Self-learning calibration method for servo control system based on multi-source information fusion

Abstract

The application relates to the technical field of multi-source servo intelligent calibration, and particularly discloses a self-independent intelligent calibration method for a servo control system based on multi-source information fusion, which comprises the following steps: in response to a system start or a calibration instruction, obtaining device attribute information of each servo device and multi-source sensor data synchronized through a global time protocol; and constructing a device correlation matrix representing coupling strength between devices according to physical space distribution data and transmission connection relationship data in the device attribute information. The application can intelligently identify various cross-device coupling conflict characteristics including transmission, electromagnetism and load, and through a dynamic weight adjustment and coupling projection reconstruction mechanism, can accurately strip external interference noise from sensor data, ensure that the control system only calibrates real intrinsic errors of the devices themselves, and avoid false compensation and system instability caused by coupling interference.

Description

Technical Field

[0001] The present invention relates to the field of multi-source servo intelligent calibration technology, in particular to an autonomous intelligent calibration method for servo control systems based on multi-source information fusion. Background Art

[0002] With the development of high-end equipment manufacturing towards high speed and precision, multi-axis linked servo control systems have been widely used in industrial robots, precision CNC machine tools and automated production lines. In traditional servo control architectures, calibration of each axis is usually based on the single-axis independent closed-loop assumption, that is, it is considered that the sensor feedback of each servo device only characterizes the operating status of the device itself. The control system usually adopts standard PID regulation or a simple synchronous control strategy, assuming that the physical environment is statically decoupled. Such traditional methods can still meet requirements under low-speed or weakly-coupled scenarios, but under complex working conditions involving rigid mechanical connection, common-bus electrical driving or high-frequency load switching, there objectively exist complex physical coupling relationships between various servo axes.

[0003] However, the prior art faces a severe conflict between sensor credibility and physical coupling interference when handling such multi-device linked scenarios. Specifically, when there is strong mechanical transmission or electromagnetic interference between devices, the sensor reading of a certain servo device often superposes vibration noise or signal crosstalk from associated devices. Existing control algorithms lack the ability to distinguish local intrinsic errors from cross-device coupling interference, and often misjudge external coupling interference as the operating deviation of the local device, and then forcibly implement incorrect calibration compensation.

[0004] This mis-calibration not only fails to eliminate system errors, but also causes system oscillation due to over-adjustment. Even in the asynchronous cooperation process with rapid load switching, destructive internal stress between devices is caused due to ignoring physical inertia lag, which severely restricts the overall accuracy and stability of the servo system. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems in the related art to a certain extent. Therefore, the objective of the present invention is to provide an autonomous intelligent calibration method for servo control systems based on multi-source information fusion, so as to solve the problems of mis-calibration and system oscillation caused by physical coupling in multi-device linkage.

[0006] To achieve the above objective, an embodiment of the first aspect of the present invention provides an autonomous intelligent calibration method for servo control systems based on multi-source information fusion, comprising the following steps: In response to a system start-up or calibration instruction, acquiring device attribute information of each servo device and multi-source sensor data synchronized via a global time protocol; Based on the physical spatial distribution data and transmission connection relationship data in the equipment attribute information, a device association matrix representing the coupling strength between devices is constructed. The multi-source sensor data is preprocessed to extract cross-device coupling conflict features, and the cross-device coupling conflict features are input into a preset conflict identification model to obtain the output conflict type label. Based on the conflict type label and the currently identified device linkage scenario type, the corresponding fusion strategy is invoked, and the data fusion weights of each servo device are dynamically and collaboratively adjusted based on the device association matrix to generate cross-device fusion features; Based on the cross-device fusion feature and the preset collaborative calibration strategy, the calibration parameter compensation value of each servo device is calculated, and calibration instructions are sent to each servo device to execute the multi-device synchronous calibration process. The process of constructing the device association matrix that characterizes the coupling strength between devices includes: calculating the association coefficient between each pair of devices based on the physical distance between devices, the quantification coefficient of the transmission connection method, and the load distribution ratio, and constructing the device association matrix from all the association coefficients.

[0007] To achieve the above objectives, a second aspect of the present invention proposes an autonomous intelligent calibration system for a servo control system based on multi-source information fusion, comprising: The data acquisition and correlation modeling module is used to acquire device attribute information of each servo device and multi-source sensor data synchronized through a global time protocol in response to system startup or calibration commands; and to construct a device correlation matrix characterizing the coupling strength between devices based on the physical spatial distribution data and transmission connection relationship data in the device attribute information; wherein, the process of constructing the device correlation matrix characterizing the coupling strength between devices includes: calculating the correlation coefficient between each pair of devices based on the physical distance between devices, the quantization coefficient of the transmission connection method and the load distribution ratio, and the device correlation matrix is ​​composed of all correlation coefficients; The conflict feature recognition module is used to preprocess the multi-source sensor data to extract cross-device coupling conflict features, input the cross-device coupling conflict features into a preset conflict recognition model, and obtain the output conflict type label. The dynamic weight coordination module is used to call the corresponding fusion strategy according to the conflict type label and the currently identified device linkage scenario type, and to dynamically coordinate and adjust the data fusion weight of each servo device based on the device association matrix to generate cross-device fusion features. The collaborative calibration execution module is used to calculate the calibration parameter compensation value of each servo device based on the cross-device fusion features and the preset collaborative calibration strategy, and to issue calibration instructions to each servo device to execute the multi-device synchronous calibration process.

[0008] To achieve the above objectives, a third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory. When the computer program is executed by the processor, it implements the above-described autonomous intelligent calibration method for a servo control system based on multi-source information fusion.

[0009] The autonomous intelligent calibration method for servo control systems based on multi-source information fusion in this invention can intelligently identify various cross-device coupling conflict characteristics, including transmission, electromagnetic, and load. Through dynamic weight adjustment and coupling projection reconstruction mechanisms, it can accurately remove external interference noise from sensor data, ensuring that the control system calibrates only for the true intrinsic error of the device itself, thereby avoiding false compensation and system instability caused by coupling interference. Meanwhile, for rapid load switching in asynchronous collaborative scenarios, this solution introduces a dynamic reference correction mechanism based on physical inertia to eliminate pseudo-synchronization errors caused by the asynchrony between electrical signals and mechanical responses. In addition, the establishment of a global redundant resource pool enables the system to maintain high-precision collaborative control by scheduling associated sensors when some sensors fail or are severely disturbed, which significantly improves the robustness and adaptability of the servo control system under complex working conditions. Attached Figure Description

[0010] Figure 1 This is a flowchart illustrating the autonomous intelligent calibration method for servo control systems based on multi-source information fusion provided by the present invention. Figure 2 This is a schematic diagram illustrating the implementation of the autonomous intelligent calibration system for a servo control system based on multi-source information fusion provided by the present invention. Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0011] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0012] The following description, with reference to the accompanying drawings, outlines an autonomous intelligent calibration method, system, and electronic device for a servo control system based on multi-source information fusion, according to embodiments of the present invention.

