Methods and related equipment for the movement control of magnetic drive conveyor systems

Abstract

The present application proposes a method and related equipment for controlling the movement of a magnetic drive conveyor system. The method includes: first, acquiring the electrical signal and current operating parameters of the target mover at its current position in the magnetic drive conveyor system, and acquiring the target operating parameters at the target position; then, determining the load mass of the target mover based on the electrical signal; finally, generating operating control parameters based on the load mass, current operating parameters, and target operating parameters, and controlling the movement of the target mover based on the operating control parameters, so as to improve the accuracy of the mover operation control in the magnetic drive conveyor system and reduce the setup difficulty and cost of the magnetic drive conveyor system.

Description

Technical Field

[0001] This application relates to the field of control technology, and in particular to a method and related equipment for controlling the movement of a mover in a magnetic drive conveyor system. Background Technology

[0002] Maglev transport technology has wide applications in industrial automation, such as assembling and packaging goods on logistics lines, and SMT (Surface Mount Technology) of precision electronic components. These applications typically require the movers to run sequentially on a maglev transport track, performing processing operations on the workpieces on the movers during operation. To further improve the efficiency of the processing flow, appropriate operating parameters need to be pre-defined for each mover.

[0003] In related technologies, before transporting the mover on a maglev transport track, the overall operating parameters are typically planned in advance based on the target operating parameter requirements of the mover on the maglev transport track, and the mover is controlled to run on the maglev transport track based on these planned operating parameters. However, during the operation of the mover, the load mass of the workpiece it carries needs to be processed, which changes the mover's load mass. As a result, controlling the mover's operation based on the original planned operating parameters will not be able to achieve the required target operating parameter requirements, leading to poor accuracy in the mover's operation control. Summary of the Invention

[0004] This application provides a method and related equipment for controlling the movement of a mover in a magnetic drive conveyor system, which can improve the accuracy of the movement control of the mover when conveying workpieces in the magnetic drive conveyor system.

[0005] To achieve the above objectives, a first aspect of this application proposes a method for controlling the movement of a mover in a magnetically driven conveyor system, the method comprising:

[0006] Acquire the electrical signal and current operating parameters of the target mover at its current position in the magnetic drive conveyor system, and acquire the target operating parameters at the target position;

[0007] The load mass of the target mover is determined based on the electrical signal;

[0008] Based on the load quality, the current operating parameters, and the target operating parameters, operating control parameters are generated, and the target actuator is operated and controlled based on the operating control parameters.

[0009] In some embodiments, determining the load mass of the target mover based on the electrical signal includes:

[0010] Obtain the target workpiece type corresponding to the target workpiece carried by the target mover;

[0011] The electrical signal features are extracted based on Fourier transform.

[0012] The electrical signal characteristics and the target workpiece type are input into the load quality identification model for data processing to obtain the load quality.

[0013] In some embodiments, the electrical signal features include signal phase angle difference, power factor, and total harmonic distortion. The step of extracting features from the electrical signal based on Fourier transform to obtain the electrical signal features includes:

[0014] The electrical signal is converted to the frequency domain based on the Fourier transform to obtain a frequency domain electrical signal, which includes a frequency domain current signal and a frequency domain voltage signal.

[0015] The signal phase angle difference between the frequency domain current signal and the frequency domain voltage signal is obtained, and the power factor is obtained based on the cosine value of the signal phase angle difference;

[0016] The fundamental current amplitude and harmonic current amplitude in the frequency domain current signal are obtained, and the current harmonic distortion is obtained based on the ratio of the current harmonic amplitude to the fundamental current amplitude.

[0017] The voltage fundamental amplitude and voltage harmonic amplitude in the frequency domain voltage signal are obtained, and the voltage harmonic distortion is obtained based on the ratio of the voltage harmonic amplitude to the voltage fundamental amplitude.

[0018] The total harmonic distortion is obtained based on the average values ​​of the current harmonic distortion and the voltage harmonic distortion.

[0019] In some embodiments, the current operating parameters include the current operating speed and the current operating acceleration, and the target operating parameters include the target operating speed. Generating operating control parameters based on the load quality, the current operating parameters, and the target operating parameters includes:

[0020] Obtain the positional distance between the target location and the current location;

[0021] The control acceleration is generated based on the target operating speed, the current operating speed, and the position distance;

[0022] The operating control parameters are generated based on the load mass and the control acceleration.

[0023] In some embodiments, generating control acceleration based on the target running speed, the current running speed, and the positional distance includes:

[0024] Based on the target operating speed, the current operating speed, and the position distance, an initial control acceleration is generated;

[0025] The current running speed is adjusted to the initial control acceleration based on the preset acceleration, and the changed running speed and changed position of the target mover after the acceleration adjustment are obtained;

[0026] The control acceleration is obtained based on the changing running speed, the changing position, the target position, and the target running speed.

[0027] In some embodiments, generating the operating control parameters based on the load mass and the control acceleration includes:

[0028] Based on the load mass and the control acceleration, the control thrust is obtained;

[0029] Obtain the stator coil parameters of the stator in the magnetic drive conveyor system;

[0030] The operating control parameters are generated based on the stator coil parameters and the control thrust.

[0031] In some embodiments, the construction step of the load quality identification model includes:

[0032] Acquire multiple training signal feature data and the training workpiece type corresponding to each training signal feature data, and generate multiple decision tree nodes based on the training signal feature data;

[0033] Multiple first sub-decision tree models are generated based on the decision tree nodes, and the multiple training signal feature data are divided into a first sub-feature data set corresponding to each first sub-decision tree model based on the decision tree nodes.

[0034] The decision tree nodes are segmented, and a second sub-decision tree model associated with the first sub-decision tree model is generated based on the segmented decision tree nodes. The first sub-feature data set is divided into a second feature data set corresponding to each second sub-decision tree model until the segmented subsets are less than a preset data quantity threshold.

[0035] An initial load quality identification model is obtained based on all the decision tree nodes, the first sub-decision tree model, and the second sub-decision tree model. The initial load quality identification model is then trained multiple times based on the multiple training signal feature data and the training workpiece type. Finally, the load quality identification model is obtained based on the trained initial load quality identification model.

[0036] In some embodiments, the step of controlling the operation of the target mover based on the operation control parameters includes:

[0037] The load mass difference between the load mass and the preceding load mass of the target mover during the last operation control is obtained;

[0038] When the load quality difference is greater than the preset quality difference, the target mover is controlled to operate based on the operation control parameters.

[0039] In some embodiments, the step of controlling the operation of the target mover based on the operation control parameters includes:

[0040] Obtain the difference between the operating control parameters and the preceding operating control parameters of the target mover during the previous operating control;

[0041] When the difference in the control parameters is greater than the preset control difference, multiple progressive operation control parameters are generated between the preceding operation control parameters and the operation control parameters, and the target mover is controlled based on the multiple progressive operation control parameters.

[0042] To achieve the above objectives, a second aspect of this application provides a mover operation control device for a magnetic drive conveyor system, the device comprising:

[0043] The parameter acquisition module is used to acquire the electrical signal and current operating parameters of the target mover at its current position in the magnetic drive conveyor system, as well as the target operating parameters at the target position.

[0044] A load quality calculation module is used to determine the load quality of the target mover based on the electrical signal;

[0045] The operation control module is used to generate operation control parameters based on the load quality, the current operation parameters and the target operation parameters, and to perform operation control on the target mover based on the operation control parameters.

[0046] To achieve the above objectives, a third aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the mover operation control method of the magnetic drive conveyor system as described in the first aspect.

[0047] To achieve the above objectives, a fourth aspect of the present application provides a storage medium, which is a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the mover operation control method of the magnetic drive conveyor system described in the first aspect.

