the grab ship unloader of the power plant wharf into a training set and a validation set, using the training set and the validation set to train the random forest model, and obtaining a sinking and digging control model of the multi-drive system of the grab ship unloader of the power plant wharf;

[0008] Step S103, receiving the sinking and digging control task of the multi-drive system of the grab ship unloader of the power plant wharf, substituting the sinking and digging control task of the multi-drive system of the grab ship unloader of the power plant wharf into the sinking and digging control model of the multi-drive system of the grab ship unloader of the power plant wharf, and obtaining sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf;

[0009] Step S104, extracting data features from the sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf, obtaining sinking and digging data features of the multi-drive system of the grab ship unloader of the power plant wharf, collecting corresponding data according to the sinking and digging data features of the multi-drive system of the grab ship unloader of the power plant wharf, and obtaining data to be detected;

[0010] Step S105, compare the data to be detected with the sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf. If the comparison data results are inconsistent, the sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf replaces the inconsistent data, and uses the replaced data as the sinking and digging control data of the multi-drive system of the grab ship unloader of the power plant wharf, substitutes the sinking and digging control data of the multi-drive system of the grab ship unloader of the power plant wharf into the sinking and digging model of the multi-drive system of the grab ship unloader of the power plant wharf, outputs the real-time control task, transmits the real-time control task to the device end, and the device end executes the real-time control task.

[0011] Furthermore, in the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf described in the present invention, the step S101 comprises:

[0012] From the multi-drive system of the grab ship unloader at the power plant dock, real-time data is collected through the arranged displacement sensors, force sensors, and speed sensors;

[0013] Use global positioning system, laser rangefinder or encoder positioning equipment to collect real-time position data of the grab in three-dimensional space;

[0014] The weight data of the material in the grab bucket is collected in real time through a weighing sensor or load monitoring device;

[0015] Obtain system status data from the control system of the multi-drive system, including the voltage, current, power factor of the electric drive system, the operating status of the drive mechanism, and alarm information;

[0016] The control command data are obtained from the operator console or the automatic control system. The control command data include the lifting, opening, closing, and moving action instructions of the grab bucket, and the set value of the sinking and excavation amount.

[0017] Furthermore, in the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf described in the present invention, the step S102 comprises:

[0018] The preprocessed data is randomly divided into a training set and a validation set. The training set is used to train the model, and the validation set is used to evaluate the performance of the model.

[0019] The random forest model is selected as the basis of the subsidence control model, the training set data is used to train the random forest model, and the validation set data is used to validate the trained random forest model;

[0020] The trained random forest model is saved in a loadable format to obtain the sinking and digging control model of the multi-drive system of the grab ship unloader at the power plant wharf.

[0021] Furthermore, in the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf described in the present invention, the step S103 comprises:

[0022] Receive the excavation control task from the control system or operator console of the grab ship unloader at the power plant dock, the excavation control task including the excavation depth, speed, position, material type and grab size;

[0023] Parse the received sinking and excavation control task and extract the control parameters, which include the starting position, ending position, target depth and expected speed of the sinking and excavation;

[0024] According to the excavation control task, sensor data, position data and load data are extracted from the real-time data of the multi-drive system of the grab ship unloader at the power plant dock as the initial conditions of the model input;

[0025] Load the sinking and digging control model of the multi-drive system of the grab ship unloader of the power plant terminal trained in step S102, substitute the parsed sinking and digging control task parameters and the prepared real-time data into the sinking and digging control model, and the model will make decisions and predictions based on the input data using the branch structure of the random forest algorithm;

[0026] The sinking and excavation control model generates simulation data of the multi-drive system of the grab ship unloader at the power plant wharf when performing the sinking and excavation task based on the input data and internal algorithm. The simulation data when performing the sinking and excavation task includes the expected motion trajectory of each drive mechanism, load changes and system status.

[0027] Furthermore, in the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf described in the present invention, the step S104 comprises:

[0028] Loading the sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf generated in step S103, the sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf includes the expected motion trajectory, load change and system status information of each transmission mechanism when performing the sinking and digging task;

[0029] Identify the sinking and digging control data features of the loaded simulation data, which include the movement speed and position of the grab bucket, the instantaneous change of the load, the response time of the system, and the coordination relationship between the various transmission mechanisms;

[0030] The extracted data features are sorted to form a feature data set, and data correspondence is established based on the extracted data features. The data correspondence includes real-time collection of data corresponding to these features through sensors and monitoring systems during the actual operation of the grab ship unloader at the power plant terminal;

[0031] The collected actual data is matched with the extracted data features to generate a data set to be tested.