[0013] Example 1

[0014] This embodiment details an autonomous intelligent calibration method for servo control systems based on multi-source information fusion. This method aims to address calibration deviations in multi-axis linkage servo systems under complex industrial scenarios caused by mechanical transmission coupling, electromagnetic interference, and dynamic load variations. The method in this embodiment primarily operates within the global edge controller of the servo control system, which possesses a high-performance computing unit and a real-time industrial bus interface.

[0015] Reference Figure 1 The flowchart shown illustrates the specific steps included in this embodiment: Step S1: In response to system startup or calibration commands, acquire device attribute information of each servo device and multi-source sensor data synchronized via a global time protocol.

[0016] For example, the global edge controller of the servo control system monitors the system's operating status in real time. The calibration process is initiated when the system completes power-on initialization, receives a calibration command from maintenance personnel through the human-machine interface, or automatically triggers a calibration request when the system detects a decrease in operating accuracy.

[0017] Acquiring device attribute information is a crucial step in establishing the system's static physical model. The global edge controller reads the electronic nameplate data stored internally by each servo driver via the bus, or downloads configuration files from the cloud configuration database. This device attribute information covers motor parameters such as rated power, rated torque, moment of inertia, and number of pole pairs of the servo motor, as well as transmission component parameters such as the reduction ratio of the reducer, the lead of the lead screw, and the stiffness coefficient of the coupling. Crucially, the device attribute information explicitly records the physical spatial distribution coordinates of each device in the industrial environment and the mechanical connection topology between devices; for example, whether device A and device B share the same base, or whether they are mechanically coupled via belts or gears.

[0018] To address the challenge of aligning multi-source data in the time domain, this embodiment strictly employs a global time protocol, specifically the IEEE 1588 Precision Time Protocol (PTP). During the data acquisition phase, the global edge controller acts as the PTP master clock, while each servo driver and independent sensor node serves as a slave clock. Through the PTP protocol's delay measurement and clock skew correction mechanism, the system achieves sub-microsecond time synchronization accuracy. Driven by this synchronized clock source, the system synchronously triggers the acquisition of multi-source sensor data. This multi-source sensor data includes not only position, speed, and torque / current data fed back from the servo motor's built-in encoder, but also data from vibration accelerometers externally mounted at key points of the mechanical structure, laser displacement sensor data installed on the end effector, and temperature sensor data monitoring environmental changes. These data are immediately stamped with a unified, high-precision timestamp upon acquisition, laying a solid temporal foundation for subsequent correlation analysis.

[0019] Step S2: Based on the physical space distribution data and transmission connection relationship data in the device attribute information, construct a device association matrix that characterizes the coupling strength between devices.

[0020] For example, traditional control strategies often assume that axes are independent of each other, while the core of this embodiment lies in quantifying the mutual influence between devices. Constructing a device correlation matrix is ​​the first step in achieving this goal. This matrix is ​​a... The square array, in which, This represents the number of servo devices in the system. Each element in the matrix quantifies the likelihood of two devices physically interfering with or interacting with each other.

[0021] The process of constructing the device association matrix, which characterizes the coupling strength between devices, specifically includes: calculating the association coefficient between each pair of devices based on the physical distance between devices, the quantification coefficient of the transmission connection method, and the load distribution ratio; and constructing the device association matrix from all association coefficients. During the calculation, the system iterates through each pair of devices, comprehensively considering spatial proximity, mechanical connection tightness, and load sharing relationship.

[0022] The calculation of the correlation coefficient between each pair of devices includes calculating the device correlation coefficient using the following formula. Correlation coefficient between equipment : ; in, Characterization equipment With equipment The physical distance between the devices is calculated using spatial coordinates from the device attribute information. The closer the physical distance, the greater the likelihood of vibration transmission or electromagnetic crosstalk between the devices via their bases. The formula above uses... This inverse relationship is reflected by the reciprocal of the distance; that is, the closer the distance, the larger the value of the correlation term. This coefficient characterizes the transmission link and is used to quantify the tightness of a mechanical connection. Depending on whether it's direct transmission, indirect transmission, or no transmission relationship, this coefficient takes a preset first value, a second value, or zero. For example, if the equipment... With equipment Through direct meshing of rigid couplings or gears, mechanical vibration and torque transmission are extremely direct. The value is the first numerical value, such as If the two are connected by a belt or a long drive shaft, there is a certain degree of flexibility and buffering. The value is the second number, such as If the two are completely physically isolated in terms of mechanical structure and have no transmission relationship, then... The value is zero; This represents the load sharing coefficient of the equipment. In scenarios where multiple motors work together to drive the same load, such as a dual-drive gantry crane, the two motors share the load torque. If the equipment... With equipment The close load-sharing ratios indicate a strong dynamic coupling between the two components; a torque fluctuation in one directly affects the operational stability of the other. Therefore, Used to reflect the coupling depth at this load level; , , These are preset weighting coefficients, corresponding to the relative importance of spatial distance, mechanical transmission, and load distribution factors in the overall correlation. These three weighting coefficients can be flexibly configured according to different application scenarios. For example, in a compact precision machining center, where spatial electromagnetic interference is a primary concern, these coefficients would be increased. The value; in heavy-duty transmission lines, where mechanical transmission is the primary concern, the value should be increased. The value of .

[0023] Furthermore, for ease of subsequent calculations, the correlation coefficient... The range of values ​​is normalized to a closed interval between zero and one. When the calculated result is greater than... At that time, forced truncation is The resulting device association matrix can be presented intuitively as a heatmap, guiding the system to quickly locate areas with high coupling risks.

[0024] Step S3: Preprocess the multi-source sensor data to extract cross-device coupling conflict features, input the cross-device coupling conflict features into a preset conflict identification model, and obtain the output conflict type label.

[0025] For example, the raw sensor data collected often contains noise and has varying dimensions, making direct input into the model ineffective. The preprocessing stage first cleans the data, using Kalman filtering to remove measurement white noise and employing Z-score normalization to map data with different dimensions (such as ampere values ​​for current and micrometer values ​​for position) to a standard normal distribution range. Subsequently, the system performs sliding window truncation on the time series data, forming fixed-length time slice sequences.

[0026] The cross-device coupling conflict characteristics include at least: transmission coupling conflict characteristics characterizing the mutual influence of mechanical transmissions, electromagnetic coupling conflict characteristics characterizing electrical signal interference, and load coupling conflict characteristics characterizing load distribution deviations. The system does not simply input raw data into the model, but rather extracts feature vectors with clear engineering significance based on physical mechanisms.

[0027] The specific generation process of the cross-device coupling conflict feature includes the following sub-steps: First, computing devices With equipment The Pearson correlation coefficient of torque fluctuations between the two devices is used as the torque coupling coefficient in the transmission coupling conflict characteristics. The system extracts the torque-current sequences of the two devices within the same time window and calculates the ratio of the product of their covariance and standard deviation. If the Pearson correlation coefficient is close to 1 or -1, it indicates that the torque fluctuations of the two devices are highly positively or negatively correlated, indicating strong mechanical transmission coupling oscillations; if it is close to 0, it indicates that they do not affect each other. Simultaneously, the cross-spectral density of the vibration signals can also be calculated to further characterize the transmission coupling.