[0048] This application proposes a method and related equipment for controlling the movement of a mover in a magnetic drive conveyor system. The method includes: first, acquiring the electrical signal and current operating parameters of the target mover at its current position in the magnetic drive conveyor system, and acquiring the target operating parameters at the target position; then, determining the load mass of the target mover based on the electrical signal; and finally, generating operating control parameters based on the load mass, current operating parameters, and target operating parameters, and controlling the movement of the target mover based on the operating control parameters. This application addresses a target mover carrying a workpiece that operates in real-time on a magnetic drive conveyor system. It accurately determines the real-time changing load mass of the target mover on the magnetic drive conveyor system based on the real-time electrical signal of the target mover, and then generates operating control parameters based on this load mass to ensure that the mover reaches the target operating parameters at the target position, thereby improving the accuracy of mover operation control in the magnetic drive conveyor system. Furthermore, by using the real-time electrical signal of the target mover to calculate the load mass of the target mover, the complexity of setting up a quality detection device in the magnetic drive conveyor system is avoided, thus reducing the difficulty and cost of setting up the magnetic drive conveyor system.

[0049] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the description, claims and drawings. Attached Figure Description

[0050] Figure 1 This is a schematic diagram of the structure of a magnetic drive conveying system provided in an embodiment of this application.

[0051] Figure 2 This is a flowchart of a mover operation control method for a magnetic drive conveyor system provided in another embodiment of this application.

[0052] Figure 3 yes Figure 2 The flowchart for step 202.

[0053] Figure 4 yes Figure 3 The flowchart for step 302.

[0054] Figure 5 This is a flowchart illustrating the construction of a load quality identification model provided in another embodiment of this application.

[0055] Figure 6 This is a schematic diagram of the structure of an initial load quality identification model provided in another embodiment of this application.

[0056] Figure 7 yes Figure 2 The flowchart for step 203.

[0057] Figure 8 yes Figure 7 The flowchart for step 702.

[0058] Figure 9 This is a schematic diagram illustrating the generation of controlled acceleration, provided in another embodiment of this application.

[0059] Figure 10 yes Figure 7 The flowchart for step 703.

[0060] Figure 11 yes Figure 2 Another flowchart for step 203.

[0061] Figure 12 yes Figure 2 Another flowchart for step 203.

[0062] Figure 13 This is a schematic diagram of the structure of the mover operation control device of a magnetic drive conveyor system provided in an embodiment of this application.

[0063] Figure 14 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0065] It should be noted that although functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart.

[0066] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0067] Maglev transport technology has wide applications in industrial automation, such as assembling and packaging goods on logistics lines, and SMT (Surface Mount Technology) of precision electronic components. These applications typically require the movers to run sequentially on a maglev transport track, performing processing operations on the workpieces on the movers during operation. To further improve the efficiency of the processing flow, appropriate operating parameters need to be pre-defined for each mover.

[0068] In related technologies, before transporting the mover on a maglev transport track, the overall operating parameters are typically planned in advance based on the target operating parameter requirements of the mover on the maglev transport track, and the mover is controlled to run on the maglev transport track based on these planned operating parameters. However, during the operation of the mover, the load mass of the workpiece it carries needs to be processed, which changes the mover's load mass. As a result, controlling the mover's operation based on the original planned operating parameters will not be able to achieve the required target operating parameter requirements, leading to poor accuracy in the mover's operation control.

[0069] To improve the accuracy of mover operation control in a magnetic drive conveyor system during workpiece transport, this application embodiment targets a target mover carrying a workpiece that operates in real-time on the magnetic drive conveyor system. Based on the real-time electrical signals of the target mover, the real-time changing load mass of the target mover on the magnetic drive conveyor system is accurately determined. Then, based on this load mass, operating control parameters are generated to ensure the mover reaches the target operating parameters at the target position, thereby improving the accuracy of mover operation control in the magnetic drive conveyor system. Furthermore, by using the real-time electrical signals of the target mover to calculate the load mass, the complexity of setting up a quality detection device in the magnetic drive conveyor system is avoided, thus reducing the difficulty and cost of setting up the magnetic drive conveyor system.

[0070] To better illustrate the mover operation control method of the magnetic drive conveyor system provided in this application embodiment, this embodiment first describes a magnetic drive conveyor system applying the mover control method. (Refer to...) Figure 1 The diagram shown is a structural schematic of a magnetic drive conveying system provided in an embodiment of this application. Figure 1 As shown, the magnetic drive conveyor system includes a magnetic levitation conveyor track and at least one mover running on the track. The mover carries a workpiece, and during operation, processing equipment performs processing operations on the workpieces carried by the mover. Furthermore, to ensure the rational operation planning of the mover on the magnetic levitation conveyor track, the mover is typically pre-set to reach a specific position (e.g., ...). Figure 1 When the target position is reached, the mover needs to reach the preset target operating parameters (such as a specific speed, a specific acceleration, etc.). These target positions can be the necessary mover cooperative processing speed of the processing equipment corresponding to a certain position, etc. Then, reasonable operating planning parameters are planned in advance for the mover, so as to control the mover to run on the magnetic levitation conveyor track according to the operating planning parameters, so that the mover can reach the corresponding target operating parameters when it runs to each target position.

[0071] Furthermore, multiple stators are typically installed beneath the maglev transport track. These stators are wound with coils, and when these coils are energized, they generate corresponding control magnetic fields based on parameters such as the magnitude, direction, and frequency of the current. When a mover carrying a magnet or magnetic component passes over the stator, the control magnetic field generated by the stator produces a magnetic thrust that drives the mover to run on the maglev transport track. Moreover, the current parameters of the coils in the stator can be adjusted flexibly in real time, thus allowing for flexible control of the mover's movement.

[0072] However, while allowing for flexible control, to improve the precise coordinated control between the stator and mover—that is, to avoid other electromagnetic instruments affecting the magnetic field—gravity sensors (such as pressure sensors) for real-time monitoring of the mover's load mass are typically not installed on the maglev transport track. Furthermore, as the mover operates on the maglev transport track, the load mass of the mover inevitably changes after the processing equipment processes the workpiece carried on it. This change in load mass leads to operational control deviations under the influence of pre-set operating parameters, causing the mover's operating parameters to fail to reach (or exceed) the target operating parameters when it reaches a certain target position.

[0073] Therefore, it is necessary to detect the real-time load quality of the mover in actual mover operation control, so as to regenerate new operation control parameters based on the load quality, thereby controlling the mover to run precisely to the target position with the target operation parameters.

[0074] Based on the above-described magnetic drive conveyor system, the mover operation control method of the magnetic drive conveyor system in the embodiments of this application will be described in detail below. (Refer to...) Figure 2 This is an optional flowchart of the mover operation control method for the magnetic drive conveyor system provided in the embodiments of this application. Figure 2 The method may include, but is not limited to, steps 201 to 203. It is also understood that this embodiment... Figure 2 The order of steps 201 to 203 is not specifically limited; the order of steps can be adjusted or certain steps can be added or removed according to actual needs. The mover operation control method of the magnetic drive conveyor system provided in this application embodiment can be applied to intelligent terminals, servers, computers, etc. connected to the magnetic drive conveyor system.

[0075] Step 201: Obtain the electrical signal and current operating parameters of the target mover at its current position in the magnetic drive conveyor system, and obtain the target operating parameters at the target position.

[0076] Step 201 will be described in detail below.

[0077] In some embodiments, in order to meet the operational requirements of the target mover carrying the workpiece in the magnetic drive conveyor system, operational data is usually pre-planned for the target mover to control its operation on the magnetic drive conveyor system.

[0078] To further refine the operational control of the target mover, ensuring it reaches the required operating parameters upon reaching the target position, it is necessary to acquire, in real-time, the target mover's electrical signals and current operating parameters at a specific detection position (i.e., the detection position) using electromagnetic sensors and speed sensors positioned near the magnetic drive conveyor track. This allows for the subsequent estimation of the target mover's current load mass. Finally, the operating control parameters are regenerated using the load mass, current operating parameters, and target operating parameters.