[0032] Furthermore, in the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf described in the present invention, the step S105 comprises:

[0033] The data to be tested is aligned with the sinking and digging control simulation data in terms of timestamps, and the data to be tested is compared with the sinking and digging control simulation data item by item, including the motion trajectory of each transmission mechanism, load changes, and system state parameters;

[0034] During the comparison process, the data that differs between the data to be tested and the simulated data is identified. The data that differs between the data to be tested and the simulated data is caused by data transmission errors, sensor failures, and system state changes.

[0035] The data with differences between the identified data to be tested and the simulated data are judged to determine whether they are fluctuations within a reasonable range. If they are not fluctuations within a reasonable range, a data replacement decision is executed.

[0036] Furthermore, in the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf described in the present invention, the step S105 comprises:

[0037] For the data that needs to be replaced, the corresponding part in the sinking and excavation control simulation data is replaced with the data to be detected to form the adjusted sinking and excavation control data;

[0038] Verify the adjusted sinking and digging control data, and substitute the verified and qualified adjusted sinking and digging control data into the sinking and digging control model of the multi-drive system of the grab ship unloader of the power plant wharf as the input data of the model;

[0039] Generate real-time control tasks based on the processing results of the model. The real-time control tasks include control instructions and motion parameters of each transmission mechanism.

[0040] The generated real-time control tasks are transmitted to the device side, and the device side performs specific control operations.

[0041] The sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf described in the present invention has beneficial effects mainly in the following aspects:

[0042] The present invention constructs a sinking and digging control model based on random forest. The present invention can accurately predict the expected motion trajectory, load change and system state of each transmission mechanism of the grab ship unloader when performing the sinking and digging task, thereby significantly improving the accuracy of sinking and digging control.

[0043] During the data preprocessing and comparison verification process, the present invention can effectively identify and process errors and delays in data transmission, improve the accuracy of control data, and reduce control errors caused by data transmission problems. By real-time acquisition of system data, generation of simulation data, comparison verification, and generation of real-time control tasks, the present invention can significantly shorten the system response time and improve the working efficiency of the grab ship unloader. By predicting and discovering potential problems in advance, the present invention can reduce the equipment failure rate, reduce downtime and maintenance costs caused by failures.

[0044] The present invention can ensure the stable operation of the grab ship unloader in a complex industrial environment, and improve the reliability and safety of the system. The sinking and excavation control method of the present invention can be applied to different material characteristics and operating environments. By adjusting the model parameters and control strategies, it can flexibly respond to various operating requirements, and improve the adaptability of the system. Through the automated sinking and excavation control and data processing process, the present invention can optimize the operating process, reduce manual intervention, and improve operating efficiency and quality.

[0045] In summary, the present invention significantly improves the sinking and digging control accuracy of the multi-transmission system of the grab ship unloader at the power plant terminal, reduces the failure rate and maintenance cost, and enhances the reliability of the system by constructing a sinking and digging control model based on random forest, combining the steps of real-time data acquisition, simulation data generation, data comparison and verification, and real-time control task generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on the drawings without paying any creative labor.

[0047] Figure 1 A schematic flow chart of a sinking and digging control method for a multi-drive system of a grab ship unloader at a power plant wharf provided by the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The technical solutions provided by the embodiments of the present invention are described in detail below in conjunction with the drawings.

[0049] In order to better understand the purpose of the present invention, the present invention is described in further detail below.

[0050] See also Figure 1 The present invention provides a sinking and digging control method for a multi-drive system of a grab ship unloader at a power plant wharf, comprising:

[0051] Step S101, obtaining basic data of the multi-drive system of the grab ship unloader at the power plant wharf, the basic data of the multi-drive system of the grab ship unloader at the power plant wharf including sensor data, position data, load data, system status data, material characteristic data, control instruction data, and historical data of the multi-drive system of the grab ship unloader at the power plant wharf;

[0052] Obtain various basic data of the multi-drive system of the grab ship unloader at the power plant terminal, including sensor data, position data, load data, system status data, material property data, control instruction data and historical data. By fully acquiring data, a rich information foundation is provided for subsequent steps.