[0028] Secondly, the percentage of overlapping intervals of the same harmonic frequencies between devices is calculated as the current harmonic spectrum overlap degree in the electromagnetic coupling conflict characteristics. The system performs a Fast Fourier Transform (FFT) on the phase current data of each device to obtain the amplitude-frequency response curve in the frequency domain. Subsequently, the system analyzes the spectrum of different devices to identify characteristic harmonic frequencies with significant amplitudes. If the devices... With equipment If there is a high degree of overlap in a specific high-order harmonic frequency range, and this frequency is not the fundamental frequency, then it is highly likely that the electromagnetic coupling conflict is caused by common bus interference or electromagnetic radiation in space. The higher the proportion of the overlapping range, the greater the possibility of electromagnetic interference.

[0029] Finally, the difference between the actual load distribution ratio and the preset ratio is calculated as the load deviation rate in the load coupling conflict characteristic. The system calculates the actual load torque borne by each axis in real time and compares it with the preset theoretical load distribution value in the control algorithm. If the actual load distribution deviates significantly from the preset value at a certain moment, for example, if the dual motors that should have evenly distributed the load become a push-pull state, this constitutes a significant load coupling conflict characteristic.

[0030] After feature extraction is completed, the step of inputting the cross-device coupling conflict features into a pre-set conflict recognition model to obtain the output conflict type label includes: inputting the extracted cross-device coupling conflict features and the device association matrix as input vectors into the conflict recognition model containing a convolutional neural network layer and a self-attention mechanism layer. This model is a deep neural network, where the convolutional neural network layer (CNN) is used to extract the spatial correlation of frequency domain features and local temporal domain features, and the self-attention mechanism layer (Self-Attention) is used to capture long-distance temporal dependencies and global association weights between features of different devices.

[0031] Optionally, the probability distribution values ​​of various types of conflicts output by the conflict identification model are obtained, and it is determined whether the highest probability value is greater than a preset conflict confidence threshold. If so, the category corresponding to the highest probability value is determined as the conflict type label. The model output layer uses the Softmax function to output the probability that the current state belongs to the categories of transmission coupling conflict, electromagnetic coupling conflict, load coupling conflict, or no conflict. If the highest probability is lower than the confidence threshold, the system can determine it as a mixed complex conflict, and a more conservative calibration strategy needs to be initiated.

[0032] Step S4: Based on the conflict type label and the currently identified device linkage scenario type, call the corresponding fusion strategy, and dynamically and collaboratively adjust the data fusion weights of each servo device based on the device association matrix to generate cross-device fusion features.

[0033] For example, in the process of multi-source information fusion, not all sensor data have equal credibility. The core of this step is to dynamically suppress the weight of data affected by interference sources according to the specific type of conflict, highlighting the role of high-credibility data.

[0034] The dynamic and coordinated adjustment of the data fusion weights of each servo device based on the device association matrix includes: retrieving a preset weight adjustment rule base according to the conflict type label, and determining the local basic weight adjustment strategy corresponding to the affected device. For example, the rule base defines that when an electromagnetic conflict occurs, the weight of the current sensor should be reduced first while the weight of the position encoder is maintained; when a transmission conflict occurs, the weight of the accelerometer should be reduced.

[0035] For example, based on the correlation coefficient in the device correlation matrix, the weight adjustment range of the affected devices is calculated, and the weight adjustment range is transmitted to the associated devices for coordinated adjustment. The weight adjustment is not isolated; if device A is deemed to have unreliable data, then device B, which has a very high correlation with device A, may also have its data contaminated. Therefore, the system utilizes the correlation coefficient... As a transfer factor, the weight reduction operation of device A is proportionally transmitted to device B, thereby achieving collaborative optimization of global weights.

[0036] If the conflict type label is transmission coupling conflict, then a weight attenuation factor is calculated based on the correlation coefficient, and the weight ratio of the affected sensor in the fusion calculation is reduced using the weight attenuation factor. Specifically, the weight attenuation factor can be defined as... , where k is the adjustment coefficient. The higher the correlation, the more severe the attenuation, thus effectively suppressing the transmission of mechanical coupling noise during the data fusion stage and preventing erroneous vibration signals from misleading the calibration algorithm.

[0037] For example, in the extreme case of strong coupling, simply reducing the weights might cause the system to lose its perception of the true state of the devices. Therefore, before calculating the weight attenuation factor based on the correlation coefficient if the conflict type label is a transmission coupling conflict, an anomaly handling step for strong coupling scenarios is included: determining whether the correlation coefficient between devices in the device correlation matrix is ​​greater than a preset strong coupling threshold. If the correlation coefficient is less than or equal to the threshold, then weight reduction is performed according to the normal procedure.

[0038] If the value exceeds the preset strong coupling threshold, the step of adjusting the weight ratio of the affected sensors using the weight attenuation factor is paused, and the coupling projection reconstruction process is initiated. This is because under strong coupling, although the signal is aliased, it also contains highly correlated information, and directly discarding (downweighting) it would be a waste of information.

[0039] The coupled projection reconstruction process includes: acquiring real-time status data of associated devices, and calculating the coupling interference projection amount of the associated devices on the current device by combining the correlation coefficient and the calculated mechanical transmission delay time. This step essentially establishes an interference observer, using the known correlation coefficient to infer the magnitude of the interference. Next, the coupled interference projection amount is subtracted from the original sensor data of the current device to extract the local intrinsic motion component characterizing the actual motion state of the current device. This component is a clean signal after removing external coupling noise, truly reflecting the device's own error. Finally, the signal-to-noise ratio (SNR) of the local intrinsic motion component is calculated, and the SNR is used as a positive correction factor to adjust the gain of the local base weights of the current device. Through this strategy of subtracting interference and increasing weights, the system can still capture minute local fault characteristics even in a strongly coupled environment.

[0040] Optionally, to further improve the robustness of the system before performing the multi-device synchronous calibration process, the method further includes: reading the local redundant sensor information of each servo device and constructing a global redundant resource pool. The global redundant resource pool records the sensor type, accuracy parameters, and current occupancy status. When the primary sensor is downgraded or even fails due to a conflict, a backup sensor in the resource pool will take over as a substitute. Backup sensors include auxiliary grating rulers and redundant encoders.

[0041] For example, a Long Short-Term Memory (LSTM) network and attention mechanism model are used to perform time-series analysis on the cross-device coupling conflict characteristics within a historical time window, predicting the probability of conflict occurrence in future time windows. LSTM networks excel at processing time series and can predict whether more severe coupling conflicts will occur in the next moment based on current oscillation trends.

[0042] If the predicted probability of a conflict exceeds a preset intervention probability threshold, then based on the device correlation matrix, readings from idle cross-device redundant sensors with correlation coefficients less than a preset safety threshold are scheduled from the global redundant resource pool to intervene in the data fusion process. This scheduling strategy is highly intelligent: the system intentionally selects those sensors with low correlation to the current conflict source (i.e.,...). By introducing small sensors and external data sources that provide clear, objective calibration references, we can effectively break the vicious cycle of local coupling.

[0043] Step S5: Based on the cross-device fusion features and the preset collaborative calibration strategy, calculate the calibration parameter compensation value of each servo device, and issue calibration instructions to each servo device to execute the multi-device synchronous calibration process.