[0079] Electrical signals typically include current and voltage signals, current operating parameters include current operating speed and current operating acceleration, and target operating parameters include target operating speed.

[0080] Step 202: Determine the load mass of the target mover based on the electrical signal.

[0081] Step 202 will be described in detail below.

[0082] In some embodiments, after obtaining the current electrical signal of the target mover, the current load mass of the target mover is estimated based on the electrical signal, as described below.

[0083] Reference Figure 3 The load mass of the target mover is determined based on electrical signals, including the following steps 301 to 303.

[0084] Step 301: Obtain the target workpiece type corresponding to the target workpiece carried by the target mover.

[0085] Step 302: Extract features from the electrical signal based on Fourier transform to obtain electrical signal features.

[0086] Steps 301 to 302 are described in detail below.

[0087] In some embodiments, for the same load mass, the electrical signals generated by a mover during operation will inevitably differ depending on the type of workpiece carried by the mover. Therefore, in order to accurately estimate the load mass of the target mover, it is also necessary to pre-determine the type of target workpiece carried by the target mover.

[0088] Furthermore, after acquiring the real-time electrical signal of the target mover, features are extracted from this electrical signal based on Fourier transform to obtain electrical signal features that can characterize the current electrical properties of the target mover. These electrical signal features are then used to estimate the load mass of the target mover. The electrical signal features include signal phase angle difference, power factor, and total harmonic distortion. These features reflect the load mass of the mover and provide a basis for adjusting the control gain. The following section further describes how to obtain the corresponding electrical signal features.

[0089] Reference Figure 4 The electrical signal features are extracted based on Fourier transform, and the electrical signal features are obtained, including the following steps 401 to 405.

[0090] Step 401: Perform frequency domain conversion on the electrical signal based on Fourier transform to obtain the frequency domain electrical signal.

[0091] Step 402: Obtain the signal phase angle difference between the frequency domain current signal and the frequency domain voltage signal, and obtain the power factor based on the cosine value of the signal phase angle difference.

[0092] Step 403: Obtain the fundamental current amplitude and harmonic current amplitude in the frequency domain current signal, and obtain the current harmonic distortion based on the ratio of the current harmonic amplitude to the fundamental current amplitude.

[0093] Step 404: Obtain the voltage fundamental amplitude and voltage harmonic amplitude in the frequency domain voltage signal, and obtain the voltage harmonic distortion based on the ratio of the voltage harmonic amplitude to the voltage fundamental amplitude.

[0094] Step 405: Obtain the total harmonic distortion based on the average values ​​of current harmonic distortion and voltage harmonic distortion.

[0095] Steps 401 to 405 are described in detail below.

[0096] In some embodiments, after obtaining the current real-time electrical signal (including voltage and current signals) of the target mover, the electrical signal is first filtered to filter out redundant parts. Next, the filtered electrical signal is discretized, that is, the electrical signal is discretely sampled. The sampling frequency can be customized according to the requirements, and according to the Nyquist theorem, the sampling frequency is at least twice the highest frequency in the electrical signal.

[0097] Next, the discrete electrical signal is transformed into the frequency domain using Fast Fourier Transform (FFT) to obtain the corresponding frequency domain electrical signal, which includes the frequency domain current signal and the frequency domain voltage signal.

[0098] Furthermore, the phase angle difference θ between the frequency domain current signal and the frequency domain voltage signal is determined.

[0099] Furthermore, since the power factor (PF) is a measure of the ratio of effective power to total power in an AC circuit, that is, the ratio of effective power P to apparent power S in the circuit, i.e., PF = P / S. In an AC circuit, apparent power S is the product of voltage and current, i.e., S = V * I; effective power P is the product of apparent power S and power factor, i.e., P = S * PF. Therefore, the power factor in the circuit can be calculated based on the phase difference between current and voltage, i.e., PF = cos(θ).

[0100] Therefore, for the target mover, its power factor can be obtained based on the cosine value of the signal phase angle difference θ.

[0101] Then, based on the acquired frequency domain current signal and frequency domain voltage signal, the fundamental current amplitude A1 and the current harmonic amplitude A1 of each harmonic in the frequency domain current signal are determined one by one. n Furthermore, the current harmonic distortion THD1 is obtained based on the ratio of the square root of the sum of squares of all current harmonic amplitudes to the fundamental current amplitude, as shown in the following formula (1).

[0102]

[0103] Similarly, the fundamental voltage amplitude B1 and the voltage harmonic amplitude B of each harmonic in the frequency domain voltage signal are determined one by one. n Furthermore, the voltage harmonic distortion THD2 is obtained based on the ratio of the square root of the sum of squares of all voltage harmonic amplitudes to the voltage fundamental amplitude, as shown in the following formula (2).

[0104]

[0105] Finally, based on the mean values ​​of current harmonic distortion THD1 and voltage harmonic distortion THD2, the total harmonic distortion THD of the entire electrical signal is obtained as THD = (THD1 + THD2) / 2, and the total harmonic distortion THD, power factor PF, and signal phase angle difference θ are used as electrical signal features that reflect the current characteristics of the target mover.

[0106] Among them, the power factor is used to reflect the degree of effective energy utilization of the power supply by the load corresponding to the mover. Generally, the power factor is higher for lighter loads and lower for heavier loads. The signal phase angle difference is used to reflect the relative relationship between the current signal and the voltage signal. The phase angle will be different depending on the load mass. The total harmonic distortion is used to reflect the nonlinear characteristics of the load mass. Generally, the total harmonic distortion is lower for lighter loads and higher for heavier loads.

[0107] For example, when the load mass of the mover is relatively light, the corresponding power factor is generally close to 1, and the total harmonic distortion (THD) is low; when the load mass of the mover is neither too light nor too heavy, the corresponding power factor is between 0.8 and 0.9, and the total harmonic distortion (THD) is slightly higher; when the load mass of the mover is relatively high, the corresponding power factor is low, and the total harmonic distortion (THD) is high.

[0108] Through steps 401 to 405 above, the time-domain electrical signal is converted into a frequency-domain electrical signal using Fourier transform to determine the signal phase angle difference between voltage and current. Then, based on the signal phase angle difference, the power factor used to reflect the effective energy utilization of the target mover is determined. The total harmonic distortion used to reflect the nonlinear characteristics of the load mass is determined using the frequency-domain electrical signal to reflect the current utilization of the target mover. This allows for the accurate estimation of the load mass of the target mover using the characteristics of the electrical signal.

[0109] Step 303: Input the electrical signal characteristics and target workpiece type into the load quality identification model for data processing to obtain the load quality.

[0110] Step 303 will be described in detail below.

[0111] In some embodiments, after obtaining the current electrical signal characteristics of the target mover and the target workpiece type, these data are input into a pre-built load mass identification model specifically designed for estimating the load mass of the mover for data processing, so as to accurately estimate the current load mass of the target mover.

[0112] To ensure the reliability of the estimated load quality, the following describes how to construct the load quality identification model in advance.

[0113] Reference Figure 5 The construction steps of the load quality identification model include the following steps 501 to 504.

[0114] Step 501: Obtain multiple training signal feature data and the training workpiece type corresponding to each training signal feature data, and generate multiple decision tree nodes based on the training signal feature data.

[0115] Step 502: Generate multiple first sub-decision tree models based on decision tree nodes, and divide the multiple training signal feature data into the first sub-feature data set corresponding to each first sub-decision tree model based on the decision tree nodes.

[0116] Step 503: Segment the decision tree nodes, and generate a second sub-decision tree model associated with the first sub-decision tree model based on the segmented decision tree nodes. Divide the first sub-feature data set into the second feature data set corresponding to each second sub-decision tree model, until the segmented subsets are less than a preset data quantity threshold.