[0053] Step S102, preprocessing the basic data of the multi-drive system of the grab ship unloader of the power plant wharf, dividing the preprocessed basic data of the multi-drive system of the grab ship unloader of the power plant wharf into a training set and a validation set, using the training set and the validation set to train the random forest model, and obtaining a sinking and digging control model of the multi-drive system of the grab ship unloader of the power plant wharf;

[0054] The acquired basic data is preprocessed and then divided into a training set and a validation set. The random forest model is trained using the training set and the validation set to obtain the sinking and digging control model of the multi-drive system of the grab ship unloader at the power plant wharf. The data quality is improved through preprocessing to ensure the accuracy of model training. The random forest model can handle complex data relationships and has strong generalization ability, and can predict the behavior of the system based on the input data.

[0055] Step S103, receiving the sinking and digging control task of the multi-drive system of the grab ship unloader of the power plant wharf, substituting the sinking and digging control task of the multi-drive system of the grab ship unloader of the power plant wharf into the sinking and digging control model of the multi-drive system of the grab ship unloader of the power plant wharf, and obtaining sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf;

[0056] Receive the sinking and excavation control task of the multi-drive system of the grab ship unloader at the power plant wharf, substitute the task parameters and real-time data into the trained sinking and excavation control model, and generate simulation data. The simulation data can reflect the expected motion trajectory and load changes of each transmission mechanism during the actual sinking and excavation process. This helps to discover potential problems in advance and provide a basis for subsequent comparison and adjustment.

[0057] Step S104, extracting data features from the sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf, obtaining sinking and digging data features of the multi-drive system of the grab ship unloader of the power plant wharf, collecting corresponding data according to the sinking and digging data features of the multi-drive system of the grab ship unloader of the power plant wharf, and obtaining data to be detected;

[0058] Data features are extracted from the simulation data to obtain the features of the submerged data. Then, the corresponding data is collected based on these features to obtain the data to be tested. Through feature extraction, the key factors that have a significant impact on the system behavior can be identified. The data to be tested is collected during the actual operation process and is used to compare with the simulation data to verify the accuracy of the model.

[0059] Step S105, compare the data to be detected with the sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf. If the comparison data results are inconsistent, the sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf replaces the inconsistent data, and uses the replaced data as the sinking and digging control data of the multi-drive system of the grab ship unloader of the power plant wharf, substitutes the sinking and digging control data of the multi-drive system of the grab ship unloader of the power plant wharf into the sinking and digging model of the multi-drive system of the grab ship unloader of the power plant wharf, outputs the real-time control task, transmits the real-time control task to the device end, and the device end executes the real-time control task.

[0060] The data to be tested is compared with the simulated data. If the data is inconsistent, the simulated data is used to replace the inconsistent part of the data to be tested. Then, the replaced data is substituted into the sinking and excavation control model, the real-time control task is output, and it is transmitted to the device for execution. Data comparison and replacement can timely discover and correct data errors or delays to ensure the accuracy and stability of control data. The generation and execution of real-time control tasks can achieve precise control of the system and avoid motion errors caused by data transmission stability problems or complex coupling relationships of the system.

[0061] In summary, through the coordinated work of these five steps, the present invention can effectively solve the problems of data transmission stability being susceptible to interference, control command delays, and motion errors caused by the complex coupling relationship between the transmission mechanisms in the multi-transmission system. It can not only improve the operating efficiency and accuracy of the multi-transmission system of the grab ship unloader at the power plant terminal, but also reduce maintenance costs and safety risks.

[0062] Specifically, the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf described in the present invention, the step S101 comprises:

[0063] From the multi-drive system of the grab ship unloader at the power plant dock, real-time data is collected through the arranged displacement sensors, force sensors, and speed sensors;

[0064] Use global positioning system, laser rangefinder or encoder positioning equipment to collect real-time position data of the grab in three-dimensional space;

[0065] The weight data of the material in the grab bucket is collected in real time through a weighing sensor or load monitoring device;

[0066] Obtain system status data from the control system of the multi-drive system, including the voltage, current, power factor of the electric drive system, the operating status of the drive mechanism, and alarm information;

[0067] The control command data are obtained from the operator console or the automatic control system. The control command data include the lifting, opening, closing, and moving action instructions of the grab bucket, and the set value of the sinking and excavation amount.

[0068] In step S101, the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf according to the present invention specifically implements the following data collection process:

[0069] From the multi-drive system of the grab ship unloader at the power plant wharf, the arranged displacement sensors, force sensors, and speed sensors are used to collect data in real time. These data can reflect the real-time motion status of the grab and its transmission mechanism, such as displacement, force, and speed. Using positioning equipment such as the global positioning system (GPS), laser rangefinders, or encoders, the real-time position data of the grab in three-dimensional space is accurately collected. This helps to achieve accurate positioning and navigation of the grab. The weight data of the material in the grab is collected in real time through weighing sensors or load monitoring devices. This is crucial for controlling the lifting and sinking depth of the grab, ensuring that the grab can stably grab and unload materials during operation.