[0044] For example, after the above steps, the system obtains a cross-device fusion feature that integrates multi-source information and eliminates coupling interference. This feature can accurately reflect the overall operational deviation of the system.

[0045] The calculation of calibration parameter compensation values ​​for each servo device based on the cross-device fusion features and the preset collaborative calibration strategy includes: identifying the current device linkage scenario type. Different linkage methods require different calibration logic.

[0046] If the device linkage scenario is a synchronous transmission scenario, such as electronic gear synchronization or gantry synchronization, then the device with the highest correlation coefficient value in the device correlation matrix is ​​selected as the reference device. The calibration parameters of other devices are calculated based on the difference between the reference device's state data and the local state data, combined with the correlation coefficient. This master-slave calibration strategy ensures that the entire system follows the strongest and most stable axis movement, guaranteeing trajectory consistency.

[0047] If the device linkage scenario is an asynchronous collaborative scenario, such as collaborative handling or flexible processing, then there is no absolute master axis. The load-weighted benchmark value is calculated based on the load distribution ratio. Calibration parameters are then calculated based on the difference between the load-weighted benchmark value and the local state data, combined with the load coupling coefficient. The system calculates a virtual center of gravity as a benchmark, and all axes converge towards this center of gravity to achieve force balance.

[0048] For example, in asynchronous collaborative scenarios, load switching is often very rapid, which can easily lead to misjudgments. If the device linkage scenario type is an asynchronous collaborative scenario, the calculation process of its calibration parameters also includes an inertial lag compensation step for rapid load switching: before calculating the load weighted reference value, the rate of change of the load allocation ratio of each servo device with respect to time is monitored in real time.

[0049] Determine whether the rate of change exceeds a preset transient switching threshold. If the rate of change is low, it indicates a steady-state switching, and no compensation is required.

[0050] If the threshold is exceeded, the system is determined to be in a dynamic load switching phase, triggering an inertial hysteresis compensation mechanism. This mechanism includes: acquiring a preset equipment moment of inertia coefficient and calculating the theoretical inertial hysteresis by multiplying the rate of change by the moment of inertia coefficient. According to Newton's second law, changes in torque produce acceleration, and changes in velocity and position require time; this time difference is inertial hysteresis. If this is not considered, the system will treat normal physical hysteresis as a synchronization error and force calibration, leading to overshoot. Next, the theoretical inertial hysteresis is superimposed on the load-weighted reference value calculated based on a static ratio to generate a dynamic inertial correction reference value. Finally, the dynamic inertial correction reference value replaces the load-weighted reference value as the basis for calculating the difference between the reference value and the local state data. By artificially slowing down the reference value to match the inertial response of the physical system, the system successfully masks spurious errors in the transient process, achieving a smooth transition.

[0051] Step S6: After executing the multi-device synchronous calibration process, the following steps are also included: collecting the calibrated multi-device linkage data and calculating closed-loop verification indicators, including cross-device coordination error and coupling conflict resolution rate. After the calibration command is issued, the system continues to monitor subsequent operating data to evaluate the calibration effect. Cross-device coordination error reflects synchronization accuracy, and coupling conflict resolution rate reflects vibration suppression effect.

[0052] Optionally, it can be determined whether the closed-loop verification index meets the preset calibration qualification standard. If the index meets the standard, it indicates that the current conflict identification model and weight adjustment strategy are effective.

[0053] If the conditions are not met, the single-device feature extraction layer parameters in the conflict identification model are kept unchanged, and the cross-device coupling feature extraction layer parameters are updated and iterated until the closed-loop verification index meets the calibration qualification standard. This online learning mechanism enables the system to evolve. By freezing the single-device feature parameters at the bottom layer, catastrophic forgetting of the model is prevented; only the coupling feature parameters at the higher layers are fine-tuned, allowing the model to quickly adapt to new mechanical aging states or changes in operating conditions, continuously improving the accuracy of identifying complex coupled conflicts.

[0054] In summary, this embodiment constructs a complete autonomous intelligent calibration closed loop for a servo control system by introducing a device association matrix and a deep learning conflict identification model, combined with dynamic weight adjustment and inertial lag compensation techniques. This method not only theoretically solves the conflict resolution problem in multi-source information fusion, but also provides an effective means to cope with extreme conditions such as strong coupling and rapidly changing loads in engineering practice, significantly improving the control accuracy and intelligence level of multi-axis linkage servo systems.

[0055] Example 2

[0056] Building upon Example 1, this embodiment further elaborates on an enhanced calibration processing mechanism based on coupled projection reconstruction, specifically addressing the potentially severe, strongly coupled conditions in servo control systems. In Example 1, for conventional transmission coupling conflicts, the system primarily employs a strategy of reducing the weights of affected sensors to suppress noise. However, in certain high-precision or heavy-load industrial applications, such as dual-arm robots for semiconductor wafer transport or dual-drive feed axes in heavy-duty gantry machining centers, the mechanical connection stiffness between devices is extremely high. This causes the coupling effect to become more than just interference noise; it becomes a dominant system characteristic. In such strongly coupled scenarios, simply using a weight reduction strategy not only fails to effectively eliminate interference but also significantly reduces the control system's ability to perceive the true dynamics of the equipment due to the loss of crucial state information. Therefore, this embodiment introduces a coupled projection reconstruction process. By actively modeling and stripping coupled components, it transforms what was originally considered interference—strongly coupled signals—into a core basis for improving calibration accuracy.

[0057] During the multi-source information fusion process, when the conflict type label output by the conflict identification model is determined to be a transmission coupling conflict, the system does not immediately perform a weight decay operation. Instead, it first enters a crucial decision branch, namely, a quantitative assessment of the coupling strength. This assessment process is based on the device association matrix that has already been constructed in Implementation Example 1.

[0058] Optionally, the system first determines whether the correlation coefficient between devices in the device association matrix is ​​greater than a preset strong coupling threshold. This strong coupling threshold is a pre-set empirical value used to distinguish between ordinary coupling and strong coupling. In practical engineering applications, this threshold is usually set to a relatively high value, such as 0.7 or 0.8. The system reads the device... With equipment correlation coefficient between and compare it with a preset strong coupling threshold. Compare them. If the correlation coefficient... Less than or equal to the strong coupling threshold The system will maintain the processing logic in Example 1, that is, it will assume that the coupling at this time is mainly manifested as noise interference, and then calculate the weight attenuation factor, and use the weight attenuation factor to reduce the weight ratio of the affected sensor in the fusion calculation.

[0059] If the correlation coefficient Greater than the preset strong coupling threshold This indicates that the device With equipment There is a very strong physical bond between them. In this case, the vibration or torque fluctuation signals collected by the sensors contain a large number of deterministic dynamic transmission components from the associated devices. The system determines that simple weight reduction processing would result in a significant loss of useful information. Therefore, the system will pause the step of reducing the weight ratio of the affected sensors using the weight attenuation factor and immediately initiate the coupled projection reconstruction process. The core idea of ​​this process is to decouple and separate the mixed signals to restore the true behavior of the devices themselves.