[0117] Step 504: Obtain the initial load quality identification model based on all decision tree nodes, the first sub-decision tree model, and the second sub-decision tree model. Perform multiple rounds of training on the initial load quality identification model based on multiple training signal feature data and training workpiece types. Obtain the load quality identification model based on the trained initial load quality identification model.

[0118] Steps 501 to 504 are described in detail below.

[0119] In some embodiments, it is first necessary to obtain a training dataset, which includes multiple training signal feature data, the training artifact type corresponding to each training signal feature data, and the corresponding label data.

[0120] Then, in addition to obtaining the training dataset, it is also necessary to pre-construct an initial load quality identification model so that it can be trained using the training dataset later. In this embodiment, the initial load quality identification model will be constructed based on the decision tree XGBoost algorithm. The XGBoost algorithm can better learn and capture the complex relationship between training signal feature data and mover load quality, thereby improving the estimation accuracy of the target mover load quality.

[0121] As is understandable, XGBoost (Extreme Gradient Boosting) is a high-efficiency machine learning algorithm based on the gradient boosting framework. Its core principle is to achieve high-precision predictions by constructing and optimizing multiple decision trees (usually CART trees). During the decision tree construction process, the XGBoost algorithm selects appropriate node partitioning strategies based on the characteristics of the dataset and gradually generates the decision tree model.

[0122] In some embodiments, firstly, following a similar process to steps 401 to 405 above, training data (including different training artifact types, different training signal feature data, and corresponding label data) of different movers at multiple sampling times are obtained. Next, based on this training dataset, multiple decision tree nodes are generated using the XGBoost algorithm. Then, multiple first sub-decision tree models are generated based on these decision tree nodes, and the training dataset is divided according to the number of decision tree nodes (including training signal feature data, corresponding training artifact types, and label data in the training dataset) to obtain the first sub-dataset corresponding to each first sub-decision tree model.

[0123] Next, based on model criteria such as information gain and Gini index, each decision tree node is segmented, and a second sub-decision tree model associated with the first sub-decision tree model is generated based on the segmented decision tree nodes. The first subset is then divided into second subsets corresponding to each second sub-decision tree model. The above segmentation steps are repeated until the segmented subsets are less than a preset data quantity threshold or the depth of the decision tree nodes reaches a preset maximum depth.

[0124] Finally, based on all decision tree nodes, the first sub-decision tree model, and the second sub-decision tree model, an initial load quality identification model is obtained, where each leaf node represents a probability distribution of a load quality value.

[0125] In addition, to prevent the generated initial load quality identification model from overfitting, a pruning operation can be performed on the generated initial load quality identification model, that is, by deleting some nodes or subtrees to simplify the initial load quality identification model, so as to improve the generalization ability of the model.

[0126] Reference Figure 6The diagram shown is a structural schematic of an initial load quality identification model provided in an embodiment of this application. Taking a three-layer initial load quality identification model as an example, using the XGBoost algorithm, firstly, two first sub-decision tree models (including first sub-decision tree model 1 at node A11 and first sub-decision tree model 2 at node A12) are generated based on the training dataset. Then, the balanced sample dataset is divided into first sub-datasets corresponding to the two first sub-decision tree models. Next, the nodes of the two first sub-decision tree models are further segmented to obtain multiple second sub-decision tree models associated with each first sub-decision tree model (including second sub-decision tree model 1 at node A111, second sub-decision tree model 2 at node A112, and second sub-decision tree model 2 at node A112). (e.g., decision tree model 2, etc.) At this point, each first subset is further divided into second subsets corresponding to each second sub-decision tree model. Then, the nodes of each second sub-decision tree are further divided to obtain multiple third sub-decision tree models associated with each second sub-decision tree model (including third sub-decision tree model 1 of node A1111, third sub-decision tree model 2 of node A1112, etc.), and simultaneously, each second subset is further divided into third subsets corresponding to each third sub-decision tree model. At this point, the number of third subsets after division is less than a preset data quantity threshold, and the segmentation step stops. The multiple sub-decision tree models at this point (including multiple first sub-decision tree models in the first layer, multiple second sub-decision tree models in the second layer, and multiple third sub-decision tree models in the third layer) are used as the initial load quality identification model.

[0127] After obtaining the initial load quality identification model based on the decision tree XGBoost algorithm, the initial load quality identification model is trained multiple times using the obtained training dataset (including multiple training signal feature data and training workpiece type and label data). The initial load quality identification model that has been trained and meets the preset load quality estimation accuracy is used as the load quality identification model for practical application.

[0128] Through steps 501 to 504 above, multiple sub-decision models are constructed using multiple training signal feature data and training workpiece types. The nodes of the decision tree model are further segmented using criteria such as information gain and Gini index, gradually forming multiple sub-decision trees in a multi-layered system. Each sub-decision tree in each layer represents the probability distribution of each load quality value. This allows the initial load quality identification model to better learn and capture the complex relationship between the load quality of the mover and electrical signal features and workpiece type, thereby improving the learning ability of the initial load quality identification model in subsequent training processes and improving the accuracy of the load quality identification model in estimating the load quality of the target mover in practical applications.

[0129] Step 203: Generate operating control parameters based on load quality, current operating parameters and target operating parameters, and perform operating control on the target mover based on the operating control parameters.

[0130] Step 203 will be described in detail below.

[0131] In some embodiments, after estimating the current load mass of the target mover, the operating control parameters for accurately operating the target mover to reach the target position based on the current operating parameters of the target mover at the current position and the target operating parameters required for the target position are regenerated, so that the target mover can be accurately operated based on the target operating parameters to reach the target position based on the load mass. This facilitates subsequent precise operation control of the target mover based on the operating control parameters.

[0132] The following section will further describe how to generate the runtime control parameters.

[0133] Reference Figure 7 The process involves generating operating control parameters based on load quality, current operating parameters, and target operating parameters, including steps 701 to 703.

[0134] Step 701: Obtain the distance between the target location and the current location.

[0135] Step 702: Generate control acceleration based on target running speed, current running speed, position distance, and current running speed.

[0136] After obtaining the current load mass of the target mover, in order to generate appropriate operating control parameters, the positional distance X between the target position and the current position needs to be determined in advance.

[0137] Then, using relevant kinematic formulas, a control acceleration At is generated based on the target running speed Ve, the current running speed Vs, and the position distance X, such as X=Vs*t+1 / 2*At^2, At=(Ve-Vs) / t, where t is a time variable parameter. This control acceleration can be used to generate the corresponding operating control parameters in the magnetic drive conveyor system, and thus the target mover can be precisely controlled using these operating control parameters.

[0138] However, considering that the mover itself usually has a fixed jerk due to hardware limitations, in actual mover operation control, it is not possible to immediately adjust the target mover from the current running acceleration As corresponding to the current position to the control acceleration At. The adjustment process requires a certain adjustment time. Therefore, if the target mover is directly controlled by the running control parameters corresponding to the control acceleration, new control errors may be generated, resulting in inaccurate control.

[0139] The following section will further correct this error.

[0140] Reference Figure 8 The control acceleration is generated based on the target running speed, the current running speed, the position distance, and the current running speed, and also includes the following steps 801 to 803.

[0141] Step 801: Generate initial control acceleration based on the target running speed, current running speed, and position distance.

[0142] Step 802: Adjust the current running speed to the initial control acceleration based on the preset jerk, and obtain the changed running speed and changed position of the target mover after the acceleration adjustment.

[0143] Step 803: Based on the changing running speed, changing position, target position, and target running speed, obtain the control acceleration.

[0144] Steps 801 to 803 are described in detail below.