[0070] Obtain system status data from the control system of the multi-drive system, including electrical parameters such as voltage, current, power factor, etc. of the electrical drive system, as well as the operating status and alarm information of the drive mechanism, etc. These data can reflect the overall health and performance of the system and provide a basis for fault prediction and timely handling.

[0071] The control command data is obtained from the operator console or automatic control system, including the lifting, opening, closing, and moving action instructions of the grab bucket, as well as the set value of the sinking and excavation volume, etc. These instructions are the core of controlling the grab bucket operation, ensuring the accuracy and efficiency of the operation.

[0072] By comprehensively collecting these basic data, step S101 provides a reliable information basis for subsequent data preprocessing, model training and real-time control, thereby effectively solving the problem that the stability of data transmission is easily disturbed in complex industrial environments, resulting in control command delays, and the complex coupling relationship between the transmission mechanisms in the multi-transmission system causes motion errors.

[0073] Specifically, the sinking and digging control method of the multi-drive system of the grab ship unloader of a power plant wharf according to the present invention, the step S102 comprises:

[0074] The preprocessed data is randomly divided into a training set and a validation set. The training set is used to train the model, and the validation set is used to evaluate the performance of the model.

[0075] The random forest model is selected as the basis of the subsidence control model, the training set data is used to train the random forest model, and the validation set data is used to validate the trained random forest model;

[0076] The trained random forest model is saved in a loadable format to obtain the sinking and digging control model of the multi-drive system of the grab ship unloader at the power plant wharf.

[0077] In step S102, the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf of the present invention processes the data in depth and successfully constructs the sinking and digging control model. The specific process is as follows:

[0078] The preprocessed data is randomly divided into a training set and a validation set. The training set is used to train the model so that it can learn the rules and patterns in the data; the validation set is used to evaluate the performance of the model to ensure that the model has good generalization ability and accuracy.

[0079] The random forest model was selected as the basis for the sinking and excavation control model. Random forest is an ensemble learning method that improves the accuracy and stability of the model by building multiple decision trees and combining their prediction results. This model performs well in processing complex and high-dimensional data and is very suitable for sinking and excavation control of the multi-drive system of the grab ship unloader at the power plant terminal.

[0080] The random forest model is trained using the training set data to learn the various characteristics and laws of the sinking process of the grab ship unloader multi-drive system. Then, the trained model is verified using the validation set data to evaluate its performance. By continuously adjusting and optimizing the model parameters, the model can be ensured to have the best prediction effect.

[0081] The trained random forest model is saved in a loadable format to obtain the sinking and digging control model of the multi-drive system of the grab ship unloader at the power plant wharf. In this way, in subsequent practical applications, the model can be directly loaded for prediction and control without retraining, which greatly improves efficiency and accuracy.

[0082] Through the processing of step S102, the present invention successfully constructs a random forest-based sinking and excavation control model for the multi-drive system of the grab ship unloader at the power plant wharf. The model can accurately predict the key parameters such as the motion trajectory and load change of the grab during the sinking and excavation process, providing strong support for subsequent real-time control. At the same time, through steps such as data division and model verification, the accuracy of the model is improved, and the problems of data transmission stability being easily disturbed, control command delay, and motion errors caused by complex coupling relationships between transmission mechanisms in the multi-drive system are effectively solved.

[0083] Specifically, the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf described in the present invention, the step S103 comprises:

[0084] Receive the excavation control task from the control system or operator console of the grab ship unloader at the power plant dock, the excavation control task including the excavation depth, speed, position, material type and grab size;

[0085] Parse the received sinking and excavation control task and extract the control parameters, which include the starting position, ending position, target depth and expected speed of the sinking and excavation;

[0086] According to the excavation control task, sensor data, position data and load data are extracted from the real-time data of the multi-drive system of the grab ship unloader at the power plant dock as the initial conditions of the model input;

[0087] Load the sinking and digging control model of the multi-drive system of the grab ship unloader of the power plant terminal trained in step S102, substitute the parsed sinking and digging control task parameters and the prepared real-time data into the sinking and digging control model, and the model will make decisions and predictions based on the input data using the branch structure of the random forest algorithm;

[0088] The sinking and excavation control model generates simulation data of the multi-drive system of the grab ship unloader at the power plant wharf when performing the sinking and excavation task based on the input data and internal algorithm. The simulation data when performing the sinking and excavation task includes the expected motion trajectory of each drive mechanism, load changes and system status.