[0060] Optionally, the first step of the coupled projection reconstruction process is to acquire the real-time status data of the associated devices, and, in conjunction with the correlation coefficient and the calculated mechanical transmission delay time, calculate the coupling interference projection amount of the associated devices on the current device. During this process, the global edge controller reads the associated devices, which act as interference sources, in real time via a high-speed bus. The sensor data sequence, denoted as Simultaneously, the system needs to calculate the mechanical vibration waves or torque waves emitted from the equipment. Transfer to device The required time, i.e. the mechanical transmission delay time.

[0061] The calculation of the mechanical transmission delay time is based on physical acoustic principles and system geometric parameters. The system calls the physical distance between devices stored in the device attribute information. And the material properties of the connecting medium. Assume the mechanical wave propagation speed of the connecting medium, such as a cast iron base or a steel lead screw, is... Then the mechanical transmission delay time Through physical distance Divided by the speed of propagation Furthermore, the system can also utilize cross-correlation analysis algorithms, through computing devices, to arrive at a more precise conclusion. With equipment The time lag corresponding to the peak value of the cross-correlation function of the historical vibration data sequence, relative to the theoretically calculated mechanical transmission delay time. Dynamic corrections are made to ensure the accuracy of the time parameters.

[0062] After determining the delay time, the system further calculates the coupling interference projection of the associated device on the current device. This projection quantity characterizes the coupling interference projection of the associated device. The motion state is transmitted through the mechanical structure and then into the equipment. The theoretical response value generated. System construction projection function. This function uses the state data of the associated device before the delay time. As the independent variable, and using the correlation coefficient As the transfer gain. Specifically, the projection amount of coupling interference. It can be expressed as the correlation coefficient. Related device status data after delay The product of these terms, plus a correction term representing transmission losses. This projected quantity is physically equivalent to: if the device It is completely stationary, and only the device The equipment caused by the action Theoretical readings of the sensor.

[0063] The second step of the coupled projection reconstruction process is to subtract the coupled interference projection from the original sensor data of the current device to extract the local intrinsic motion components characterizing the actual motion state of the current device. This is the most critical signal separation step in the entire reconstruction process. Assume the device... The raw sensor data is This data is a superposition of local motion and external coupled disturbances. The system performs a subtraction operation to calculate the local intrinsic motion components. Its value is equal to the original sensor data. Subtract the calculated coupling interference projection amount .

[0064] Through the above subtraction operation, the system effectively separates strongly correlated devices. The resulting externally forced vibration or torque following component. The remaining local intrinsic motion components. Although its amplitude may be much smaller than the original signal, it reflects the device's signal extremely purely. Its own load characteristics, friction and wear conditions, and potential local fault characteristics. For example, in a dual-drive gantry crane, the two motors theoretically move synchronously, but if the motors... The guide rails show signs of corrosion; this minute resistance characteristic is often detected by the motor. The immense traction force transmitted through the crossbeam masks this characteristic. Through the extraction process described above, this minute drag feature, i.e., the local intrinsic motion component, becomes apparent, serving as the basis for subsequent precise calibration.

[0065] The third step of the coupled projection reconstruction process is to calculate the signal-to-noise ratio (SNR) of the local intrinsic motion components and use this SNR as a positive correction factor to adjust the gain of the local base weights of the current device. After extracting the local intrinsic motion components, the system needs to evaluate the quality of these components to determine their role in the final multi-source information fusion. The system selects a preset time window to calculate the local intrinsic motion components. The effective power is taken as the signal power, and the high-frequency residual filtered out in the preprocessing stage is calculated as the noise power. The ratio of the two is the signal-to-noise ratio. .

[0066] Optionally, unlike the weight reduction processing for ordinary coupling in Embodiment 1, in strongly coupled scenarios, once a high signal-to-noise ratio (SNR) local intrinsic motion component is successfully extracted, the system needs to increase the weight of this data. This is because the reconstructed data has eliminated external interference and contains extremely high information density, playing an irreplaceable role in revealing the true health status of the device. The system constructs a weight gain function to increase the SNR... Mapped to a positive correction factor The correction factor is a value greater than one and is positively correlated with the signal-to-noise ratio.

[0067] System reads device Local base weights The base weights are default values ​​assigned during system initialization. Subsequently, the system utilizes the calculated positive correction factors. Multiply the local base weights to obtain the final dynamic fusion weights. ,Right now equal Multiply Through this gain adjustment, the device The influence of sensor data in multi-source information fusion algorithms is significantly amplified. This means that the system will place greater trust in cleaned local data and primarily rely on this data to generate calibration instructions.

[0068] This strategy based on coupled projection reconstruction not only solves the signal aliasing problem under strong coupling, but also constitutes a virtual active noise reduction mechanism. It enables the servo control system to maintain perceptual clarity similar to single-axis independent control even in extremely complex mechanical linkage environments. For example, during the rapid start-up and shutdown of a heavy load, strong coupling causes drastic fluctuations in sensor readings across all relevant axes. Conventional algorithms might misinterpret this as system-wide instability, triggering an emergency stop or erroneous, drastic reverse compensation. However, using the reconstruction method in this embodiment, the system can clearly distinguish which fluctuations are due to normal following caused by mechanical transmission, and which are due to abnormal vibrations caused by excessive backlash in a particular axis's leadscrew. Based on this, it performs micron-level precise position compensation for that specific axis, thus achieving calibration with extreme accuracy while ensuring system safety.

[0069] In summary, this embodiment achieves a technological leap from passively suppressing interference to actively separating signals by introducing a strong coupling threshold determination mechanism and innovatively applying a coupled projection reconstruction process under strong coupling conditions. Through calculating mechanical transmission delay, constructing an interference projection model, extracting intrinsic motion components, and adjusting weighted gain based on the signal-to-noise ratio, the method in this embodiment effectively solves the error masking problem in strongly coupled servo systems. This ensures that in complex linkage scenarios, each servo device can obtain autonomous intelligent calibration based on its actual operating state, greatly expanding the applicability and engineering value of this method.

[0070] Example 3

[0071] This embodiment, based on Embodiments 1 and 2, discloses a calibration parameter calculation process including an inertial lag compensation mechanism for the most complex asynchronous collaborative scenario in multi-device linkage, which is highly prone to control oscillations. In Embodiment 1, the system solved the coupling interference problem in steady-state or quasi-steady-state conditions by constructing a device association matrix and adjusting weights. However, in actual industrial production, scenarios such as quadrant switching in backlash-free dual-motor drive, load handover in multi-robotic arm collaborative handling, and process transitions on flexible production lines are all typical asynchronous collaborative scenarios. In such scenarios, the load distribution ratio borne by each servo device is not constant, but changes drastically and rapidly with the needs of the process flow. This change often occurs within milliseconds or even microseconds at the electrical signal level, but the rotor of the servo motor and the connected mechanical load, due to their objective physical mass, are inevitably limited by their rotational inertia, resulting in an unavoidable physical lag. If the control system ignores this physical law and forcibly calibrates the unresponsive mechanical body based on the instantaneous changes in the electrical signal, it will inevitably lead to severe overshoot and oscillations. Therefore, this embodiment discloses in detail how to introduce an inertial hysteresis compensation step for rapid load switching during the calculation of calibration parameters.