[0145] In some embodiments, firstly, based on the target running speed Ve, the current running speed Vs, and the position distance X, the aforementioned kinematic formulas are used to generate an initial control acceleration A0. Then, based on a preset jerk that is fixed for the target mover, the current running speed As is adjusted to the initial control acceleration A0, and the adjustment time T0 = (A0 - As) / jerk is obtained during the acceleration adjustment process. Based on this adjustment time T0 and in combination with the relevant kinematic formulas, the changed running speed V0 = As*t + 1 / 2*jerk^2 of the target mover after the acceleration adjustment and the corresponding changed position X0 are determined.

[0146] Next, based on the new changing operating speed V0, the changing position X0, and the target operating speed corresponding to the target position, as described in steps 701 to 702 above, the control acceleration At between the changing position X0 and the target position is regenerated.

[0147] Understandably, to further improve control accuracy, after generating a new control acceleration, the error correction method shown in steps 801 to 803 can be repeated. However, in the actual speed adjustment process, there is a certain difference between the initial running acceleration and the final running acceleration, but it is already very small. Therefore, the new adjustment time from the initial running acceleration A0 to the control acceleration At with a fixed preset jerk will be very small, and thus the new error generated is also very small and can be basically ignored.

[0148] Reference Figure 9 This is a schematic diagram illustrating the generation of controlled acceleration according to an embodiment of this application. Figure 9As shown, firstly, an initial control acceleration is generated based on the current operating parameters corresponding to the current position and the target operating parameters corresponding to the target position. Then, the current operating acceleration of the target mover is adjusted to the initial control acceleration. Based on the adjusted operating parameters, a control acceleration that can run to the target position with the target operating parameters is regenerated. Then, the acceleration of the target mover is adjusted from the initial control acceleration to the control acceleration, and the control acceleration is used as the generated control parameters.

[0149] Through steps 801 to 803 above, targeted corrections are made to the adjustment errors caused by the limitations of the mover hardware during the acceleration adjustment process, so as to improve the reliability of the generated control acceleration. This makes it easier to use the running control parameters generated by the control acceleration to control the mover and improve the control accuracy.

[0150] Step 703: Generate operating control parameters based on load quality and control acceleration.

[0151] Steps 701 to 703 are described below.

[0152] In some embodiments, after generating a control acceleration that can be used to move the target mover from its current position to the target position with target operating parameters, the system further generates operating control parameters in the magnetic drive conveyor system that can stably provide the target mover with the magnetic thrust corresponding to the control acceleration under the specific load mass of the target mover, based on the estimated load mass and control acceleration of the current target mover, as described below.

[0153] Reference Figure 10 The process of generating operating control parameters based on load quality and control acceleration includes the following steps 1001 to 1003.

[0154] Step 1001: Based on the load mass and control acceleration, obtain the control thrust.

[0155] Step 1002: Obtain the stator coil parameters of the stator in the magnetic drive conveyor system.

[0156] Step 1003: Generate operating control parameters based on stator coil parameters and control thrust.

[0157] Steps 1001 to 1003 are described in detail below.

[0158] In some embodiments, after determining the current load mass M and control acceleration At of the target mover, the control thrust F = M * At, which can provide control acceleration At to the target mover with load mass M, is obtained based on the product of the load mass M and control acceleration At.

[0159] Then, based on the fixed stator coil parameters of multiple stators in the magnetic drive conveyor system, including the adjustable range of current and voltage for each stator, the control frequency of the AC current, and the maximum current and voltage of each coil in the stator, etc., it is understandable that the fixed stator coil parameters between each stator are usually consistent.

[0160] Therefore, based on the maximum current Amax and the maximum voltage Vmax of each coil, the maximum coil power of each coil can be determined as: Pmax = Vmax × Amax.

[0161] Meanwhile, based on the control thrust F and the current operating speed Vs, the control power required for the stator to provide the control thrust F1 to the target mover at the current position can be obtained as: P = F * Vs.

[0162] Understandably, the current running speed V2 of the target mover at the current position is used as the reference value for determining the control power P. Then, using kinematic formulas, the running speed of the target mover along each path from the current position to the target position with control acceleration can be calculated one by one on the stator. Finally, the control power corresponding to the stator is determined based on the running speed.

[0163] After determining the control power of each stator, adding 1 to the divisor based on the control power P and the maximum coil power Pmax yields the number of coils required for each stator to provide the control thrust F.

[0164] Next, the control power is divided among the selected number of coils, and the control current and control voltage of each control coil after power division are determined. Then, the control current and control voltage corresponding to each stator are used as the operation planning parameters for controlling the operation of the target mover in the magnetic drive conveyor system.

[0165] Through steps 701 to 703 and steps 1001 to 1003 above, using the load mass of the target mover accurately estimated based on electrical signals, and taking the target operating parameters of the target position as the planning target, the control acceleration of the target mover can be accurately determined. Then, combined with the stator coil parameters of the fixed stator, the operating control parameters used to drive the target mover to the target position with the target operating parameters are accurately obtained, thereby enabling precise operation control of the target mover.

[0166] In some embodiments, in order to avoid frequent adjustments to the target mover operation control and cause instability in the magnetic drive conveyor system, it is also necessary to determine whether correction control is required during the real-time operation control of the target mover, as described below.

[0167] Reference Figure 11 The target mover is controlled based on the operating control parameters, including the following steps 1101 to 1102.

[0168] Step 1101: Obtain the load quality difference between the load quality and the preceding load quality of the target mover during the last run control.

[0169] Step 1102: When the load quality difference is greater than the preset quality difference, the target mover is controlled based on the operation control parameters.

[0170] Steps 1101 to 1102 are described in detail below.

[0171] In some embodiments, before performing the operation control of the target mover based on the generated new operation control parameters, it is also necessary to obtain the load mass difference between the estimated load mass of the target stator at the current position and the estimated preceding load mass corresponding to the last operation control.

[0172] When the load mass difference is less than the preset mass difference, the current load mass of the target mover does not change much, and the original operating control parameters can basically meet the requirements of the target operating parameters corresponding to the original target position. Therefore, it is not necessary to control the target mover according to the new operating control parameters, and the original control parameters can be maintained.

[0173] When the load mass difference exceeds the preset mass difference, the current load mass of the target mover changes significantly, and the original operating control parameters cannot meet the requirements of the target operating parameters corresponding to the original target position. At this time, it is necessary to control the target mover according to the new operating control parameters to meet the requirements of the target operating parameters corresponding to the target position.

[0174] Through steps 1101 to 1102 above, the difference between the current load quality and the previous load quality is compared with the preset quality difference. Only when the load quality change exceeds the preset quality difference will the target mover be controlled by new operating control parameters. This avoids frequent adjustments that could cause instability in the magnetic drive conveyor system, thereby improving the reliability of mover operation control in the magnetic drive conveyor system.

[0175] Reference Figure 12 The operation control of the target mover based on the operation control parameters also includes the following steps 1201 to 1202.

[0176] Step 1201: Obtain the difference between the operating control parameters and the preceding operating control parameters of the target mover during the last operating control.

[0177] Step 1202: When the difference in control parameters is greater than the preset control difference, generate multiple progressive operation control parameters from the preceding operation control parameters to the operation control parameters, and perform operation control on the target mover based on the multiple progressive operation control parameters.

[0178] Steps 1201 to 1202 are described in detail below.

[0179] In some embodiments, in order to avoid instability or overshoot of the magnetic drive control system due to excessively abrupt changes in the operating control parameters, it is also necessary to obtain the control parameter difference (including the difference in the number of selected coils, the difference in control current, the difference in control voltage, etc.) between the newly obtained operating control parameters and the previous operating control parameters of the target mover during the last operating control.

[0180] Then, when the difference in control parameters does not reach the preset control difference, the change between the newly generated operating control parameters and the original operating control parameters is not significant. Therefore, directly using the newly generated operating control parameters to control the movement will not cause instability or overshoot in the magnetic drive control system. Thus, the newly generated operating control parameters can be used directly to control the movement.