[0089] In step S103, the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf according to the present invention realizes the process of converting the sinking and digging control task into specific simulation data, and the specific steps are as follows:

[0090] Receive excavation control tasks from the control system or operator console of the grab ship unloader at the power plant terminal. These tasks usually include key information such as excavation depth, speed, position, material type and grab size.

[0091] The received excavation control task is parsed to extract specific control parameters, including the starting position, end position, target depth, and expected speed of the excavation, which will directly determine the movement trajectory and speed of the grab during the excavation process.

[0092] According to the requirements of the sinking and excavation control task, relevant sensor data, position data and load data are extracted from the real-time data of the multi-drive system of the grab ship unloader at the power plant wharf. These data are used as the initial conditions of the model input and can reflect the current state of the grab and its drive system.

[0093] The sinking and digging control model of the multi-drive system of the grab ship unloader of the power plant terminal trained in step S102 is loaded. This model has learned various characteristics and laws in the sinking and digging process of the multi-drive system of the grab ship unloader, and can make accurate predictions and decisions based on the input data.

[0094] Substitute the parsed excavation control task parameters and the prepared real-time data into the excavation control model. Based on these data, the model will use the branch structure of the random forest algorithm to make decisions and predictions, and generate simulation data when the grab performs the excavation task.

[0095] Based on the input data and internal algorithms, the sinking and excavation control model generates simulation data of the multi-drive system of the grab ship unloader at the power plant wharf when performing sinking and excavation tasks. These simulation data include key information such as the expected motion trajectory of each drive mechanism, load changes, and system status, which can reflect the actual movement of the grab during the sinking and excavation process.

[0096] Through the processing of step S103, the present invention successfully converts the sinking and excavation control task into specific simulation data.

[0097] Specifically, the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf described in the present invention, the step S104 comprises:

[0098] Loading the sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf generated in step S103, the sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf includes the expected motion trajectory, load change and system status information of each transmission mechanism when performing the sinking and digging task;

[0099] Identify the sinking and digging control data features of the loaded simulation data, which include the movement speed and position of the grab bucket, the instantaneous change of the load, the response time of the system, and the coordination relationship between the various transmission mechanisms;

[0100] The extracted data features are sorted to form a feature data set, and data correspondence is established based on the extracted data features. The data correspondence includes real-time collection of data corresponding to these features through sensors and monitoring systems during the actual operation of the grab ship unloader at the power plant terminal;

[0101] The collected actual data is matched with the extracted data features to generate a data set to be tested.

[0102] In step S104, the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf of the present invention further extracts features from the simulation data, and corresponds and matches them with the actually collected data. The specific steps are as follows:

[0103] The sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf generated in step S103 are loaded. These data include the expected motion trajectory, load change and system status information of each drive mechanism when performing the sinking and digging task, which is the basis for subsequent feature extraction.

[0104] An in-depth analysis of the loaded simulation data is carried out to identify the characteristics of the sinking and excavation control data. The sinking and excavation control data characteristics include the movement speed and position of the grab, the instantaneous change of the load, the response time of the system, and the coordination relationship between the various transmission mechanisms, which can fully reflect the dynamic behavior of the grab during the sinking and excavation process.

[0105] The extracted data features are sorted to form a feature data set, which contains all the data features that have an important impact on sinking and excavation control, providing convenience for subsequent data correspondence and matching.

[0106] Based on the extracted data features, a data correspondence relationship is established. This relationship indicates which real-time collected data corresponds to these features during the actual operation of the grab ship unloader at the power plant dock. For example, the grab movement speed data collected by the sensor corresponds to the movement speed feature in the feature data set.

[0107] During the actual operation of the grab ship unloader at the power plant wharf, data corresponding to the features are collected in real time through sensors, monitoring systems, etc. Then, these actual data are matched and matched with the extracted data features to generate a data set to be tested. The data set to be tested contains all the key data in the actual operation process and will be used for subsequent data comparison and verification.

[0108] Through the processing of step S104, the present invention successfully extracts the key data features of sinking and excavation control from the simulation data, and corresponds and matches them with the actual collected data. This provides strong support for subsequent data comparison, model verification and real-time control, and ensures the accuracy of the multi-drive system of the grab ship unloader at the power plant wharf when performing sinking and excavation tasks.