[0072] For example, the method in this embodiment also runs in the global edge controller of the servo control system and relies on multi-source sensor data synchronized by a global time protocol. The system first needs to identify the current device linkage scenario type. When the system determines that it is currently in an asynchronous collaborative scenario, it means that there is no absolute master-slave rigid constraint between the servo devices, but rather the system maintains balance and cooperation by dynamically allocating load torque. In this context, the core basis of the calibration algorithm is the load-weighted reference value. However, to avoid misjudgments caused by physical inertia, the system must perform a crucial pre-step before calculating the load-weighted reference value: real-time monitoring of the rate of change of the load allocation ratio of each servo device with respect to time.

[0073] The load distribution ratio is a torque distribution command coefficient that the control algorithm sends to each servo drive in real time according to process requirements. For example, in a scenario where two motors drive the same load, the sum of the load distribution ratios of motor A and motor B is usually 100%. At the moment of load switching, the ratio of motor A may drop rapidly from 80% to 20%, while that of motor B increases accordingly. The system uses a differential algorithm or differential filter to perform real-time differentiation on this ratio signal. Let the load distribution ratio at time t be... The system calculates its first derivative with respect to time to obtain the rate of change. The rate of change It intuitively reflects the drastic extent to which the control system attempts to change the physical load state.

[0074] The system then proceeds to a judgment process to determine whether the rate of change exceeds a preset transient switching threshold. The transient switching threshold... This is a pre-calibrated critical value based on the system's dynamic characteristics. This threshold defines a boundary between the system's steady-state operating region and its transient switching region. During steady-state or slowly changing load adjustments, the rate of change... Typically small, less than or equal to the transient switching threshold. At this point, the inertial lag effect of the physical system is not significant, and the inertial influence can be ignored, allowing the static proportional calculation of the baseline value to be used directly. However, when the process requires the load to be transferred significantly within a very short time, the rate of change... It will spike instantly and exceed the transient switching threshold. .

[0075] If the rate of change Exceeding the transient switching threshold If this occurs, the system determines that it is currently in a dynamic load switching phase. This determination means the system immediately recognizes that while the electrical signal command has changed abruptly, the physical mechanical structure is likely still in its old state or is slowly accelerating. The large position or velocity deviations reported by the sensors at this time are largely not a loss of control precision, but rather a reasonable delay inherent to the system by physical laws. Therefore, to prevent the calibration algorithm from erroneously correcting this reasonable delay, the system immediately triggers the inertial hysteresis compensation mechanism.

[0076] The first step of the inertial lag compensation mechanism is to quantify this physical lag. The system acquires a preset equipment moment of inertia coefficient. This coefficient is a physical parameter obtained during the system's commissioning phase through frequency response analysis or adaptive identification algorithms. It characterizes the ability of the servo motor rotor and its connected transmission chain and load to resist changes in motion state. Let this equipment moment of inertia coefficient be denoted as... Subsequently, the system performs a calculation step, multiplying the rate of change by the rotational inertia coefficient to calculate the theoretical inertial hysteresis. Let the theoretical inertial hysteresis be... Its calculation formula can be expressed as: ; In the above formula, the rate of change This represents the rate of change of torque command, while the moment of inertia... This represents the ease or difficulty of system response; the product of these two factors precisely quantifies the theoretical state lag that the physical system will experience under the current drastic change in instructions. This value is a directional vector, and its sign depends on the trend of load change.

[0077] The second step of the inertial hysteresis compensation mechanism is to perform dynamic correction on the reference value. When this mechanism is not triggered, the system calculates an idealized static reference based solely on the current static load distribution ratio, denoted as... This static baseline assumes the physical system is a massless, infinitely fast-responding perfect model; therefore, it will change instantaneously with jumps in load ratio. After compensation is triggered, the system adds the theoretical inertial hysteresis to the load-weighted baseline value calculated based on the static ratio, generating a dynamic inertial correction baseline value. Let the dynamic inertial correction baseline value be denoted as... The corrected formula is: ; in, This is a dimension unification coefficient used to map the dimensions of a hysteresis quantity to the same dimension as the reference value, such as the position or velocity dimension.

[0078] Through this superposition operation, the system artificially constructs a reference value that is half a beat slower. When the electrical signal command... When the target point has been reached, the dynamic inertial correction reference value Due to the addition of hysteresis Its value was temporarily pulled towards the old state. Over time, the rate of load change... Gradually declining, lagging quantity It also decreases accordingly, eventually It will converge smoothly to This trajectory of change closely matches the response trajectory of a real physical mechanical system under inertia.

[0079] The final step of the inertial hysteresis compensation mechanism is to replace the load-weighted reference value with the dynamic inertial correction reference value as the basis for calculating the difference between the reference value and the local state data. When performing calibration parameter calculations, the system no longer forces the current servo device to chase that unattainable static reference. Instead, it requires it to follow this dynamic benchmark that fully considers physical inertia. The system calculates the real-time status data fed back by local sensors. With dynamic inertia correction reference value The difference between them is denoted as the effective calibration deviation. .

[0080] For example, due to dynamic benchmarks The initial design intent was to simulate the real response of a physical system; therefore, if the servo device is operating normally, its feedback data... Should with They are very close, thus making the calculated effective calibration deviation... This is maintained within a very small range. This means that by introducing inertial hysteresis compensation, the system successfully eliminates large, reasonable deviations caused by inertia from the calibration deviations. The system only performs calibration compensation for abnormal errors that deviate from the normal inertial trajectory and are truly caused by mechanical clearance, sudden changes in friction, or mismatched control parameters.

[0081] To further illustrate the beneficial effects of this mechanism, we can compare it with the case where it is not used. In the traditional method without inertia compensation, the system directly calculates... Compared with static reference The difference. At the moment of sudden load change, due to Delay, A sudden change occurs, with a significant difference between the two values. The calibration algorithm might mistakenly interpret this as a large positional loss and issue an excessively large acceleration command to compensate. However, when the equipment actually accelerates to catch up due to inertia, this extra compensation command can cause the equipment to overshoot, resulting in severe overshoot. This can lead to intense torque conflicts between multiple devices and even damage to mechanical transmission components.

[0082] In this embodiment, the calibration command becomes extremely restrained and precise. During the transient process of load switching, although the physical position lags, as long as this lag conforms to the law of inertia, the system considers the device healthy and does not intervene or only applies a minor synchronization correction. The system only intervenes when the actual lag of the device exceeds the allowable range of the theoretical inertial lag. This intelligent calibration strategy enables the servo control system to maintain a silky smooth operating state even when facing high-frequency load switching conditions such as several times per second. It ensures both the stability of the dynamic process and the high-precision synchronization after steady state, perfectly solving the control problem in asynchronous cooperative scenarios.

[0083] In summary, this embodiment accurately identifies the dynamic load switching phase by monitoring the load change rate in real time and setting a transient switching threshold. Based on this, it creatively achieves mathematical compensation for physical inertial lag by introducing the equipment's rotational inertia coefficient to calculate the theoretical inertial lag and constructing a dynamic inertial correction benchmark. This mechanism fundamentally eliminates the time mismatch between electrical signal commands and mechanical physical responses, ensuring the correctness and stability of the calibration algorithm under extreme dynamic conditions, and providing a solid technical guarantee for the high-speed, high-precision collaborative control of high-end servo equipment.