[0181] When the difference in control parameters exceeds the preset control difference, corresponding to a large change between the newly generated operating control parameters and the original operating control parameters, multiple progressive operating control parameters with equal intervals will be generated between the previous operating control parameters and the current operating control parameters. Based on these multiple progressive operating control parameters, progressive operating control will be performed on the target mover to avoid instability or overshoot in the magnetic drive control system.

[0182] Through steps 1201 to 1202 above, the difference between the current operating control parameters and the previous operating control parameters is compared with the preset control difference. If the change in control parameters exceeds the preset control difference, a gradual control change is used to gradually control the target mover using multiple gradual operating control parameters. This avoids instability or overshoot in the magnetic drive control system and improves the reliability of mover operation control in the magnetic drive conveyor system.

[0183] The present application proposes a method and related equipment for controlling the movement of a magnetic drive conveyor system. The method includes: first, acquiring the electrical signal and current operating parameters of the target mover at its current position in the magnetic drive conveyor system, and acquiring the target operating parameters at the target position; then, acquiring the target workpiece type corresponding to the target workpiece carried by the target mover, performing frequency domain conversion on the electrical signal based on Fourier transform to obtain a frequency domain electrical signal, which includes a frequency domain current signal and a frequency domain voltage signal; acquiring the signal phase angle difference between the frequency domain current signal and the frequency domain voltage signal, and obtaining the power factor based on the cosine value of the signal phase angle difference; acquiring the fundamental current amplitude and harmonic current amplitude in the frequency domain current signal, and based on the current harmonic amplitude and fundamental current amplitude... The ratio of the values ​​yields the current harmonic distortion. The voltage fundamental amplitude and voltage harmonic amplitude in the frequency domain voltage signal are obtained. The voltage harmonic distortion is obtained based on the ratio of the voltage harmonic amplitude to the voltage fundamental amplitude. The total harmonic distortion is obtained based on the average of the current harmonic distortion and the voltage harmonic distortion. Multiple training signal feature data and the corresponding training workpiece type for each training signal feature data are obtained. Multiple decision tree nodes are generated based on the training signal feature data. Multiple first sub-decision tree models are generated based on the decision tree nodes. The multiple training signal feature data are divided into first sub-feature data sets corresponding to each first sub-decision tree model based on the decision tree nodes. The decision tree nodes are segmented, and a relationship between the segmented decision tree nodes and the first sub-decision tree model is generated. The second sub-decision tree model divides the first sub-feature data set into a second feature data set corresponding to each second sub-decision tree model until the number of sub-data sets is less than a preset data quantity threshold. An initial load quality identification model is obtained based on all decision tree nodes, the first sub-decision tree model, and the second sub-decision tree model. This initial load quality identification model is then trained multiple times based on multiple training signal feature data and training workpiece types. A final load quality identification model is obtained based on the trained initial load quality identification model. Next, electrical signal features and target workpiece types are input into the load quality identification model for data processing to obtain the load quality. Finally, the positional distance between the target position and the current position is obtained, based on the target running speed. The system generates an initial control acceleration based on the current operating speed and position distance. It then adjusts the current operating speed to the initial control acceleration based on a preset jerk, and obtains the changed operating speed and position of the target mover after the acceleration adjustment. Based on the changed operating speed, changed position, target position, and target operating speed, it obtains the control acceleration. Based on the load mass and control acceleration, it obtains the control thrust. It also obtains the stator coil parameters of the stator in the magnetic drive conveyor system, generates operating control parameters based on the stator coil parameters and control thrust, and obtains the load mass difference between the load mass and the preceding load mass of the target mover during the previous operating control. When the load mass difference is greater than a preset mass difference, it performs operating control on the target mover based on the operating control parameters.Furthermore, it acquires the control parameter difference between the operating control parameters and the preceding operating control parameters of the target mover during the previous operating control. When the control parameter difference is greater than a preset control difference, it generates multiple progressive operating control parameters from the preceding operating control parameters to the operating control parameters, and performs operating control on the target mover based on these multiple progressive operating control parameters.

[0184] This application addresses a target mover carrying a workpiece that operates in real-time on a magnetic drive conveyor system. Based on the real-time electrical signals of the target mover, the real-time changing load mass of the target mover on the magnetic drive conveyor system is accurately determined. Then, based on this load mass, operating control parameters are generated to ensure the mover reaches the target operating parameters at the target position, thereby improving the accuracy of mover operation control in the magnetic drive conveyor system. Furthermore, by using the real-time electrical signals of the target mover to calculate the load mass, the complexity of setting up a quality detection device in the magnetic drive conveyor system is avoided, thus reducing the design complexity of the magnetic drive conveyor system. The text discusses various aspects of electrical engineering, including: Firstly, it mentions the difficulty and cost of setting up electrical signals. This involves using Fourier transform to convert time-domain electrical signals into frequency-domain electrical signals to determine the phase angle difference between voltage and current. Based on this phase angle difference, a power factor reflecting the effective energy utilization of the target mover is determined. Secondly, the text discusses using the frequency-domain electrical signals to determine the total harmonic distortion (THD) of nonlinear characteristics reflecting the load mass, thus representing the current utilization of the target mover. This facilitates accurate estimation of the target mover's load mass using these electrical signal characteristics. Finally, it mentions constructing multiple sub-decision models using multiple training signal feature data and training workpiece types. The nodes of the decision tree model are further segmented using criteria such as information gain and Gini index, gradually forming multiple sub-decision trees in a multi-layered system. Each sub-decision tree in each layer represents the probability distribution of each load mass value. This allows the initial load mass identification model to better learn and capture the complex relationship between the mover load mass, electrical signal characteristics, and workpiece type, thereby improving the learning ability of the initial load mass identification model in subsequent training processes. This enhances the accuracy of the load mass identification model in estimating the load mass of the target mover in practical applications. Furthermore, regarding the mover acceleration adjustment process, due to the limitations of the mover hardware... The resulting adjustment error is specifically corrected to improve the reliability of the generated control acceleration, thereby facilitating the subsequent use of the operating control parameters generated by the control acceleration for mover control and improving control accuracy. In addition, using the load mass of the target mover accurately estimated based on electrical signals, and with the target operating parameters at the target position as the planning target, the control acceleration that can accurately determine the target mover is determined. Then, combined with the fixed stator coil parameters, the operating control parameters used to drive the target mover to the target position with the target operating parameters are accurately obtained, thereby enabling precise operation control of the target mover.In other aspects, the system uses the difference between the current load quality and the previous load quality, and a preset quality difference, to determine whether the load quality change exceeds the preset quality difference. Only when the load quality change exceeds the preset quality difference is a new operating control parameter applied to the target mover. This avoids frequent adjustments that could cause instability in the magnetic drive conveyor system. Simultaneously, the system uses the difference between the current operating control parameter and the previous operating control parameter, and a preset control difference, to determine whether the control parameter change exceeds the preset control difference. This involves using multiple progressive operating control parameters to progressively control the target mover, thus avoiding instability or overshoot in the magnetic drive control system and improving the reliability of mover operation control in the magnetic drive conveyor system.

[0185] This application also provides a mover operation control device for a magnetic drive conveyor system, which can implement the above-described mover operation control method for the magnetic drive conveyor system. (Refer to...) Figure 13 The device 1300 includes:

[0186] The parameter acquisition module 1310 is used to acquire the electrical signal and current operating parameters of the target mover at its current position in the magnetic drive conveyor system, as well as to acquire the target operating parameters at the target position.

[0187] The load mass calculation module 1320 is used to determine the load mass of the target mover based on electrical signals.

[0188] The operation control module 1330 is used to generate operation control parameters based on load quality, current operation parameters and target operation parameters, and to perform operation control on the target mover based on the operation control parameters.