[0109] Specifically, the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf described in the present invention, the step S105 comprises:

[0110] The data to be tested is aligned with the sinking and digging control simulation data in terms of timestamps, and the data to be tested is compared with the sinking and digging control simulation data item by item, including the motion trajectory of each transmission mechanism, load changes, and system state parameters;

[0111] During the comparison process, the data that differs between the data to be tested and the simulated data is identified. The data that differs between the data to be tested and the simulated data is caused by data transmission errors, sensor failures, and system state changes.

[0112] The data with differences between the identified data to be tested and the simulated data are judged to determine whether they are fluctuations within a reasonable range. If they are not fluctuations within a reasonable range, a data replacement decision is executed.

[0113] In step S105, the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf of the present invention performs data comparison and verification to ensure the consistency between the actual operation data and the simulation data. The specific steps are as follows:

[0114] The data to be tested and the sinking and excavation control simulation data are aligned in timestamp to ensure the accuracy and reliability of the comparison. Then, the data to be tested and the sinking and excavation control simulation data are compared item by item, including key information such as the motion trajectory of each transmission mechanism, load changes, and system status parameters.

[0115] During the comparison process, carefully identify the differences between the data to be tested and the simulated data. These differences may be caused by various reasons such as data transmission errors, sensor failures, system status changes, etc. By identifying the differences, potential problems can be discovered in a timely manner, providing a basis for subsequent judgment and decision-making.

[0116] Make a reasonable judgment on the identified difference data. Determine whether these differences are fluctuations within a reasonable range. For example, small differences caused by normal reasons such as environmental factors and equipment wear are usually acceptable. However, if the difference exceeds the preset reasonable range, further analysis of the cause is required.

[0117] If the difference data does not fluctuate within a reasonable range, a data replacement decision needs to be made. This means replacing the outliers in the data to be tested with the corresponding values ​​in the simulated data to ensure the accuracy of the data. Data replacement decisions need to be made carefully to avoid introducing new errors or problems.

[0118] Through the processing of step S105, the present invention successfully realizes the comparison and verification of the data to be detected and the sinking and digging control simulation data. This process is crucial to ensure the sinking and digging control accuracy and stability of the multi-drive system of the grab ship unloader of the power plant wharf. By timely discovering and processing data differences, control errors caused by data transmission errors, sensor failures, etc. can be effectively avoided, thereby improving the operating efficiency of the entire system.

[0119] Specifically, the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf described in the present invention, the step S105 comprises:

[0120] For the data that needs to be replaced, the corresponding part in the sinking and excavation control simulation data is replaced with the data to be detected to form the adjusted sinking and excavation control data;

[0121] Verify the adjusted sinking and digging control data, and substitute the verified and qualified adjusted sinking and digging control data into the sinking and digging control model of the multi-drive system of the grab ship unloader of the power plant wharf as the input data of the model;

[0122] Generate real-time control tasks based on the processing results of the model. The real-time control tasks include control instructions and motion parameters of each transmission mechanism.

[0123] The generated real-time control tasks are transmitted to the device side, and the device side performs specific control operations.

[0124] In the detailed description of step S105, the sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant wharf according to the present invention elaborates on the process of data replacement, verification, model input, and control task generation and transmission, and the specific steps are as follows:

[0125] For the data that needs to be replaced, the corresponding part of the sinking and excavation control simulation data is accurately replaced with the data to be tested. This step ensures the accuracy of the data and eliminates the impact of abnormal data on control accuracy caused by data transmission errors, sensor failures, etc.

[0126] The adjusted sinking and excavation control data is strictly verified. The verification process includes checking the integrity, consistency and rationality of the data, so that the replaced data can accurately reflect the actual operating status of the grab ship unloader multi-drive system. The qualified data will be used for subsequent model input and control task generation.

[0127] The adjusted sinking and digging control data that has passed the verification is substituted into the sinking and digging control model of the multi-drive system of the grab ship unloader of the power plant terminal as the input data of the model. Based on the input data, the model will simulate and predict the sinking and digging process of the grab bucket in combination with its internal algorithm and decision-making mechanism, and generate a real-time control strategy.

[0128] Based on the processing results of the model, real-time control tasks are generated. These tasks include control instructions and motion parameters of each transmission mechanism, such as motor speed, direction, torque, etc., as well as the movement trajectory and speed of the grab bucket. The generation of control tasks ensures that the grab bucket unloader can perform sinking and excavation operations according to the predetermined goals and requirements.