[0084] Example 4

[0085] like Figure 2 As shown, this embodiment, based on the logical foundation of the aforementioned method embodiments one, two, and three, elaborates in detail, from the perspective of system architecture and hardware deployment, an autonomous intelligent calibration system for a servo control system based on multi-source information fusion. This system aims to resolve the conflict between sensor reliability and physical coupling interference in multi-device linkage scenarios as pointed out in the background art through modular functional design and a tight signal flow mechanism, thereby achieving high-precision autonomous collaboration of the servo control system.

[0086] The autonomous intelligent calibration system for servo control systems based on multi-source information fusion provided in this embodiment has its core logic entity deployed within the global edge controller of a multi-device interconnected servo control system. This global edge controller, acting as the system's central brain, possesses high-performance parallel computing capabilities and communication interfaces compatible with industrial real-time buses such as EtherCAT or Profinet. From a functional module perspective, the system mainly includes a data acquisition and correlation modeling module, a conflict feature identification module, a dynamic weight coordination module, and a collaborative calibration execution module. These four modules interact with each other through shared memory or message queues, collectively forming a closed-loop intelligent calibration system.

[0087] First, the data acquisition and correlation modeling module is the foundation for the system's perception of the physical world. This module is configured to proactively initiate scanning and data acquisition tasks of the physical system in response to system startup or calibration commands. It reads the electronic nameplates or configuration files of each servo device via the industrial bus to obtain device attribute information. More importantly, this module integrates the master clock function of the IEEE 1588 precision time protocol, ensuring the acquisition of multi-source sensor data synchronized via a global time protocol. This means that whether it's the data from the servo motor's built-in encoder or the data from externally installed vibration sensors, they are strictly aligned on the time axis, thus eliminating the interference of timing deviations on subsequent correlation analysis.

[0088] Building upon this foundation, this module performs the core modeling task: constructing a device correlation matrix characterizing the coupling strength between devices based on the physical spatial distribution data and transmission connection relationship data from the device attribute information. This matrix is ​​not merely a mathematical array; it is a digital mapping of physical coupling relationships. Constructing this device correlation matrix is ​​a multi-dimensional quantification process. The module assesses the potential risk of spatial electromagnetic interference based on the physical distance between devices, evaluates the transmission efficiency of mechanical vibration based on the quantification coefficient of the transmission connection method, and evaluates the dynamic interaction based on the load distribution ratio. Finally, the module calculates the correlation coefficient between each pair of devices, and all correlation coefficients constitute the device correlation matrix, providing subsequent modules with prior knowledge about the mutual influence between devices.

[0089] Secondly, the conflict feature identification module is responsible for signal analysis and pattern recognition. This module receives raw data from upstream and preprocesses the multi-source sensor data to extract cross-device coupling conflict features. This preprocessing includes filtering and denoising, and data normalization, while feature extraction focuses on uncovering the physical patterns hidden behind the data, such as the correlation of torque fluctuations or the spectral overlap of current harmonics. Subsequently, the module inputs the cross-device coupling conflict features into a pre-set conflict identification model. This model is a deep neural network trained on a large number of samples, possessing powerful nonlinear mapping capabilities. Through the model's inference operations, the module obtains the output conflict type label, clearly indicating whether the current system faces transmission coupling conflict, electromagnetic coupling conflict, or load coupling conflict. This provides a precise decision-making basis for addressing the pain point mentioned in the background technology of lacking the ability to distinguish between local intrinsic errors and cross-device coupling interference.

[0090] Secondly, the dynamic weight coordination module is the core of the system's decision-making, reassessing data credibility based on the identification results. This module is used to invoke the corresponding fusion strategy according to the conflict type label and the currently identified device linkage scenario type. Its operation is not isolated, but rather dynamically and collaboratively adjusts the data fusion weights of each servo device based on the device association matrix. Under normal conflict conditions, this module reduces the weight of the interfered sensor; while under the strong coupling extreme condition described in Example 2, this module activates the coupling projection reconstruction logic, separating the intrinsic components from the mixed signal and increasing their weights. Furthermore, this module also has the ability to invoke the global redundant resource pool, introducing third-party sensor data when necessary. After this series of complex calculations, the module finally generates cross-device fusion features. This feature eliminates external coupling noise, truly reflects the operating status of each device, and solves the root cause of miscalibration.

[0091] Finally, the collaborative calibration execution module is the actuator that transforms data into control actions. This module calculates the calibration parameter compensation values ​​for each servo device based on the cross-device fusion features and the preset collaborative calibration strategy. During the calculation process, this module intelligently distinguishes between synchronous drive scenarios and asynchronous collaborative scenarios according to the logic described in Embodiment 3. Especially during the rapid load switching phase in asynchronous collaborative scenarios, this module introduces an inertial lag compensation mechanism to shield against pseudo-errors caused by physical inertia by constructing a dynamic benchmark. After the calculation is completed, the module issues calibration commands to each servo device to execute the multi-device synchronous calibration process. These commands reach each servo drive in real time via the industrial bus, correcting the control parameters of its position loop or speed loop, thereby eliminating deviations at the physical level.

[0092] In summary, the system in this embodiment materializes the technical solution from the method embodiment through the close collaboration of the four modules described above. The data acquisition and correlation modeling module solves the problem of digitizing physical relationships, the conflict feature identification module solves the problem of qualitatively identifying interference sources, the dynamic weight coordination module solves the problem of verifying the authenticity of signals, and the collaborative calibration execution module solves the problem of accurately generating control commands. This system architecture ensures that the control system can intelligently isolate external interference, calibrate only the true intrinsic error of the device itself, and effectively cope with the inertial effects caused by sudden load changes, thereby achieving the beneficial effect of improving the overall accuracy, stability, and robustness of the servo system.

[0093] Example 5

[0094] Corresponding to the above embodiments, the present invention also proposes an electronic device.

[0095] like Figure 3The diagram shows a structural schematic of an electronic device according to the present invention. The electronic device 100 includes a processor 101 and a memory 103. The processor 101 and the memory 103 are connected, for example, via a bus 102. Optionally, the electronic device 100 may further include a transceiver 104. It should be noted that in practical applications, the transceiver 104 is not limited to one unit, and the structure of this electronic device 100 does not constitute a limitation on the embodiments of the present invention.

[0096] Processor 101 may be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in connection with this disclosure. Processor 101 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0097] Bus 102 may include a pathway for transmitting information between the aforementioned components. Bus 102 may be a PCI bus or an EISA bus, etc. Bus 102 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0098] The memory 103 stores a computer program corresponding to the autonomous intelligent calibration method for a servo control system based on multi-source information fusion according to the above embodiments of the present invention. This computer program is executed by the processor 101. The processor 101 executes the computer program stored in the memory 103 to implement the content shown in the aforementioned method embodiments.