[0189] In some embodiments, the load quality calculation module 1320 is further configured to:

[0190] Obtain the target workpiece type corresponding to the target workpiece carried by the target mover;

[0191] Features of electrical signals are extracted based on Fourier transform to obtain electrical signal features;

[0192] The electrical signal characteristics and target workpiece type are input into the load quality identification model for data processing to obtain the load quality.

[0193] In some embodiments, the load quality calculation module 1320 is further configured to:

[0194] The electrical signal is converted into the frequency domain based on the Fourier transform to obtain the frequency domain electrical signal, which includes the frequency domain current signal and the frequency domain voltage signal.

[0195] The phase angle difference between the frequency domain current signal and the frequency domain voltage signal is obtained, and the power factor is obtained based on the cosine value of the phase angle difference.

[0196] The fundamental current amplitude and harmonic current amplitude in the frequency domain current signal are obtained, and the current harmonic distortion is obtained based on the ratio of the current harmonic amplitude to the fundamental current amplitude.

[0197] The voltage fundamental amplitude and voltage harmonic amplitude are obtained from the frequency domain voltage signal, and the voltage harmonic distortion is obtained based on the ratio of the voltage harmonic amplitude to the voltage fundamental amplitude.

[0198] The total harmonic distortion is obtained based on the average values ​​of current harmonic distortion and voltage harmonic distortion.

[0199] In some embodiments, the operation control module 1330 is further configured to:

[0200] Get the distance between the target location and the current location;

[0201] The control acceleration is generated based on the target operating speed, the current operating speed, and the position distance.

[0202] Operational control parameters are generated based on load quality and control acceleration.

[0203] In some embodiments, the operation control module 1330 is further configured to:

[0204] The initial control acceleration is generated based on the target running speed, the current running speed, and the position distance;

[0205] The current running speed is adjusted to the initial control acceleration based on the preset jerk, and the changed running speed and changed position of the target mover after the acceleration adjustment are obtained;

[0206] The control acceleration is obtained based on the changing operating speed, changing position, target position, and target operating speed.

[0207] In some embodiments, the operation control module 1330 is further configured to:

[0208] The control thrust is obtained based on the load mass and control acceleration;

[0209] Obtain the stator coil parameters of the stator in the magnetic drive conveyor system;

[0210] Operating control parameters are generated based on stator coil parameters and control thrust.

[0211] In some embodiments, the load quality calculation module 1320 is further configured to:

[0212] Acquire multiple training signal feature data and the training workpiece type corresponding to each training signal feature data, and generate multiple decision tree nodes based on the training signal feature data;

[0213] Multiple first sub-decision tree models are generated based on decision tree nodes, and multiple training signal feature data are divided into first sub-feature data sets corresponding to each first sub-decision tree model based on decision tree nodes.

[0214] The decision tree nodes are segmented, and a second sub-decision tree model associated with the first sub-decision tree model is generated based on the segmented decision tree nodes. The first sub-feature data set is divided into the second feature data set corresponding to each second sub-decision tree model until the segmented subsets are less than a preset data quantity threshold.

[0215] An initial load quality identification model is obtained based on all decision tree nodes, the first sub-decision tree model, and the second sub-decision tree model. The initial load quality identification model is then trained multiple times based on multiple training signal feature data and training workpiece types. Finally, a load quality identification model is obtained based on the trained initial load quality identification model.

[0216] In some embodiments, the operation control module 1330 is further configured to:

[0217] Obtain the load quality difference between the load quality and the preceding load quality of the target mover during the last control run;

[0218] When the load quality difference is greater than the preset quality difference, the target mover is controlled based on the operation control parameters.

[0219] In some embodiments, the operation control module 1330 is further configured to:

[0220] Obtain the difference between the operating control parameters and the preceding operating control parameters of the target mover during the last operating control;

[0221] When the difference in control parameters is greater than the preset control difference, multiple progressive operation control parameters are generated between the preceding operation control parameters and the operation control parameters, and the target mover is controlled based on the multiple progressive operation control parameters.

[0222] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, the specific implementation of the mover operation control device of the magnetic drive conveyor system is basically the same as the specific implementation of the mover operation control method of the magnetic drive conveyor system, and will not be repeated here.

[0223] In this embodiment, the mover operation control device of the magnetic drive conveyor system targets a target mover carrying a workpiece and operating in real time on the magnetic drive conveyor system. Based on the real-time electrical signals of the target mover, it accurately determines the real-time changing load mass of the target mover as it runs on the magnetic drive conveyor system. Then, based on this load mass, it generates operating control parameters that can actually ensure the mover reaches the target operating parameters at the target position, thereby improving the accuracy of mover operation control in the magnetic drive conveyor system. Furthermore, by using the real-time electrical signals of the target mover to calculate the load mass, the complexity of setting up a quality detection device in the magnetic drive conveyor system is avoided. This reduces the setup difficulty and cost of magnetic drive conveyor systems. Specifically, Fourier transform is used to convert time-domain electrical signals into frequency-domain electrical signals to determine the phase angle difference between voltage and current. Based on this phase angle difference, the power factor reflecting the effective energy utilization of the target mover is determined. Furthermore, the frequency-domain electrical signals are used to determine the total harmonic distortion (THD) of the nonlinear characteristics reflecting the load mass, thus representing the current utilization of the target mover. This facilitates accurate estimation of the target mover's load mass using these electrical signal characteristics. Additionally, multiple training signal feature data and training workpiece types are used to construct multiple... The sub-decision model, and further segmentation of the nodes of the decision tree model using criteria such as information gain and Gini index, gradually form multiple sub-decision trees in a multi-layered system. Each sub-decision tree in each layer represents the probability distribution of each load quality value, thereby enabling the initial load quality identification model to better learn and capture the complex relationship between the mover load quality and electrical signal characteristics and workpiece type. This improves the learning ability of the initial load quality identification model in subsequent training processes, thus enhancing the accuracy of the load quality identification model in estimating the load quality of the target mover in practical applications. Furthermore, regarding the mover acceleration adjustment process, due to the mover hardware... To address the limitations, the resulting adjustment errors are specifically corrected to improve the reliability of the generated control acceleration. This facilitates subsequent use of the control acceleration to generate operating control parameters for mover control, thereby enhancing control accuracy. Furthermore, by utilizing the load mass of the target mover accurately estimated based on electrical signals, and using the target operating parameters at the target position as the planning target, the control acceleration that can accurately determine the target mover is identified. Then, combined with the fixed stator coil parameters, the operating control parameters used to drive the target mover to the target position with the target operating parameters are accurately obtained, thus enabling precise operation control of the target mover.In other aspects, the system uses the difference between the current load quality and the previous load quality, and a preset quality difference, to determine whether the load quality change exceeds the preset quality difference. Only when the load quality change exceeds the preset quality difference is a new operating control parameter applied to the target mover. This avoids frequent adjustments that could cause instability in the magnetic drive conveyor system. Simultaneously, the system uses the difference between the current operating control parameter and the previous operating control parameter, and a preset control difference, to determine whether the control parameter change exceeds the preset control difference. This involves using multiple progressive operating control parameters to progressively control the target mover, thus avoiding instability or overshoot in the magnetic drive control system and improving the reliability of mover operation control in the magnetic drive conveyor system.

[0224] This application also provides an electronic device, including:

[0225] At least one memory;

[0226] At least one processor;

[0227] At least one program;

[0228] The program is stored in a memory, and the processor executes the at least one program to implement the mover operation control method of the magnetic drive conveyor system described above in this application. The electronic device can be any smart terminal, including mobile phones, tablets, personal digital assistants (PDAs), in-vehicle computers, etc.

[0229] Please see Figure 14 , Figure 14 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0230] The processor 1401 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0231] The memory 1402 can be implemented in the form of ROM (Read-Only Memory), static storage device, dynamic storage device, or RAM (Random Access Memory). The memory 1402 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1402 and is called and executed by the processor 1401 to execute the mover operation control method of the magnetic drive conveyor system of this application embodiment.