[0129] The generated real-time control task is transmitted to the device side through the communication network or control system. After receiving the control task, the device side will perform specific control operations according to the task requirements, such as adjusting the speed of the motor, controlling the movement trajectory of the grab bucket, etc. This step realizes the seamless transfer and execution of the control task from the model to the actual device.

[0130] Through the detailed processing of step S105, the sinking and digging control method of the multi-transmission system of the grab ship unloader at the power plant wharf described in the present invention realizes the timely processing of data anomalies, the accurate generation and effective execution of control tasks, thereby improving the control accuracy, stability and operation efficiency of the entire system.

[0131] The technical solution of the present invention solves the problem of errors in the sinking and digging control of the multi-drive system of the grab ship unloader of the power plant wharf in a complex industrial environment through the following steps:

[0132] First, in step S101, the basic data of the multi-drive system of the grab ship unloader at the power plant wharf is fully acquired, including but not limited to sensor data, position data, load data, system status data, material property data, control instruction data and historical data. These data provide a solid foundation for subsequent model training and sinking control.

[0133] In step S102, the acquired basic data is preprocessed and divided into a training set and a validation set. The random forest model is trained using these data to obtain a sinking and digging control model for the multi-drive system of the grab ship unloader at the power plant wharf. This model can predict various parameters in the sinking and digging process based on the input data, such as the motion trajectory of the drive mechanism, load changes, etc.

[0134] Then, in step S103, the sinking and excavation control task is received, and the task parameters and real-time data are substituted into the trained sinking and excavation control model to obtain simulation data. The simulation data simulates the expected motion trajectory, load changes, etc. of each transmission mechanism during the actual sinking and excavation process, providing a basis for subsequent comparison and adjustment.

[0135] In step S104, data features are extracted from the simulation data to obtain sinking data features, and corresponding data are collected according to these features to obtain data to be tested. These data are collected during the actual operation and are used for comparison with the simulation data.

[0136] Finally, in step S105, the data to be tested is compared with the simulated data. If the data is inconsistent, the simulated data is used to replace the inconsistent part of the data to be tested to improve the accuracy of the control data. The adjusted data is substituted into the sinking and excavation control model to generate a real-time control task and transmitted to the device for execution.

[0137] Through this series of steps, the present invention effectively solves the problem that data transmission stability is susceptible to interference, control command delays, and motion errors caused by complex coupling relationships between transmission mechanisms in a multi-transmission system. The method of the present invention can adjust control data in real time and accurately, so that the sinking and digging control of the multi-transmission system of the grab ship unloader of the power plant wharf is accurate and error-free.

Claims

1. A sinking and digging control method for a multi-drive system of a grab ship unloader at a power plant wharf, characterized in that: include: Step S101, obtaining basic data of the multi-drive system of the grab ship unloader at the power plant wharf, the basic data of the multi-drive system of the grab ship unloader at the power plant wharf including sensor data, position data, load data, system status data, material characteristic data, control instruction data, and historical data of the multi-drive system of the grab ship unloader at the power plant wharf; Step S102, preprocessing the basic data of the multi-drive system of the grab ship unloader of the power plant wharf, dividing the preprocessed basic data of the multi-drive system of the grab ship unloader of the power plant wharf into a training set and a validation set, using the training set and the validation set to train the random forest model, and obtaining a sinking and digging control model of the multi-drive system of the grab ship unloader of the power plant wharf; Step S103, receiving the sinking and digging control task of the multi-drive system of the grab ship unloader of the power plant wharf, substituting the sinking and digging control task of the multi-drive system of the grab ship unloader of the power plant wharf into the sinking and digging control model of the multi-drive system of the grab ship unloader of the power plant wharf, and obtaining sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf; Step S104, extracting data features from the sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf, obtaining sinking and digging data features of the multi-drive system of the grab ship unloader of the power plant wharf, collecting corresponding data according to the sinking and digging data features of the multi-drive system of the grab ship unloader of the power plant wharf, and obtaining data to be detected; Step S105, compare the data to be detected with the sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf. If the comparison data results are inconsistent, the sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf replaces the inconsistent data, and uses the replaced data as the sinking and digging control data of the multi-drive system of the grab ship unloader of the power plant wharf, substitutes the sinking and digging control data of the multi-drive system of the grab ship unloader of the power plant wharf into the sinking and digging model of the multi-drive system of the grab ship unloader of the power plant wharf, outputs the real-time control task, transmits the real-time control task to the device end, and the device end executes the real-time control task.