[0099] Among them, electronic devices 100 include, but are not limited to: mobile terminals such as laptops and PADs (tablet computers) and fixed terminals such as desktop computers. Figure 3 The electronic device 100 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0100] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. An autonomous intelligent calibration method for a servo control system based on multi-source information fusion, characterized in that, Includes the following steps: In response to system startup or calibration commands, acquire device attribute information of each servo device and multi-source sensor data synchronized via a global time protocol; Based on the physical spatial distribution data and transmission connection relationship data in the equipment attribute information, a device association matrix representing the coupling strength between devices is constructed. The multi-source sensor data is preprocessed to extract cross-device coupling conflict features. These features are then input into a preset conflict identification model to obtain the output conflict type label. This process includes: inputting the extracted cross-device coupling conflict features and the device association matrix as input vectors into the conflict identification model, which includes a convolutional neural network layer and a self-attention mechanism layer; obtaining the probability distribution values ​​of various types of conflicts output by the conflict identification model; determining whether the highest probability value is greater than a preset conflict confidence threshold; if so, determining the category corresponding to the highest probability value as the conflict type label; wherein, the cross-device coupling conflict... The features include at least: transmission coupling conflict features characterizing the mutual influence of mechanical transmissions, electromagnetic coupling conflict features characterizing electrical signal interference, and load coupling conflict features characterizing load distribution deviations; the specific generation process of the cross-device coupling conflict features includes: calculating the Pearson correlation coefficient of torque fluctuation between device i and device j as the torque coupling coefficient in the transmission coupling conflict features; calculating the proportion of overlapping intervals of the same harmonic frequencies between devices as the current harmonic spectrum overlap in the electromagnetic coupling conflict features; and calculating the difference ratio between the actual load distribution ratio and the preset ratio as the load deviation rate in the load coupling conflict features. Based on the conflict type label and the currently identified device linkage scenario type, the corresponding fusion strategy is invoked, and the data fusion weights of each servo device are dynamically and collaboratively adjusted based on the device association matrix to generate cross-device fusion features. The dynamic and collaborative adjustment of the data fusion weights of each servo device based on the device association matrix includes: retrieving a preset weight adjustment rule library based on the conflict type label to determine the local basic weight adjustment strategy corresponding to the affected device; calculating the weight adjustment range of the affected device based on the correlation coefficient in the device association matrix, and transmitting the weight adjustment range to the associated device for collaborative adjustment; wherein, if the conflict type label is a transmission coupling conflict, a weight attenuation factor is calculated based on the correlation coefficient, and the weight attenuation factor is used to reduce the weight ratio of the affected sensor in the fusion calculation. Based on the cross-device fusion feature and the preset collaborative calibration strategy, the calibration parameter compensation value of each servo device is calculated, and calibration instructions are sent to each servo device to execute the multi-device synchronous calibration process. The process of constructing the device association matrix that characterizes the coupling strength between devices includes: calculating the association coefficient between each pair of devices based on the physical distance between devices, the quantification coefficient of the transmission connection method, and the load distribution ratio, and constructing the device association matrix from all the association coefficients.

2. The method according to claim 1, characterized in that, The calculation of the correlation coefficient between each pair of devices includes: calculating the device correlation coefficient using the following formula. With equipment correlation coefficient between : ； in, Characterization equipment With equipment The physical distance between them; The transmission link coefficient is characterized by taking a preset first value, second value, or zero value depending on whether it is a direct transmission, indirect transmission, or no transmission relationship. Characterizing the load ratio of equipment; , , The weighting coefficients are preset, and the correlation coefficients are... The range of values ​​is normalized to a closed interval between zero and one.

3. The method according to claim 1, characterized in that, Before performing the multi-device synchronous calibration process, the following is also included: Read the local redundant sensor information of each servo device and construct a global redundant resource pool. The global redundant resource pool records the sensor type, accuracy parameters and current occupancy status. The cross-device coupling conflict characteristics within a historical time window are analyzed using a long short-term memory network and attention mechanism model to predict the probability of conflict occurrence in future time windows. If the predicted probability of conflict exceeds a preset intervention probability threshold, then based on the device association matrix, the readings of idle cross-device redundant sensors with an association coefficient less than a preset safety threshold are scheduled from the global redundant resource pool to intervene in the data fusion process.

4. The method according to claim 1, characterized in that, The calculation of calibration parameter compensation values ​​for each servo device based on the cross-device fusion features and the preset collaborative calibration strategy includes: Identify the current device interaction scenario type; If the device linkage scenario type is a synchronous transmission scenario, then the device with the largest correlation coefficient value in the device correlation matrix is ​​selected as the reference device. The calibration parameters of other devices are calculated by weighting the correlation coefficient based on the difference between the status data of the reference device and the local status data. If the device linkage scenario type is an asynchronous collaborative scenario, then the load weighting benchmark value is calculated based on the load distribution ratio, and the calibration parameters are calculated based on the difference between the load weighting benchmark value and the local status data, combined with the load coupling coefficient.

5. The method according to claim 1, characterized in that, After performing the multi-device synchronous calibration process, the following is also included: Collect calibrated multi-device linkage data and calculate closed-loop verification indicators, including cross-device coordination error and coupling conflict resolution rate. Determine whether the closed-loop verification index meets the preset calibration qualification standard; If the conditions are not met, the parameters of the single-device feature extraction layer in the conflict identification model remain unchanged, and the parameters of the cross-device coupled feature extraction layer are updated and iterated until the closed-loop verification index meets the calibration qualification standard.

6. The method according to claim 1, characterized in that, If the conflict type label is a transmission coupling conflict, before calculating the weight attenuation factor based on the correlation coefficient, an anomaly handling step for strongly coupled scenarios is also included: Determine whether the correlation coefficient between devices in the device association matrix is ​​greater than a preset strong coupling threshold; If so, then pause the step of adjusting the weight ratio of the affected sensor using the weight attenuation factor and start the coupling projection reconstruction process. The coupled projection reconstruction process includes: acquiring real-time status data of associated devices, combining the correlation coefficient and the calculated mechanical transmission delay time to calculate the coupling interference projection amount of the associated devices on the current device; subtracting the coupling interference projection amount from the original sensor data of the current device to extract the local intrinsic motion components characterizing the actual motion state of the current device; calculating the signal-to-noise ratio of the local intrinsic motion components, and using the signal-to-noise ratio as a positive correction factor to adjust the gain of the local base weights of the current device.

7. The method according to claim 4, characterized in that, If the device linkage scenario type is an asynchronous collaborative scenario, the calculation process of its calibration parameters also includes an inertial hysteresis compensation step for rapid load switching: Before calculating the load-weighted baseline value, monitor the rate of change of the load distribution ratio of each servo device over time in real time. Determine whether the rate of change exceeds a preset transient switching threshold; If so, it is determined that the current state is in the dynamic load switching phase, triggering the inertial lag compensation mechanism; The inertial hysteresis compensation mechanism includes: obtaining a preset equipment rotational inertia coefficient; calculating the theoretical inertial hysteresis by multiplying the rate of change by the rotational inertia coefficient; superimposing the theoretical inertial hysteresis onto the load-weighted reference value calculated based on a static ratio to generate a dynamic inertial correction reference value; and using the dynamic inertial correction reference value to replace the load-weighted reference value as the basis for calculating the difference between the data and the local state data.

Images