[0232] The input / output interface 1403 is used to implement information input and output;

[0233] The communication interface 1404 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0234] Bus 1405 transmits information between various components of the device (e.g., processor 1401, memory 1402, input / output interface 1403, and communication interface 1404);

[0235] The processor 1401, memory 1402, input / output interface 1403 and communication interface 1404 are connected to each other within the device via bus 1405.

[0236] This application embodiment also provides a storage medium, which is a computer-readable storage medium, storing a computer program. When the computer program is executed by a processor, it implements the above-described mover operation control method of the magnetic drive conveyor system.

[0237] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0238] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0239] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0240] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0241] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0242] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0243] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0244] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. The coupling or direct coupling or communication connection between the shown or discussed units may be through some interfaces, or indirect coupling or communication connection between the apparatus or units, and may be electrical, mechanical, or other forms.

[0245] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0246] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0247] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0248] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for controlling the movement of a mover in a magnetically driven conveyor system, characterized in that, include: Acquire the electrical signal and current operating parameters of the target mover at its current position in the magnetic drive conveyor system, and acquire the target operating parameters at the target position; The load mass of the target mover is determined based on the electrical signal; Based on the load quality, the current operating parameters, and the target operating parameters, operating control parameters are generated, and the target mover is controlled based on the operating control parameters. Determining the load mass of the target mover based on the electrical signal includes: Obtain the target workpiece type corresponding to the target workpiece carried by the target mover; The electrical signal features are extracted based on Fourier transform. The electrical signal characteristics and the target workpiece type are input into the load quality identification model for data processing to obtain the load quality; The electrical signal features include signal phase angle difference, power factor, and total harmonic distortion. The feature extraction of the electrical signal based on Fourier transform to obtain the electrical signal features includes: The electrical signal is converted to the frequency domain based on the Fourier transform to obtain a frequency domain electrical signal, which includes a frequency domain current signal and a frequency domain voltage signal. The signal phase angle difference between the frequency domain current signal and the frequency domain voltage signal is obtained, and the power factor is obtained based on the cosine value of the signal phase angle difference; The fundamental current amplitude and harmonic current amplitude in the frequency domain current signal are obtained, and the current harmonic distortion is obtained based on the ratio of the current harmonic amplitude to the fundamental current amplitude. The voltage fundamental amplitude and voltage harmonic amplitude in the frequency domain voltage signal are obtained, and the voltage harmonic distortion is obtained based on the ratio of the voltage harmonic amplitude to the voltage fundamental amplitude. The total harmonic distortion is obtained based on the average values ​​of the current harmonic distortion and the voltage harmonic distortion.

2. The method for controlling the movement of the mover in a magnetic drive conveyor system according to claim 1, characterized in that, The current operating parameters include the current operating speed, and the target operating parameters include the target operating speed. Generating operating control parameters based on the load quality, the current operating parameters, and the target operating parameters includes: Obtain the positional distance between the target location and the current location; The control acceleration is generated based on the target operating speed, the current operating speed, and the position distance; The operating control parameters are generated based on the load mass and the control acceleration.

3. The mover operation control method of the magnetic drive conveyor system according to claim 2, characterized in that, The current operating parameters include the current operating acceleration, and the generation of control acceleration based on the target operating speed, the current operating speed, and the position distance includes: Based on the target operating speed, the current operating speed, and the position distance, an initial control acceleration is generated; The current running speed is adjusted to the initial control acceleration based on the preset acceleration, and the changed running speed and changed position of the target mover after the acceleration adjustment are obtained; The control acceleration is obtained based on the changing running speed, the changing position, the target position, and the target running speed.

4. The mover operation control method of the magnetic drive conveyor system according to claim 2, characterized in that, The process of generating the operating control parameters based on the load mass and the control acceleration includes: Based on the load mass and the control acceleration, the control thrust is obtained; Obtain the stator coil parameters of the stator in the magnetic drive conveyor system; The operating control parameters are generated based on the stator coil parameters and the control thrust.

5. The mover operation control method of the magnetic drive conveyor system according to claim 1, characterized in that, The steps for constructing the load quality identification model include: Acquire multiple training signal feature data and the training workpiece type corresponding to each training signal feature data, and generate multiple decision tree nodes based on the training signal feature data; Multiple first sub-decision tree models are generated based on the decision tree nodes, and the multiple training signal feature data are divided into a first sub-feature data set corresponding to each first sub-decision tree model based on the decision tree nodes. The decision tree nodes are segmented, and a second sub-decision tree model associated with the first sub-decision tree model is generated based on the segmented decision tree nodes. The first sub-feature data set is divided into a second feature data set corresponding to each second sub-decision tree model until the segmented subsets are less than a preset data quantity threshold. An initial load quality identification model is obtained based on all the decision tree nodes, the first sub-decision tree model, and the second sub-decision tree model. The initial load quality identification model is then trained multiple times based on the multiple training signal feature data and the training workpiece type. Finally, the load quality identification model is obtained based on the trained initial load quality identification model.

6. The mover operation control method of the magnetic drive conveyor system according to claim 1, characterized in that, The operation control of the target mover based on the operation control parameters includes: The load mass difference between the load mass and the preceding load mass of the target mover during the last operation control is obtained; When the load quality difference is greater than the preset quality difference, the target mover is controlled to operate based on the operation control parameters.

7. The mover operation control method for the magnetic drive conveyor system according to claim 1, characterized in that, The operation control of the target mover based on the operation control parameters includes: Obtain the difference between the operating control parameters and the preceding operating control parameters of the target mover during the previous operating control; When the difference in the control parameters is greater than the preset control difference, multiple progressive operation control parameters are generated between the preceding operation control parameters and the operation control parameters, and the target mover is controlled based on the multiple progressive operation control parameters.

8. A mover operation control device for a magnetic drive conveyor system, characterized in that, The device includes: The parameter acquisition module is used to acquire the electrical signal and current operating parameters of the target mover at its current position in the magnetic drive conveyor system, as well as the target operating parameters at the target position. A load quality calculation module is used to determine the load quality of the target mover based on the electrical signal; The operation control module is used to generate operation control parameters based on the load quality, the current operation parameters and the target operation parameters, and to perform operation control on the target mover based on the operation control parameters; Determining the load mass of the target mover based on the electrical signal includes: Obtain the target workpiece type corresponding to the target workpiece carried by the target mover; The electrical signal features are extracted based on Fourier transform. The electrical signal characteristics and the target workpiece type are input into the load quality identification model for data processing to obtain the load quality; The electrical signal features include signal phase angle difference, power factor, and total harmonic distortion. The feature extraction of the electrical signal based on Fourier transform to obtain the electrical signal features includes: The electrical signal is converted to the frequency domain based on the Fourier transform to obtain a frequency domain electrical signal, which includes a frequency domain current signal and a frequency domain voltage signal. The signal phase angle difference between the frequency domain current signal and the frequency domain voltage signal is obtained, and the power factor is obtained based on the cosine value of the signal phase angle difference; The fundamental current amplitude and harmonic current amplitude in the frequency domain current signal are obtained, and the current harmonic distortion is obtained based on the ratio of the current harmonic amplitude to the fundamental current amplitude. The voltage fundamental amplitude and voltage harmonic amplitude in the frequency domain voltage signal are obtained, and the voltage harmonic distortion is obtained based on the ratio of the voltage harmonic amplitude to the voltage fundamental amplitude. The total harmonic distortion is obtained based on the average values ​​of the current harmonic distortion and the voltage harmonic distortion.

9. An electronic device, characterized in that, The system includes a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the mover operation control method of the magnetic drive conveyor system according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the mover operation control method of the magnetic drive conveyor system as described in any one of claims 1 to 7.

Images