2. The sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant dock as claimed in claim 1 is characterized in that: The step S101 includes: From the multi-drive system of the grab ship unloader at the power plant dock, real-time data is collected through the arranged displacement sensors, force sensors, and speed sensors; Use global positioning system, laser rangefinder or encoder positioning equipment to collect real-time position data of the grab in three-dimensional space; The weight data of the material in the grab bucket is collected in real time through a weighing sensor or load monitoring device; Obtain system status data from the control system of the multi-drive system, including the voltage, current, power factor of the electric drive system, the operating status of the drive mechanism, and alarm information; The control command data are obtained from the operator console or the automatic control system. The control command data include the lifting, opening, closing, and moving action instructions of the grab bucket, and the set value of the sinking and excavation amount.

3. The sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant dock as claimed in claim 1, characterized in that: The step S102 includes: The preprocessed data is randomly divided into a training set and a validation set. The training set is used to train the model, and the validation set is used to evaluate the performance of the model. The random forest model is selected as the basis of the subsidence control model, the training set data is used to train the random forest model, and the validation set data is used to validate the trained random forest model; The trained random forest model is saved in a loadable format to obtain the sinking and digging control model of the multi-drive system of the grab ship unloader at the power plant wharf.

4. The sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant dock as claimed in claim 1, characterized in that: The step S103 includes: Receive the excavation control task from the control system or operator console of the grab ship unloader at the power plant dock, the excavation control task including the excavation depth, speed, position, material type and grab size; Parse the received sinking and excavation control task and extract the control parameters, which include the starting position, ending position, target depth and expected speed of the sinking and excavation; According to the excavation control task, sensor data, position data and load data are extracted from the real-time data of the multi-drive system of the grab ship unloader at the power plant dock as the initial conditions of the model input; Load the sinking and digging control model of the multi-drive system of the grab ship unloader of the power plant terminal trained in step S102, substitute the parsed sinking and digging control task parameters and the prepared real-time data into the sinking and digging control model, and the model will make decisions and predictions based on the input data using the branch structure of the random forest algorithm; The sinking and excavation control model generates simulation data of the multi-drive system of the grab ship unloader at the power plant wharf when performing the sinking and excavation task based on the input data and internal algorithm. The simulation data when performing the sinking and excavation task includes the expected motion trajectory of each drive mechanism, load changes and system status.

5. The sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant dock as claimed in claim 1, characterized in that: The step S104 includes: Loading the sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf generated in step S103, the sinking and digging control simulation data of the multi-drive system of the grab ship unloader of the power plant wharf includes the expected motion trajectory, load change and system status information of each transmission mechanism when performing the sinking and digging task; Identify the sinking and digging control data features of the loaded simulation data, which include the movement speed and position of the grab bucket, the instantaneous change of the load, the response time of the system, and the coordination relationship between the various transmission mechanisms; The extracted data features are sorted to form a feature data set, and data correspondence is established based on the extracted data features. The data correspondence includes real-time collection of data corresponding to these features through sensors and monitoring systems during the actual operation of the grab ship unloader at the power plant terminal; The collected actual data is matched with the extracted data features to generate a data set to be tested.

6. The sinking and digging control method of the multi-drive system of the grab ship unloader of the power plant dock as claimed in claim 1, characterized in that: The step S105 includes: The data to be tested is aligned with the sinking and digging control simulation data in terms of timestamps, and the data to be tested is compared with the sinking and digging control simulation data item by item, including the motion trajectory of each transmission mechanism, load changes, and system state parameters; During the comparison process, the data that differs between the data to be tested and the simulated data is identified. The data that differs between the data to be tested and the simulated data is caused by data transmission errors, sensor failures, and system state changes. The data with differences between the identified data to be tested and the simulated data are judged to determine whether they are fluctuations within a reasonable range. If they are not fluctuations within a reasonable range, a data replacement decision is executed.

7. A sinking and digging control method for a multi-drive system of a grab ship unloader at a power plant dock as claimed in claim 6, characterized in that: The step S105 includes: For the data that needs to be replaced, the corresponding part in the sinking and excavation control simulation data is replaced with the data to be detected to form the adjusted sinking and excavation control data; Verify the adjusted sinking and digging control data, and substitute the verified and qualified adjusted sinking and digging control data into the sinking and digging control model of the multi-drive system of the grab ship unloader of the power plant wharf as the input data of the model; Generate real-time control tasks based on the processing results of the model. The real-time control tasks include control instructions and motion parameters of each transmission mechanism. The generated real-time control tasks are transmitted to the device side, and the device side performs specific control operations.

Images